Background: Processing whole-slide images (WSI) to train neural networks can be intricate and laborious. We developed an open-source library covering recurrent tasks in processing of WSI and in evaluating the performance of the trained networks for classification tasks. Methods: Two histopathology use-cases were selected. First we aimed to train a CNN to distinguish H&E-stained slides obtained from neuropathologically classified low-grade epilepsy-associated dysembryoplastic neuroepithelial tumor (DNET) and ganglioglioma (GG). The second project we trained a convolutional neural network (CNN) to predict the hormone expression of pituitary adenoms only from hematoxylin and eosin (H&E) stained slides. In the same approach, we addressed the issue to also predict clinically silent corticotroph adenoma. We included four clinico-pathological disease conditions in a multilabel approach. Results: Our best performing CNN achieved an area under the curve (AUC) of 0.97 for the receiver operating characteristic (ROC) for corticotroph adenoma, 0.86 for silent corticotroph adenoma and 0.98 for gonadotroph adenoma. Our DNET-GG classifier achieved an AUC of 1.00 for the ROC curve. All scores were calculated with the help of our library on predictions on a case basis. Conclusions: Our comprehensive library is most helpful to standardize the work-flow and minimize the work-burden in training CNN. It is also compatible with fastai. Indeed, our new CNNs reliably extracted neuropathologically relevant information from the H&E staining only. This approach will supplement the clinico-pathological diagnosis of brain tumors, which is currently based on cost-intense microscopic examination and variable panels of immunohistochemical stainings.

Diagnosing melanocytic lesions is among the most challenging problems in the practice of pathology. The difficulty of physically masking melanin pigment and the similarity of its color to commonly used chromogens often complicate examination of the cytomorphology and immunohistochemical staining results for tumor cells. Melanin bleach can be very helpful for histopathological diagnosis of heavily pigmented melanocytic lesions. Although various depigmentation methods have been reported, no standardized methods have been developed. This study developed a fully automated platform that incorporates hydrogen peroxide-based melanin depigmentation in an automated immunohistochemical analysis. The utility of the method was tested in one cell block of malignant melanoma cells in pleural effusion, ten ocular melanoma tissue samples, and ten cutaneous melanoma tissue samples. Our results demonstrated that the proposed method, which can be performed in only 3 hours, effectively preserves cell cytomorphology and immunoreactivity. The method is particularly effective for removing melanin pigment to facilitate histopathological examination of cytomorphology and for obtaining an unmasked tissue section for immunohistochemical analysis.

The accurate prediction of molecular properties such as lipophilicity and aqueous solubility are of great importance and pose challenges in several stages of the drug discovery pipeline. Machine learning methods like graph-based neural networks (GNNs) have shown exceptionally good performance in predicting these properties. In this work, we introduce a novel GNN architecture, called directed edge graph isomorphism network (D-GIN). It is composed of two distinct sub-architectures (D-MPNN, GIN) and achieves an improvement in accuracy over its sub-architectures employing various learning, and featurization strategies. We argue that combining models with different key aspects help make graph neural networks deeper and simultaneously increase their predictive power. Furthermore, we address current limitations in assessment of deep-learning models, namely, comparison of single training run performance metrics, and offer a more robust solution.

This work describes and compares the backpropagation algorithm with the Extended Kalman filter, a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.

In the realm of metal steel and iron manufacturing, there is a constant drive to optimize production efficiency and enhance the quality of the final products. This abstract explores a paradigm shift in this industry through the utilization of Computational Fluid Dynamics (CFD) as a powerful tool for achieving these goals .The study focuses on various critical aspects of the manufacturing process. Firstly, it delves into three-phase processes such as slag and gas entrainment in liquid steel, which have a significant impact on the overall product quality. Understanding and optimizing these processes is crucial to ensure the desired chemical composition and physical properties of the final metal.The abstract investigates the role of CFD in vacuum degassing, a process that plays a pivotal role in removing impurities, such as hydrogen and oxygen, from the liquid steel. By leveraging CFD to simulate and analyze the fluid flow patterns, researchers and engineers can design more efficient vacuum degassing systems, leading to improved product purity and reduced waste.Another crucial aspect explored in this abstract is the alloy melt and mixing process. By employing CFD simulations, researchers can gain insights into the movement of different alloy components and optimize their distribution within the melt. This aids in achieving the desired alloy composition, ensuring uniformity, and enhancing the mechanical properties of the final product.In addition, the study delves into the movement and flotation of inclusions, which are unwanted impurities present in the metal. CFD can be utilized to model and analyze the behavior of these inclusions, enabling engineers to design efficient strategies for their removal, thereby enhancing the purity and integrity of the final product.Moreover, the abstract considers the impact of melt temperature losses, which can occur during different stages of the manufacturing process. By employing CFD, it becomes possible to understand and mitigate these temperature losses, leading to improved energy efficiency and better control over the manufacturing parameters.Part 1 of this abstract critically evaluates the use of CFD in iron making, analyzing its benefits and limitations. It highlights how CFD can aid in process optimization, improving the understanding of complex phenomena involved in iron making, and ultimately leading to enhanced production efficiency.Part 2 focuses on the application of CFD in steel making and steel operation. It explores the fluid flow dynamics during different stages of steel production, including refining, casting, and rolling. By leveraging CFD, engineers can optimize these processes, leading to improved product quality, reduced defects, and increased productivity.This abstract demonstrates the transformative potential of Computational Fluid Dynamics in metal, steel, and iron manufacturing. By utilizing CFD as a tool to model and analyze complex fluid flow phenomena, researchers and engineers can revolutionize the production process, maximizing efficiency, and ensuring high-quality end products.

The importance of energy systems and its role in economics and politics is not hidden for anyone. This issue is not only important for the advanced industrialized countries, which are major energy consumers, but is also important for oil-rich countries. In addition to the nature of these fuels which contains polluting substances, the issue of their ending up has aggravated the growing concern. Biofuels can be used in different fields for energy production like electricity production, power production or for transportation. Various scenarios have been written about the estimated biofuels from different sources in the future energy system. The availability of biofuels for the electricity market, heating and liquid fuels is very important. Accordingly, the need for handling, modelling, decision making and future forecasting for biofuels can be one of the main challenges for scientists. Recently, machine learning and deep learning techniques have been popular in modeling, optimizing and handling the biodiesel production, consumption and its environmental impacts. The main aim of this study is to evaluate the ML and DL techniques developed for handling biofuels production, consumption and environmental impacts, both for modeling and optimization purposes. This will help for sustainable biofuel production for the future generations.

: Image guided superficial radiation therapy (IGSRT) combines superficial radiation therapy (SRT) with full dermal visualization (FDV) via high resolution dermal ultrasound (HRDUS) for the treatment of non-melanoma skin cancer (NMSC). The gold standard for IGSRT delivery includes a comprehensive cancer care model with support for the dermatologists by a multidisciplinary team. When delivered in this model, IGSRT can achieve cure rates of 99% for treatment of NMSC. This paper focuses on the benefits of IGSRT during therapy. Medical records from 7 dermatology clinics of 883 patients with 1,507 cases of NMSC treated with IGSRT be-tween 2017 and 2018 were retrospectively reviewed. 92% of the NMSC lesions showed daily depth fluctuations, 60.32% of lesions did not require changes during therapy, and nearly 40% of lesions required at least one compensatory change during therapy. 83% of NMSC lesions were labeled high-risk based on the 2024 NCCN guidelines. Increasing and decreasing tumor depth measurements during IGSRT inform dermatologists when adaptive changes in energy (kV), TDF and dose will result in more efficacy and less toxicity, respectively.

The atomic nucleus contains protons and neutrons surrounded by a structured electron cloud. Some combinations of protons and neutrons induce the nucleus to behave like a microscopic magnet, possessing a unique magnitude and orientation known as the nuclear magnetic moment (µ). When the numbers of protons and neutrons are both even then µ=0, but otherwise each nu-clide’s nuclear magnetic moment is unique. A second unique nuclear physical property relates to the nucleon binding energy (BE), which can be thought of as the energy between protons and neu-trons bound within the nucleus. The sequence of stable nuclides increases one nucleon at a time through 36Ar. The binding energy associated with the addition of each successive nucleon (∆BE) through this progression is unique. The hypothesis here is that the unique non-zero magnetic mo-ment and ∆ binding energy of each nuclide derive from its respective microscopic nuclear struc-ture, analogous to the way that the atomic physical properties of an element ultimately derive from its unique electron orbital structure. By extension, the identification of nuclear periodic pat-terns might eventually inform a theory of nuclear structure. The light, stable nuclides through 36Ar were arranged in ascending order according to atomic mass, and their nuclear magnetic mo-ments and binding energies were evaluated for periodic patterns. Fixed-period lengths from 4 through 18 nuclides per period were considered. These fixed periods, each of equal length, were stacked one upon the other and analyzed for vertical trends. The best evidence of periodicity in both µ and ∆BE converges precisely at the fixed 12-nuclide period. Implications for nuclear structure are discussed.

Next-generation cancer and oncology research needs to take full advantage of the multi-modal structured, or graph, information, with the graph datatypes ranging from molecular structures to spatially resolved imaging and digital pathology to biological networks to knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on the large multi-modal datasets. In this review article, we survey the landscape of recent (2020-present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. Subsequently, we identify the most promising directions for future research. We compare GNNs with graphical models and "non-structured" deep learning, and devise the guidelines for cancer and oncology researchers or physician-scientists asking the question of whether they should adopt the GNN methodology in their research pipelines.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

Background. Chest CT is widely regarded as a dependable imaging technique for detecting pneumonia in COVID-19 patients, but there is growing interest in microwave radiometry (MWR) of the lungs as a possible substitute for diagnosing lung involvement. Aim. The aim of the study is to examine the utility of the MWR approach as a screening tool for diagnosing pneumonia with complications in patients with COVID-19. Methods. Our study involved two groups of participants. The control group consisted of 50 individuals (24 male and 26 female) between the ages of 20 to 70 years who underwent clinical evaluations and had no known medical conditions. The main group included 142 participants (67 men and 75 women) between the ages of 20 to 87 years who were diagnosed with COVID-19 complicated by pneumonia and were admitted to the emergency department between June 2020 to June 2021. Skin and lung temperatures were measured at 14 points, including 2 additional reference points, using a previously established method. Lung temperature data were obtained with the MWR2020 (RTM-01-RES) (MMWR LTD, Edinburgh, UK), a CE Class I device. All participants underwent clinical evaluations, laboratory tests, chest CT scans, MWR of the lungs, and reverse transcriptase polymerase chain reaction (RT-PCR) testing for SARS-CoV-2. Results. The MWR exhibits a high predictive capacity as demonstrated by its sensitivity of 98.6% and specificity of 84.0%. Conclusions. MWR of the lungs can be a valuable substitute for chest CT in diagnosing pneumonia in patients with COVID-19, especially in situations where chest CT is unavailable or impractical.

Deep learning (DL) algorithms have recently emerged from machine learning and soft computing techniques. Since then, several deep learning (DL) algorithms have been recently introduced to scientific communities and are applied in various application domains. Today the usage of DL has become essential due to their intelligence, efficient learning, accuracy and robustness in model building. However, in the scientific literature, a comprehensive list of DL algorithms has not been introduced yet. This paper provides a list of the most popular DL algorithms, along with their applications domains.

Post-menopausal women are at risk of osteoporotic vertebral fractures (OVFs), which if undetected and untreated, can lead to significant pain and morbidity. However, OVFs are often not reported by radiologists on routine chest radiographs. Artificial Intelligence (AI) is increasingly used in medical applications with improvements in detection and diagnosis. This study aims to investigate the clinical value of a newly developed AI tool, Ofeye 1.0 for automated detection of OVFs on lateral chest radiographs in post-menopausal women (>60 years) who were referred to undergo chest x-rays for other reasons. A total of 510 de-identified lateral chest radiographs from three clinical sites were retrieved and analysed by Ofeye1.0 tool. These images were then reviewed by a consultant radiologist to decide whether there is any fracture present or not with findings served as the reference standard for determining the diagnostic performance of the AI tool. The percentage of radiologist reports which included the OVF was analysed by comparing diagnostic reports with AI findings, while the accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive values (NPV) of the AI tool were calculated. Out of all the original radiologist reports, missed OVFs were found in 14% images but were detected by the AI tool. The AI tool demonstrated a relatively high specificity 92.8% (95% CI: 89.6, 95.2%), moderate accuracy 80.3% (95% CI: 76,3, 80.4%), PPV 73.7% (95% CI: 65.2, 80.8%) and NPV 81.5% (95%CI: 79, 83.8%), but low sensitivity 49% (95%CI: 40.7, 57.3%). The high false negative results were mainly due to mild OVFs with <20% vertebral height loss. The new AI software tool has high specificity with a low false positive rate of 5.1%, showing that it can be used as a complimentary tool to the routine diagnostic reports for reduction of missed OVF in elderly women. The low sensitivity with high false negative rates indicate the necessity of radiologist’s in identifying and reporting early OVFs.

Despite saltmarshes being considered as nature-based solutions (NbS) towards climate change mitigation, India’s saltmarsh ecosystems are least studied. This study quantifies the seasonal variation in carbon stocks mono-specific saltmarsh species (Porteresia coarctata) and its potential to play an important role in India’s climate change mitigation plans. Seasonal (pre-and post-monsoon) sampling of P. coarctata surface water, biomass and 30 cm sediment core was collected across four locations on the east coast of India to quantify sediment dry bulk density (DBD), organic matter (OM%), organic carbon (Corg%), Corg stocks of sediment and biomass, total carbon (C%) and nitrogen (N%) and stable isotopes of δ13C and δ15N. In general, the sediment DBD, OM and Corg of P. coarctata meadows was higher in post-monsoon and was influenced by salinity and pH changes. Isotope (δ¹³C) modelling of various sediment C sources suggested, particulate organic matter (POM) contribution was highest (0.04-0.79%) followed by P. coarctata (0.01–052%) and other macrophytes across our study locations. The seasonal variation of δ¹³C showed increased contribution of marine derived particulate and dissolved organic matter into P. coarctata meadows in post-monsoon season. Heavier δ¹⁵N values were observed in post-monsoon season suggesting anthropogenic input, that was utilized by P. coarctata to increase its above and below-ground biomass and shoot density. The combined ecosystem (30 cm sediment + biomass) Corg stocks of P. coarctata was 1.7-fold higher in post-monsoon (4021.20± 917 Mg C) compared to pre-monsoon (2297.36 ±647 Mg C) season among the four locations with a sediment Corg contribution >70%. Based on the International Panel for Climate Change Tier II assessment the P. coarctata meadows (443 ha) can help in avoiding the pre and post-monsoon emissions of 8431.34 and 14757.84 Mg CO₂ respectively. The combined price of the total CO₂ equivalent stored in P. coarctata meadows in pre- and post-monsoon is US$ 14.50 and US$ 25.38 million respectively. Further studies quantifying the NbS potential of P. coarctata mono-specific and mixed meadows of India’s coast is needed along with integration of saltmarsh ecosystems into India’s National Action Plan on Climate Change.

Attackers are perpetually modifying their tactics to avoid detection and frequently leverage legitimate credentials with trusted tools already deployed in a network environment, making it difficult for organizations to proactively identify critical security risks. Network traffic analysis products have emerged in response to attackers’ relentless innovation, offering organizations a realistic path forward for combatting creative attackers. Additionally, thanks to the widespread adoption of cloud computing, Device Operators (DevOps) processes, and the Internet of Things (IoT), maintaining effective network visibility has become a highly complex and overwhelming process. What makes network traffic analysis technology particularly meaningful is its ability to combine its core capabilities to deliver malicious intent detection. In this paper, we propose a novel darknet traffic analysis and network management framework to real-time automating the malicious intent detection process, using a weight agnostic neural networks architecture. It is an effective and accurate computational intelligent forensics tool for network traffic analysis, the demystification of malware traffic, and encrypted traffic identification in real-time. Based on Weight Agnostic Neural Networks (WANNs) methodology, we propose an automated searching neural net architectures strategy that can perform various tasks such as identify zero-day attacks. By automating the malicious intent detection process from the darknet, the advanced proposed solution is reducing the skills and effort barrier that prevents many organizations from effectively protecting their most critical assets.

Accurate medical image segmentation is paramount for precise diagnosis and treatment in modern healthcare. This research presents a comprehensive study on the efficacy of Particle Swarm Optimization (PSO) combined with Histogram Equalization (HE) preprocessing for medical image segmentation, focusing on Lung CT-Scan and Chest X-ray datasets. Best Cost values reveal the PSO algorithm’s performance, with HE preprocessing demonstrating significant stabilization and enhanced convergence, particularly in complex Lung CT-Scan images. Evaluation metrics, including Accuracy, Precision, Recall, F-Score, Specificity, Dice, and Jaccard, show substantial improvements with HE preprocessing, emphasizing its impact on segmentation accuracy. Comparative analyses against alternative methods, such as Otsu, Watershed, and K-means, confirm the competitiveness of the PSO-HE approach, especially in Chest X-ray images. The study also underscores the positive influence of preprocessing on image clarity and precision. These findings highlight the promise of the PSO-HE approach in advancing the accuracy and reliability of medical image segmentation, paving the way for further research and method integration to enhance this critical healthcare application.

Market crises pose significant challenges for businesses, emphasizing the importance of effective crisis management strategies. Central to these strategies is the ability to identify and retain loyal customers, who often serve as the bedrock of stability during tumultuous times. This paper investigates the application of deep meta-learning analysis to predict loyal customers as a cornerstone of market crisis management. Drawing upon an extensive literature review, the study explores previous research on market crises, customer loyalty, and the evolution of deep learning and meta-learning in crisis management contexts. Methodologically, the paper outlines data collection, model development, and evaluation procedures tailored for deep meta-learning-based customer prediction. In results, the overall accuracy of model 85%, a precision 0.88, recall 0.82, and F1-score 0.85 were obtained. The analysis demonstrates the effectiveness of deep meta-learning models in accurately identifying loyal customers during market crises, offering insights into their performance and applicability compared to traditional methods. Practical implications include potential applications in crisis management for businesses and considerations for real-world implementation.

Photovoltaic (PV) systems, which are renewable energy sources, are increasingly being utilized in distributed generation. To maintain a stable energy balance, energy storage systems such as batteries (BAT) play a vital role. Electric vehicles (EVs) offer a promising solution with rechargeable battery systems for operation. The BATs must maintain their state of charge within design boundaries, despite intermittent PV and load power fluctuations, and advanced power control and management techniques are essential for their effective operation. The article evaluates an intelligent controller that uses a Sliding Mode Control adaptive deep learning algorithm Convolutional Neural Networks (SMC-CNN) and a unique Strategy for managing supervisory power. (SPMS) for photovoltaic systems with battery energy storage for better regulation of DC bus voltage. SMC-CNN offers exceptional resilience and seamless functionality, minimizing fluctuations in DC bus voltage in the control strategy design requirements. The primary goals are maintaining a consistent power supply and ensuring continuous service by preventing system components from exceeding capacity. This study aims to enhance the control of DC bus voltage in the PV and battery system, with the primary significance focusing on the following aspects. The advanced SPMS has been created, incorporating control system constraints to enhance SOC balancing speed and reduce fluctuations in DC bus voltage. Power flow management involves optimizing energy flow between the PV system, battery system, and load while minimizing battery capacity requirements. The proposed SMC-CNN and SPMS are demonstrated through real-time simulation using Matlab/Simulink, as demonstrated in comprehensive case studies.

Background: Prediction of neurorehabilitation outcomes after a Spinal Cord Injury (SCI) is crucial for healthcare resource management and improving prognosis and rehabilitation strategies. Arti-ficial neural networks (ANNs) have emerged as a promising alternative to conventional statistical approaches for identifying complex prognostic factors in SCI patients. Materials: a database of 1256 SCI patients admitted for rehabilitation was analyzed. Clinical and demographics data and SCI characteristics, were used to predict functional outcomes using both ANN and linear regression models. The former was structured with input, hidden, and output layers, while the linear regression identified significant variables affecting outcomes. Both ap-proaches aimed to evaluate and compare their predictive accuracy for rehabilitation outcomes measured by the Spinal Cord Independence Measure (SCIM) score. Results: Both ANN and linear regression models identified key predictors of functional outcomes, such as age, injury level, and initial SCIM scores (correlation with actual outcome: R=0.75 and 0.73, respectively). When alimented also with parameters recorded during hospitalization, the ANN highlighted the importance of these additional factors like motor completeness and compli-cations during hospitalization, showing an improvement in its predictive accuracy (R=0.87). Conclusion: ANN seemed to be not widely superior to classical statistics in general, but, taking into account complex and non-linear relationships among variables, emphasized the impact of complications during the hospitalization on recovery, particularly respiratory issues, deep vein thrombosis, and urological complications. These results suggested that the management of com-plications is crucial for improving functional recovery in SCI patients.

Methotrexate is an antimetabolic agent with proliferative and immunosuppressive activity. It has been demonstrated to be an effective treatment for acute lymphoblastic leukemia (ALL) in children. However, there is evidence of an association between methotrexate and toxicity risks, which influences the personalization of treatment, particularly in the case of childhood ALL. This article presents the development and implementation of an algorithm based on artificial neural networks to detect methotrexate toxicity in pediatric patients with acute lymphoblastic leukemia. The algorithm utilizes historical clinical and laboratory data, with an effectiveness of 99% in the tests performed with the patients dataset. The use of neural networks in medicine is often linked to disease diagnosis systems. However, neural networks are not only capable of recognizing examples, but also hold very important information. For this reason, one of the main areas of application of neural networks is the interpretation of medical data. In this article we diagnose with the application of neural networks in medicine with a concrete example: Detecting Methotrexate in Pediatric Patient in its early stages.

The Spiking Neural Network (SNN) has attracted more and more attention recently. It adopts binary spike signals to transmit information. Benefitting from the information passing paradigm of SNNs, the multiplications of activations and weights can be replaced by additions, which are more energy-efficient. However, its ``Hard Reset" mechanism for the firing activity would ignore the difference among membrane potentials when the membrane potential is above the firing threshold, causing information loss. Meanwhile, quantifying the membrane potential to 0/1 spikes at the firing instants will inevitably introduce the quantization error thus bringing about information loss too. To address these problems, we propose to use the ``Soft Reset" mechanism for the supervised training-based SNNs, which will drive the membrane potential to a dynamic reset potential according to its magnitude, and Membrane Potential Rectifier (MPR) to reduce the quantization error via redistributing the membrane potential to a range close to the spikes. Results show that the SNNs with the ``Soft Reset" mechanism and MPR outperform their vanilla counterparts on both static and dynamic datasets.

Neural networks require a large quantity of training spectra and detector responses in order to learn to solve the inverse problem of neutron spectrum unfolding. In addition, due to the under-determined nature of unfolding, non-physical spectra which would not be encountered in usage should not be included in the training set. While physically realistic training spectra are commonly determined experimentally or generated through Monte Carlo simulation, this can become prohibitively expensive when considering the quantity of spectra needed to effectively train an unfolding network. In this paper, we present three algorithms for the generation of large quantities of realistic and physically motivated neutron energy spectra. Using an IAEA compendium of 251 spectra, we compare the unfolding performance of neural networks trained on spectra from these algorithms, when unfolding real-world spectra, to two baselines. We also investigate general methods for evaluating the performance of and optimizing feature engineering algorithms.

The Physics Informed Neural Networks framework is applied to the understanding of the dynamics of Coronavirus of 2019. To provide the governing system of equations used by the framework, the Susceptible-Infected-Recovered-Death mathematical model is used. The study focused on finding the patterns of the dynamics of the disease which involves predicting the infection rate, recovery rate and death rate; thus predicting the active infections, total recovered, susceptible and deceased at any required time. The study used data that was collected on the dynamics of COVID-19 from the Kingdom of Eswatini between March 2020 and September 2021. The obtained results showed less errors thus making highly accurate predictions.

In this paper, the Group Method of Data Handling (GMDH) type of neural networks is used for the inductance calculation of variable inductors. The relation between the inductance of the inductor in the linear and nonlinear regions is investigated, and parameters such as the voltage across the inductor, bias current, and ac current are taken into account. The experimental setup is used for generating the data needed for training the neural network. Over 800 experiments were conducted and were used for training and validation of the neural network results. The results are compared with the reluctance equivalent circuit method, and they show a much better accuracy. The proposed method can be used for the calculation of various magnetic components, and it is not limited to variable inductors.

In the last decade, unprecedented progress in the development of neural networks influenced dozens of different industries, among which are signal processing for the electroencephalography process (EEG). Electroencephalography, even though it appeared in the first half of the 20th century, to this day didn’t change the physical principles of operation. But the signal processing technique due to the use of neural networks progressed significantly in this area. Evidence for this can serve that for the past 5 years more than 1000 publications on the topic of using machine learning have been published in popular libraries. Many different models of neural networks complicate the process of understanding the real situation in this area. In this manuscript, we provided the most comprehensive overview of research where were used neural networks for EEG signal processing.

The principal minimum horizontal stress plays an important role in the study of reservoir characteristics, modeling of oil and gas reservoir, drilling, production and stimulating wells. However, it is currently not possible to measure the minimum horizontal stress along the wellbore as a geophysical parameter logging. Minimum horizontal stress is measured by leak-off test (LOT) at only several points in a well. In order to have the values all along the wellbore, experimental formulas were established to determine the minimum horizontal stresses for different fields. Then these formulas must be calibrated with LOT data whose number is usually limited, even sometimes unavailable. On the other hand, the empirical formulas of one field might not be accurate for another. This study presents a new approach to solve the problem of minimum horizontal stress estimation by a combination of artificial intelligence and geostatistics. The method consists of using artificial neural network (ANN) to build a model of minimum horizontal stress estimation from relevant parameters such as true vertical depth, pore pressure and vertical stress, then combined with Kriging interpolation to obtain the distribution in space of the minimum horizontal stress. Hence, this method can estimate the minimum horizontal stress with a limited amount of available data and therefore we do not need to drill new wells or to find empirical formulas for each survey area. The method was then applied in a case study involved real geomechanical dataset of Hai Thach - Moc Tinh field in Nam Con Son basin, Vietnam.

This paper presents a study and implementation of a convolutional neural network to identify and recognize humpback whale specimens from the unique patterns of their tails. Starting from a dataset composed of images of whale tails, all the phases of the process of creation and training of a neural network are detailed – from the analysis and pre-processing of images to the elaboration of predictions, using TensorFlow and Keras frameworks. Other possible alternatives are also explained when it comes to tackling this problem and the complications that have arisen during the process of developing this paper.

We developed an ovarian cancer-targeted drug delivery system based on a follicle-stimulating hormone receptor (FSHR) peptide. The lipophilic chemotherapeutic drug SN38 and the photosensitizer IR820 were loaded into the phospholipid bilayer of liposomes. Near-infrared laser irradiation stimulated the generation of reactive oxygen species, causing short-term reactive molecular species and spatial-temporal restricted photodamage to the biological targets. The reactive molecular species and spatial-temporal restricted photodamage enhanced the release and uptake of chemotherapy drugs and increased the sensitivity to chemotherapy drugs in ovarian cancer cells. FSH liposomes loaded with SN38 and IR820 (SN38/IR820-Lipo@FSH) were prepared using thin-film hydration-sonication. FSH peptide binding was analyzed using 1H NMR spectrum and Maldi-Tof. The average size and zeta potential of SN38/IR820-Lipo@FSH were 105.1 ± 1.15 nm (PDI: 0.204 ± 0.03) and −27.8 ± 0.42 mV, respectively. SN38/IR820-Lipo@FSH exhibited good drug-loading properties and the in vitro release was slow. FSH significantly increased the uptake of liposomes, inhibited cell proliferation, and induced apoptosis in A2780 cells. Moreover, SN38/IR820-Lipo@FSH exhibited good tumor-targeting ability and anti-ovarian cancer activity in vivo. The SN38/IR820-Lipo@FSH exhibited specific targeting to A2780 ovarian cancer cells. The combination of chemotherapy and photodynamic treatment based on an FSH peptide-targeted delivery system may be an effective approach to treating ovarian cancer.

The application potential of cellulosic materials in natural composites and other fields needs to be explored to develop innovative, sustainable, lightweight, functional biomass materials that are also environmentally friendly. This study investigated Typha augostifolia (Typha sp.) as a potential new raw material for extracting cellulose nanocrystals (CNCs) for application in wastewater treatment composites. Alkaline treatments and bleaching were used to remove cellulose from the stem fibers. The CNCs were then isolated from the recovered cellulose using acid hydrolysis. The study showed a few distinct functional groups (O-H, -C-H, =C-H and C-O, and C-O-C) in the Fourier Transform Infrared (FTIR) spectra. Scanning electron microscope (SEM) revealed the smooth surface of CPC and CNCs that resulted from removing lignin and hemicellulose from powdered Typha augostifolia. Based on the crystalline index, the powdered Typha augostifolia, CPC, and CNCs were 42.86%, 66.94% and 77.41%. The loss of the amorphous section of the Typha sp. fiber resulted in a decrease in particle size. It may be inferred from the features of a Typha sp. CNC that CNCs may be employed as reinforcement in composites for wastewater treatment.

Network Embedding (NE) is an important method to learn the representations of network via a low-dimensional space. Conventional NE models focus on capturing the structure information and semantic information of vertices while neglecting such information for edges. In this work, we propose a novel NE model named BimoNet to capture both the structure and semantic information of edges. BimoNet is composed of two parts, i.e., the bi-mode embedding part and the deep neural network part. For bi-mode embedding part, the first mode named add-mode is used to express the entity-shared features of edges and the second mode named subtract-mode is employed to represent the entity-specific features of edges. These features actually reflect the semantic information. For deep neural network part, we firstly regard the edges in a network as nodes, and the vertices as links, which will not change the overall structure of the whole network. Then we take the nodes' adjacent matrix as the input of the deep neural network as it can obtain similar representations for nodes with similar structure. Afterwards, by jointly optimizing the objective function of these two parts, BimoNet could preserve both the semantic and structure information of edges. In experiments, we evaluate BimoNet on three real-world datasets and task of relation extraction, and BimoNet is demonstrated to outperform state-of-the-art baseline models consistently and significantly.

Background: Little is known about risk and prognostic factors in very old patients developing sepsis secondary to community-acquired pneumonia (CAP). Methods: We conducted a retrospective observational study of data prospectively collected at the Hospital Clinic of Barcelona over a 13-year period. Consecutive patients hospitalized with CAP were included if they were very old (≥80 years) and divided into those with and without sepsis for comparison. Sepsis was diagnosed based on the Sepsis-3 criteria. The main clinical outcome was 30-day mortality. Results: Among the 4,219 patients hospitalized with CAP during the study period, 1,238 (29%) were very old. The prevalence of sepsis in this aged group was 71%. Male sex, chronic renal disease, and diabetes mellitus were independent risk factors for sepsis, while antibiotic therapy before admission was independently associated with a lower risk of sepsis. Thirty-day and intensive care unit (ICU) mortality did not differ between patients with and without sepsis. In CAP-sepsis group, chronic renal disease and neurological disease were independent risk factors for 30-day mortality. Conclusion: In very old patients hospitalized with CAP, in-hospital and 1-year mortality rates were increased if they developed sepsis. Antibiotic therapy before hospital admission was associated with a lower risk of sepsis.

This study aimed to identify whether gyrate atrophy of the choroid and retina (GACR) heterozygous individuals have possible clinical manifestations and to explore the potential pathogenic mechanism. In this retrospective study, we surveyed a two-generation pedigree of an individual diagnosed with GACR. Two family members underwent ophthalmological, hematologic, and genetic tests. An arginine-restricted diet with vitamin B6 supplementation was implemented; clinical assessments were repeated every 3 months during follow-up. Relative OAT mRNA expression was determined using real-time quantitative polymerase chain reaction. The 19-year-old compound heterozygous daughter (OAT: c.1186C>T; c.748C>T), had bilateral high myopia, posterior staphyloma, chorioretinal atrophy, macular abnormalities, and elevated hematologic ornithine. The 54-year-old heterozygous mother (OAT: c.1186C>T), presented with bilateral severe myopia, asymmetric posterior staphyloma, retina and choroidal capillary layer atrophy, retinal pigment epithelium abnormalities, and mildly elevated hematologic ornithine. Compared to normal individuals, the daughter and mother had 29% and 46% relative OAT mRNA expression, respectively (P<0.001). We believe that this is the first report of a carrier of one OAT variant allele with mild phenotypes, suggesting that family members should be aware of the possible involvement of autosomal recessive conditions. Additional data suggests nonsense mediated decay-initiated mRNA degradation may cause GACR.

Change detection with heterogeneous remote sensing images (Hete-CD) plays an important role in practical applications, especially when homogenous remote sensing images are unavailable. However, bitemporal heterogeneous remote sensing images (HRSIs) cannot compare directly to measure change magnitude, and many deep learning methods require large amounts of samples to train the module. Moreover, labeling many samples for land cover change detection with HRSIs is time-consuming and labor-intensive. Therefore, acquiring satisfactory performance of Hete-CD remains a challenge for deep learning networks with very small training samples. In this study, we promote a novel deep-learning framework for Hete-CD to obtain satisfactory performance while the initial samples are very small. We initially design a multiscale network with select kernel-attention module to focus on capturing different change targets with various sizes and shapes. Then, a simple yet effective non-parametric sample-enhanced algorithm based on the Pearson correlation coeffi-cient is promoted to explore potential samples around each initial sample. Finally, the proposed network and sample-enhanced algorithm are fused into one iterative framework to improve the change detection performance with very small samples. Experimental results conducted on four pairs of actual HRSIs indicated that the proposed framework can achieve competitive accuracies with very small samples for initialization when compared with some state-of-the-art methods. For example, the improvement is approximately 3.38% and 1.99% when compared with the selected traditional methods and deep learning methods, respectively.

Published data or available literature on sustainable building plan-design, construction, performance, and renovation criteria have covered some stages or some parts of each stage. These data usually have been published partially in many different papers―there have not been any papers that published these data together. Hence, this paper aims to collectively review these data and publish them together. The collection and review of these data were carried out by our twenty-five team members who specialized in sustainable urban, architectural, and civil engineering and construction management. The gathered and reviewed outputs were combined and validated based on a general group consensus. This consensus decision-making proceeded through two major group meetings with several follow-up meetings. The first major meeting was to combine and improve the gathered reviewed sustainable building criteria for Cambodia. The second major meeting was to validate the improved reviewed sustainable building criteria for Cambodia. The several follow-up meetings were to discuss the relevance and importance of the validated data “criteria and their classifications and descriptions” in all stages and more focused on their importance and applicability to Cambodia. The collective reviewed data in this paper would be useful to researchers in the fields. They could also be useful collective knowledge and information for policymakers from governmental agencies and development partners, particularly for sustainable building and construction companies.

The B169L protein (pB169L) of African swine fever virus (ASFV) is a structural protein with an unidentified function during the virus replication. The sequences of the B169L gene and the downstream B438L gene are separated by short intergenic regions. However, the regulatory mode of the gene transcription remains unknown. Here, we identified two distinct promoter regions and two transcription start sites (TSS) located upstream of the open reading frame (ORF) of B438L. Using the promoter reporter system, we demonstrated that the cis activity of the ORF proximal promoter exhibited significantly higher levels compared with that of the distal promoter located in the B169L gene. Furthermore, transfection with the plasmids with two different promoters for B438L could initiate the transcription and expression of the B438L gene in HEK293T cells, and the cis activity of the ORF proximal promoter also displayed the higher activities compared with the distal promoter. Interestingly, the B438L distal promoter also initiated the transcription of the alternatively spliced B169L mRNA (B169L mRNA2) encoding a truncated pB169L (tpB169L) (amino acids 92–169), and the gene transcription efficiency was increased upon mutation of the initiation codon located upstream of the alternatively spliced B169L gene. Taken together, we demonstrated that the distal promoter of B438L gene initiates the transcription of both the B438L mRNA and B169L mRNA2. Comprehensive analysis of the transcriptional regulatory mode of the B438L gene is beneficial for the understanding of the association of B438L protein and pB169L and the construction of the gene-deleted ASFV.

Recent advances in artificial intelligence combined with behavioral sciences have led to the development of cutting-edge tools for recognizing human emotions based on text, video, audio, and physiological data. However, these data sources are expensive, intrusive, and regulated, unlike plants which have been shown to be sensitive to human steps and sounds. A methodology is proposed to use plants as human emotion detectors. Electrical signals from plants are tracked and labeled based on video data. Labeled data are then used for classification. MLP, biLSTM, MFCC-CNN, MFCC-ResNet, and additionally, Random Forests, 1-Dimensional CNN, and biLSTM without windowing models are set using a grid search algorithm with cross-validation. Finally, best-parameterized models are trained and used with the test set for classification. The performance of this methodology is measured with a case study with 54 participants, who were watching an emotionally charged video, as ground truth their facial emotions were simultaneously measured using face emotion analysis. The Random Forest model shows the best performance, particularly in recognizing high-arousal emotions, achieving an overall weighted accuracy of 55.2% and demonstrating high weighted recall in emotions such as fear 61.0% and happiness 60.4%. The MFCC-ResNet model offers decently balanced results, with Accuracy(MFCC-ResNet)=0.318 and Recall (MFCC-ResNet)=0.324. With the MFCC-ResNet model fear and anger are recognized with 75% and 50% recall respectively. Thus, using plants as an emotion recognition tool seems worth investigating, addressing both cost and privacy concerns.

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

: This Systematic Review focused on the use of Bifidobacterium infantis and Bifidobacterium breve in neurodegenerative diseases. The study of metabolomics has demonstrated the relationship between dysbiosis and neuronal death. The modulation of the gut microbiota in the intervention of these pathologies has become a promising area of study, showing beneficial results such as the improvement of synaptic function, the reduction of neuroinflammation, as well as the improvement of associated neuropsychiatric symptoms. Several studies have addressed the administration of Bifidobacterium infantis and Bifidobacterium breve, alone, in conjunction or in combination with other strains, in the intervention of neurodegenerative diseases. This Systematic Review includes the results of 17 research articles (n=5 in humans and n=12 in animal models) and the main result was that the use of these Bifidobacterium strains, alone, in conjunction or in combination with other strains, produced improvements in neurodegenerative disease-related symptomatology and degenerative cellular processes. However, some studies shown neutral results in certain variables. These data suggest that the use of these probiotics has a neuroprotective effect that may delay the progression of the disease. This research provides relevant and updated information on the use of these Bifidobacterium strains in neurodegenerative pathologies such as Alzheimer's disease and Parkinson's disease.

This paper delves into the intricate interactions of photons in the realms of gravity and antigravity. Photons, being fundamental particles of light, exhibit remarkable behaviors as they traverse through the cosmos. They journey through the vast expanses of the universe until they venture into the enigmatic invisible realm. The photon's encounters with gravity and antigravity are explored in detail. When confronting the gravitational influence of massive objects, such as celestial bodies, photons neither gain nor lose energy, but they exchange momentum with the external gravitational field while steadfastly preserving their intrinsic momentum. Intriguingly, the photon's interaction with the mysterious force of antigravity, propelled by dark energy, presents an irreversible transformation. The consequences of this interaction are profound, as photons undergo a cosmic redshift of a magnitude greater than that induced by gravity or other redshift mechanisms. This distinctive effect manifests as the photon departs from the gravitational embrace of galaxies and embarks on a journey beyond their boundaries, where the domain of zero gravity commences. Furthermore, the paper elucidates the dynamics of external forces exerted by massive objects on photons during their interactions. These forces momentarily carry the photons while they engage with the massive objects. Yet, despite this external assistance, the photons maintain their original momentum. Notably, within a gravitational field, the effective deviation from this transportation remains zero, reaffirming the photon's commitment to its initial trajectory.

As technology and multimedia production have advanced, there has been a significant rise in attacks on digital media, resulting in duplicated, fraudulent, and altered data and the infringement of copyright laws. This paper presents a robust and secure digital image watermarking technique that has been implemented in the spatial domain and exploits the erratic and chaotic behaviour of the powerful elementary cellular automata rule-30. The crucial characteristics of the watermarking system, i.e., imperceptibility, capacity, and robustness, have been perfectly balanced by the suggested blind watermarking technique. In this approach, prior to embedding, the grayscale watermark image is downsized to its two Most Significant Bits (MSBs). Then, the 2-MSBs watermark is encrypted using an ECA rule-30 so as to level up the security attribute of the system. Then, the host image is scrambled using ECA rule-30 to distribute the watermark pixels throughout the host image and thus achieve the highest robustness against geometrical attacks. Finally, the encrypted watermark data is embedded into the scrambled host image using the ECA rule-30-based embedding key. The proposed method performs better in terms of imperceptibility, capacity, and robustness when compared to several systems with similar competencies. The simulation's findings demonstrate strong imperceptibility as evaluated by the Peak Signal-to-Noise Ratio (PSNR), which has an average value of 58.3735 dB and a high payload. The experimental outcomes, observed across a diverse range of standardized attack scenarios, unequivocally establish the ascendancy of the proposed algorithm over competing methodologies in the realm of image watermarking.

Ethanolic extracts of propolis collected from Apis mellifera hives have been shown to reduce Nosema ceranae infection in honey bee workers. This study aimed to determine the propolis concentration that optimizes the control of N. ceranae infection in honey bee workers. Newly emerged worker bees were individually fed 2 μL of 50% sucrose solution (w/v) containing 105 N. ceranae spores per bee, and treated with 0%, 25%, 50%, and 75% ethanolic extracted propolis in 50% sucrose solution (v/v). The treated bees were maintained in cages at 34 ± 2˚C and 55 ± 5% RH throughout the study. The number of dead bees was counted and removed from the cages daily for 30 days to generate survival curves. The number of N. ceranae spores per bee (infectivity) was quantified using a hemocytometer, and the number of infected bees per hundred bees (infection rate) was determined. The survival rates of N. ceranae infected bees fed 25%, 50%, and 75% propolis (NP1, NP2, NP3, respectively) were significantly higher than those of infected bees not fed propolis (NO). Furthermore, the infectivity and infection rates of NP2 and NP3 groups were significantly lower than those of the NO group. The infectivity and infection rates of the NP1 group were not different than those of the NO group. Our data suggest that 50% and 75% propolis extracts are appropriate concentrations for treating N. ceranae infection in honey bees. Ethanolic extracted propolis can be an alternative treatment for N. ceranae infection in Western honey bees.

Dementia, primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD), affects millions worldwide, making detection and monitoring crucial. To enable these tasks, we propose encoding in-text pauses and filler words (i.e., “uh” and “um”) in text-based language models, and thoroughly evaluate their effect in performance. Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrated the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% F1-score. Compared to the state-of-the-art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.

Transformative education significantly advances society's growth as an essential doorway to fresh language learning chances. It equips people to succeed in a complicated world by encouraging critical thinking, inclusivity, social responsibility, lifelong learning, and international collaboration. Adopting transformative education can result in a more inventive, sustainable, and equal society where everyone can realize their potential and advance society's interests as educational systems change. This paper aims to gather literature regarding how transformative education becomes a door toward new learning opportunities in societal development especially language. Transformative education may produce a generation of knowledgeable, sympathetic, and proactive students who can bring about constructive social change by prioritizing holistic development. Hence, educators should work to foster a learning atmosphere where all students feel supported and respected. Through integrating social justice ideals into the educational process, transformative education equips students to act as change agents and advocates for equity both within and outside their communities.

It is strongly desirable to accurately detect the clouds in hyperspectral images onboard before compression. However, conventional onboard cloud detection methods are not appropriate to all situation such as shadowed cloud or darken snow covered surfaces which are not identified properly in the NDSI test. In this paper, we propose a new spectral–spatial classification strategy to enhance the orbiting cloud screen performances obtained on hyperspectral images by integrating threshold exponential spectral angle map (TESAM), adaptive Markov random field (aMRF) and dynamic stochastic resonance (DSR). TESAM is performed to classify the cloud pixels coarsely based on spectral information. Then aMRF is performed to do optimal process by using spatial information, which improved the classification performance significantly. Some misclassification points still exist after aMRF processing because of the noisy data in the onboard environment. DSR is used to eliminate misclassification points in binary labeling image after aMRF. Taking level 0.5 data from hyperion as dataset, the average overall accuracy of the proposed algorithm is 96.28% after test. The method can provide cloud mask for the on-going EO-1 images and related satellites with the same spectral settings without manual intervention. The experiment indicate that the proposed method reveals better performance than the classical onboard cloud detection or current state-of-the-art hyperspectral classification methods.

Predictive studies are essential to establish fundamental data for monitoring and controlling Xylella fastidiosa infections in our country. Limited knowledge exists about how Xylella fastidiosa interacts with the plant host's immune system, leaving numerous unanswered questions regarding Xylella fastidiosa biology and its interactions with national plant hosts. Key inquiries include understanding of how the plant immune system interfaces with Xylella fastidiosa in the xylem and identifying the specific or shared mechanisms underlying the susceptibility of different hosts. Factors such as the presence of insect vectors, abundance of host plants, and climate suitability play pivotal roles in Xylella fastidiosa dispersal. We recommend that countries identified with relatively high risk, like Portugal, undertake thorough individual risk analyses. The implementation of preventive measures and, if necessary, the enhancement of surveillance systems for early detection of Xylella fastidiosa in plants and insect vectors are crucial steps. Additionally, raising awareness is of equal importance to mitigate socioeconomic and ecological impacts on their ecosystems.

We describe the design and fabrication of an industrial injection moulding system which can be mounted and used on the NCD-SWEET Small-angle X-Ray Scattering Beamline at ALBA. We show how highly useful time-resolved data can be obtained using this system. We are able to evaluate the fraction of material in the mould cavity and identify the first material to solidify and how this varies with the injection tem-perature. The design follows current industrial practice and provides opportunities to collect time-resolved data at several points within the mould cavity so we can build up a 4D perspective of the morphology and its temporal development. The quantitative data obtained will prove invaluable for the optimisation of the next generation of in-jection moulding techniques. This preliminary work used results from the injection moulding of a general purpose isotactic polypropylene.

Dual energy X-ray absorptiometry (DEXA) measuring tool is a reliable and accurate technology to measure bone density and bone mineral composition. This research examined the composition and bone density (bone mineral composition and bone mineral density) of the whole body and representative body parts using DEXA. The participants were 240 healthy adult men and women who were divided into three groups based on age. The total bone mineral density (BMD) of women amounted to an average of 1.14 g/㎠ in Group A, 1.14 g/㎠ in Group B, and 0.98 g/㎠ in Group C. For men, the average BMD was 1.25 g/㎠ in Group A, 1.20 g/㎠ in Group B, and 1.17 g/㎠ in Group C. As a result, the reduction of age-specific BMD was shown to have a correlation with aging and body mass index(BMI), and it is determined that exercising on a regular basis can prevent reduction in BMD by maintaining appropriate muscle mass.

Accurate crop diseases classification is crucial for ensuring food security and enhancing agricultural productivity. However, existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhances multimodal synergy for better crop disease classification than traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to using solely the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing prompt quality. Secondly, we integrate the cross-attention and the SE (Squeeze-and-Excitation) attention into the training-free mode VLCD (Vision-Language model for Crop Diseases classification) and the training-required mode VLCD-T (VLCD-Training) respectively for prompt text processing, enhancing classifier weights by emphasizing key text features. Experimental outcomes conclusively prove our method’s heightened classification effectiveness in few-shot crop disease scenarios, tackling data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

Abstract: Rationale. Object tracking has significance in many applications ranging from control of unmanned vehicles to autonomous monitoring of specific situations and events, especially when providing safety for patients with certain adverse conditions such as epileptic seizures. Conventional tracking methods face many challenges, such as the need for dedicated attached devices or tags, influence by high image noise, complex object movements, and intensive com-putational requirements. We have developed earlier computationally efficient algorithms for global optical flow reconstruction of group velocities that provide means for convulsive seizure detection and have potential applications in fall and apnea detection. Here, we address the chal-lenge of using the same calculated group velocities for object tracking in parallel. Methods. We propose a novel optical flow-based method for object tracking. It utilizes real-time image se-quences from the camera and directly reconstructs global motion-group parameters of the con-tent. These parameters can steer a rectangular region of interest surrounding the moving object to follow the target. The method successfully applies to multi-spectral data, further improving its effectiveness. Results. Experimental results on simulated tests and complex real-world data demonstrate the method's capabilities. The proposed optical flow reconstruction can provide accurate, robust, and faster results compared to current state-of-the-art approaches.

Inflammation involves the activation of innate immune cells and is believed to play an important role in the development and progression of both infectious and non-infectious diseases such as neurodegeneration, rheumatoid arthritis or cancer. Inflammation in the brain is marked by the upregulation of the translocator protein (TSPO) in microglia. Moreover, high TSPO levels are found, for example in macrophages during rheumatoid arthritis and in malignant tumor cells compared to its relatively low physiological expression. The same applies for cycloxygenase-2 (COX-2), which is constitutively expressed in the kidney, brain, thymus and gastrointestinal tract, but induced in microglia, macrophages and synoviocytes during inflammation. This puts TSPO and COX-2 in the spotlight as important targets for the diagnosis of inflammation. Imaging modalities, such as positron emission tomography and single-photon emission tomography, can be used to localize inflammatory processes and to track their progression over time. They could also enable to monitor the efficacy of therapy and predict its outcome. This review focuses on the current development of PET and SPECT tracers not only for the detection of neuroinflammation, but also for emerging diagnostic measures in infectious and other non-infectious diseases like rheumatic arthritis, cancer, cardiac inflammation and in lung diseases.

Many clinical research datasets have a large percentage of missing values that directly impacts their usefulness in yielding high accuracy classifiers when used for training in supervised machine learning. While missing value imputation methods have been shown to work well with smaller percentages of missing values, their ability to impute sparse clinical research data can be problem specific. We previously attempted to learn quantitative guidelines for ordering cardiac magnetic resonance imaging during the evaluation for pediatric cardiomyopathy, but missing data significantly reduced our usable sample size. In this work, we sought to determine if increasing the usable sample size through imputation would allow us to learn better guidelines. We first review several machine learning methods for estimating missing data. Then, we apply four popular methods (mean imputation, decision tree, k-nearest neighbors, and self-organizing maps) to a clinical research dataset of pediatric patients undergoing evaluation for cardiomyopathy. Using Bayesian Rule Learning (BRL) to learn ruleset models, we compared the performance of imputation-augmented models versus unaugmented models. We found that all four imputation-augmented models performed similarly to unaugmented models. While imputation did not improve performance, it did provide evidence for the robustness of our learned models.

A 70-year-old female with a significant medical history of hypertension, hypothyroidism, chronic back pain, and a left hip prosthetic joint infection experienced complications following a total hip replacement. After multiple revisions and eventual discharge to a rehabilitation facility, she developed surgical site bleeding and a femoral head dislocation extending into the pelvis. At our hospital, imaging revealed a failed hip arthroplasty with extensive damage and infection, necessitating complex revision surgery and an antibiotic regimen. During her treatment, she developed a diffuse rash diagnosed as vancomycin-induced hypersensitivity reaction (DRESS), prompting a switch to oral linezolid and systemic corticosteroids. Despite transient eosinophilia and elevated inflammatory markers, her condition stabilized, and she was discharged with instructions for follow-up. This case underscores the importance of vigilant monitoring and timely intervention in managing complex postoperative infections and drug reactions.

A long time has passed since COVID-19 was discovered and widely disseminated. Both machine learning and deep learning have moved towards the research of diagnosing COVID-19. Compared to deep learning, traditional machine learning-based methods can also achieve good diagnostic results if they are improved based on innovative points. And deep learning remains a more popular research object. Based on the deep neural network in the field of deep learning, the convolutional neural network, recurrent neural network, long and short-term memory network, and Transformer model have been extended. These models improve the performance and processing power of neural networks by introducing new structures and algorithms. This paper will introduce the basic concepts of machine learning and deep learning, as well as the details of using the relevant methods of both to help diagnose COVID-19.

With the evolution of computing technology in many application like human robot interaction, human computer interaction and health-care system, 3D human body models and their dynamic motions has gained popularity. Human performance accompanies human body shapes and their relative motions. Research on human activity recognition is structured around how the complex movement of a human body is identified and analyzed. Vision based action recognition from video is such kind of tasks where actions are inferred by observing the complete set of action sequence performed by human. Many techniques have been revised over the recent decades in order to develop a robust as well as effective framework for action recognition. In this survey, we summarize recent advances in human action recognition, namely the machine learning approach, deep learning approach and evaluation of these approaches.

Biofuels construct an essential pillar of energy systems. Biofuels are considered as a popular resource for electricity production, heating, household, and industrial usage, liquid fuels, and mobility around the world. Thus, the need for handling, modeling, decision-making, demand, and forecasting for biofuels are of utmost importance. Recently, machine learning (ML) and deep learning (DL) techniques have been accessible in modeling, optimizing, and handling biofuels production, consumption, and environmental impacts. The main aim of this study is to review and evaluate ML and DL techniques and their applications in handling biofuels production, consumption, and environmental impacts, both for modeling and optimization purposes. Hybrid and ensemble ML methods, as well as DL methods, have found to provide higher performance and accuracy in modeling the biofuels.

Heme is located in the active site of proteins and has diverse and important biological functions, such as electron transfer and oxygen transport and/or storage. The distortion of heme porphyrin is considered an important factor for the diverse functions of heme because it correlates with the physical properties of heme, such as oxygen affinity and redox potential. Therefore, clarification of the relationship between heme distortion and the protein environment is crucial in protein science. Here, we analyzed the fluctuation in heme distortion in the protein environment for hemoglobin and myoglobin using molecular dynamics (MD) simulations and quantum mechanical (QM) calculations. We also investigated the protein structures of hemoglobin and myoglobin stored in Protein Data Bank and found that heme is distorted along the doming mode, which correlates with its oxygen affinity, more prominently in the protein environment than in the isolated state, and the magnitude of distortion is different between hemoglobin and myoglobin. This tendency was also observed in the results of MD simulations and QM calculations. These results suggest that heme distortion is affected by its protein environment and fluctuates around its fitted conformation, leading to physical properties that are appropriate for protein functions.

Abstract: The recently described perivascular unit (PVU) resides immediately adjacent to the true capillary neurovascular unit (NVU) in the postcapillary venule and contains the normal-benign perivascular spaces (PVS) and pathological enlarged perivascular spaces (EPVS). The PVS are important, in that, they also have recently been identified to be the construct and the conduit responsible for the delivery of metabolic waste from the interstitial fluid to the ventricular cerebrospinal fluid for disposal into the systemic circulation and has been termed the glymphatic system. Importantly, the outermost boundary of the PVS is lined by protoplasmic perivascular astrocyte endfeet (pvACef) that communicate with regional neurons. As compared to the well-recognized and described neurovascular unit (NVU) and NVU coupling, the PVU is less well understood and remains an emerging concept. The primary focus of this narrative review is to compare the similarities and differences between these two units and discuss each of their structural and functional relationships and how they relate not only to brain homeostasis but also how they may relate to the development of multiple clinical neurological disease states and specifically how they may relate to obesity, metabolic syndrome, and type 2 diabetes mellitus. Additionally, the concept and importance of a perisynaptic astrocyte coupling to the neuronal synapses with pre- and postsynaptic neurons will also be considered as a perisynaptic unit to provide for the creation of the information transfer in the brain via synaptic transmission and brain homeostasis. Multiple electron microscopic images and illustrations will be utilized in order to help explain these complex units.

Deep learning techniques, such as convolutional neural networks (CNN), generative adversarial networks (GAN), and graph neural networks (GNN), have over the past decade changed the ac-curacy of prediction in many diverse fields. In recent years, the application of deep learning tech-niques in computer vision tasks in pathology demonstrated extraordinary potential in assisting clinicians, automating diagnosis, and reducing costs for patients. Formerly unknown pathologi-cal evidence, such as morphological features related to specific biomarkers, copy number varia-tions, and other molecular features, were also able to be captured by deep learning models. In this paper, we review popular deep learning methods and some recent publications about their appli-cations in pathology.

Beta thalassemia is an inherited blood disorder that results in inefficient erythropoiesis due to genetic mutation that leads to reduction or absence of the hemoglobin beta-globulin protein. Approximately 8.5% of UAE residents suffer from β-thalassemia, a significant health and financial problem. The treatment options available for β-Thalassemia major are limited and associated with a wide range of complications. β-thalassemia gene therapy is emerging as a potential novel treatment option that eliminates the complications caused by the current long-term treatment modalities and the associated economic burden. This paper reviews the scientific literature related to emerging gene-therapy for β-Thalassemia by analyzing all the articles published from January 2010 to December 2023 in the English language on Databases like PubMed, Scopus, ProQuest, and CINAHL. The use of gene therapy has demonstrated promising outcomes for a permanent cure of β-Thalassemia. ZYNTEGLO (Betibeglogene autotemcel) is the only cell-based gene therapy which was approved by the FDA on 19th August, 2018. To conclude, Gene therapy is an innovative solution. It demonstrates a promising future, but does come with its own set-backs and is something that must be tackled in-order to revolutionize it in the medical world. FDA approved ZYNTEGLO is a potentially one-time curative treatment for β-Thalassemia. Although cutting-edge, its use is limited because of the high cost; a price of $2.8million per patient.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one is designed using a Jetson TX or AGX Xavier, and the other is based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-art deep-learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep-learning-based association metric approach (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep-learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

The profile of secondary metabolites occurring in apple cuticular layer is not only characteristic for particular apple cultivar, but also dynamically reflects various external factors in growing environment. In this study, the possibility to authenticate apple samples based on analysis of their cuticular layer extracts was investigated. Ultra-high-performance liquid chromatography coupled to high resolution tandem mass spectrometry (UHPLC-HRMS/MS) was employed for obtaining metabolomic fingerprints. In total, 274 authentic apple samples, four cultivars harvested within the seasons 2020 to 2022 in the Czech Republic and Poland were analysed. The generated complex data processed by univariate and multivariate statistical methods enabled to build classification models for discrimination of apple cultivars as well as their geographical origin. The models showed very good performance in differentiation of Czech and Polish samples for three of four cultivars: ‘Gala’, ‘Golden Delicious’ and ‘Idared’, moreover, the validity of the models was verified over harvest seasons. The diagnostic markers, besides metabolites of triterpene biosynthetic pathway, mainly represented wax esters. ‘Jonagold’, which is known to be susceptible to mutations, was the only cultivar for which the unambiguous classification of geographical origin was not possible.

The MAPK signaling pathway with BRAF mutations has been shown to drive the pathogenesis of 40-60% of melanomas. Inhibitors of this pathway's BRAF and MEK components are currently used to treat these malignancies. However, responses to these treatments are not always successful. Therefore, identifying noninvasive biomarkers to predict treatment responses is essential for personalized medicine of melanoma patients. Using noninvasive 1H magnetic resonance spectroscopy (1H MRS), we previously showed that BRAF inhibition reduces lactate and alanine tumor levels at early stages of effective therapy and could be construed as metabolic imaging biomarkers for drug response. The present work aimed to demonstrate if these metabolic changes and those assessed by 31P MRS are also found in preclinical human melanoma models treated with MEK inhibitors. Apart from 1H and 31P MRS, additional supporting in vitro biochemical analyses are described. Our results indicate significant early metabolic correlations with response levels to MEK inhibition in the melanoma models and are consistent with our previous study of BRAF inhibition. Given these results, our study supports the potential clinical utility of noninvasive MRS to objectively image metabolic biomarkers for early predicting melanoma response to MEK inhibition.

Computed tomography (CT) offers detailed insights into the internal anatomy of patients, partic-ularly for spinal vertebrae examination. However, CT scans are associated with higher radiation exposure and cost compared to conventional X-ray imaging. In this study, we applied a Genera-tive Adversarial Network (GAN) framework to reconstruct 3D spinal vertebrae structures from synthetic biplanar X-ray images, specifically focusing on anterior and lateral views. The synthetic X-ray images were generated using the DRRGenerator module in 3D Slicer, by incorporating segmentations of spinal vertebrae in CT scans for the region of interest focussing. The approach leverages a novel feature fusion technique based on X2CT-GAN to combine information from both views and employs a combination of Mean Squared Error (MSE) loss and adversarial loss to train the generator, resulting in high-quality synthetic 3D spinal vertebrae CTs. A total of n=440 CT data were processed. We evaluated the performance of our model using multiple metrics, in-cluding Mean Absolute Error (MAE) (for each slice of the 3D volume [MAE0] and for the entire 3D volume [MAE]), Cosine Similarity, Peak Signal-to-Noise Ratio (PSNR), 3D Peak Sig-nal-to-Noise Ratio (PSNR-3D), and Structural Similarity Index (SSIM). The average PSNR was 28.394 dB, PSNR-3D was 27.432, SSIM was 0.468, cosine similarity was 0.484, MAE0 was 0.034, and MAE was 85.359. The results demonstrated the effectiveness of the approach in reconstruct-ing 3D spinal vertebrae structures from biplanar X-rays, although some limitations in accurately capturing the fine bone structures and maintaining the precise morphology of the vertebrae were present. This technique has the potential to enhance the diagnostic capabilities of low-cost X-ray machines while reducing radiation exposure and cost associated with CT scans, paving the way for future applications in spinal imaging and diagnosis.

The burden of hypertension remains unacceptably high globally, particularly in low- and middle-income countries (LMICs). Workplace offer enormous potential as an idea setting for early detection and treatment of hypertension among the working class. Analysis of such a Workplace Screening Programme can reveal information about its potential impact. Machine learning techniques such as k-Means Clustering are untapped tools for such analyses. We set out to deploy this tool for the analysis of our university annual medical screening of workforce for hypertension. An anonymized dataset containing the demography and blood pressure measurements values obtained from staffs of different departments/units in an academic institution was obtained. The total number of samples or data points are 1, 723 in which the input dataset contains six features, including year category (2018, 2019, 2021,2022), Department/Unit (academic and non-academic), gender (male and female), while the target output is the blood pressure status (low, normal and high) respectively. Analysis of the dataset was carried out using machine learning techniques. In this retrospective analysis, it was observed that the mean age for this working class is 42 years old. Similarly, it was discovered that hypertension was prevalent among members of staff above the age of 40 irrespective of their gender or professional category (academic or non-academic). The analysis also revealed that there was a steady decline in the prevalence of hypertension from 2018 to 2022. From the research, it is evident that the adoption of machine learning techniques for periodic analyses of workplace health status screening initiative (especially for hypertension) is effective, feasible, and sustainable to diagnose and control hypertension among the working class.

Ectopic eruption of teeth rarely occurs in the mandibular condyle, orbit, nasal cavity, skin, and maxillary sinus. Ectopic eruption of teeth in the maxillary sinus can be accompanied by chronic and recurrent sinusitis, including headache, facial pain, and numbness. Fibro-osseous lesions in the paranasal sinuses are discovered incidentally on X-ray images and are often asymptomatic. Osteoma is the most common fibro-osseous lesion that develops in the paranasal and nasal sinuses. Herein, we report a rare case of osteoma (exostosis) containing supernumerary teeth within the maxillary sinus. A characteristic pedicled bone lesion with a clear border on computed tomography was the undefined orthopantomogram radiopacity in the left maxillary sinus, and the lesion contained teeth. The tumor was excised using the Caldwell–Luc procedure. Pathologically, the surgical specimen revealed an osteoma. The patient’s symptoms of chronic sinusitis disappeared, and the patient had no symptoms 2 years after the surgery. Because the patient had no history of midface trauma or surgery, the supernumerary teeth were speculated to have migrated during a reactive osteogenic process caused by chronic sinusitis.

Power quality (PQ) plays an important role in ensuring the smooth operation of power systems. PQ disturbances may cause significant consequences, impacting the reliability and efficiency of power networks. This paper presents a comprehensive review of PQ within smart grids and the integration of renewable energy sources. Methods of detecting, classifying, optimizing, and mitigating PQ events are reviewed with providing a brief theoretical explanation for each technique. Related work done in the past two decades, was conducted, presenting a clear view of the development of research in a chronological order serving as a guide for future investigations in this field of study.

Optical motion capture systems are prone to the errors connected with markers recognition – occlusion, leaving the scene or mislabelling – all these errors are then corrected in the software, but still, the process is not perfect, resulting in artifact distortions. In the article, we examine four existing types of artifacts, then propose the method for detection and classification of the distortions. The algorithm is based on the derivative analysis, low-pass filtering, mathematical morphology and loose predictor. The tests involved multiple simulations using synthetically distorted sequences, comparison of performance to the human operators on real life data and applicability analysis for the distortion removal.

Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of its nodules. Radiologists need support from automated tools for precise opinion. Automated detection of the affected lungs nodule is difficult because of the shape similarity among healthy tissues. Over the years, several expert systems have been developed that help radiologists to diagnose lung cancer. In this article, we propose a framework to precisely detect lungs cancer by classifying it between benign and malignant nodules. The framework is tested using the subset of the publicly available at the Lung Image Database Consortium image collection (LIDC-IDRI). Multiple techniques including filtering and noise removing are applied for pre-processing. Subsequently, the OTSU and the semantic segmentation are used to accurately detect the unhealthy lungs nodules. In total, 13 nodules features were extracted using Principal Components Analysis (PCA) algorithm. Four optimal features are selected based on the classification performance. In the classification phase, 9 different classifiers are used along with two types of validation schemes i.e. train test holdout validation with 70-30 data split and 10 fold cross-validation. Our experiments show that the proposed system provides 99.23\% accuracy using logic boost classifier.

Purpose: We assessed if a CXR AI algorithm can detect missed or mislabeled chest radiographs (CXRs) findings in radiology reports. Methods: We queried multi-institutional radiology reports search database of 13-million reports to identify all CXRs reports with addendums from 1999-2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addendum was created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports with addendum (279 patients) with errors related to side-discrepancy or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of AI to detect missed or mislabeled findings. Results: AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusion: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.

Helicobacter Pylori (H. Pylori) is a common pathogen with high prevalence of infection in human populations. Diagnosis of H. Pylori infection is critical for its treatment, eradication, and prognosis. Biosensors have been demonstrated to be powerful for rapid onsite detection of pathogens, particularly for point-of-care test (POCT) scenarios. In this work, we propose a novel optical biosensor, based on nanomaterial porous silicon (PSi) and photonic surface state Tamm Plasmon Polariton (TPP), for detection of cytotoxin-associated antigen A (CagA) antigen of H. Pylori bacterium. We fabricated the PSi TPP biosensor, analysed its optical characteristics and demonstrated through experiments towards sensing of CagA antigen, that TPP biosensor has sensitivity of 100 pm/(ng/ml), limit of detection of 0.01 ng/ml, and specificity in terms of positive-to-negative ratio of more than six. From these performance factors, it can be concluded that TPP biosensor can serve as an effective tool for diagnosis of H. Pylori infection, either in analytical labs or in POCT applications.

Hypophthalmichthys nobilis are widely distributed in the Yangtze River basin and its related lakes. They are an important economic fish species and are a famous cultured species known as the "Four Famous Domestic Fishes" in China. Currently, with the fishing ban in the Yangtze River basin, fishing for H. nobilis in natural water bodies of the Yangtze River basin has been completely prohibited. In order to identify the sources of H. nobilis appearing in the market, further control and accountability, it is necessary to trace the sources of H. nobilis in the Yangtze River basin and its related water bodies. Therefore, this study identified and traced different sources of H. nobilis through muscle element fingerprint analysis (EFA). The results show that H. nobilis from different stations have characteristic element compositions. The characteristic element of H. nobilis from Wuhan (WH) is Pb, which is significantly higher than that in other stations; the characteristic element from Anqing (AQ) is Hg, which is significantly higher than that in other stations; and the characteristic element from Taihu (TH) is Al, which is significantly higher than that in other water areas. Multivariate analysis selected different spatial distribution patterns of 4 discriminant elements ratios (Pb/Ca, Cr/Ca, Na/Ca, Al/Ca) in the muscle of H. nobilis in the Yangtze River basin and its related lakes. The study suggests that the screened discriminative elements can be used to visually distinguish different sources of H. nobilis, and to quickly trace and verify the origin of newly emerging samples. Therefore, the use of selected discriminant element fingerprint features to trace the origin of new samples has been proven to be feasible. By further discriminating and verifying the muscle element fingerprints of new samples, the discrimination rate is high. Therefore, Multivariate analysis for muscle element fingerprint can be used for origin traceability of samples of unknown origin in market supervision.

Drosophila melanogaster serves as a important research model both for genetic investigations and for the study of metal toxicity, facilitating the elucidation of physiological mechanisms comparable to those of human organisms. In our research, we evaluated the toxicity effect resulting from exposure to various concentrations of lead and copper on the prolificity rates throughout the life cycle (egg-adult) of four genotypes of Drosophila melanogaster: wild-type (control), white, brown, and white-vestigial. During our study, the prolificity rates were examined across three repetitions under the impact of exposure to concentrations of 0.50, 1.00, 2.00, and 4.00 mM of copper (CuSO₄) and lead (Pb(C₂H₃O₂₎₂). Prolificity rates throughout the life cycle exhibited variations as a direct consequence of genetic factors, the concentration of exposure, and the specific type of metal, either copper or lead. The mutant white-vestigial genotype revealed an IC₅₀ concentration for prolificity inhibition at lower doses of 2.00 mM for copper and 4.00 mM for lead, in contrast to the control genotype (wild-type), which exhibited an inhibition concentration rate >IC₅₀ of 4.00 mM only in the case of copper. Our results concluded that the (i) dose influences the prolificity rate in a directly proportional manner, (ii) comparative analyses between copper and lead revealed that copper displayed toxicity across all genotypes within the concentration range of 0.50 mM to 2.00 mM. In contrast, lead exhibited toxicity within the concentration range of 1.00 mM to 4.00 mM, highlighting a (iii) more acute toxicity characteristic in the case of copper. Thus, the results of this research reflect the importance of using Drosophila melanogaster as a genetic model in the comparative study of the interaction between genetic factors and the toxicity of metals, offering significant insights into monitoring their impact and defining the maximum permissible doses on organisms.

Buruli ulcer is a chronic ulcerative disease of skin and subcutaneous tissues caused by infection with Mycobacterium ulcerans. Although Australian possums are known to be susceptible to Buruli ulcer, many aspects of the disease in possums, including welfare impacts, remain largely unreported. Severe clinical Buruli ulcer was identified in four common ringtail possums (Pseudocheirus peregrinus) from Melbourne, Victoria. All four possums were euthanised due to welfare concerns and poor prognosis, based on the presence of deep ulcerative lesions to paws, some of which exposed carpal or tarsal bones. These lesions were considered likely to cause partial or complete loss of limb function, which would severely affect the welfare and survival of these wild arboreal animals. Histologically, there was severe ulcerative necrotising pyogranulomatous dermatitis, panniculitis, and myositis, with intralesional acid-fast bacteria. M. ulcerans was detected by real-time PCR in all swabs and biological tissues collected from all four cases. Buruli ulcer may be an important and under-recognised cause of poor possum welfare in endemic areas. In addition to severe cutaneous lesions, infection extends to underlying bones and joints, and the systemic distribution of M. ulcerans throughout all major tissues and internal organs, as observed in these four cases, may further impact the health and fitness of infected possums. Further research is needed to investigate the epidemiology, pathogenesis and impacts of Buruli ulcer in possums, and to inform the design of interventions that may protect the health and welfare of possums and other affected animal species.

This paper investigates the dynamic properties of artificial neural networks using differential equations and explores the influence of parameters on stability and neural oscillations. By analyzing the equilibrium point of the differential equations, we identify conditions for asymptotic stability and criteria for oscillation in artificial neural networks. Furthermore, we demonstrate how adjusting synaptic weights between neurons can effectively control stability and oscillation. The proposed model offers potential insights into the malfunctioning mechanisms of biological neural networks implicated in neurological disorders like Parkinson's disease tremors and epilepsy seizures, which are characterized by abnormal oscillations.

Measuring Marginal Reflex Distance-1 (MRD-1) is a crucial clinical tool used to evaluate the position of the eyelid margin in relation to the cornea. Traditionally, this assessment has been conducted manually by plastic surgeons, ophthalmologists, or trained technicians. However, with the advancements in Artificial Intelligence (AI) technology, there is a growing interest in the development of automated systems capable of accurately measuring MRD-1.In this context, we introduce novel MRD-1 measurement methods based on deep learning algorithms that can simultaneously capture images and compute the results. This prospective observational study involved 154 eyes of 77 patients aged over 18 years who visited Chungnam National University Hospital between September 1, 2023, and July 29, 2023. We collected four different MRD1 da-tasets from patients using three distinct measurement methods, each tailored to the individual patient. The mean MRD1 values, measured through the manual method using a penlight, the deep learning method, ImageJ analysis from RGB eye images, and ImageJ analysis from IR eye images in 56 eyes of 28 patients, were 2.64 ± 1.04 mm, 2.85 ± 1.07 mm, 2.78 ± 1.08 mm, and 3.07 ± 0.95 mm, respectively. Notably, the strongest agreement was observed between MRD1_deep learning (DL) and MRD1_IR (0.822, p < 0.01). In the Bland-Altman plot, the smallest difference was observed between MRD1_DL and MRD1_IR ImageJ, with a mean difference of 0.0611 and △LOA (limits of agreement) of 2.5162, which is the smallest among the other groups. In conclusion, this novel MRD1 measurement method, based on an IR camera and deep learning, demon-strates statistical significance and can be readily applied in clinical settings.

The role that aquatic aerosols might play in inter-ecosystem exchange in freshwater riparian environments has largely been understudied. In these environments, where freshwater streams are used both as drinking water and for treated waste disposal, water features like waterfalls, downed trees, and increased streamflow can serve as bioaerosol producers. Such water features could have an important role in the bacterial colonization of surrounding surfaces, including the riparian phyllosphere. In this study, we explore the influence of a freshwater stream’s bacterial community composition and micropollution on riparian maple leaves exposed to bioaerosols produced from the stream. Using culture-based and non-culture-based techniques, we compared phylloplane microbial communities in riparian zones, adjacent non-riparian forested zones, and the surface waters of the stream. In this system, riparian zone maple leaf surfaces had higher bacterial counts than non-riparian zone trees. Using metagenomic profiling of the 16S rRNA gene, we found that, while microbial communities on leaves in both riparian zone and forested sites were diverse, riparian zone bacterial communities were significantly more diverse. In addition, we found that riparian leaf bacterial communities shared more amplicon sequence variants (ASVs) with stream bacterial communities than forest leaves, indicating that the riparian zone phyllosphere is likely influenced by bioaerosols produced from water surfaces.

Polycystic ovary syndrome (PCOS) is a common condition in reproductive-age women. Women with PCOS are at higher risk of pregnancy complications including gestational diabetes (GDM). The prevalence of PCOS and GDM varies according to the diagnostic criteria used. The mechanism for the occurrence of GDM in women with PCOS is still unclear. Materials &amp; Methods- A systematic search of the electronic database was done using keywords like PCOS, and GDM to include studies between April 2008 and March 2023 where uniform diagnostic criteria were used. Studies were excluded with high-risk of bias after the assessment of bias, and meta-analysis was done with relative risks and confidence intervals. Results &amp; Discussion-Out of 1896 search results, 95 were selected for full-text. The quality of the studies was scrutinized and a total of 28 studies were included as they fulfilled the inclusion criteria. The incidence of GDM in women with PCOS was found to be 10.55 % (2.9- 54.9%) from pooled data involving 1,280,245. The prevalence of PCOS in women diagnosed with GDM was found from pooled data of 36,351 women in retrospective studies to be 2.47% (1.5- 50.1%). Selection predominantly included cohort studies, most commonly from China. The meta-analysis reported the risk of GDM is higher in women with PCOS than in those without PCOS (HR: 1.59, 95% CI: 1.27–1.91, p &lt; 0.001). Family history of diabetes, ethnicity, pre-pregnancy BMI, insulin resistance, gestational weight gain, use of assisted reproductive techniques, and multifetal gestation were the risk factors for GDM in women with PCOS. Conclusion- The prevalence of GDM in patients with PCOS is high, but the causality is complex. The newer predictive models are promising in clarifying the causative relationships, yet use various parameters at different cut-offs. There is a need for the development of universally acceptable parameters for the early prediction of GDM in women with PCOS.

Drug-induced liver injury (DILI) stands as a significant cause of drug attrition. To mitigate clinical DILI risks, assessing drugs using human liver models is crucial since animal studies may fall short due to species-specific liver pathway variations. Cell-based preclinical hepatotoxicity testing is often pertinent. In the present study, cells from a human liver cancer line (HepG2, HepaRG) were cultured in both formats of 2D and 3D spheroids to explore their responses to drugs. Liver-specific marker expressions across cell lines and culture formats were also examined to assess disparities in drug-induced liver injury marker expressions. In cytotoxicity assays, HepG2 cells exhibited heightened sensitivity to amiodarone HCl, while HepaRG cells showed greater sensitivity to acetaminophen. Generally, 2D cultures were more responsive to drugs than 3D cultures. Consistency was observed between cytotoxicity assays and liver injury markers AST and ALT. Variations were also noted in liver cell marker secretion, with albumin and urea concentrations declining post-drug treatment, particularly with higher baseline expression in HepaRG cells and 3D cultures. Additionally, mRNA expression levels of CYP enzymes involved in hepatocellular drug metabolism were compared following treatment with enzyme inducers. CYP1A2 and CYP2C9 were not expressed in HepG2 cells. On the other hand, CYP3A4 was expressed higher in 3D culture than in 2D culture. HepaRG cells exhibited significantly increased expression of all three enzymes post-treatment. Notably, enzyme expression was notably higher in 3D cultures than in 2D cultures. Collectively, these findings suggest that HepaRG cells and 3D cultures hold promise for evaluating DILI during early-stage drug development.

Iron (Fe), the main component of non-exhaust particulates, is known to have variable health effects that depend on the chemical species of iron. This study characterized the possible contribution of iron oxides and hydroxides to airborne brake-wear particles under realistic vehicle driving and braking conditions with different brake-pad friction materials. We found significant differences in wear coefficients and PM₁₀ emissions between non-asbestos organics (NAO) and European performance (ECE) brake pads. Iron was the dominant contributor to PM₁₀ and PM_2.5 brake-wear particles for both NAO and ECE. The iron concentration ratio in the particle mass were comparable to the disc to pads ratio measured by wear mass. The fact that magnetite, which is of interest with respect to health effects, was less abundant in NAO than in ECE suggested that tribo-oxidations occurred in NAO. Metallic iron is generated not only from abrasive wear but also from tribo-chemical reduction with magnetite as the starting material. We found differences not only in PM emissions between brake friction materials but also that the phase transformations of iron differed between friction materials. These differences were apparent in the distribution of iron oxides and hydroxides. Heat, tribo-oxidation, and tribo-reduction are intricately involved in these reactions.

Unlike electron microscopy, which can achieve very high resolutions, but to date can only be used to study static structures, time-resolved X-ray diffraction from contracting muscles can, in principle, be used to follow the molecular movements involved in force generation on a millisecond timescale albeit at moderate resolution. However, previous X-ray diffraction studies of resting muscles have come up with structures for the head arrangements in resting myosin filaments that are different from the apparently ubiquitous interacting heads motif (IHM) found by single particle analysis of electron micrographs of isolated myosin filaments from a variety of muscle types. This head organization is supposed to represent the super-relaxed state of the myosin filaments where ATP usage is minimized. Here we have tested whether the interacting heads motif structures will satisfactorily explain the observed low-angle X-ray diffraction patterns from resting vertebrate (bony fish) and invertebrate (insect flight) muscles. We find that the interacting heads motif does not, in fact, explain what is observed. Previous X-ray models fit the observations much better. We conclude that the X-ray diffraction evidence has been well interpreted in the past and that there is more than one ordered myosin head state in resting muscle. There is, therefore, no reason to question some of the previous X-ray diffraction results on myosin filaments; time-resolved X-ray diffraction should be a reliable way to follow crossbridge action in active muscle and may be one of the few ways to follow molecular changes in myosin heads on a millisecond timescale as force is actually produced.

DEXTER (Detection of EXplosives and firearms to counter TERrorism) is a project funded by NATO’s Science for Peace and Security (SPS) program with the goal of developing an integrated system capable of remotely and accurately detecting explosives and firearms in public places without impeding the flow of pedestrians. The active microwave component of the DEXTER project is referred to as MIC (Microwave Imaging Curtain), supported by the French SGDSN (General Secretariat of Defense and National Security), and utilizes a radar system capable of generating 3D images in real time to address non-checkpoint detection of explosives and fire-arms. The project, led by the ONERA (France), is based on a radar imaging system developed by the Fraunhofer FHR institute, using a MIMO architecture with an Ultra Wide-Band waveform. Although high-resolution 3D microwave imaging is already being used in expensive body scanners to detect firearms concealed under clothing, MIC's innovative approach lies in utilizing a high-resolution 3D imaging device that can detect larger dangerous objects carried by moving individuals at a longer range, in addition to providing discrete detection in pedestrian flow. Automatic detection and classification of these dangerous objects is carried out on 3D radar im-ages using a deep-learning network. This paper will outline the project's objectives and constraints, as well as the design, architecture, and performance of the final system. Additionally, it will present real-time imaging results ob-tained during a live demonstration in a relevant environment.

Biologists seek to identify a small number of significant features that are important, non-redundant, and relevant from diverse omics data. For example, statistical methods like LIMMA and DEseq distinguish differentially expressed genes between a case and control group from the transcript profile. Researchers also apply various column subset selection algorithms on genomics datasets for a similar purpose. Unfortunately, genes selected by such statistical or machine learning methods are often highly co-regulated, making their performance inconsistent. Here, we introduce a novel feature selection algorithm that selects highly disease-related and non-redundant features from a diverse set of omics datasets. We successfully applied this algorithm to three different biological problems: a) disease to normal sample classification, b) multiclass classification of different disease samples, and c) disease subtypes detection. Considering classification ROC-AUC, False-positive, and False-negative rates, our algorithm outperformed other gene selection and differential expression (DE) methods for all six types of cancer datasets from TCGA considered here for binary and multiclass classification problems. Moreover, genes picked by our algorithm improved the disease subtyping accuracy for four different cancer types over the state-of-the-art methods. Hence, we posit that our proposed feature reduction method can support the community to solve various problems, including the selection of disease-specific biomarkers, precision medicine design, and disease sub-type detection.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

In this paper, we present the idea of Self Supervised learning on the Shape Completion and Classification of point clouds. Most 3D shape completion pipelines utilize autoencoders to extract features from point clouds used in downstream tasks such as Classification, Segmentation, Detection, and other related applications. Our idea is to add Contrastive Learning into Auto-Encoders to learn both global and local feature representations of point clouds. We use a combination of Triplet Loss and Chamfer distance to learn global and local feature representations. To evaluate the performance of embeddings for Classification, we utilize the PointNet classifier. We also extend the number of classes to evaluate our model from 4 to 10 to show the generalization ability of learned features. Based on our results, embedding generated from the Contrastive autoencoder enhances Shape Completion and Classification performance from 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.

Investigation of oomycete diversity in rice paddies of Fars Province in Iran led to the identification of two new Pythium sensu lato (s.l.) species as Globisporangium izadpanahii sp. nov. and Pythium banihashemianum sp. nov. The identification was based on morphological and physiological features as well as the phylogenetic analysis of nuclear (ITS and βtub) and mitochondrial (cox1 and cox2) loci using Bayesian inference and Maximum Likelihood. A major characteristic of G. izadpanahii was the production of globose hyphal swellings; this species did not produce vesicles and zoospores. The present paper describes formally these two new species and defines their phylogenetic relationships with other congeneric species. According to multiple gene genealogy analysis, G. izadpanahii grouped with other species of Globisporangium in the former clade G of Pythium s.l. and was closely related to both G. nagaii and the recently described G. coniferarum. The second species, designated P. banihashemianum, grouped with other species of Pythium sensu stricto in the former clade B of Pythium s.l. and according to the phylogenetic analysis shared an ancestor with P. plurisporium. In pathogenicity tests on rice seedlings, P. banihashemianum isolates were highly pathogenic causing severe root and crown rot, while G. izadpanahii isolates were not pathogenic.

Probiotics are microorganisms infused in products for health benefits including acceleration of nutrient digestion, however, it is also important to ensure the safety prior to incorporation. Here, we present evidence of the ability of two probiotic isolates,Lacticaseibacillus paracasei BCRC-16100 and Lacticaseibacillus paracasei ZFM54, in the (1) enhancement of carbohydrate digestion, (2) tolerance to stress, and (3) antibiotic resistance. Approaches include whole genome sequence (WGS) analysis and bioactivity assays. WGS revealed genes suggesting the ability of the two isolates to promote carbohydrate digestion, tolerance to stress and antibiotic resistance. Carbohydrate digestive ability was confirmed through a biochemical assay where the two isolates cause glucose release from starch. The two isolates also showed versatility in a range of temperature and alcohol concentration. For antibiotic resistance particularly on vancomycin, there are three mechanisms namely transporter control, transcriptional regulation, and efflux pump. Furthermore, promoter and transposable element analysis showed that some of the active antibiotic resistant (AbR) genes can be laterally transferred. Altogether, we show the potential of two probiotic isolates to be incorporated in products for improved carbohydrate digestion and the need to address the removal of active and mobile antibiotic resistance genes that may compromise safety.

It is important for food recognition to separate each ingredient within a food image at the pixel level. In this paper, we propose a new approach to segment ingredients by utilizing a CNN-based Single-Ingredient Classification Model. In detail, we firstly introduce a standardized biological-based hierarchical ingredient structure and construct a single-ingredient image dataset based on this structure. Then, we build a single-ingredient classification model based on a novel convolutional neural network (CNN) architecture that utilizes an attention mechanism. Afterwards, we propose a new framework for segmentation using the above single-ingredient classification model as the backbone. In this framework, two methods are involved in segmenting ingredients in the food images. We introduce five evaluation metrics (IoU, Dice, Purity, Entirety, Loss of GTs) to assess the performance of ingredient segmentation in terms of ingredient classification. Extensive experiments demonstrate the effectiveness of the proposed method, achieving an maximal mIoU of 0.65, mDice of 0.77, mPurity of 0.83, mEntirety of 0.80, and mLoGTs of 0.06 on the FoodSeg103 dataset. The results confirm that our CNN-based architecture achieves higher segmentation performance compared to ResNet18 and EfficientNet-B0 when used as the backbone for ingredient segmentation. We believe that our ingredient segmentation approach lays the foundation for subsequent ingredient recognition.

Human beatboxing is a vocal art making use of speech organs to produce vocal drum sounds and imitate musical instruments. Beatbox sound classification is a current challenge that can be used for automatic database annotation and music-information retrieval. In this study, a large-vocabulary humanbeatbox sound recognition system was developed with an adaptation of Kaldi toolbox, a widely-used tool for automatic speech recognition. The corpus consisted of eighty boxemes, which were recorded repeatedly by two beatboxers. The sounds were annotated and transcribed to the system by means of a beatbox specific morphographic writing system (Vocal Grammatics). The image processing techniques plays vital role on image Acquisition, image pre-processing, Clustering, Segmentation and Classification techniques with different kind of images such as Fruits, Medical, Vehicle and Digital text images etc. In this study the various images to remove unwanted noise and performs enhancement techniques such as contrast limited adaptive histogram equalization, Laplacian and Harr filtering, unsharp masking, sharpening, high boost filtering and color models then the Clustering algorithms are useful for data logically and extract pattern analysis, grouping, decision-making, and machine-learning techniques and Segment the regions using binary, K-means and OTSU segmentation algorithm. It Classifying the images with the help of SVM and K-Nearest Neighbour(KNN) Classifier to produce good results for those images.

This study challenges the prevailing belief in the necessity of complex models for accurate forecasting by demonstrating the effectiveness of parsimonious econometric models, namely ARCH(1) and GARCH(1,1), over deep learning robust approaches, such as LSTM and 1D-CNN neural networks, in modeling historical volatility within pre-emerging stock markets, specifically the Moroccan and Bahraini stock markets. The findings suggest reevaluating the balance between model complexity and predictive accuracy. Future research directions include investigating the potential existence of threshold effects in market capitalization for optimal model performance. This research contributes to a deeper understanding of volatility dynamics and enhances forecasting models’ effectiveness in diverse market conditions.

Increasing population size and income growth are causing and increasing demand for food and protein of animal origin. Insects are an interesting alternative to conventional animal source proteins as they can convert by-products from the agricultural industry to biomass for commercial feed for livestock and potentially as a food source for human consumption. Microorganisms have been found to affect insects and can be accumulated via horizontal and vertical transmission. This study aimed to identify if the removal of egg- and substrate-associated microorganisms impact larval performance through the following parameters: development of biomass, final biomass, and the survival rate of house fly (Musca domestica) larvae. Four treatments were tested on substrate consisting of 10.81% alfalfa (Medicago sativa), 21.62% wheat bran (Triticum aestivum), and 67.57% water: (A) disinfected eggs and non-autoclaved substrate, (B) non-disinfected eggs and autoclaved substrate, (C) disinfected eggs and autoclaved substrate, and (D) a control without any removal of microbiota. The results showed a significant decrease in final biomass for the treatments with only disinfected eggs, only autoclaved substrate and both when comparing to the control, and a significant decrease in survival rate for B and D. Moreover, the development of biomass showed a significant difference between days within all treatments. Together this suggest that microorganisms of housefly eggs and the growth substrate plays an important role for growth, which is critical in commercial insect production. Further studies must be performed to examine these parameters in more commercially relevant substrates.

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

In recent years, unmanned aerial vehicles (UAVs) have become a valuable platform for many applications, including communication networks. UAV-enabled wireless communication faces challenges in complex urban and dynamic environments. UAVs can suffer from power limitations and path losses caused by non-line-of-sight connections, which may hamper better communication performance. To address these issues, reconfigurable intelligent surfaces (RIS) have been proposed as a helpful tool to enhance UAV communication networks. However, due to the high mobility of UAV, complex channel environments, and dynamic RIS configurations, it is challenging to estimate the link quality of ground users. In this paper, we propose a link quality estimation model using a gated recurrent unit (GRU) to assess the link quality of ground users for a multi-user RIS-assisted UAV-enabled wireless communication system. Our proposed framework uses a time series of user channel data and RIS phase shift information to estimate the quality of the link for each ground user. Simulation results showed that the proposed GRU model effectively and accurately estimates the link quality of the ground users in the RIS-assisted UAV-enabled wireless communication network.

Electron beam treatment of ZnS:Cu,Br (Cu activator content 0…0.6%wt.) radioluminescent phosphors as well as charge mixture with the electron energy 900 keV and absorbed dose of 600 kGy resulted in a enhancement of brightness up to 80%. The increased brightness is due to increase of content of wurtzite phase relative to sphalerite one with formation of wurtzite/sphalerite nanocomposite structure. Transformation of crystal structure is accompanied with corresponding change in content of active surface centers characteristic for sphalerite and wurtzite phases. A model describing surface centers of ZnS:Cu,Br radioluminescent phosphor is suggested.

Legionella pneumophila can cause a large panel of symptoms beside the classic pneumonia presentation. We present here a case of fatal nosocomial cellulitis in an immunocompromised patient followed, a year later, by a second case of legionnaires’ disease in the same ward. While the first one was easily assumed as nosocomial based on the date of symptoms onset, the other case needed to rely on clear typing results to be either assigned as nosocomial and related to the same environmental source as the first one, or community acquired. To untangle this specific question, we applied Core-genome MultiLocus Typing (MLST), whole-genome Single Nucleotide Polymorphism and whole-genome MLST methods to a collection of 36 Belgian and 41 international sequence-type 1 (ST1) isolates using both thresholds recommended in the literature and tailored threshold based on local epidemiological data. Based on the thresholds applied to cluster isolates together, the three methods gave different results and no firm conclusion about the nosocomial setting of the second case could been drawn. Our data highlight that despite promising results in the study of outbreaks and for large scale epidemiological investigations, NGS typing methods applied to ST1 outbreak investigation still need standardization regarding both wet-lab protocols and bioinformatics. A deeper evaluation of L. pneumophila evolutionary clock is also required to increase our understanding of genomic differences between isolates sampled during a clinical infection and in environment.

Melioidosis is an endemic infectious disease caused by Burkholderia pseudomallei bacteria, which contaminates soil and water. To better understand the environmental changes that have contributed to melioidosis outbreaks, this study used spatiotemporal analyses to clarify the distribution pattern of melioidosis and the relationship between melioidosis morbidity rate and local environmental indicators (land surface temperature, normalised difference vegetation index, normalised difference water index) and rainfall. A retrospective study was conducted from January 2013 to December 2022, covering data from 219 sub-districts, with each exhibiting varying morbidity rate of melioidosis on a monthly basis. Spatial autocorrelation was determined using local Moran’s I, and the relationship between melioidosis morbidity rate and the environmental indicators was evaluated using geographically weighted Poisson regression. The results revealed clustered spatiotemporal patterns of melioidosis morbidity rate across sub-districts, with hotspots predominantly observed in the northern region. Furthermore, we observed a range of coefficients for the environmental indicators, varying from negative to positive, which provided insights into their relative contributions to melioidosis in each local area and month. These findings highlight the presence of spatial heterogeneity driven by environmental indicators and underscore the importance of public health offices implementing targeted monitoring and surveillance strategies for melioidosis in different locations.

Predicting the prices of cryptocurrency owing to its volatility, instability, and other factors has been challenging; investors and traders especially in Nigeria have been on a constant look for a more reliable way of knowing market trends and prices and while there has been so many research conducted using deep learning, the results for which has fall short of what investors could called a strong predictor. This research reviewed the results of many works that had been done and proposed two types of recurrent neural network (RNNs) namely Long Short-Term Memory and Gated Recurrent Unit (GRU) for predicting the future prices of two of the most common crypto assets namely Bitcoin (BTC) and Ethereum (ETH), these two were selected based on their popularity, the volume traded and their market capitalization. The experiment was conducted in a GPU Jupyter Notebook environment and the performance of our experiment was evaluated on a test set using root mean square error (RMSE) and based on its values, the LSTM presented a better performance with rsme scores of 654.66, and 80.30 respectively for BTC and ETH as compared to GRU. The paper proceeds further to compare the results of this experiment with other related works and we discovered that its performance is a great improvement.

Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, a great deal of mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks as well as their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain in-depth the building blocks to design deep learning models, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library.

Prediction of stock groups values has always been attractive and challenging for shareholders. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals and basic metals from Tehran stock exchange are chosen for experimental evaluations. Data are collected for the groups based on ten years of historical records. The values predictions are created for 1, 2, 5, 10, 15, 20 and 30 days in advance. The machine learning algorithms utilized for prediction of future values of stock market groups. We employed Decision Tree, Bagging, Random Forest, Adaptive Boosting (Adaboost), Gradient Boosting and eXtreme Gradient Boosting (XGBoost), and Artificial neural network (ANN), Recurrent Neural Network (RNN) and Long short-term memory (LSTM). Ten technical indicators are selected as the inputs into each of the prediction models. Finally, the result of predictions is presented for each technique based on three metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. Also, for tree_based models, there is often an intense competition between Adaboost, Gradient Boosting and XGBoost.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.