Bearing component damage contributes significantly to rotating machinery failures. It is vital for the rotor-bearing system to be in good condition to ensure proper functioning of the machine. Over recent decades, extensive research has been devoted to the condition monitoring of rotational machinery, with a particular focus on bearing health. This paper provides a comprehensive literature review of recent advancements in intelligent condition monitoring technologies for rolling element bearings. Fundamental monitoring strategies are introduced, covering various sensing, signal processing, and feature extraction techniques for detecting defects in rolling element bearings. While vibration-based monitoring remains prevalent, alternative sensor types are also explored, offering complementary diagnostic capabilities or detecting different defect types compared to accelerometers alone. Signal processing and feature extraction techniques, including time domain, frequency domain, and time-frequency domain analysis, are discussed for their ability to provide diverse perspectives for signal representation, revealing unique insights relevant to condition monitoring. Special attention is given to information fusion methodologies and the application of intelligent algorithms. Multisensor systems, whether homogeneous or heterogeneous, integrated with information fusion techniques, hold promise in enhancing accuracy and reliability by overcoming limitations associated with single sensor monitoring. Furthermore, the adoption of AI techniques, such as machine learning and metaheuristic optimisation, has led to significant advancements in condition monitoring, yielding successful outcomes in various studies. Finally, avenues for further advancements to improve monitoring accuracy and reliability are identified, offering insights into future research directions.

Stress is an inherent sensation of being unable to handle demands and occurrences. If not properly managed, stress can develop into a chronic condition, leading to the onset of additional chronic health issues like cardiovascular illnesses and diabetes. Various stress meters have been suggested in the past, along with diverse approaches for its estimate. However, in the case of more serious health issues such as hypertension and diabetes, the results can be significantly improved. This study presents the design and implementation of a distributed wearable sensor computing platform with multiple channels. The platform aims to estimate stress levels in diabetes patients by utilizing a fuzzy logic algorithm that is based on the assessment of several physiological indicators. Additionally, a mobile application was created to monitor users' stress levels and integrate data on their blood pressure and blood glucose levels. Validation experiments were performed on patients with chronic diabetes, and the initial findings are presented in the study.

Supramolecular solvent (SUPRAS) has received increasing interest as an innovative, efficient, and green solvent for the effective extraction and separation of bioactive compounds from natural resources. However, studies on the use of SUPRAS for the extraction of phenolic components from plants, which are highly valued in food products due to their excellent antioxidant capacity, are still lacking. The present study developed a green ultrasound-assisted and efficient SU-PRAS method to simultaneously determine three phenolic acids in Prunella vulgaris by high-performance liquid chromatography (HPLC) and the experimental parameters were optimized in detail. The efficiency and antioxidant properties of the phenolic compounds obtained by different extraction methods were also compared. Under the optimal conditions, the extraction efficiency of SUPRAS, prepared with octanoic acid reverse micelles dispersed in ethanol-water, was substantially higher than conventional organic reagents. Moreover, this SUPRAS method also showed more significant antioxidant capacities. The confocal laser scanning microscopy (CLSM) images presented the spherical droplet structure of SUPRAS (A well-defined circle), which coincided with the position of the fluorescence position of phenolic acids. The phenolic acids were encapsulated in the vesicles by the SUPRAS droplets, which indicated the efficient extraction capacities of SUPRAS for the target compounds. Finally, combined with the CLSM method, the mechanism of the proposed method was further clarified, and the superior extraction performance of SUPRAS was theoretically demonstrated through molecular dynamics simulations. In comparison with conventional methods, the higher extraction efficiency of SUPRAS can be illustrated by the larger solvent contact surface area, more types of hydrogen bonds between extractants and supramolecular solvents, and stronger and more stable interaction forces. The results of the theoretical studies are in rational agreement with the experimental outcome.

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of -0.99. The dependency relation followed with -0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and -0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models’ factual integrity.

The study aimed to isolate and characterize bacteriocin-producing Enterococcus species from Ethiopian traditional fermented foods and beverages. The bacteriocin bioassay was tested against food-borne pathogens at various temperatures, pH, solvents, additives, and enzymes. A solvent extraction method was established to concentrate bacteriocins from Enterococcus species. The study found that crude extracts with proteinase K, pepsin, and trypsin deactivated antimicrobial activity, confirming their proteinaceous nature. Organic solvents were more effective at extracting bacteriocins from CFS, with chloroform alone and in combination providing rapid and efficient recovery. The optimal bacteriocin production and strong inhibition activity were achieved at 37°C with a pH range of 5.5 to 6.5 incubated for 16-18 hours. The six Enterococcus faecium species were the best bacteriocin-producing isolates. Optimizing bacteriocin production and changing environmental growing circumstances can enhance the application of bacteriocins as food preservation agents. Traditional fermented products are potential sources of bacteriocin-producing LAB.

A novel approach based on response surface methodology (RSM) was developed to predict and apply the best extraction conditions for the isolation of various-type polyphenolic antioxidants from the dried flower buds of Magnolia x soulangeana Soul.-Bod. var. ‘Lennei’ (Magnoliaceae). As a method of choice, ultrasound-assisted extraction was used and the optimized extraction parameters (temperature, time of extraction, the composition of aqueous-ethanolic extractants and solvent to solid ratio) have been determined using a central composite design factorial analysis, followed by appropriate spectrophotometric methods (with Folin–Ciocalteu and 2,2-diphenyl-1-picrylhydrazyl reagents) to determine the antioxidant and antiradical potential of extracts, respectively. The use of 66.8% (V/V) ethanol, as the extraction solvent during the 55.2 min extraction protocol, and the ratio of extractant volume to herbal substance of 46.8 mL/g gave the highest total yield of bioactive antioxidant phenolics in the extract obtained. For this herbal preparation, qualitative and quantitative analysis was performed using combined chromatographic (LC), spectroscopic (PDA) and tandem mass spectrometric (ESI-QTOF–MS/MS) techniques. A detailed phytochemical profiling, conducted for the first time, documented substantial amounts of polyphenolic antioxidants, especially phenylethanoids and flavonoids in the flower buds of M. soulangeana ‘Lennei’. Their average total content exceeded 30.3 and 36.5 mg/g dry weight, respectively.

Cascalote pods are an important source of phenolic compounds, mainly recovered using solvent extraction methods. As a sustainable alternative, this study aimed to evaluate solid-state fermentation (SSF) to enhance the extractability of total phenolic compounds (TPC) with antioxidant activity (AA) from cascalote pods. Aspergillus niger GH1 was selected based on the amount of TPC released and AA measured (ABTS, DPPH, FRAP) in a shorter time. Moreover, moisture, temperature, inoculum size, and mineral composition were evaluated. The largest amount of TPC released was 124.17 mg/gdm (g of dry material) after 12 h of culture, strongly and highly significantly correlated with the AA. Moisture and KH2PO4 concentration were the main influencing factors on TPC release. Treatment 6 [1x 107 spores/gdm, 30 °C, 60% moisture, mineral composition (g/L): KH2PO4, 1.52; NaNO3, 7.65; and MgSO4, 1.52] was selected due to the highest values of both TPC and AA. SSF-assisted extraction allowed increase 118 % and 93 % in TPC and AA values, respectively. Corilagin, lagerstannin, geraniin, and ellagic acid were the main phenolic compounds identified by RP-HPLC-ESI-MS in cascalote extracts. The results obtained demonstrate the feasibility of SSF-assisted extraction as a biotechnological alternative for the recovery of important bioactive molecules from this underutilized material.

Drugs-drugs interactions(DDI) are entities composed of different chemical substructures (functional groups). In existing methods that predict drug–drug interactions based on the usage of substructures, each node is considered the center of a substructure, and adjacent nodes eventually become centers of similar substructures, resulting in redundancy. Furthermore, the significant differ- ences in structure and properties among compounds can lead to unrelated pairings, making it difficult to integrate information. This heterogeneity negatively affects the prediction results. To address these issues, we propose a drug–drug interaction prediction method based on substructure signature learning (DDI-SSL). This method extracts useful information from local subgraphs surrounding drugs and effectively utilizes substructures to assist in predicting drug side effects. Additionally, a deep clustering algorithm is used to aggregate similar substructures, allowing any individual subgraph to be reconstructed using this set of global signatures. Furthermore, we developed a layer-independent collaborative attention mechanism to model the mutual influence between drugs, generating signal strength scores for each class of drugs to mitigate noise caused by heterogeneity. Finally, we evaluated DDI-SSL on a comprehensive dataset and demonstrated improved performance in DDI prediction compared to state-of-the-art methods.

This comprehensive review paper provides a detailed analysis of the extraction methods employed in the dimension stone industry. Natural rock materials used in construction, have been historically extracted using primitive techniques such as thermal shock, hammer and chisel, and plug and feather. However, significant technological advancements have revolutionized the industry, leading to the widespread adoption of mechanized methods. One highly efficient technique is diamond wire cutting, which involves the utilization of diamond-engraved bits affixed to a tensioned steel wire. This method has demonstrated remarkable capabilities in minimizing waste generation and ensuring exceptional machining quality. Nonetheless, challenges such as high operating costs and wire breakage persist and require further investigation. In addition to diamond wire cutting, this review explores the utilization of circular diamond saws and frame sawing as alternative extraction methods. The geotechnical characteristics of the stone play a critical role in the selection of appropriate machinery, and researchers worldwide have conducted numerous studies to investigate the impact of each parameter on the extraction efficiency of these mechanized techniques. Moreover, controlled blasting with explosives emerges as a promising alternative for dimension stone extraction, warranting further exploration and optimization.

In order to realize the performance degradation trend prediction accurately, a prediction method based on multi-domain features and temporal convolutional network (TCN) is proposed. Firstly, construct a high-dimensional feature set in the multi-domain of vibration signals, and use comprehensive evaluation indicators to preliminarily screen performance degradation indexes with good sensitivity and strong trend. Secondly, the kernel principal component analysis (KPCA) method is adopted to eliminate redundant information between multi-domain features, and construct a health index (HI) based on convolutional auto-encoder (CAE) network. Thirdly, a TCN-based performance degradation trend prediction model is constructed, and direct multi-step prediction is used to predict the performance degradation trend of the monitored object. On this basis, the validity of the proposed method is verified using the bearing public data, and it is successfully applied to performance degradation trend prediction of rolling contact fatigue specimen. The results show that the feature set can be reduced from 14 dimensions to 4 dimensions by using KPCA, while 98.33% of the information of the original feature set is retained. Furthermore, the method of constructing HI based on CAE network is effective. The change process of the HI constructed truly reflects the performance degradation process of the rolling contact fatigue specimen. Compared with the two commonly used HI construction methods, auto-encoding (AE) network and gaussian mixture model (GMM), this method has obvious advantages. At the same time, the prediction model based on TCN can accurately predict the performance degradation of the rolling contact fatigue specimen with the root mean square error 0.0146 and the mean absolute error 0.0105, which has better performance and higher prediction accuracy than the prediction model based on the long short-term memory (LSTM) network and the gated recurrent unit (GRU). This method has general significance and may be extended to the performance degradation prediction of other mechanical equipment/parts.

Visual signals are the upmost important source for robots, vehicles or machines to achieve human-like intelligence. Human beings heavily depend on binocular vision to understand the dynamically changing world. Similarly, intelligent robots or machines must also have the innate capabilities of perceiving knowledge from visual signals. Until today, one of the biggest challenges faced by intelligent robots or machines is the matching in stereovision. In this paper, we present the details of a new principle toward achieving a robust matching solution which leverages on the use and integration of top-down image sampling strategy, hybrid feature extraction, and RCE neural network for incremental learning (i.e., cognition) as well as robust match-maker (i.e., recognition). A preliminary version of the proposed solution has been implemented and tested with data from Maritime RobotX Challenge (www.robotx.org). The contribution of this paper is to attract more research interest and effort toward this new direction which may eventually lead to the development of robust solutions expected by future stereovision systems in intelligent robots, vehicles and machines.

The combination of organic matter, iron oxide, and clay minerals is of great significance for the adsorption of copper ions (Cu). The purpose of this study is to explore the characteristics of Cu adsorption and laws governing Cu complexation to organic–inorganic, organic–clay mineral, and iron-oxide–clay mineral complexes in the sediments in the estuary of plateau fault and sinking lake——Dianchi Lake. In this study, Cu adsorption tests were performed on the three complexes, in order to study the kinetic behavior of adsorption, Langmuir and Freundlich isotherm models were used. The samples before and after adsorption were characterized via scanning electron microscope (SEM), Fourier infrared spectroscopy (FTIR), and X-ray diffraction (XRD). Our results show that, the Freundlich isotherm models model was able to describe adsorbent behavior in comparison to the Langmuir models. During the Cu adsorption process, the iron-oxide–clay mineral complex is able to adsorb Cu, via coordination exchange, through the –OH contained therein. Organic-matter–clay mineral complexes bonded to the surfaces of clay minerals by replacing the hydroxyl groups with functional groups (carboxyl groups or phenolic hydroxyl groups) contained in the organic matter. Organic–inorganic composites then adsorbed Cu through the coordination exchange of –OH in the polar functional groups of alcohols, phenols, and carboxylic acids. The adsorption capacity of Cu in these three sediment complexes was observed to have the following order: organic–inorganic complex > organic-matter–clay mineral complex > iron-oxide–clay mineral complex. The semi-quantitative analysis results of Fourier Infrared Spectroscopy show that the organic matter (changes in the peak area of functional groups such as carboxyl groups) in the organic-inorganic composite material has an important effect on the amount of copper ions adsorbed by clay minerals.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.

Background: The gut microbiome plays a major role in chronic diseases, of which several are characterized by an altered composition and diversity of bacterial communities. Large-scale sequencing projects allowed characterizing the perturbations of these communities. However, translating these discoveries into clinical applications remains a challenges. To facilitate routine implementation of microbiome profiling in clinical settings, portable, real-time, and low-cost sequencing technologies are needed. Results: Here, we propose a computational and experimental protocol for whole genome quantitative metagenomics studies of human gut microbiome with Oxford Nanopore sequencing technology (ONT) that could be applied to other microbial ecosystems. We developed a bioinformatic protocol to analyse ONT sequences taxonomically and functionally and optimized pre-analytic protocols including stool collection and DNA extraction methods to maximize read length. This is a critical parameter for the sequence alignment and classification. Our protocol was evaluated using simulations of metagenomic communities which reflect naturally occuring compositional variations. Next, we validated both protocols using stool samples from a bariatric surgery cohort, sequenced with ONT, Illumina and SOLiD technologies. Results revealed similar diversity and microbial composition profiles. Conclusion: This protocol can be implemented in the clinical or research setting, bringing rapid personalized whole genome profiling of target microbiome species.

Deep convolutional neural network (CNN) has shown their great advantages in the single image deraining task. However, most existing CNN-based single image deraining methods still suffer from residual rain streaks and details lost. In this paper, we propose a deep neural network including the Multi-scale feature extraction module and the channel attention module, which are embed in the feature extraction sub-network and the rain removal sub-network respectively. In the feature extraction sub-network, the Multi-scale feature extraction module is constructed by a Multi-layer Laplacian pyramid, and is then integrated multi-scale feature maps by a feature fusion module. In the rain removal sub-network, the channel attention module, which assigns different weights to the different channels, is introduced for preserving image details. Experimental results on visually and quantitatively comparison demonstrate that the proposed method performs favorably against other state-of-the-art approaches

Autonomous driving systems are increasingly becoming a necessary trend towards building smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that effectively considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper has reviewed various techniques towards proposing our own end-to-end autonomous vehicle system, considering the latest state on the art on computer vision, DSs, path planning, and parallelization.

A novel machine learning approach is presented in this paper, based on extracting latent information and using it to assist decision making on ambulance attendance and conveyance to a hospital. The approach includes two steps: in the first, a forward model analyzes the clinical and, possibly, non-clinical factors (explanatory variables), predicting whether positive decisions (response variables) should be given to the ambulance call, or not; in the second, a backward model analyzes the latent variables extracted from the forward model to infer the decision making procedure. The forward model is implemented through a machine, or deep learning technique, whilst the backward model is implemented through unsupervised learning. An experimental study is presented, which illustrates the obtained results, by investigating emergency ambulance calls to people in nursing and residential care homes, over a one-year period, using an anonymized data set provided by East Midlands Ambulance Service in United Kingdom.

The extracts from the aerial parts of Helianthus salicifolius A. Dietr and Helianthus tuberosus L. collected in June were obtained using carbon dioxide supercritical fluid extraction with water as co-solvent. The antimicrobial activity in vitro of these extracts were determined against the reference species of Gram-positive and Gram-negative bacteria as well as fungi, representing by the yeast species of Candida spp. The following parameters were estimated: minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) or minimum fungicidal concentration (MFC). Both extracts were found to possess antimicrobial activity with MIC = 0.62-5 mg mL-1 for bacteria and MIC = 5-10 mg mL-1 for yeasts, showing bactericidal (MBC/MIC = 2-4) or fungicidal effect (MFC/MIC = 1-2 ). The highest activity was observed against S. aureus ATCC 29213 (MIC = 0.62 mg mL-1 for H. salicifolius extract; MIC = 2.5 mg mL-1 for H. tuberosus extract). Bactericidal effect of both extracts against S. aureus ATCC 29213 was confirmed by time-kill assay. Higher antioxidant activity was found for H. tuberosus extract (EC50 = 0.332 mg mL-1) as compared to that of H. salicifolius (EC50 = 0.609 mg mL-1). The total polyphenol content (TPC) expressed as gallic acid equivalents (GAE) was 13.75 ± 0.50 mg GAE (g of H. salicifolius extract)-1 and 33.06 ± 0.80 mg GAE (g of H. tuberosus extract)-1. There was a correlation between the antioxidant potential of both extracts and TPC but not between antistaphylococcal activity and TPC. The obtained data suggest potential application of these extracts as the natural preparations with the biocidal activity, including those with antistaphylococcal activity. Besides, both extracts may be regarded as potential natural conservants in cosmetics as well as natural preservatives in food.

Quebec is the third-largest wine grape producing province in Canada, and the industry is constantly expanding. Traditionally, 90% of the grapevine cultivars grown in Quebec were rustic or semi-rustic and largely dominated by winter hardy interspecific hybrid Vitis sp. cultivars. Over the years, the winter protection techniques adopted by growers and climate changes have offered an opportunity to establish V. vinifera L. cultivars (e.g. Pinot Noir). We characterized the virome of leafroll-infected interspecific hybrid cultivar and compared it to the virome of V. vinifera cultivar to support and facilitate the transition of the industry. A dsRNA sequencing method was used to sequence symptomatic and asymptomatic grapevine leaves of different cultivars. The results suggested a complex virome in terms of composition, abundance, richness, and phylogenetic diversity. Three viruses, grapevine Rupestris stem pitting-associated virus, grapevine leafroll-associated virus (GLR) 3 and 2 and hop stunt viroid (HSVd) largely dominated the virome. However, their presence and abundance varied among grapevine cultivars. The symptomless grapevine cultivar Vidal was frequently infected by multiple virus and viroid species and different strains of the same virus, including GLR virus 3 and 2. Our data shows that viruses and viroids associated with the highest number of grapevines expressing symptoms included HSVd, GLR3 and GLR2, in gradient order. However, co-occurrence analysis revealed that the presence of GLR species was randomly associated with the development of virus-like symptoms. These findings and their implication for grapevine leafroll disease management were discussed.

Cellulose nanocrystals are of major research interest because of their use in biodegradable bioplastcs and food packaging, biomaterials, medical and pharmaceutical applications, cosmetics, electronics, and construction materials. This study introduces an approach combining microwave-assisted extraction (MAE) of cellulose from Aloe Vera plant residue and subsequent isolation of cellulose nanocrystals (CNCs) utilizing sulfuric acid hydrolysis. The MAE process, characterized by its rapid heating and penetrating ability, was optimized to maximize cellulose yield from raw biomass sources under various conditions (microwave power, solvent ratio, and time). Following extraction, the purified cellulose was subjected to sulfuric acid hydrolysis under controlled conditions to yield CNCs, with the aim of preserving the intrinsic crystalline structure while enhancing the material's physicochemical properties. The search for biocompatible and biodegradable materials suitable for biomedical applications has led to significant interest in hydrogels composed of natural polymers. Among these, hydrogels synthesized from cellulose and polyvinyl alcohol (PVA) have emerged as promising candidates due to their unique physical properties and compatibility with biological tissues. This study presents the formulation, characterization, and potential biomedical applications of a cellulose/PVA hydrogel. The hydrogel was synthesized to enable the formation of a semi-crystalline network that imparts the material with enhanced mechanical properties.

The accurate diagnosis and effective treatment of mental health disorders such as depression remain challenging owing to the complex underlying causes and varied symptomatology. Traditional information extraction methods struggle to adapt to evolving diagnostic criteria such as the Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5) and to contextualize rich patient data effectively. This study proposes a novel approach for enhancing information extraction from mental health data by integrating medical knowledge graphs and large language models (LLMs). Our method leverages the structured organization of knowledge graphs specifically designed for the rich domain of mental health combined with the powerful predictive capabilities and zero-shot learning abilities of LLMs. This research enhances the quality of knowledge graphs through entity linking and demonstrates superiority over traditional information extraction techniques, making a significant contribution to the field of mental health. It enables a more fine-grained analysis of the data and the development of new applications. Our approach redefines the manner in which mental health data are extracted and utilized. By integrating these insights with existing healthcare applications, the groundwork is laid for the development of real-time patient monitoring systems. The performance evaluation of this knowledge graph highlights its effectiveness and reliability, indicating significant advancements in automating medical data processing and depression management.

Litsea martabanica root's antioxidant and AChE activity showed promise as a pesticide detoxification agent in our previous study. In addition to roots, its leaves can help mitigate pesticide exposure, although there is limited scientific evidence supporting their efficacy. However, the use of roots in many countries, such as Thailand, could contribute to environmental degradation, as highland communities traditionally cut down whole trees to obtain them. This study aims to evaluate the antioxidant activity and anti-pesticide potential of water extracts from L. martabanica leaves instead of its roots through in vitro and in vivo investigations. The findings showed that L. martabanica water extracts and fractions demonstrated varied antioxidant activity. The water extract, obtained using traditional extraction methods, was chosen for in vivo experiments. Rats received the extract followed by chlorpyrifos exposure for 16 days. Results indicated reduced acetylcholinesterase activity in chlorpyrifos-exposed rats, while treatment with leaf extract led to increased activity, suggesting its potential as a detoxifying agent. Histopathological examination revealed no liver cell necrosis and showed liver cell regeneration, indicating potential protection against free radical-induced liver damage without affecting rat liver weight or biochemical profiles. Utilizing L. martabanica leaves for healthcare purposes holds promise without negative environmental impact.

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

The pharmaceutical industry is one of the largest pollutants and generator of toxic solvent resi-dues for the environment and human beings. In the last decade, there has been a huge evolution in the design and development of new environmentally friendly products and processes, in re-sponse to the global environmental concern and the growing demand for products with quality ingredients and manufacturing processes aimed at achieving sustainability. Consumers are looking for products with the benefits of natural products, with sustainable and environmentally friendly formulations with few synthetic molecules as possible. Thus, based on the origins of the pharmaceutical industry, it is important to return to Nature and enjoy the benefits that natural products bring to us. Deep eutectic solvents appear as an alternative to toxic solvents commonly used to extract bioactive compounds. These solvents are considered green solvents because they are made up of natural compounds such as sugars, amino acids, and carboxylic acids. In addition, they are simple to prepare, with an atomic economy of 100%, with attractive physicochemical properties. This paper is a comprehensive review in which is described the main properties, characteristics, and production methods of deep eutectic solvents as well as its application to extract from natural sources bioactive compounds with pharmaceutical interest.

Deep learning is based on matrix computing with a large amount of hidden parameters that is not visible outside the computing module. Deep learning is a non-linear system and a linear approach is not possible. It is natural for people to visualize the algorithm and to follow some hidden parameters. In this paper, we propose a simple graphical programming of a nonlinear system based on drawing the simplest unit, such as a single neuron model. A more complex scheme of a classical neural network is obtained by commands copy-move-place of one neuron. The number of neurons and layers can be chosen arbitrarily. Once the scheme is complete, the implementation code is evaluated with symbolic parameters and nonlinear activation functions. This cannot be done manually. With the symbolic expression of outputs in terms of inputs and symbolic parameters, including symbolic activation pure functions, some other properties can be derived in closed form. This unique original approach can help scientists and developers and design numerical algorithms for machine learning and to understand how deep learning algorithms work.

In industrial settings, gears play a crucial role by assisting various machinery functions such as speed control, torque manipulation, and altering motion direction.The malfunction or failure of these gear components can have serious repercussions, resulting in production halts and financial losses. As a result, there is an increasing requirement to monitor the state of these components in order to avoid such issues from occurring. To address this need, research efforts have focused on early defect detection in gears in order to reduce the impact of possible failures. This study focused on analyzing vibration and thermal datasets from two extruder machine gearboxes using an autoencoder Long Short-Term Memory (LSTM) model. The major goal is to implement an outlier detection approach to detect and classify defects. The results of this study highlighted the extraordinary performance of the Autoencoder LSTM model, which achieved an impressive accuracy rate of 94.42% in recognizing malfunctioning gearboxes within the extruder machine system. Furthermore, the study used a thorough global metrics evaluation methodology to further test the model’s dependability and efficacy, consequently substantiating the proposed approach’s validity.

In commercial terms, Virgin Olive Oil (VOO) is considered an exceptional food of excellent sensory and nutritional quality, for its taste and genuine odour and, as well as for its bioactive compounds, of a great interest for the health. This quality can be affected by oxidative degradation, chemical as well as enzymatic (activity of oxidative endogenous enzymes from polyphenol oxidase and peroxidase olive fruit type), of essential components during extraction and conservation of VOO. In the bibliography, the reduction of oxygen during the malaxation process and the storage of the oil has been studied in different ways. However, research about the reduction of oxygen in the crushing of olive fruit, malaxation of the paste and/or both at the same time in “real extraction condition” is scarce. The reduction of oxygen has been compared to control conditions (concentration of atmospheric oxygen of 21%). Batches of 200 kg of olive fruit, Picual cultivar, were used and the following treatments were applied: Control (21% O2 Mill - 21% O2 Mixer), “IM-NM”: Inerted milling -Normal malaxation (6.5% O2 Mill-21% O2 Mixer), “NM-IM”: Normal milling-Inerted malaxation (21% O2 Mill-4 % O2 Mixer) and “IM-IM”: Inerted milling-Inerted malaxation (5.5% O2 Mill-10% O2 Mixer). The parameters of commercial quality covered by Regulation: free acidity, peroxide value and absorbency in ultra-violet (k 232 and k270) did not suffer any change in relationship to the control, the oils belong to the comercial category of “Extra virgin olive oil”. The phenolic compounds are involved in the distinctive bitter and purgent taste and, their healthy properties and their oxidative stability, increased with the downsizing amounts of oxygen regarding control and the IM-NM, NM-IM and IM-IM treatments with an average of 4, 10 and 20 %, respectively. By contrast, total volatile compounds decrease between a 10-20 % in all oxygen reduction treatments. The volatile compounds arising from lipoxygenase pathway, which are responsable for the green and fruity notes of VOO, also decreased their concentration with the treatments, between 15-20%. The results show how the reduction of oxygen in the milling and malaxation stages of olive fruit can modulate the content of phenols, volatile compounds, carotenoids and chlorophyll pigments of the VOO avoiding the degradation of compound with sensorial and nutritional interest.

Almond beverages are gaining ever-increasing consumer preference in the growing market of non-alcoholic vegetable beverages, ranking in first place among oilseed-based drinks, mainly due to the perceived healthy benefits. However, the high cost of the raw material, time and energy consuming pre-treatments such as soaking, blanching and peeling, and post-treatments such as thermal sterilization, leading also to the loss of valuable macronutrients and micronutrients, hinder the sustainability, affordability and spread of almond beverages. Hydrodynamic cavitation processes were applied, as a single-unit operation, to the extraction in water of almond skinless kernels in the form of flour and fine grains, and to whole almond seeds in the form of coarse grains, up to high concentrations. The results showed full compliance with a high-end commercial product and with the expected levels based on the properties of the raw materials. The concentrated extract obtained from whole almond seeds showed a comparatively much higher antiradical activity, likely due to the contribution of the almond kernel skin. In conclusion, hydrodynamic cavitation could represent a convenient alternative processing route to the production of conventional and new integral almond beverages, avoiding multiple and costly technological steps, while affording fast production cycles of potentially healthier beverages.

With the increasing availability of large digitized fine art collections, automated analysis and classification of paintings is becoming an interesting area of research. However, due to domain specificity, implicit subjectivity, and pervasive nuances that vaguely separate art movements, analyzing art using machine learning techniques poses significant challenges. Residual networks, or variants thereof, are one the most popular tools for image classification tasks, which can extract relevant features for well-defined classes. In this case study, we focus on the classification of a selected painting 'Portrait of the Painter Charles Bruni' by Johann Kupetzky and the analysis of the performance of the proposed classifier. We show that the features extracted during residual network training can be useful for image retrieval within search systems in online art collections.

The extraction of grape processing waste (wine pomace) via microwave-hydrodiffusion and gravity (MHG) from three different cultivars grown in Sicily (Syrah, Perricone and Nero d’Avola) rapidly affords aqueous extracts highly concentrated in valued biophenols including flavonoids, anthocyanins and phenolic acids. The method does not employ organic solvent, acid or base and does not require grinding or freeze drying of the wine pomace nor separation of the grape skins from seeds and stem. All the extracts have a pronounced stability as shown by their red-violet color fully retained after storage for more than a year (15 months) in freezer under air. Concentrations of phenolics up to 2000 ppm were detected in the aged extracts of Sicily’s local cultivar Perricone, which also has the highest content of flavonoids. These findings provide a simple and economically viable extraction route to biophenol-rich red extracts that can be used as food colorants as well as to formulate nutraceutical, cosmetic and personal care products starting from an agricultural by-product available in >10 million tonne yearly amount.

Scintillators play a key role in the detection chain of several applications which rely on the use of ionizing radiation, and it is often mandatory to extract and detect the generated scintillation light as efficiently as possible. In positron emission tomography (PET), for example, both energy resolution and coincidence resolving time, two of the key detection parameters, depend strongly on the total amount of light which reaches the photodetector surface as well as its spatial and temporal distribution. Typical inorganic scintillators do however feature a high index of refraction, which impacts light extraction efficiency in a negative way. Furthermore, several applications such as preclinical PET rely on pixelated scintillators with small pitch. In this case, applying reflectors on the crystal pixel surface, as done conventionally, can have a dramatic impact of the packing fraction and thus the overall system sensitivity. This paper presents a study on light extraction techniques, as well as combinations thereof, for two of the most used inorganic scintillators (LYSO and BGO). Novel approaches, employing distributed Bragg reflectors (DBRs), metal coatings, and a modified Photonic Crystal (PhC) structure, are described in detail and compared with commonly used techniques. The nanostructure of the PhC is surrounded by a hybrid organic/inorganic silica sol-gel buffer layer which ensures robustness while maintaining its performance unchanged. We observed in particular a maximum light gain of about 41% on light extraction and 21% on energy resolution for BGO, a scintillator which has gained interest in the recent past due to its prompt Cherenkov component and lower cost.

Marine invertebrates are model organisms in several areas of biological sciences, being a source of massive biological information. Although, the scientific relevance of marine invertebrates, the research with them can be limited for their tissue characteristics and troubles for the replication of physical and chemical properties of seawater. Thence, the main goal of this laboratory workflow is to provide a useful methodological approach to reduce the experimental limitations during the study of marine invertebrates. The present study describes experimental methodologies for the collection, transport, and maintenance of sessile tunicates. Also, an approach to observe and characterize, a diverse population of blood cells in marine invertebrates, by several cytological stains and electron microscopy. Lastly, suggestions and protocols to extract quality RNA from samples with high concentrations of salts, pigments, secondary metabolites, and polysaccharides. This methodological approach can be easily adapted to other marine invertebrates, moreover uses low-cost reagents and widely available laboratory equipment. Making possible the study of different types of marine animals in diverse locations.

One of the most common and important destructive attacks on the victim system is Advanced Persistent Threats (APT)-attack. The APT attacker can achieve his hostile goals by obtaining information and gaining financial benefits regarding the infrastructure of a network. One of the solutions to detect a secret APT attack is using network traffic. Due to the nature of the APT attack in terms of being on the network for a long time and the fact that the network may crash because of high traffic, it is difficult to detect this type of attack. Hence, in this study, machine learning methods such as C5.0 decision tree, Bayesian network and deep neural network are used for timely detection and classification of APT-attacks on the NSL-KDD data set. Moreover, 10-fold cross validation method is used to experiment these models. As a result, the accuracy (ACC) of the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 95.64%, 88.37% and 98.85%, respectively, and also, in terms of the important criterion of the false positive rate (FPR), the FPR value for the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 2.56, 10.47 and 1.13, respectively. Other criterions such as sensitivity, specificity, accuracy, false negative rate and F-measure are also investigated for the models, and the experimental results show that the deep learning model with automatic multi-layered extraction of features has the best performance for timely detection of an APT-attack comparing to other classification models.

Continuous research into the availability of phosphorus (P) in forest soil is critical for sustainable management of forest ecosystems. In this study, we used sequential chemical extraction and 31P-nuclear magnetic resonance spectroscopy (31P-NMR) to evaluate the form and distribution of inorganic P (Pi) and organic P (Po) in Casuarina forest soils of a subtropical coastal sand dune at Houlong in Taiwan. The soil samples were collected from humic (+2-0 cm) and mineral layers (mineral-I: 0-10, mineral-II: 10-20 cm) at two topographic locations (upland and lowland) by elevation. Sequential chemical extraction revealed that the NaOH-Po fraction, as moderately recalcitrant P, was the dominant form in humic and mineral-I layers in both upland and lowland soils, whereas the cHCl-Pi fraction was the dominant form in the mineral-II layer. Resistant P content, including NaOH-Pi, HCl-Pi, cHCl-Pi, and cHCl-Po fractions, was higher in the upland than lowland in the corresponding layers; however, labile P content, NaHCO3-Po, showed the opposite pattern. Content of resistant Pi (NaOH-Pi, HCl-Pi, and cHCl-Pi) increased significantly with depth, but that of labile Pi (resin-Pi and NaHCO3-Pi) and recalcitrant Po (NaHCO3-Po, NaOH-Po, and cHCl-Po) decreased significantly with depth at both locations. 31P-NMR spectroscopy revealed inorganic orthophosphate and monoesters-P as the major forms in this area. The proportions of Pi and Po evaluated by sequential chemical extraction and 31P-NMR spectroscopy were basically consistent. The results indicated that the soils were in weathered conditions. Furthermore, the P distribution and forms significantly differed between the upland and lowland by variation in elevation and eolian aggradation effects in this coastal sand dune landscape.

The feasible, reliable and selective multi-template molecularly imprinted polymers (MT-MIPs) based on SBA-15 (SBA-15@MT-MIPs) for the selective separation and determination of the trace level of ginsenoside Rb₁ (Rb₁), ginsenoside Rg₁ (Rg₁) and notoginsenoside R₁ (R₁) (Panax notoginseng saponins, PNS) from biological samples were developed. The polymers were constructed by SBA-15 as support, Rb₁, Rg₁, R₁ as multi-template, acrylamide (AM) as functional monomer and ethylene glycol dimethacrylate (EGDMA) as cross-linker. The new synthetic SBA-15@MT-MIPs were satisfactorily applied to solid-phase extraction (SPE) coupled with high performance liquid chromatography (HPLC) for the separation and determination of trace PNS in plasma samples. Under the optimized conditions, the limits of detection (LODs) and quantitation (LOQs) of the proposed method for Rb₁, Rg₁ and R₁ were in the range of 0.63-0.75 ng mL^-1 and 2.1-2.5 ng mL^-1, respectively. The recoveries of R₁, Rb₁ and Rg₁ were obtained between 93.4% and 104.3% with relative standard deviations (RSDs) in the range of 3.3-4.2%. All results show that the obtained SBA-15@MT-MIPs could be a promising prospect for the practical application in the selective separation and enrichment of trace PNS in the biological samples.

This study was designed for the first time to improve phenolic yield and antioxidant activity of ultrasonic-assisted extraction from Acer truncatum leaves (ATL) using response surface methodology, and phenolic composition in ATL extracted under the optimized condition were characterized by UPLC-QTOF-MS/MS. Solvent and extraction time were selected based on preliminary experiments, and a four-factors-three-levels central composite design was conducted to optimize solvent concentration (X₁), material-to-liquid ratio (X₂), ultrasonic temperature (X₃) and power (X₄) for an optimal total phenol yield (Y₁) and DPPH• antioxidant activity (Y₂). The results showed that the optimal combination was ethanol: water (v:v) 66.21%, material-to-liquid ratio 1:15.31 g/mL, ultrasonic temperature 60 °C, power 267.30 W, and time 30 min with three extractions, giving a maximal total phenol yield of 7593.62 mg gallic acid equivalent /100 g d.w. and a maximal DPPH• antioxidant activity of 74241.61 μmol Trolox equivalent/100 g d.w.. Furthermore, 22 phenolics were first identified in ATL extract obtained under the optimized conditions, indicating that gallates, gallotannins, quercetin, myricetin and chlorogenic acid derivatives were the main phenolic composition in ATL. What’s more, a gallotannins pathway existing in ATL from gallic acid to penta-O-galloyl-glucoside was interpreted. All these results provided practical information aiming at full utilization of phenolics in ATL, together with fundamental knowledge for further research.

Surface water distribution extracted from remote sensing data has been used in water resource assessment, coastal management, and environmental change studies. Traditional manual methods for extracting water bodies cannot satisfy the requirements for mass processing of remote sensing data; therefore, accurate automated extraction of such water bodies has remained a challenge. The histogram bimodal method (HBM) is a frequently used objective tool for threshold selection in image segmentation. The threshold is determined by seeking twin peaks, and the valley values between them; however, automatically calculating the threshold is difficult because complex surfaces and image noise which lead to not perfect twin peaks (single or multiple peaks). We developed an operational automated water extraction method, the modified histogram bimodal method (MHBM). The MHBM defines the threshold range of water extraction through mass static data; therefore, it does not require the identification of twin histogram peaks. It then seeks the minimum values in the threshold range to achieve automated threshold. We calibrated the MHBM for many lakes in China using Landsat 8 Operational Land Imager (OLI) images, for which the relative error (RE) and squared correlation coefficient (R2) for threshold accuracy were found to be 2.1% and 0.96, respectively. The RE and root-mean-square error (RMSE) for the area accuracy of MHBM were 0.59% and 7.4 km2. The results show that the MHBM could easily be applied to mass time-series remote sensing data to calculate water thresholds within water index images and successfully extract the spatial distribution of large water bodies automatically.

Gastric cancer is the fifth most common and fourth deadliest cancer worldwide, with a bleak 5-year survival rate of about 20%. Despite significant research into its pathobiology, prognostic predictability remains insufficient due to pathologists’ heavy workloads and the potential for diagnostic errors. Consequently, there is a pressing need for automated and precise histopathological diagnostic tools. This study leverages Machine Learning and Deep Learning techniques to classify histopathological images into healthy and cancerous categories. By utilizing both handcrafted and deep features and shallow learning classifiers on the GasHisSDB dataset, we conduct a comparative analysis to identify the most effective combinations of features and classifiers for differentiating normal from abnormal histopathological images without employing fine-tuning strategies. Our methodology achieves an accuracy of 95% with the SVM classifier, underscoring the effectiveness of feature fusion strategies. Additionally, cross-magnification experiments produced promising results with accuracies close to 80% and 90% when testing the models on unseen testing images with different resolutions.

Product attribute extraction is an growing field in e- commerce business, with several applications including product ranking, product recommendation, future assortment planning and improving online shopping customer experiences. Under- standing the customer needs is critical part of online business, specifically fashion products. Retailers uses assortment planning to determine the mix of products to offer in each store and channel, stay responsive to market dynamics and to manage inventory and catalogs. The goal is to offer the right styles, in the right sizes and colors, through the right channels. When shoppers find products that meet their needs and desires, they are more likely to return for future purchases, fostering customer loyalty. Product attributes are a key factor in assortment planning. In this paper we present PAE, a product attribute extraction algorithm for future trend reports consisting text and images in PDF format. Most existing methods focus on attribute extraction from titles or product descriptions or utilize visual information from existing product images. Compared to the prior works, our work focuses on attribute extraction from PDF files where upcoming fashion trends are explained. This work proposes a more comprehensive framework that fully utilizes the different modalities for attribute extraction and help retailers to plan the assortment in advance. Our contributions are three-fold: (a) We develop PAE, an efficient framework to extract attributes from unstructured data (text and images); (b) We provide catalog matching methodology based on BERT representations to discover the existing attributes using upcoming attribute values; (c) We conduct extensive experiments with several baselines and show that PAE is an effective, flexible and on par or superior (avg 92.5% F1-Score) framework to existing state-of-the-art for attribute value extraction task.

The rapid spread of African swine fever virus (ASFV), causing severe and often lethal disease in domestic pigs and Eurasian wild boar, continues to be a threat for pig populations and dependent industries. Despite scientific achievements that deepen our understanding of ASFV pathogenesis, alternative transmission routes for ASFV remain to be elucidated. We previously demonstrated the efficient transmission of ASFV from infected boars to naïve recipient gilts via artificial insemination, thereby highlighting the importance of surveillance in boar semen prior to shipment. Since accurate and reliable detection of even low amounts of ASFV in boar semen is key for disease prevention and control, we established a suitable diagnostic pipeline to efficiently detect ASFV genome in boar semen. Here, we assessed sensitivity, specificity and overall performance of various routine nucleic acid extraction kits as well as qPCR protocols in detecting ASFV genome in blood and semen of boars. Feasibility of respective kits and methods for future use in boar studs was also considered. Variability in sensitivity mostly concerned samples with low to very low amounts of ASFV genome. Ultimately, we defined a well-suited pipeline to precisely detect ASFV genome in boar semen, as early as 2 days post ASFV infection.

The growth rate in academic and scientific publications increased very fast. Researchers must choose a good representative and significant literature in publications, which has become challenging worldwide. Usually, the paper citation number indicates this paper's potential influence and importance. However, this standard metric of citation numbers cannot be used as a measurement to judge the popularity and significance of the recently published papers. To address this challenge, this paper presents an effective prediction method called FutureCite to predict the future citation level of research articles. FutureCite combines machine learning with text and graph mining techniques, leveraging their abilities in classification, datasets in-depth analysis, and feature extraction. FutureCite aims to predict future citation levels of research articles applying a multilabel classification approach. FutureCite can extract significant semantic features and capture the interconnection relationships found in scientific articles during feature extraction using textual content, citation networks, and metadata as feature resources. Our goal is to contribute to the advancement of substantial effective approaches impacting the citation counts in scientific publications by enhancing the precision of future citations. We conducted several experiments using a comprehensive publication dataset to evaluate our method and determine the impact of using a variety of machine learning algorithms. FutureCite demonstrated its robustness and efficiency and showed promising results based on different evaluation metrics. Using the FutureCite model has significant implications in improving the researchers' ability to determine targeted literature for their research and better understand the potential impact of research publications.

ABSTRACT Purpose: Tongue image analysis for disease diagnosis is an ancient traditional non-invasive diagnosis technique widely used by traditional medicine practitioners. Deep Learning based multi-label disease detection models offer tremendous potential to clinical decision support systems, by facilitating preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline, where in observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. All images are voluntarily given by subjects consulting collaborating physicians. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolution neural network (MobileNetV2) model for binary classification. Once the diseased label is predicted, the image is used to diagnose multiple diseases using the prediction algorithm based on DenseNet121. Results: Average accuracy of 93 % was achieved in classifying diseased from normal healthy tongue by detection model with MobileNetV2 architecture. Multilabel disease classification produced more than 90% accurate results for the seven class labels considered. Conclusion: AI based image analysis shows promising results and an extensive dataset could provide further improvements to this approach. Rather than employing high-cost sophisticated image capturing setup, experimenting with smartphone images opens opportunity to provide preliminary health status to individuals on smartphone prior to further line of treatment and diagnosis.

The article presents the results of cyanide leaching of gold-containing concentrate using the trichlorocyanuric acid (TCCA) oxidizer. Gold-containing concentrate obtained from a gold tailings sample from a gold recovery factory (GRF) in one of the deposits of Kazakhstan that was not previously studied for concentrability. According to X-ray phase analysis and energy dispersive spectrometry (DSM) data, the main compounds in the tailings sample under study are: pyrite FeS2, quartz SiO2, calcite CaCO3, albite NaAlSi3O8, muscovite KAl2Si3AlO10(OH)8, dolomite CaMg(CO3)2, and oxidized iron compounds. Microscopic studies have established the presence of gold grains in free form, ranging in size from 0.9-10.2 mkm Au-ultrafine and fine gold. Obtaining a gold-containg concentrate with a gold content of 15.95 g / t is possible according to the enrichment scheme, which includes centrifugal separation, classification according to the fineness class -0.05 mm, additional grinding of hydrocyclone sands to a fineness of 90.0-95.0% of the class finer than 0.050 mm, and control centrifugal separation. Since pyrite in technogenic raw materials is the main gold-containing mineral, this paper presents studies on the oxidizability of pyrite with the TCCA oxidizer. The results of studies on the oxidation of pyrite using the TCCA oxidizer show that the products of its hydrolysis oxidize pyrite with the formation of various iron compounds on its surface. Pretreatment of gold-containing concentrate with oxidizer TCCA for 3 hours before the cyanidation process (20 hours) allows to increase the recovery of gold in the solution by 5.8 %.

Cinnamomum tamala leaf (CTL), also known as tejpat and Indian bay leaf, is used all over the world for seasoning, flavouring, and medicinal purposes. Numerous researchers are interested in exploring the nutritional and medicinal benefits of CTL due to their potential as nutraceuticals. These characteristics could be explained by the presence of several essential bioactive substances and lipid derivatives. There are no reports available on this species about its metabolites profile. In this work, rapid screen and identify chemical compounds in supercritical (SC)-CO2 extracts of CTL by use of UPLC-Q-TOF-MSE with multivariate statistical analysis approach was established in both negative and positive mode. As a results, a total of 166 compounds, including 66 monocarboxylic fatty acids, 52 dicarboxylic fatty acids, 27 fatty acid amides, and 21 others were tentatively identified based on accurate mass, and the mass spectrometric fragmentation pattern, out of which 142 compounds are common and found in all five CTL extracts. They displayed robust [M+H]+ and/or [M-H]- ions in both low- and high-energy collision-induced dissociations (CIDs). Based on chemical profiling and chemometric analysis, CTL4 (300bar/55°C) extract was found significantly more potent in other CTL’s extracts. A new mono- and di-carboxylic fatty acids, fatty acid amides and other essential bioactive compounds were separated within 20 min runtime and identified in CTL for the first time. The combination of UPLC-Q-TOF-MSE and chemometric analysis is a powerful method to rapidly screen the metabolites profile for the quality control of C. tamala leaf.

From a structural point of view, understanding interfacial electrostatic features of ligand-receptor complexes is crucial for biophysics-based design of therapeutics with improved efficacy and safety. Here, with a high-throughput structural feature extraction approach, this article reports a set of electrostatic structural features from glucagon-like peptide-1 (GLP-1) and GLP-1 receptor (GLP-1R) complex structures determined using experimental tools. Leveraging a set of computational structural biophysical analyses, this article systematically characterized the electrostatic interactions within the GLP-1-GLP-1R complexes with two sets of criteria to identify interfacial salt bridges and hydrogen bonds. Overall, the results here reveal intricate details of electrostatic interactions critical for GLP-1 binding to its receptor GLP-1R, providing biophysical insights into the stabilization of the GLP-1-GLP-1R complex structure and the molecular basis of GLP-1/GLP-1R signaling. Furthermore, the electrostatic structural features extracted from GLP-1 and GLP-1R complex structures are useful in the development of a machine learning-based ligand-receptor binding affinity calculating model, i.e., a GLP-1-GLP-1R-specific general intermolecular binding affinity calculator (GIBAC), paving the way for accelerated discovery and structure-based design of drug candidates targeting the GLP-1/GLP-1R system with improved efficacy and safety.

The goal of this article was to evaluate the antioxidant and anti-inflammatory like activities of three species from genus Primula L. growing in Georgia: Primula macrocalyx, Primula woronowii and Primula saguramica . First, fractions containing shoot and root parts were air-dried, grinded and extracted by 80% ethanol followed by condensation and freeze-drying. Second, further chromatographic separations were done on Diaion HP-20 with the following solvents: H2O, methanol (50% and 100 %) and ethylacetate 100% to obtain the expected fractions.

Background: Although electronic health records (EHR) provide useful insights into disease patterns and patient treatment optimisation, their reliance on unstructured data presents a difficulty. Because of their narrative structure, echocardiography reports, which provide extensive pathology information for cardiovascular patients, are particularly challenging to extract and analyse. Although natural language processing (NLP) has been utilised successfully in a variety of medical fields, it is not commonly used in echocardiography analysis. Objectives: To develop an NLP-based approach for extracting and categorizing data from echocardiography reports by accurately converting continuous (e.g. LVOT VTI, AV VTI, and TR Vmax) and discrete (e.g. Regurgitation severity) outcomes in semi-structured narrative format into structured and categorized format, allowing for future research or clinical use. Methods: 135,062 Trans-Thoracic Echocardiogram (TTE) reports were derived from 146967 baseline Echocardiogram reports and split into three cohorts: Training and Validation (n = 1075), Test Dataset (n = 98) and Application Dataset (n = 133,889). The NLP system was developed and iteratively refined using medical expert knowledge. The system was used to curate a moderate-fidelity database from extractions of 133,889 reports. A hold-out validation set of 98 reports was blindly annotated and extracted by two clinicians for comparison with the NLP extraction. Agreement, discrimination, accuracy and calibration of outcome measure extractions were evaluated. Results: Continuous outcomes including LVOT VTI, AV VTI, and TR Vmax exhibited perfect inter-rater reliability using intra-class correlation scores (ICC=1.00, P< 0.05) alongside high R2 values, demonstrating an ideal alignment between the NLP system and clinicians. Good level (ICC =0.75-0.9, P<0.05) of inter-rater reliability were observed for outcomes such as LVOT Diam, Lateral MAPSE, Peak E Velocity, Lateral E' Velocity, PV Vmax, Sinuses of Valsalva, and Ascending Aorta diameters. Furthermore, the accuracy rate for discrete outcome measures was 91.38% in the confusion matrix analysis, indicating effective performance. Conclusions: The NLP-based technique yielded good results when it came to extracting and categorising data from echocardiography reports. The system demonstrated a high degree of agreement and concordance with clinician extractions. This study contributes to the effective use of semi-structured data by providing a useful tool for converting semi-structured text to structured echo report that can be used for data management. Additional validation and implementation in healthcare settings can improve data availability and support research and clinical decision-making.

Development and implementation of safe natural alternatives to synthetic pesticides are urgent needs that will provide ecological solutions for control of plant diseases, bacteria, viruses, nematodes, pests, and weeds, to ensure economic stability of the farmers and food security as well as protection of the environment and human health. Unambiguously, production of botanical pesticides will allow sustainable and efficient use of natural resources and finally decrease the use of chemical inputs and burden. This is underlined by the strict regulations on pesticide residues in agricultural products and harmonized with the Farm to Fork strategy aimed to reduce pesticide use by 55%, by 2030. Recognizing the urgent need for natural pesticides development, this work is an overview of the current research on the valorization of Mediterranean plants as potential source of biopesticides. More specifically, the extraction methods, the chemical composition, the biopesticidal activity, the commonly used assays for evaluating the antimicrobial, the pesticidal, the repellant and the herbicidal activity of plant extracts as well as toxicological and safety aspects of biopesticides formulation are discussed in detail. Finally, the aspects that have not yet been investigated or are under- investigated and future perspectives are highlighted.

A morphological feature estimation method is presented, that can be used to monitor fish from low contrast underwater images and videos. The fish orientation is classified in order to apply a shape alignment technique that is based on the Ensemble of Regression Trees machine learning method. Shape alignment allows the estimation of fish dimensions (length, height, mass) and the location of fish body parts of particular interest such as the eyes and gills. The developed system can be exploited both for fish monitoring in open sea as well as aquacultures where non-invasive, low cost morphological feature extraction is essential. Fish health can be assessed from malformations in body shape, the color of the eyes or the gills as well as the fish behavior. The proposed method can estimate the position of 18 landmarks with an accuracy of about 95% from low resolution and low contrast underwater images where the fish can be hardly distinguished from its background. Hardware acceleration can be applied at various stages of the proposed method for real time video processing. As a case study, the developed system has been trained and tested with several Mediterranean fish species in the category of seabream or similar: diplodous sargus annularis (white seabream), diplodus annularis seabream (spawn), oblada melanura (saddled seabream), pagrus pagrus (common seabream), etc. A large dataset with low resolution underwater videos and images has been created in the context of this work.

This paper presents an Artificial Intelligence approach to mining context and emotions related to olfactory cultural heritage narratives, in particular to fairy tales. We provide an overview of the role of smell and emotions in literature, as well as highlight the importance of olfactory experience and emotions from psychology and linguistic perspectives. We introduce a methodology for extracting smells and emotions from text, as well as demonstrate the context-based visualizations related to smells and emotions implemented in a novel Smell Tracker tool. The evaluation is performed using a collection of fairy tales from Grimm and Andersen. We find out that fairy tales often connect smell with emotional charge of situations. The experimental results show that we can detect smells and emotions with F1 score of 92.7 and 79.2, respectively.

This paper proposes several LabVIEW applications to accomplish the data acquisition, processing, features extraction and real-time classification of the electroencephalographic (EEG) signal detected by the embedded sensor of the NeuroSky Mindwave Mobile headset. The LabVIEW applications are aimed at the implementation of a Brain-Computer Interface system, which is necessary to people with neuromotor disabilities. It is analyzed a novel approach regarding the preparation and automatic generation of the EEG dataset by identifying the most relevant multiple mixtures between selected EEG rhythms (both time and frequency domains of raw signal, delta, theta, alpha, beta, gamma) and extracted statistical features (mean, median, standard deviation, route mean square, Kurtosis coefficient and others). The acquired raw EEG signal is processed and segmented into temporal sequences corresponding to the detection of the multiple voluntary eye-blinks EEG patterns. The main LabVIEW application accomplished the optimal real-time artificial neural networks techniques for the classification of the EEG temporal sequences corresponding to the four states: 0 - No Eye-Blink Detected; 1 - One Eye-Blink Detected; 2 – Two Eye-Blinks Detected and 3 – Three Eye-Blinks Detected. Nevertheless, the application can be used to classify other EEG patterns corresponding to different cognitive tasks, since the whole functionality and working principle could estimate the labels associated with various classes.

Introduction. Bacterial resistance to antibiotics is estimated to cause the major number of deaths by 2050 if we do not find strategies to slow down the rise of drug resistance [1]. Reviews on Mediterranean Wild Edible Plants (MWEPs) with antimicrobial properties are scarce in the mean databases (Pubmed, Scopus and WoS). Hence, we proceeded to a new review of the studies on MWEPs. Methods. We used Wild Edible Plant and Antimicrobial as keywords. We only included the Mediterranean plants, and studies in non-Mediterranean countries, but for plants growing in Mediterranean basin. Exclusion criteria were the document type, studies not concerning plant, plants not edible, not antimicrobial properties, or totally out of topic. Results. Finally, the number of studies reviewed, starting from one hundred and ninety-two, was thirty-eight (19,8%), concerning the antimicrobial properties of seventy-four MWEPs species, be-longing to twenty-five Families. Fifty-seven (77%) out of seventy-four species, proved to be antimicrobial with a stringent threshold selection. Conclusions. The studies are still very heterogeneous. We still know too little about MWEPs properties, but what we already know seriously recommends continuing.

One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. At a time when the speed and reliability of results, especially for COVID-19 positive patients, is important, the development of applications that would facilitate the work of untrained staff involved in the evaluation is also crucial. Our model takes the form of a simple and intuitive application, into which you only need to upload X-rays: tens or hundreds at once. In just a few seconds, the physician will determine the patient's diagnosis, including the percentage accuracy of the estimate. While the original idea was a mere binary classifier that could tell if a patient was suffering from pneumonia or not, in this paper we present a model that distinguishes between a bacterial disease, a viral infection, or a finding caused by COVID-19. The aim of this research is to demonstrate whether pneumonia can be detected or even spatially localized using a uniform, supervised classification.

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents is growing enormously in recent years through instant messaging, social networking posts, blogs, online portals, and other digital platforms. Unfortunately, the misapplication of technologies has boosted with this rapid growth of online content which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier `tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

Manual interpretation of these huge amounts of image volumes are susceptible to inter-reader variability and human error. Thus, accurate automated CAD scheme is highly desirable in clinical pathological diagnosis. In this research, plethora of machine learning paradigms (e.g. feature extraction, dimensionality reduction and supervised classification methods) were explored, evaluated, compared and analyzed to identify the optimal pathway for brain MR images (normal vs neoplastic) binary classification task. External validation dataset was used to test the generalizability of the optimal predictive models implemented. Relevant and informative features were selected to construct cross-validated decision tree and eventually simple rule set was built based on the decision tree. The experimental results show that almost all pattern recognition paradigms achieve high accuracy with careful selection of number of attributes. LDA+ELM with 55 features are the optimal pipelines which achieve perfect classification when training and test data are of same source; and achieving (accuracy=97.5%, AUC=0.989, sensitivity=95% and specificity=100%) under balanced test dataset; (accuracy=99.5%, AUC=0.988, sensitivity=95% and specificity=100%). Cross-validated decision tree model also shows comparable performance: accuracy=98.8%, AUC=99.1%, sensitivity=99.6% and specificity=98.2%. Three highly relevant and robust attributes are visualized and selected for construction of decision tree models and finally a rule sets are read directly off the decision tree. This rule sets can potentially serve as fast and accurate classification algorithm.

Nymphaea lotus L. is the medicinal plant that has long been used as food, cosmetic and traditional medicines in Africa and Asia since the ancient time. Its flavonoids and other interesting phytochemical compounds from rhizome, leaf, and the whole flowers have been reported in the previous published researches. However, stamens, which are essential for reproductive functions, may also represent new alternative sources of potential antioxidant flavonoids as investigated in this study. The innovative green chemistry method i.e. ultrasound-assisted extraction (USAE) as well as macroporous resin (MPR) purification procedure were employed in this current research. The optimal ultrasound-assisted extraction condition is 90 % (v/v) aqEtOH with 34.65 khz ultrasonic frequency and 46 minutes of extraction time. Comparing with heat reflux extraction (HRE) conventional method, the significant gain of 1.35 total flavonoids content was obtained using optimized USAE conditions, jumping to 2.80 when this USAE associated with MPR purification. Not only in vitro cell free antioxidant activity of N. lotus stamen extracts, but also in cellulo antioxidant investigation using yeast model showed the same trend to indicate that the best antioxidant flavonoid can be found in USAE coupled with MPR purification. Moreover, the key antioxidant genes expression in yeast model such as SIR2 and SOD2 were also expressed at the highest level in yeast cell treated with the extract from USAE together with MPR purification. Consequently, it can be seen that the USAE combined with MPR purification can help to enhance the flavonoids antioxidant potential of the stamens extract from this medicinal species.

Repair mortar is commonly used to rehabilitate reinforced concrete structures or components that exhibit a relatively high level of distresses. Yet, this repair mortar can be contaminated by salt from its service environment. This work employs a two-dimensional finite element model to investigate the transport behavior of ionic species in salt-contaminated and water-saturated repair mortar under an externally applied electric field. The model was experimentally validated and then utilized to evaluate the effectiveness of electrochemical chloride extraction (ECE) with or without electrical injection of corrosion inhibitor (EICI). In the case study, both the ECE alone and the ECE+EICI treatment was found effective in decontaminating the zone in front of the steel rebar. In both techniques, the magnitude of current density has a significant effect on removing chloride out of the mortar and increasing the pH of the pore solution near the rebar, whereas the treatment time any not have a significant effect under some scenarios. The injection of the organic corrosion inhibitor significantly slowed down the removal of chloride. Changes in the ionic distribution in the mortar were generally beneficial in reducing the corrosion risk of the steel rebar and thus extending the service life of the repair mortar.

Bearing fault diagnosis is crucial for ensuring the stable operation of mechanical equipment. With the continuous development of deep learning technology, Convolutional Neural Networks (CNNs) have demonstrated significant advantages in the field of fault diagnosis. This paper proposes a new method that combines various CNN architectures to improve the accuracy of bearing fault diagnosis. We designed five different convolutional network structures, including SerConv, ResConv, One-Shot Aggregation Convolution (OSAConv), Cross-Stage Aggregation Convolution (CSAConv), and MD-DAConv. Experimental results on the Case Western Reserve University (CWRU) bearing dataset show that the proposed method exhibits high accuracy and robustness in fault diagnosis. The results indicate that strategies such as multi-directional, multi-scale, and residual connections play a crucial role in enhancing the depth and breadth of feature extraction, while simple and effective feature fusion and information transmission mechanisms are key to ensuring the robustness and generalization ability of the model.

Water samples for bacterial microbiome studies undergo a biomass concentration, DNA extraction and taxonomic identification steps. Through benchmarking, we studied the applicability of Skimmed milk flocculation (SMF) for bacterial enrichment, an adapted in-house DNA extraction protocol, and six 16S rRNA databases (16S-DBs). Surface water samples from two rivers were treated with SMF and Vacuum filtration (VF) and subjected to amplicon or shotgun metagenomics. A mock community standard underwent five DNA extraction protocols, taxonomical identification with six different 16S-DBs and evaluated by the Measurement Integrity Quotient (MIQ) score. In SMF samples, the skimmed milk was metabolized by members of lactic acid bacteria or genera such as Polaromonas, Macrococcus, and Agitococcus, resulting in increased relative abundance (p &lt; 0.5) up to 5.0 log fold change compared to VF, rendering SMF inapplicable for bacterial microbiome studies. The best performing DNA extraction protocols were FastSpin Soil, the in-house method and EurX. All 16S-DBs yielded comparable MIQ scores within each DNA extraction kit, ranging from 61-66 (ZymoBIOMICs) up to 80-82 (FastSpin). DNA extraction kits exert more bias to the composition than the 16S-DBs. This benchmarking study presented valuable insights to inform future water metagenomic study designs.

In an era marked by digitization and automation, extracting relevant information from business documents, like electricity invoices, remains a major challenge. To address this, we need to use machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new method for extracting key values from this type of invoice, including customer personal data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach uses a bag-of-words strategy and custom-designed features specifically tailored for electricity data. We tested the method on the IDSEM dataset, which includes 75.000 electricity invoices with eighty-six different fields. The method converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of the model on unseen documents. The precision obtained with Support Vector Machines is 91,86%, peaking at 98,47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices.

The Folla Redonda grape is indigenous to the region of Rias Bajas in Galicia, Spain. This grape is distinguished by its characteristic acid flavor and pulp of remarkable coloration. Despite the wine obtained from this grape is highly valued by consumers of this region for its surprising acidic notes and thickness, it is important to note that it is not a variety of Vitis vinifera and its production is not legally regulated. In the present study, an evaluation of the physicochemical properties of the Folla Redonda grape (pH, °Brix, °Bé, density, acidity, sugar content, etc.) as well as its content in bioactive compounds (total polyphenols and anthocyanins) was carried out. Additionally, the antioxidant potential of the extracts obtained from this grape was demonstrated. This study proved the interesting organoleptic characteristics of the grape, along with a high content of compounds of interest and an important antioxidant activity comparable to that of Vitis vinifera grapes. Therefore, the grape's natural consumption and its application in different industries such as nutraceutical or pharmacological would result in an important revaluation of the grape and significant health benefits. In case that the production of wine from this variety is legalized, consumers will not only be able to enjoy a wine with a characteristic dense reddish color and important acid tones, but also with interesting concentrations of bioactive compounds.

Machine learning models are increasingly being used in critical domains, but their complexity, lack of transparency, and poor interpretability remain problematic. Decision trees (DTs) and rule-based approaches are well-known examples of interpretable models, and numerous studies have investigated techniques for approximating tree ensembles using DTs or rule sets; however, tree ensemble approximators do not consider interpretability. These methods are known to generate three main types of rule sets: DT-based, unordered-based, and decision list-based. However, no known metric has been devised to distinguish and compare these rule sets. Therefore, the present study proposes an interpretability metric to allow comparisons of interpretability between different rule sets, such as decision list- and DT-based rule sets, and investigates the interpretability of the rules generated by the tree ensemble approximators. To provide new insights into the reasons why decision list-based and inspired classifiers do not work well for categorical datasets consisting of mainly nominal attributes, we compare objective metrics and rule sets generated by the tree ensemble approximators and the \textit{Recursive-Rule eXtraction algorithm (Re-RX) with J48graft}. The results indicated that \textit{Re-RX with J48graft} can handle categorical and numerical attributes separately, has simple rules, and achieves high interpretability, even when the number of rules is large.

Biochar is a carbon-rich material that recently received attention due to its increasing agronomical potential. The agricultural utilization of biochar relates to its potential to act in the soil as a soil conditioner, nevertheless, the complex information on the direct dependence of biochar physical properties (texture, particle size) and corresponding leaching and availability of organic molecules (e.g. the polycyclic and heterocyclic organic compounds) and inorganic mineral salts (based on micro– and macroelements) are still not consistent. These aspects were addressed in our study. A multi-elemental analysis (ICP-OES) was used to access the information on the aqueous-extractable and total contents of inorganic macro- and macroelements in used commercial biochar samples (purchased from Sonnenerde GmbH, Novoterrra Sonnenerde GmbH, Biouhel.cz, s.r.o.). Potassium (K) was identified as the major macroelement, responsible for alkaline pH and the conductivity of biochar extract. Our results indicate an indirect relation between the size fraction of biochar and the content of extractable K, sodium (Na), and calcium (Ca) and a direct relation with the contents of phosphorus (P) and magnesium (Mg). As the total determined amounts of inorganic elements were significantly higher compared to aqueous-extractable amounts, we believe it could indicate the potential for repeated release to the surrounding soil. These findings were also confirmed by the analysis of biochar samples obtained after the cultivation (duration of 2 years) in selected representative soil samples from the Czech Republic (Cambisol, Fluvisol, Regosol, Chernozem). Moreover, gas chromatography (GC) coupled with mass spectroscopy (MS) was further used to reveal the concentrations of available polycyclic aromatic and heterocyclic compounds in biochar samples. The detected concentration of these types of organic compounds were far below the certified limits. We believe our in-depth analysis could provide the necessary insight into the description of biochar mineral content, its connection to biochar texture, corresponding physicochemical properties and potential availability to leach nutrients to the soil. These findings could help in further assessment of the potential applications of biochar in modern agriculture as a soil conditioner.

Falls are extremely damaging to the elderly. The number of elderly who have experienced falls has increased over the years, several of the elderly stay alone or in in badly maintained elderly homes. This makes a low-cost fall detection system a necessity. There has been huge improvements in terms of IoT systems, ML algorithms. Varied data sets have been collected across the world for fall detection. These data sets have a very little in common among them, in terms of user demographics, sensors used, the ADL and Fall activities Hence in this paper we present a data set that has wide user demographics, we used various sensors – such as accelerometer, gyroscope, magnetometer and hear rate. We used wrist worn sensors to collect data. In this paper we present a detailed analysis of the data set we collected using common ML algorithms such as – Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF) and Support Vector Machines (SVM). We analyzed the performance of these algorithms for variations in accuracy with respect to age, gender, height, weight and health issues and we have identified outliers by analyzing each incorrect prediction. This paper provides the complete details of the data collection methodology, The methods used for analysis and presents the results of analysis in complete detail.

Pomegranate (Punica granatum L.) is well known for its high content in bioactives including polyphenols, flavonoids and tannins, which have been shown to exhibit a wide range of biological activity such as antioxidant, antimicrobial and anticancer effects. It is worth noting that the majority of these molecules are found in the peels (PP), which are usually disposed of after processing, causing a significant amount of waste, amounting to more than 3.6 million t/y. This work investigates MW-assisted extraction (MAE) in water for the recovery of antioxidants from PP, including the optimization of temperature and extraction times. The total phenolics, anthocyanin, flavonoid and tannin contents of the recovered extracts have been determined, as have their antioxidant activities, which were found to be 356.35 mgGAE/gextr., 303.97 µgCy3G/gextr., 37.28 mgQE/gextr., 56.48 mgGAE/gextr. and 1.43 µmolTE/gextr., respectively (according to the adopted reference). All results have been compared with those obtained using a conventional protocol. In addition, the potential for water recycling by means of nanofiltration downstream in optimized MAE has been investigated, leading to overall water reuse of approx. 75%. Energy consumption (20.92W/mgGAE) and the common green metrics, RME, E-Factor and PMI (PME), have been considered in evaluating the proposed PP valorization strategy. Finally, the biological activity of the main products has been assessed. The antimicrobial properties of the PP extracts against three Gram-positive and three Gram-negative bacteria, and their antiproliferative activity towards human cancer cells have been tested. The S. aureus bacteria was the most susceptible to the PP extracts. All tested products displayed antiproliferative activity in HeLa cells when higher concentrations were tested, with D-PP/NF being the most effective. This result was also confirmed in a clonogenic analysis, which generally indicated the possible anti-cancer activity of pomegranate peel extracts obtained using this green approach.

Fit-for-purpose land administration (FFPLA) seeks to simplify cadastral mapping via lowering the costs and time associated with conventional surveying methods. The approach can be applied to both initial establishment and on-going maintenance of system. In Ethiopia, cadastral maintenance remains an on-going challenge, especially in rapidly urbanizing peri-urban areas, where farmers' land rights and tenure security are often jeopardized. Automatic Feature Extraction (AFE) is an emerging FFPLA approach, proposed as an alternative for mapping and updating cadastral boundaries. This study explores the role of the AFE approach for updating cadastral boundaries in the vibrant peri-urban areas of Addis Ababa. Open-source software solutions are utilized to assess the (semi-) automatic extraction of cadastral boundaries from orthophotos (segmentation), designation of 'boundary' and 'non-boundary' outlines (classification), and delimitation of cadastral boundaries (interactive delineation). Both qualitative and quantitative assessments of the achieved results (validation) are undertaken. A high-resolution orthophoto of the study area and a reference cadastral boundary shape file are used, respectively, for extracting the parcel boundaries and validating the interactive delineation results. Qualitative (visual) assessment verified the completed extraction of newly constructed cadastral boundaries in the study area, although non-boundary outlines such as footpaths and artefacts are also retrieved. For the buffer overlay analysis, the interactively delineated boundary lines and the reference cadastre were buffered within the spatial accuracy limits for urban and rural cadasters. As a result, the quantitative assessment delivered 52% correctness and 32% completeness for a buffer width of 0.4m and 0.6m, respectively, for the interactively delineated and reference boundaries. The study further demonstrated the potentially significant role AFE could assist in delivering fast, affordable, and reliable cadastral mapping. Further investigation, based on user input and expertise evaluation, could help to improve the approach and apply it to a real-world setting.

We introduce the Open Research Knowledge Graph Agriculture Named Entity Recognition (the ORKG Agri-NER) corpus and service for contribution-centric scientific entity extraction and classification. The ORKG Agri-NER corpus is a seminal benchmark for the evaluation of contribution-centric scientific entity extraction and classification in the agricultural domain. It comprises titles of scholarly papers that are available as Open Access articles on a major publishing platform. We describe the creation of this corpus and highlight the obtained findings in terms of the following features: 1) a generic conceptual formalism focused on capturing scientific entities in agriculture that reflect the direct contribution of a work; 2) a performance benchmark for named entity recognition of scientific entities in the agricultural domain by empirically evaluating various state-of-the-art sequence labeling neural architectures and transformer models; and 3) a delineated 3-step automatic entity resolution procedure for the resolution of the scientific entities to an authoritative ontology, specifically AGROVOC that is released in the Linked Open Vocabularies cloud. With this work we aim to provide a strong foundation for future work on the automatic discovery of scientific entities in the scholarly literature of the agricultural domain.

The aim of this work was the study and evaluation of winery by-products in the framework of circular bioeconomy. Grape seeds and grape skins from Greek traditional Ionian Islands varieties were analyzed in an attempt to provide the appropriate basis for model development of their sustainable exploitation at a local or regional level. The wastes collected directly from the wineries immediately after the vinification process and analyzed by chromatographic and spectroscopic techniques. Also, annual production and yields were estimated. Grape seed oil quality was evaluated based on fatty acid methyl esters (FAMEs) composition. Grape skins phenolic fraction was extracted by an eco-friendly, non-toxic water-glycerol solvent system and were detected qualitatively. Also, total phenolic content (TPC) and antioxidant activity were measured. Based on estimated yields, our results demonstrate that winery by-products have the potential to promote the cyclical bioeconomy in a modern economic growth model that will reduce waste, and environmental costs as they can be reused as whole material in foods, dietary supplements, cosmetic ingredients, food colorants and preservatives.

Extracts from parts of coniferous trees have received increased interest due to their valuable bioactive compounds and properties, useful for plenty of experimental and consolidated applications, in fields comprising nutraceutics, cosmetics, pharmacology, food preservation, and stimulation of plant growth. However, the variability of the bioactive properties, the complexity of the extraction methods, and the use of potentially harmful synthetic chemicals, still represent an obstacle to the spreading of such valuable natural compounds. Hydrodynamic cavitation is emerging as a promising innovative technique for the extraction of precious food components and by-products from waste raw material of the agro-food production chain, which can improve processing efficiency, reduce resource consumption, and produce healthy, high-quality products. In this study, a process based on controlled hydrodynamic cavitation was applied for the first time to the production of aqueous solutions of silver fir (Abies Alba Mill.) needles with enhanced antioxidant activity. The observed levels of the in vitro antioxidant activity, comparable or higher than those found for reference substances, pure extracts, and other water extracts and beverages, highlight the very good potential of the HC process for the creation of solvent-free, aqueous solutions endowed with bioactive compounds extracted from silver fir needles.

Wide bandgap (WBG) power semiconductor devices are increasingly replacing silicon IGBTs in high-power and high-voltage power electronics applications. However, there is a significant gap in the literature regarding efficient testing methodologies for high-power and high-voltage converters under constrained laboratory resources. This paper addresses this gap by presenting comprehensive, hardware-focused testing methodologies for high-power and high-voltage WBG power semiconductor based converters, preceding the control evaluation phase. The proposed methods enable thorough evaluation and evaluation of converter hardware, including device switching characteristics, driving circuit functionality, thermal management performance, insulation integrity, and sustained operation at full power. We utilize the double pulse test (DPT) to characterize switching performance in a two-level phase leg configuration, extract circuit parasitics, and validate magnetic components. The DPT is further applied to optimize gate driving circuits, validate overcurrent protection mechanisms, and measure device on-resistance. Additionally, a multicycle test is introduced to rapidly assess steady-state converter performance and estimate efficiency. Recognizing the critical role of thermal management in high-power converters, our methodologies extend to the experimental extraction of key thermal parameters—such as junction-to-ambient thermal resistance and thermal capacitance—via a heat loss injection method. A correlation method between temperature sensor measurements and junction temperature is presented to enhance the accuracy of device temperature monitoring during tests. To ensure reliability and safety, dielectric withstand tests and partial discharge measurements are conducted at both component and converter levels under conventional 60 Hz sinusoidal and high-frequency PWM waveforms. Finally, we highlight the importance of testing converters under full voltage, current, and thermal conditions through power circulating tests with minimal power consumption, applicable to both non-isolated and isolated high-power converters. Practical examples are provided to demonstrate the effectiveness and applicability of these hardware testing methodologies.

The hydrophobic reagent 6-hexyl-4-(2-thiazolylazo)resorcinol (HTAR) was investigated as part of a cloud point extraction (CPE) system for the spectrophotometric determination of Zn(II). In the system, complexes with different stoichiometries, including 1:1 and 2:2 (Zn:HTAR), are formed. Their ground-state equilibrium geometries were optimized at the B3LYP/6-31G level of theory. The obtained structures were then used to calculate vertical excitation energies in order to generate theoretical UV/Vis absorption spectra. The comparison between theoretical and experimental spectra demonstrated that, under optimal conditions, a binuclear complex containing oxygen bridging atoms is the dominant species. The absorbance was found to be linearly dependent on the concentration of Zn(II) within the range of 15.7 to 209 ng mL–1 (R2 = 0.9996). The fraction extracted (%E), logarithm of the conditional extraction constant (log Kex), and molar absorption coefficient (ε) at λmax = 553 nm were calculated to be 98.3%, 15.9, and 4.47 105 L mol–1 cm–1, respectively. The method developed is characterized by simplicity, convenience, profitability, sensitivity, and ecological friendliness. It has been successfully applied to the analysis of pharmaceutical and industrial samples.

Wearable sensors have become increasingly popular for assessing athletic performance, but the optimal methods for processing and analysing the data remain unclear. This study investigates the efficacy of discrete and continuous feature extraction methods, separately and in combination, for modelling countermovement jump performance using wearable sensor data. We demonstrate that continuous features, particularly those derived from Functional Principal Component Analysis, outperform discrete features in terms of model performance, robustness to variations in data distribution and volume, and consistency across different datasets. Our findings underscore the importance of methodological choices, such as signal type, alignment methods, and model selection, in developing accurate and generalisable predictive models. We also highlight the potential pitfalls of relying solely on domain knowledge for feature selection and the benefits of data-driven approaches. Furthermore, we discuss the implications of our findings for the broader field of sports biomechanics and provide practical recommendations for researchers and practitioners aiming to leverage wearable sensor data for athletic performance assessment. Our results contribute to the development of more reliable and widely applicable predictive models, facilitating the use of wearable technology for optimising training and enhancing athletic outcomes across various sports disciplines.

This study comprehensively evaluates the DNA/RNA Defend Pro (DRDP) sample collection buffer designed to inactivate and stabilize patient samples. The primary objectives encompassed assessing DRDP's efficacy in ensuring sample stability, facilitating extraction-free polymerase chain reaction (PCR), and ensuring compatibility with rapid antigen testing.Ninety-five diagnostic nasopharyngeal swab samples tested for influenza A/B, RSV A/B, and/or SARS-CoV-2 were diluted 1/10 with DRDP and anonymized. Stability testing involved incubating 31 positive samples at 4 °C, 20 °C, and 37 °C for 7 days, with regular extraction-free nucleic acid amplification testing (NAAT).Results demonstrated that DRDP guaranteed viral RNA stability at all temperatures for influenza, SARS-CoV-2 and RSV showing stability up to 7 days at 4 °C. DRDP-diluted samples exhibited robust compatibility with direct PCR, as 72 out of 88 samples positive for cobas Liat also tested positive for direct PCR. Non-concordant results could be explained by the 200-fold lower input in the extraction-free NAAT.Compared to NAAT, rapid antigen testing demonstrated lower sensitivity, as expected, while maintaining perfect specificity. Clear cutoffs between positive and negative rapid antigen testing results were observed in both cobas Liat and direct PCR analyses, validating DRDP's compatibility with these techniques. In conclusion, DRDP is an effective stabilizing medium compatible with direct PCR and rapid antigen testing and shows great potential for optimizing diagnostic processes, particularly in resource-limited or time-sensitive scenarios.

The aim of this study is to solve the problems of complicated pretreatment and high analytical cost in the detection technology of trace drug toxicants in municipal wastewater. A high-performance magnetic sorbent was synthesized for enrichment of trace drug substances in wastewater to develop magnetic solid-phase extraction pretreatment combined with the acoustic ejection mass spectrometry (AEMS) analytical methods for the molecules in wastewater drug toxicants. The magnetic nanospheres was successfully prepared by magnetic nanoparticles modified with divinylbenzene and vinyl pyrrolidone.The results showed that the linear dynamic range of 17 drugs was 1-500 ng/L, the recovery was 43%-105%, the matrix effect was more than 67%, the limit of quantitative detection was 1-2 ng/L, and the detection time of each sample was 2.98s. It can be seen that the developed magnetic solid-phase extraction (MSPE) method is a good solution to the problem of complicated pre-treatment and analytical cost in the detection of drugs in wastewater. The developed magnetic material and acoustic excitation coupled mass spectrometry analysis method can realize the low-cost, efficient enrichment and fast analysis of different kinds of drug molecules in urban sewage.

With the rapid advancements in remote sensing technology, the spectral information from hyperspectral remote sensing images has become increasingly rich, facilitating detailed spectral analysis of the Earth's surface objects. However, this abundance of spectral data poses significant challenges in data processing, such as the curse of dimensionality leading to the “Hughes” phenomenon, "strong correlation" due to high resolution, and "non-linear characteristics" caused by varied surface reflectance rates. Therefore, dimensionality reduction of hyperspectral data has become a crucial task. This paper, grounded in manifold theory and manifold learning techniques, and considering the non-linear structures and features in hyperspectral remote sensing data, elucidates the principles and processes of dimensionality reduction in hyperspectral remote sensing images using manifold learning, with a formalized expression of the process. This article introduces spectral information divergence (SID) into the nearest neighbor graph computation of manifold learning algorithms. The principles and computational processes of nearest neighbor graph algorithms based on Euclidean distance (ED), spectral angle mapping (SAM), and SID are studied, and a comparative analysis of the dimensionality reduction effects under these three metrics in hyperspectral data is conducted. Experiments on feature extraction under different metrics were performed using the publicly available Indian Pines hyperspectral dataset. The intrinsic features obtained post-dimensionality reduction were used as inputs for classification algorithms in ground objects classification experiments, with algorithm runtime, overall accuracy, and Kappa coefficient as evaluation metrics for dimensionality reduction quality. The results demonstrate that nearest neighbor graph computation based on SAM and SID outperforms traditional ED methods; SAM-based computation has the lowest time complexity, while SID-based manifold learning yields the highest accuracy in ground objects classification. Thus, manifold learning based on SAM and SID metrics proves to be an effective method for feature extraction in hyperspectral remote sensing data, underscoring the potential of manifold learning techniques in the dimensionality reduction of hyperspectral remote sensing images.

Geothermal energy is a weather-independent, permanently available renewable energy source. In addition to producing heat and electricity, geothermal energy can be used to extract critical raw materials dissolved in the heat-carrying fluid. Researchers working on the frontiers of geothermal energy utilisation may be able to transform ultra-deep metallic mineral formations into “orebody-Enhanced Geothermal Systems”. In the planned technology, the metal-containing geological formation would be manipulated in such a way that cogeneration of energy and metals is possible and can be optimised in the future according to market needs. The potential of geothermal energy for sustainable mineral extraction and energy production aligns with Sustainable Development Goal (SDG) 7, which aims to ensure access to affordable, reliable, sustainable, and modern energy for all. This new technology could substantially decrease Europe’s dependency on importing critical metallic minerals (such as lithium and tungsten) and energy; over and above, it has a small environmental footprint, including very low carbon emissions

Thrombosis is characterized by the pathological formation of fibrin clots within a blood vessel, leading to the obstruction of blood flow. Fibrinolytic enzymes from microorganisms have exhibited promising effects to dissolve clots in a more efficient and safe way. Then, the aim of this study was to evaluate the biomass and fibrinolytic enzyme production of Tetradesmus obliquus under autotrophic and mixotrophic conditions using different concentration of corn steep liquor (CSL). Different extraction and precipitating methods were tested, and the enzyme was purified by ion exchange chromatography. More advantageous culture condition was mixotrophic using 0.25% CSL, showing the highest values of biomass productivity (Px = 169.3 ± 44.36 mg∙L-1day-1) and specific growth rate (µmax = 0.17 ± 0.00 day-1), and significant fibrinolytic production (391.34 ± 40.03 U∙mg-1). Moreover, fibrinolytic activity was higher when extracted by homogenization and precipitated using acetone, which exhibited clear zone of fibrin degradation in the fibrinolytic plate assay. Additionally, the purified enzyme showed specific activity of 1176.90 ± 140.37 U∙mg-1 and molecular weight around 97 kDa. Finally, the enzyme has higher enzymatic activity than various fibrinolytic enzymes, and the obtained enzyme has potential to be developed as a therapeutic agent in thrombosis treatment. Additional studies are need to investigate the biochemical properties and biological profile of this enzyme.

Keywords: artificial bone; conical implants; cylindrical implants; dental implants; implant stability quotient; insertion torque; polyurethane; post-extraction sites; removal torque.

The paper demonstrates the analysis of Corona Virus Disease based on a probabilistic model. It involves a technique for classification and prediction by recognizing typical and diagnostically most important CT images features relating to Corona Virus. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases at applying our proposed approach for feature extraction. The combination of the conventional statistical and machine learning tools is applied for feature extraction from CT images through four images filters in combination with proposed composite hybrid feature extraction (CHFS). The selected features were classified by the stack hybrid classification system(SHC). Experimental study with real data demonstrates the feasibility and potential of the proposed approach for the said cause.

External quantum efficiency of industrial-grade green InGaN light-emitting diodes (LEDs) has been measured in a wide range of operating currents at various temperatures from 13 K to 300 K. Unlike blue LEDs, the efficiency as a function of current is found to have a multi-peak character, which could not be fitted by a simple ABC-model. This observation correlated with splitting of LED emission spectra into two peaks at certain currents. The characterization data are interpreted in terms of non-uniformity of the LED active region, which is tentatively attributed to extended defects like V-pits. We suggest a new approach to evaluation of temperature-dependent light extraction and internal quantum efficiencies taking into account the active region non-uniformity. As a result, the temperature dependence of light extraction and internal quantum efficiencies have been evaluated in the temperature range mentioned above and compared with those of blue LEDs.

Fabric phase sorptive extraction (FPSE) combines the advanced material properties of sol–gel derived microextraction sorbents and the flexible and permeable fabric support to create a robust, simple and green sample preparation device. It simultaneously improves the extraction sensitivity, and the speed of the extraction by incorporating high volume of sponge-like porous sol–gel hybrid inorganic–organic sorbents into permeable fabric substrates that is capable of extracting target analytes directly from simple to complex aqueous sample matrices. For the first time, this technique was applied to the trace level determination of selected polycyclic aromatic hydrocarbons (PAHs) in environmental water samples using a non-polar sol–gel C18 coated FPSE media. Several extraction parameters were optimized to improve extraction efficiency and to achieve high detection sensitivity. Validation tests of spiked samples showed good linearity for four selected PAHs (R² = 0.9983–0.9997) over a wide range of concentrations (0.010-10 ng/mL). Limits of detection (LODs) and quantification (LOQs) were measured at pg/mL levels, 0.1–1 pg/mL and 0.3–3 pg/mL, respectively. Inter- and intra-day precision tests showed variations of 1.1–4.1% for four selected PAHs. Average absolute recovery values were in the range of 88.1–90.5% surpassed the recovery prediction model, with relative standard deviations below 5%. The developed FPSE-HPLC-FLD protocol was finally applied to analyze 8 environmental water samples. Out of four selected PAHs, fluoranthene (Flu) and phenanthrene (Phen) were the most frequently detected in four samples, at concentration levels of 5.6–7.7 ng/mL and 4.1-11 ng/mL, respectively followed by anthracene (Anth) and pyrene (Pyr) in two samples. The newly developed FPSE-HPLC-FLD protocol is simple, green, fast and economical, with adequate sensitivity for trace levels of four selected PAHs and seems to be promising in routine monitoring of water quality and safety.

Advances in early detection of Breast cancer and treatment improvements have significant-ly increased survival rates. Traditional screening methods, including mammography, MRI, ultrasound, and biopsies, while effective, often come with high costs and risks. Recently, thermal imaging has gained attention due to its minimal risks compared to mammography, although it is not widely adopted as a primary detection tool since it depends on identifying skin temperature changes and lesions. The advent of machine learning (ML) and deep learning (DL) has enhanced the effectiveness of breast cancer detection and diagnosis using this technology. In this study a novel methodology for developing an interpretable computer-aided diagnosis (CAD) system for breast cancer detection, leveraging explaina-ble Artificial Intelligence (XAI) throughout its various phases. To achieve these goals, we proposed a new multi-objective optimization approach named Hybrid Particle Swarm Optimization algorithm (HPSO) and Hybrid spider Monkey Optimization algorithm (HSMO). These algorithms simultaneously combine the continuous and binary representations of PSO and SMO to effectively manage trade-offs between Accuracy, feature selection and hyperparameter tuning. We evaluate several CAD models and investigate the impact of handcrafted methods such as Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gabor filters, and edge detection. We further shedding light on the effect of feature selection and optimization on feature attribution and model decision-making processes using the SHapley Additive exPlanations (SHAP) framework, with a particular emphasis on cancer classification using the DMR-IR dataset. The results of our experiments demonstrate in all trials that the performance of the model is improved. Also with HSMO our models achieved a high accuracy of 98.27% and F1- score of 98.15% while selecting only 25.78% of the HOG features. This approach not only boosts the performance of CAD models but also ensures comprehensive interpretability. This method emerges as a promising and transparent tool for early breast cancer diagnosis.

The excessive use of synthetic insecticides in modern agriculture has led to the contamination of the environment and the development of insect resistance. In this study, we evaluated the potential of tangerine (Citrus reticulata L.) peel essential oil (EO) as a natural insecticide against greenhouse whitefly (Trialeurodes vaporariorum W. (Homoptera: Aleyrodidae)), a common pest in greenhouse production. Petroleum ether (PET) and n-hexane (HEX) were used as solvents to extract essential oil (EO) from tangerine peels. The yield of EO was 1.59 % and 2.00 % (m/m) for PET and HEX, respectively. The insecticidal activity of EO was evaluated by measuring the mortality rate (MR) of greenhouse whiteflies at different time intervals. The results showed that PET and HEX extracts of tangerine EO effectively controlled the greenhouse whitefly. With both solvents, it was observed that with doses of 12.5% (v/v), similar results were achieved as with the positive control (corresponding to the commercial insecticide imidacloprid). Additionally, the FTIR analysis found that the EO contained d-limonene, which may be the source of its insecticidal properties. Therefore, tangerine peel essential oil is an excellent natural insecticide candidate for controlling greenhouse whiteflies effectively and sustainably.

Pain is a multifaceted multisystem disorder that adversely affects neuro-psychological processes. This study compares the effectiveness of central-stimulation (tDCS) and peripheral-stimulation (TENS) in pain-inhibition during a cognitive-task in healthy volunteers and to observe potential neuro-cognitive improvements. Healthy eighty volunteers went through a complete experimental protocol comprising pain-induction (CPT), administration of tDCS/TENS, EEG-data acquisition, and cognitive assessments. The protocol for this study is categorized into 04-groups: G1(Control), G2(TENS), G3(Anodal-tDCS), and G4(Cathodal-tDCS). Paired t-tests (p

Cooling fans are one of the critical components of air-forced (AF) dry-type transformers for regulating internal temperatures. Therefore, effective malfunction detection is crucial to maintain the transformer temperature within an acceptable range and prevent overheating. Regular maintenance occurs periodically and issues with cooling fans may arise between maintenance periods, leading to prolonged operation under malfunctioning conditions and potential failures. In addition, utilities typically have online information about whether a fan works or not without providing information about cooling fan malfunctioning circumstances. To address these challenges, this study proposes learning-based online monitoring techniques to detect malfunctions in AF transformer cooling fans. Random forests (RFs) and convolutional neural networks (CNNs) are developed to classify the audio signals from cooling fans into normal and malfunctioning classes. Unlike RFs, which require separate feature extraction, CNNs are trained based on spectrogram images derived from audio signals. Thus, various time-frequency techniques are utilized for feature extraction in RFs. Besides, multiple data augmentation techniques are employed to enhance the dataset size and diversity. Algorithmic performance is optimized through hyperparameter tuning and classifier threshold adjustment. Simulations reveal that CNNs outperform RFs, whereas the latter provides superior interpretability of acoustic features compared to the former.

Solar radiation prediction is an important process in ensuring optimal exploitation of solar energy power. Numerous models have been applied to this problem, such as numerical weather prediction models and artificial intelligence models. However, well-designed hybridization approaches that combine numerical models with artificial intelligence models to yield a more powerful model can provide a significant improvement in prediction accuracy. In this paper, we propose novel hybrid machine learning approaches that exploit auxiliary numerical data. The proposed hybrid methods invoke different machine learning paradigms, including feature selection, classification, and regression. Additionally, numerical weather prediction (NWP) models are used in the proposed hybrid models. Feature selection is used for feature space dimension reduction to reduce the large number of recorded parameters that affect estimation and prediction processes. The rough set theory is applied for attribute reduction and the dependency degree is used as a fitness function. We investigate the effect of the attribute reduction process with thirty different classification and prediction models in addition to the proposed hybrid model. Then, different machine learning models are constructed based on classification and regression techniques to predict solar radiation. Moreover, other hybrid prediction models are formulated to use the output of the numerical model of Weather Research and Forecasting (WRF) as learning elements in order to improve the prediction accuracy. The proposed methodologies are evaluated using a data set that is collected from different regions in Saudi Arabia.

The objective of this study was to develop an ultrasonic-assisted procedure for the extraction of total phenolics from Citrus aurantium L. blossoms (CAB) and evaluate the free radical scavenging activity, anti-HMG-CoA reductase activity of total phenolics. In this work, a Box-Behnken design based on the single-factor experiments was used to explore the optimum extraction process. Under the optimum conditions (extraction solvent 70.31% ethanol, extraction temperature 61.94 °C, extraction time 51.73 min and liquid-to-solid ratio 35.63 mL/g), the extraction yield of total phenolics was 95.84 mg gallic acid equivalents (GAE)/g dry matter (DM), which was highly consistent with the theoretical value (96.12 mg GAE/g DM). The total phenolic extract showed excellent free radical scavenging properties against DPPH·, ABTS+·, ·OH and ·O2-, with the IC50 values of 197.007, 83.878, 218.643 and 158.885 μg/mL, respectively, and the extracts also showed good inhibition of HMG-CoA reductase activity, with the IC50 value of 117.165 μg/mL. Total phenolics from CAB could be a potential source of natural free radical scavenger and HMG-CoA reductase inhibitor.

When extract building from high resolution remote sensing image with meter/sub-meter accuracy, the shade of trees and interference of roads are the main factors of reducing the extraction accuracy. Proposed a Bayesian Convolutional Neural Networks(BCNET) model base on standard fully convolutional networks(FCN) to solve these problems. First take building with no shade or artificial removal of shade as Sample-A, woodland as Sample-B, road as Sample-C. Set up 3 sample libraries. Learn these sample libraries respectively, get their own set of feature vector; Mixture Gauss model these feature vector set, evaluate the conditional probability density function of mixture of noise object and roofs; Improve the standard FCN from the 2 aspect:(1) Introduce atrous convolution. (2) Take conditional probability density function as the activation function of the last convolution. Carry out experiment using unmanned aerial vehicle(UVA) image, the results show that BCNET model can effectively eliminate the influence of trees and roads, the building extraction accuracy can reach 97%.

In recent years, the demand for efficient and accurate measurement techniques has surged across various industries, driving the development of non-invasive methods that leverage computer vision technology. This paper explores the principles and applications of non-invasive measurement techniques utilizing computer vision, emphasizing their ability to deliver precise measurements without the need for physical contact or specialized sensors. We delve into the underlying algorithms, including image processing, machine learning, and deep learning methods, that enable the extraction of dimensional data from visual inputs. Case studies across diverse fields such as manufacturing, healthcare, and logistics illustrate the effectiveness of these techniques in enhancing operational efficiency and reducing measurement errors. Furthermore, we discuss the challenges and limitations of implementing computer vision-based measurement systems, including the need for robust algorithms capable of functioning in varied environmental conditions. By highlighting the transformative potential of non-invasive measurement techniques, this paper aims to provide insights into future developments in computer vision and its role in advancing measurement practices across multiple sectors.

This study employs the reflection symmetry decomposition (RSD) method to extract polarization scattering features from ground object images, aiming to determine the optimal data input scheme for deep learning networks in polarimetric synthetic aperture radar classification. Eight distinct polarizing feature combinations are designed, and the classification accuracy of various approaches is evaluated using the classic convolutional neural networks(CNNs) AlexNet and VGG16. The findings reveal that the commonly employed 6-parameter input scheme, favored by many researchers, lacks the comprehensive utilization of polarization information and warrants attention. Intriguingly, leveraging the complete 9-parameter input scheme based on the polarization coherence matrix results in improved classification accuracy. Furthermore, the input scheme incorporating all 21 parameters from the RSD and polarization coherence matrix notably enhances overall accuracy and the Kappa coefficient compared to the other 7 schemes. This comprehensive approach maximizes the utilization of polarization scattering information from ground objects, emerging as the most effective CNN input data scheme in this study. Additionally, the classification performance using the second and third component total power values (P2 and P3) from the RSD surpasses the approach utilizing surface scattering power value (PS) and secondary scattering power value (PD) from the same decomposition.

This research presents a comprehensive framework for efficiently generating forest fire datasets from Google Earth Engine data sources. The primary contribution of this work lies in providing a methodology to swiftly extract forest fire factors without the need for permissions or access to private datasets, rendering the dataset openly accessible and shared without barriers. Furthermore, given that the remote sensing data used is a global dataset, it can be applied in any region without restrictions. In this study, Peninsular Malaysia is chosen as a case study to demonstrate the framework's effectiveness. The generated dataset includes essential variables including the climate and environment, landcover, topography, and anthropogenic factors facilitating the analysis of fire occurrences. The methodology empowers data scientists, enabling them to leverage their analytical skills on the extracted dataset without requiring specialized remote sensing knowledge. Additionally, this study also showcases the adoption of large language models, specifically GPT-4 with the Noteable plugin, as a tool for conducting preliminary analyses on the generated dataset. Sample analyses reveal that several key features, including the KBDI, LST, PDSI, climate water deficit, and precipitation, significantly impact forest fire occurrences in Peninsular Malaysia. Despite the successful application of the GPT-4 with Noteable plugin, certain limitations and challenges are identified, highlighting the necessity for further validation of the tool's applicability and limitations. This study encourages future research to (1) adopt the proposed framework in other regions, (2) explore more detailed analyses encompassing all variables, and (3) leverage machine learning for advanced forecasting.

Alzheimer's disease (AD) detection acting as an essential role in global health care due to misdiagnosis and sharing many clinical sets with other types of dementia, and costly monitoring the progression of the disease over time by magnetic reasoning imaging (MRI) with consideration of human error in manual reading. This paper goal a comparative study on the performance of data mining techniques on two datasets of Clinical and Neuroimaging Tests with AD. Our proposed model in the first stage, Apply clinical medical dataset to a composite hybrid feature selection (CHFS), for extract new features to select the best features due to eliminating obscures features, In parallel with Apply a novel hybrid feature extraction of three batch edge detection algorithm and texture from MRI images dataset and optimized with fuzzy 64-bin histogram. In the second stage, we applied a clinical dataset to a stacked hybrid classification(SHC) model to combine Jrip and random forest classifiers with six model evaluations as meta-classifier individually to improve the prediction of clinical diagnosis. At the same stage of improving the classification accuracy of neuroimaging (MRI) dataset images by applying a convolution neural network (CNN) in comparison with traditional classifiers, running on extracted features from images. The authors have collected the clinical dataset of 426 subjects with (1229 potential patient sample) from oasis.org and (MRI) dataset from a benchmark kaggle.com with a total of around ~5000 images each segregated into the severity of Alzheimer's. The datasets evaluated using an explorer set of weka data mining software for the analysis purpose. The experimental show that the proposed model of ‏(CHFS) feature extraction ‏ lead to effectively reduced the false-negative rate with a relatively high overall accuracy with a stack hybrid classification of support vector machine (SVM) as meta-classifier of 96.50% compared to 68.83% of the previous result on a clinical dataset, Besides a compared model of CNN classification on MRI images dataset of 80.21%. The results showed the superiority of our CHFS model in predicting Alzheimer's disease more accurately with the clinical medical dataset in early-stage compared with the neuroimaging (MRI) dataset. The results of the proposed model were able to predict with accurately classify Alzheimer's clinical samples at a low cost in comparison with the MRI-CNN images model at the early stage and get a good indicator for high classification rate for MRI images when applying our proposed model of SHC.

Musical instrument recognition is a relatively unexplored area of machine learning due to the need to analyze complex spatial-temporal audio features. Traditional methods using individual spectrograms, like STFT, Log-Mel, and MFCC, often miss the full range of features. We propose a hierarchical residual attention network using a scaled combination of multiple spectrograms, including STFT, Log-Mel, MFCC, and CST features (chroma, spectral contrast, and Tonnetz), to create a comprehensive sound representation. This model enhances focus on relevant spectrogram parts through attention mechanisms. Experimental results with the OpenMIC-2018 dataset show significant improvement in classification accuracy, especially with the "Magnified 1/4 Size" configuration. Future work will optimize CST feature scaling, explore advanced attention mechanisms, and apply the model to other audio tasks to assess its generalizability.

: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.

Maintaining a healthy cyber society is a big challenge due to the users’ freedom of expression and behaving. It can be solved by monitoring and analyzing the users’ behavior and taking proper actions towards them. This research aims to present a platform that monitors the public content on Twitter by extracting tweet data. After maintaining the data, the users’ interactions are analyzed using Graph Analysis methods. Then the users’ behavioral patterns are analyzed by applying Metadata Analysis, in which the timeline of each profile is obtained; also, the time-series behavioral features of users are investigated. Then in the Abnormal Behavior Detection Filtering component, the interesting profiles are selected for further examinations. Finally, in the Contextual Analysis component, the contents will be analyzed using natural language processing techniques; A binary text classification model (SVM + TF-IDF with 88.89% accuracy) for detecting if the tweet is related to crime or not. Then, a sentiment analysis method is applied to the crime-related tweets to perform aspect-based sentiment analysis (DistilBERT + FFNN with 80% accuracy); because sharing positive opinions about a crime-related topic can threaten society. This platform aims to provide the end-user (Police) suggestions to control hate speech or terrorist propaganda.

Enormous quantities of softwood and hardwood tree bark are generated yearly in the pulp and woodworking industry. Chemical compounds which can be found in bark extracts have important biological properties and therefore a high potential for using in the production of special formulations. In the present study, extraction of Picea abies bark with organosolv solvents was investigated to achieve a high yield of desirable compounds. For the extraction four different solvent ratios of ethanol and water were applied. The temperature range of extraction was set between 40 and 100 °C and stirring velocity of 400 rpm. Extractions were performed with a solid/liquid ratio of 1:20. Yields of phenolics, flavonoids and tannins were determined using gallic acid for total phenolic content (TPC), quercetin for total flavonoid content (TFC) and tannic acid for total tannins content (TTC) as calibration compounds. Qualitative analysis of phenolic constituents was performed after their derivatization, by gas chromatography coupled with mass spectrometry identification. The total yield of bark extract of 14.75 wt.% was achieved by using an ethanol/water ratio of 50% (v/v) and a temperature of 100 °C. Gas chromatography results show 9 aromatic carboxylic acids as phenolic acids and quercetin and (+)-catechin as flavonoid compounds. Highest concentrations of TPC = 3.21 mg gallic acid equivalent/g, TCF = 0.62 mg quercetin equivalent/g and TTC = 0.84 tannic acid equivalent/g were determined at the same process conditions by photometric method. This study determined the conditions for organosolv extraction of useful compounds and suggests that some of extractives, e.g., taxifolin and rhamnetin presented in the spruce bark extracts, have antiviral (SARS-CoV-2) effects. Therefore, this warrants further evaluation of the antiviral properties of spruce bark constituents.

Safe sample transport is of great importance for infectious diseases diagnostics. Various treatments and buffers are used to inactivate pathogens in diagnostic samples. At the same time, adequate sample preservation, particularly of nucleic acids, is essential to allow an accurate laboratory diagnosis. For viruses with single-stranded RNA genomes of positive polarity, such as foot-and-mouth disease virus (FMDV), however, naked full-length viral RNA can itself be infectious. In order to assess the risk of infection from inactivated FMDV samples, two animal experiments were performed. In the first trial, six cattle were injected with FMDV RNA (isolate A22/IRQ/24/64) into the tongue epithelium. All animals developed clinical disease within two days and FMDV was reisolated from serum and saliva samples. In the second trial, another group of six cattle was exposed to FMDV RNA by instilling it on the tongue and spraying it into the nose. The animals were observed for 10 days after exposure. All animals remained clinically unremarkable and virus isolation as well as FMDV genome detection in serum and saliva were negative. No transfection reagent was used for any of the animal inoculations. In conclusion, cattle can be infected by injection with naked FMDV RNA, but not by non-invasive exposure to the RNA. Inactivated FMDV samples that contain full-length viral RNA carry only a negligible risk of infecting animals.

Transportation of goods is as old as human civilizations : past networks and their evolution shed light on long term trends. Transportation impact on climate change is measured as major, as well as the impact on spreading a pandemic. These two reasons motivate the importance of providing relevant and reliable historical geographic datasets of these networks. This paper focuses on reconstructing the railway network in France at its maximal extent, a century ago. The active stations and lines are well documented by the French SNCF, in open public data. However, that information ignores past stations (ante 1980), which represent probably more than what is recorded in public data. Additional open data, individual or collaborative (eg. Wikipedia) are particularly valuable, but they are not always geo-coded, and two more sources are necessary to completing that geo-coding: ancient maps and aerial photography. Therefore, remote sensing and volunteer geographic information are the two pillars of past railway reconstruction. The methods developed are adapted to the extraction of information from these sources: automated parsing of Wikipedia Infoboxes, data extraction from simple tables, even from simple text. That series of sparse procedures can be merged into a comprehensive computer-assisted process. Beyond this, a huge effort in quality control is necessary when merging these data: automated wherever possible, or finally visually controlled by observation of remote sensing information. The main output is a reliable dataset, under ODbl, of more than 9100 stations, which can be combined with the information about the 35000 communes of France, for a large variety of studies. This work demonstrates two thesis: (a) it is possible to reconstruct transport network data from the past, and generic computer assisted methods can be developed; (b) the value of remote sensing and volunteered geo info is considerable (what archeologists already know).

In this study, the optimal condition for the extraction of antioxidants from the fruit Buah Mahkota Dewa (Phaleria macrocarpa) was determined by using Response Surface Methodology (RSM). The optimization was applied using central composite design (CCD) to investigate the three independent variables, namely extraction temperature (^oC), extraction time (minutes) and extraction solvent to-feed ratio (%v/v) on the responses of free radical scavenging activity (DPPH), ferric ion reducing power assay (FRAP), total phenolic content (TPC) and total flavonoid content (TFC).The optimal conditions for the antioxidants extraction were found to be extraction temperature (64^oC), extraction time (66 minutes) and solvent to-feed ratio (75 %v/v) with the highest percentage yield of DPPH, FRAP, TPC and TFC were 86.85%, 7.47%, 292.86 mg/g and 3.22 mg/g respectively. Moreover, the data were subjected to response surface methodology (RSM) and the results showed that the polynomial equations for all models were significant, did not show lack of fit, and presented adjusted determination coefficients (R²) above 99%, proving the yield of phenolic, flavonoid and antioxidants activities obtained experimentally were close to the predicted values and the suitability of the model employed in RSM to optimize the extraction conditions. Hence, in this study, the fruit from P.macrocarpa could be considered to have the strong antioxidant ability and can be used in various cosmeceutical or medicinal applications.

There is significant need for development of a new environmentally friendly, extraction-free sample collection medium that can effectively preserve and protect genetic material for point-of-care, and/or self-collection, home-collection, and mail-back testing. Systematic Evolution of Ligands by Exponential Enrichment (SELEX) was used to create anti-ribonuclease (RNase) Deoxyribonucleic acid (DNA) aptamers against purified RNase A conjugated to paramagnetic carboxylated beads. Following 8 rounds of SELEX carried out under various stringency conditions, e.g., selection using Xtract-Free™ (XF) specimen collection medium, and elevated ambient temperature of 28 ºC, a panel of 5 aptamers was chosen following bioinformatic analysis using next-generation sequencing. The efficacy of aptamer inactivation of RNase was assessed by monitoring Ribonucleic acid (RNA) integrity by fluorometric and real-time RT-PCR analysis. Inclusion of aptamers in reaction incubations resulted in an 8,800 to 11,200-fold reduction of RNase activity, i.e., digestion of viral RNA compared to control. Thus, anti-RNase aptamers integrated into XF collection medium as well as other commercial reagents and kits have great potential for ensuring quality intact RNA for subsequent genomic analysis.