In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

Existing studies often lack a systematic solution for Unmanned Aerial Vehicles (UAV) inspection system, which hinders their widespread application in crack detection. To enhance its practicality, this study proposes a formal and systematic framework for UAV inspection systems, specifically designed for automatic crack detection and pavement distress evaluation. The framework integrates UAV data acquisition, deep learning based crack identification, and road damage assessment in a comprehensive and orderly manner. Firstly, the flight control strategy is presented, and road crack data is collected using the DJI Mini 2 UAV imagery, establishing a high-quality UAV crack image datasets with ground truth information. Secondly, a validation and comparison study is conducted to enhance the automatic crack detection capability and provide an appropriate deployment scheme for UAV inspection systems. This study develops automatic crack detection models based on mainstream deep learning algorithms(namely, Faster-RCNN, YOLOv5s, YOLOv7-tiny, and YOLOv8s) in urban road scenarios. The results demonstrate that the Faster-RCNN algorithm achieves the highest accuracy and is suitable for online data collection of UAV and offline inspection at work stations. Meanwhile, the YOLO models, while slightly lower in accuracy, are the fastest algorithm and are suitable for lightweight deployment of UAV with online collection and real-time inspection. Quantitative measurement methods for road cracks are presented to assess road damage, which will enhance the application of UAV inspection systems and provide factual evidence for maintenance decisions made by road authorities.

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to hu-man error. Recognizing this limitation, the rise of deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time-frequency domain alongside pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time-frequency (CWT) images processed using auto-encoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: remarkable 100% accuracy in most of the binary classifications, impressive performance exceeding 95% for three-class and four-class challenges, and a commendable rate exceeding 93.5% for the five-class classification.

Visual inertial SLAM algorithms enable robots to autonomously explore and navigate in unknown scenes. However, most of the current SLAM systems highly rely on static environment assumptions, which fails in the exsitence of motional objects in the real environment. To improve the robustness and localization accuracy of SLAM systems in dynamic scenes, this paper proposes a visual-inertial SLAM framework that fuses semantic and geometric information, called DA-VINS. First, this paper presents a dynamic object classification method based on feature’s current motion state, which obtains temporary static features in the environment. Secondly, a features dynamics check module based on IMU prior and adjacent frame’s geometry constraint is designed to calculate dynamic factors. It also verifies the classification results of temporary static features. Finally, a dynamic adaptive bundle adjustment module based on the features’ dynamic factors is designed to adjust the weights of features in nonlinear optimization. We evaluated our method in public and our dataset. The results show that D-VINS is one of the most real-time, accurate, and robust systems in dynamic scenes.

Unmanned aerial vehicles (UAV) provide an unprecedented capacity to monitor the development and dynamics of tree growth and structure through time. It is generally thought that the pruning of tree crops encourages new growth, has a positive effect on fruiting, makes fruit-picking easier, and may increase yield, as it increases light interception and tree crown surface area. To establish the response of pruning in an orchard of lychee trees, an assessment of changes in tree structure, i.e. tree crown perimeter, width, height, area and Plant Projective Cover (PPC), was undertaken using multi-spectral UAV imagery collected before and after a pruning event. While tree crown perimeter, width and area could be derived directly from the delineated tree crowns, height was estimated from a produced canopy height model and PPC was most accurately predicted based on the NIR band. Pre- and post-pruning results showed significant differences in all measured tree structural parameters, including an average decrease in tree crown perimeter of 1.94 m, tree crown width of 0.57 m, tree crown height of 0.62 m, tree crown area of 3.5 m², and PPC of 14.8%. In order to provide guidance on data collection protocols for orchard management, the impact of flying height variations was also examined, offering some insight into the influence of scale and the scalability of this UAV based approach for larger orchards. The different flying heights (i.e. 30, 50 and 70 m) produced similar measurements of tree crown width and PPC, while tree crown perimeter, area and height measurements decreased with increasing flying height. Overall, these results illustrate that routine collection of multi-spectral UAV imagery can provide a means of assessing pruning effects on changes in tree structure in commercial orchards, and highlight the importance of collecting imagery with consistent flight configurations, as varying flying heights may cause changes to tree structural measurements.

Unmanned aerial vehicle (UAV) usage is increasing drastically worldwide as UAVs are used in various industries for many applications, such as inspection, logistics, agriculture, and many more. This is because performing a task using UAV makes the job more efficient and reduces the workload needed. However, for a UAV to be operated manually or autonomously, the UAV must be equipped with proper safety features. An anti-collision system is one of the most crucial and fundamental safety features that UAVs must be equipped with. The anti-collision system allows the UAV to maintain a safe distance from any obstacles. The anti-collision technologies are of crucial relevance to assure the survival and safety of UAVs. Anti-collision of UAVs can be varied in the aspect of the use of sensors and the system’s working principle. This article provides a comprehensive overview of anti-collision technologies for UAVs. It also presents drone safety laws and regulations that prevent a collision at the policy level. The process of anti-collision technologies is studied from three aspects: Obstacle detection, collision prediction, and collision avoidance. A detailed overview and comparison of the methods of each element and an analysis of their advantages and disadvantages have been provided. In addition, the future trends of UAV anti-collision technologies from the viewpoint of fast obstacle detection and wireless networking are presented.

In this work, we studies the principle of ground electrode current field through ground communication technology, signal design, and optimal working mode of excitation source, so as to adapt the working mode, working frequency, and transmission medium condition of signal transmission. Through waveform design, energy is concentrated in the main conduction direction, which is beneficial for signal filtering at the receiving end and achieving high reliability data transmission; On this basis, on-site environmental testing was conducted to verify the detection and recognition technology of weak signals. Signal design and detection recognition are a very important part of the grounding electrode current field through ground communication technology. The grounding electrode current field through ground communication technology is mainly applied to solve the problem of communication between rescue personnel and trapped personnel before and during tunnel engineering collapse and rescue.

Machine learning has become widely adopted as a strategy for dealing with a variety of cybersecurity issues, ranging from insider threat detection to intrusion and malware detection. However, by their very nature, machine learning systems can introduce vulnerabilities to a security defence whereby a learnt model is unaware of so-called adversarial examples that may intentionally result in mis-classification and therefore bypass a system. Adversarial machine learning has been a research topic for over a decade and is now an accepted but open problem. Much of the early research on adversarial examples has addressed issues related to computer vision, yet as machine learning continues to be adopted in other domains, then likewise it is important to assess the potential vulnerabilities that may occur. A key part of transferring to new domains relates to functionality-preservation, such that any crafted attack can still execute the original intended functionality when inspected by a human and/or a machine. In this literature survey, our main objective is to address the domain of adversarial machine learning attacks and examine the robustness of machine learning models in the cybersecurity and intrusion detection domains. We identify the key trends in current work observed in the literature, and explore how these relate to the research challenges that remain open for future works. Inclusion criteria were: articles related to functionality-preservation in adversarial machine learning for cybersecurity or intrusion detection with insight into robust classification. Generally, we excluded works that are not yet peer-reviewed; however, the authors include some significant papers that make a clear contribution to the domain. There is a risk of subjective bias in the selection of non-peer reviewed articles; however, this is mitigated by co-author review. We selected the following databases with a sizeable computer science element to search and retrieve literature: IEEE Xplore, ACM Digital Library, ScienceDirect, Scopus, SpringerLink,Google Scholar. The literature search was conducted upto January 2022. We have striven to ensure a comprehensive coverage of the domain to the best of our knowledge. We have performed systematic searches of the literature, noting our search terms and results, and following up on all materials that appear relevant and fit within the topic domains of this review. This research was funded by the Partnership PhD scheme at the University of the West of England in collaboration with Techmodal Ltd.

In this paper we evaluate the effects of hard and soft constraints on the Iterative Data Snooping (IDS), an iterative outlier elimination procedure. Here, the measurements of a levelling geodetic network were classified according to the local redundancy and maximum absolute correlation between the outlier test statistics, referred to as clusters. We highlight that the larger the relaxation of the constraints, the higher the sensitivity indicators MDB (Minimal Detectable Bias) and MIB (Minimal Identifiable Bias) for both the clustering of measurements and the clustering of constraints. There are circumstances that increase the family-wise error rate (FWE) of the test statistics, increase the performance of the IDS. Under a scenario of soft constraints, one should set out at least three soft constraints in order to identify an outlier in the constraints. In general, hard constraints should be used in the stage of pre-processing data for the purpose of identifying and removing possible outlying measurements. In that process, one should opt to set out the redundant hard constraints. After identifying and removing possible outliers, the soft constraints should be employed to propagate their uncertainties to the model parameters during the process of least-squares estimation.

This paper proposes a crack recognition method based on high-resolution line array cameras and adaptive lifting algorithm. By defining the crack rate, this algorithm calculates the ratio of the crack area to the area of the entire collected image to characterize the damage extent of the current section. The algorithm first uses image preprocessing to reduce the image noise, then uses histogram equalization to enhance the feature of the crack region, divides the whole image into multiple sub-blocks, and extracts region features in the sub-block. At the same time, this algorithm defines related feature descriptors, and constructs weak classifiers according to each feature descriptor, and converts the weak classifiers into strong classifiers by using an adaptive lifting algorithm. Finally, this algorithm realizes the division of the crack regions. Experimental results show that the proposed algorithm can meet the actual needs and is better than other classical algorithms.

This study proposes a machine-learning-based framework for detecting mechanical damage in pipelines, utilizing physics-informed datasets collected from simulations for mechanical damage. The framework provides an effective workflow from dataset generation to damage detection and identification for three types of pipeline events: welds, clamps, and corrosion defects. While the study initially focused on optimizing the CNN structure using various advanced optimizers, it also investigated the impact of sensing systems on data classification and the effect of noise on classification performance. The study's analysis highlights the importance of selecting the appropriate sensing system for the specific application. The authors also found that the proposed framework is robust to experimentally relevant levels of noise, suggesting its applicability in real-world scenarios where noise is present. Overall, this study contributes to the development of a more reliable and effective method for detecting mechanical damage in pipelines. The proposed framework provides an effective workflow for damage detection and identification, and the findings on the impact of sensing systems and noise on classification performance add to its robustness and reliability.

Fire accidents are causing a huge human death as well as economic losses throughout the world every year. But a novel fire detection and extinguishing system could reduce these losses to a great extent. We are proposing a cost effective and yet very efficient system which has been developed in our laboratory and evaluated while in operation. Our system consists of two units: detection unit and extinguishing unit. For detection purposes we used smoke, IR and temperature sensors. While for extinguishing purposes we used both foam and water. We used a PC to process and control our system through LabVIEW software of National Instrument, USA. The detection unit will send signal through a wireless module to PC if fire is detected. Then PC (LabVIEW) will process the signal and using relay module first of all the electric power and gas lines will be turned off. The extinguishing unit will then release foam or water to extinguish the fire. The system will send SMS to the predefined numbers using GSM module. Our system is location independent as it uses GSM and can be operated from remote location using wireless module. After performance evaluation it was found to be fast and reliable.

Defect detection and identification from fruits and vegetables are particularly challenging for Indian agriculture. Defect Detection is a process to identify the defects or damages in vegetables and fruits, based on the shapes, colors and textures. The local market finds it difficult to cope with the defects and other infections in fruits and vegetables as quality evaluations and classification of vegetables and fruits have become tedious process. Recently, several approaches based on Image processing, Machine Learning and Artificial Intelligence methods have been proposed for the purpose of defect detection. On the basis of classifying the types of defects, related pathogens, and physical and morphological characteristics descriptors, we review the different approaches based on a corpus of 57 articles between 2016 and 2021. In the process of describing the defect analysis, steps from the target articles, algorithms, and methods including qualitative and quantitative evaluation are mainly summarized. The aim of this current review work is to present-day novel images and collects recent defective area calculation methods to detect surface defects of fruits and vegetables using RGB images and to classify whether the fruit is defected or fresh. A rigorous evaluation of many new algorithms provided for quality assurance by researcher’s probes of vegetables and fruits have been conducted in this work. This review work conveys that using the recent identification features will help to decrease the disadvantages in fruit storeroom owing to storage of the affected vegetables and fruits, ie. Preventing the spread of defects and other infections from the infected fruits and vegetables to the fresh ones.

This study examined the efficiency of a combined diagnostic approach in which bioamplification of Arizona 861 S1 citron was integrated with RT‒PCR to detect Citrus tristeza virus (CTV) and Hop Stunt Viroid (HSVd) in Citrus plants. The capacity of the combined method to diagnose mixed infections of CTV and HSVd, along with early single infections of both pathogens, was assessed by evaluating the incubation periods and differential detection capabilities between the combined and direct methods. The bioamplification method exhibited high sensitivity (100%) and specificity (100%) for CTV, enabling early detection even in patients with low-titer infections compared to direct RT‒PCR. However, for HSVd, the combined method achieved 50% sensitivity in early infections, highlighting the need for additional replicates to enhance diagnostic reliability. The relative concentrations of pathogens in mixed and simple infections were evaluated; the analysis revealed no significant differences, suggesting minimal interference between CTV and HSVd. This approach allows early detection of CTV but requires further refinement for HSVd diagnosis. These findings underscore the complementary roles of the cost-effectiveness of direct RT‒PCR and the sensitivity of the combined method in implementing effective disease control strategies in citrus crops.

Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparatively lightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method.

The integration of metal nanoparticles and solid carriers can achieve ideal stability, high load and good conductivity. In this work, copper nanoparticles (Cu NPs) were sequentially deposited on a cobalt metal-organic framework (Co-MOF) by bonding with exposed imino groups, followed by a reduction reaction to prepare a new Cu@Co-MOF composite. Cu@Co-MOF acts as a non-enzymatic electrochemical sensor to detect glucose (Glu) in an alkaline medium. The composite working electrode of Cu@Co-MOF/GCE (GCE = glassy carbon electrode) improves the electrocatalytic activity for Glu oxidation. Cu@Co-MOF/GCE shows excellent electrocatalytic performances in Glu concentration ranging 0.005~1.8 mmol∙L⁻¹ (mM): the sensitivities are 282.89 μA∙mM⁻¹∙cm⁻² in 0.005-0.4 mM Glu and 113.15 μA∙mM⁻¹∙cm⁻² in 0.4-1.8 mM Glu respectively with low detection limit of 1.6 μM (S/N = 3) and high selectivity and stability.

As human activities of the countries in the East Asia have been remarkably expanding over recent decades, various problems in relation to ships, such as oil spill and many other coastal marine pollution, are continuously occurring in the coastal region. In order to conserve marine resources and prepare for possible ship accidents in advance, the need for efficient ship management is increasing over time. Multi-satellite, multi-sensor, multi-wavelength or multi-frequency observations make it possible to monitor a variety of vessels in the coastal region. This study presents the results of ship detection methodology applied to multi-spectral satellite images in the seas around Korean Peninsula based on optical, hyperspectral, and microwave remote sensing. To detect ships from hyperspectral images with a few hundreds of spectral channels, spectral matching algorithms are used to investigate similarity between the spectra and in-situ measurements. In the case of SAR (Synthetic Aperture Radar) images, the Constant False Alarm Rate (CFAR) algorithm is used to discriminate the vessels from backscattering coefficients of Sentinel-1 SAR and ALOS-2 PALSAR2 images. The present ship detection methods can be extensively utilized for optical, hyperspectral, and SAR images for comprehensive coastal management purposes toward perpetual sustainability in the future.

The accurate prediction of heat load profiles with a daily resolution is required for a broad range of applications such as potential studies, design, or predictive operation of heating systems. If the heat demand of a consumer is mainly caused by (production) processes independent of the ambient temperature, existing load profile prediction methods fail. To close this gap, this study develops two ex post machine learning models for the prediction of the heat demand with a daily resolution. The selected input features are commonly available to each consumer connected to public natural gas and electricity grids or operating an energy monitoring system: Ambient temperature, weekday, electricity consumption, and heat consumption of the last seven days directly before the predicted day. The study’s database covers electricity and natural gas consumption load profiles from 82 German consumers over a period of two years. Electricity and heat consumption correlate strongly with individual patterns for many consumers. Both, shallow and deep learning algorithms are evaluated. The highest accuracy is achieved by a Long Short Term Memory (LSTM) model with a median of R² of 0.94. The ex post model architecture makes the model suitable for automated anomaly detection in energy monitoring systems.

Crack inspection is important to monitor the structural health of pavement structures and to facilitate an easier rehabilitation process. Currently, pavement crack inspection is conducted manually, which is inefficient and costly at the same time. For solving the problem, this work has developed a robotic system for automated data collection and analysis in real-time. The robotic system navigates on the pavement and collects visual images from the surface. A deep learning-based semantic segmentation framework named RCDNet was proposed and implemented on the onboard computer of the robot to identify cracks from the visual images. Simulation results show that the deep learning model obtained 96.29% accuracy for predicting the images. The proposed robotic system was tested on both indoor and outdoor environments and was observed that it can complete inspecting a 3m × 2m grid within 10 minutes and a 2.5m × 1m grid within 6 minutes. This outcome shows that the proposed robotic method can drastically reduce the time of manual inspection. Furthermore, a severity map based on the results from visual images was also generated to provide an idea of which locations should be paid more attention to repair in a test grid.

Since smoke usually occurs before a flame arises, fire smoke detection is especially significant for early warning systems. In this paper, a DSATA(Depthwise Separability And Target Awareness) algorithm based on depthwise separability and target awareness is proposed. Existing deep learning methods with convolutional neural networks pretrained by abundant and vast datasets are always used to realize generic object recognition tasks. In the area of smoke detection, collecting large quantities of smoke data is a challenging task for small sample smoke objects. The basis is that the objects of interest can be arbitrary object classes with arbitrary forms. Thus, deep feature maps acquired by target-aware pretrained networks are used in modelling these objects of arbitrary forms to distinguish them from unpredictable and complex environments. In this paper, this scheme is introduced to deal with smoke detection. The depthwise separable method with a fixed convolution kernel replacing the training iterations can improve the speed of the algorithm to meet the enhanced requirements of real-time fire spreading for detecting speed. The experimental results demonstrate that the proposed algorithm can detect early smoke, is superior to the state-of-the-art methods in accuracy and speed, and can also realize real-time smoke detection.

Rodents are known to be reservoirs of Toxoplasma gondii and keep the parasite circulation in the environment. We conducted biomonitoring to assess the role of sylvatic rodents in maintaining T. gondii and to analyse the prevalence and seroprevalence of the parasite in seven wild rodent species. Rodents were collected in our study sites (woodland and open grasslands) located in northeastern Poland and dissected. We collected brain, spleen, blood and serum samples. We applied both molecular (PCR assay, nested-PCR assay) and serological (ELISA and agglutination tests) methods to indicate the best approach for application in the biomonitoring of T. gondii in small mammals. We screened samples from 95 individuals sing PCR assays and found no T. gondii DNA. The agglutination test showed no signal. We found antibodies against T. gondii in 6 sera samples out of 74 analysed (seroprevalence = 8.11% [4.0-17.1]). Our results confirm that rodents participate in the life cycle of T. gondii as reservoirs of this parasite in the sylvatic environment. However, biomonitoring should be performed with the ELISA tests to search for T. gondii antigens, rather than a molecular approach only.

Tobamovirus species represent a threat to solanaceous crops worldwide, due to their extreme stability and being seed-borne. In particular, recent outbreaks of tomato brown rugose fruit virus in tomato and pepper crops led to the establishment of prompt control measures, and the need for reliable diagnosis was urged. Another member of the genus, tomato mottle mosaic virus, has recently risen attention due to reports in different continents and its common features with tomato brown rugose fruit virus. In this study, a new real-time RT-PCR detection system was developed for tomato brown rugose fruit virus and tomato mottle mosaic virus on tomato leaves and seeds using TaqMan chemistry. This test was designed to detect tomato mottle mosaic virus by amplifying the movement protein gene in a duplex assay with tomato brown rugose fruit virus target on the CP-3’NTR region, which was already validated as a single assay. The performance of this tests was evaluated, displaying analytical sensitivity 10-5-10-6-fold dilution for seeds and leaves, respectively, and good analytical specificity, repeatability, and reproducibility. Using the newly developed and validated test, tomato brown rugose fruit virus detection was 100% concordant with previously performed analyses on 106 official samples collected in 2021 from different continents.

Malignant growth is the most widely recognized repulsive infections winning around the world, and the patients with disease are saved just when the malignant growth is distinguished at the beginning phase. Each kind of disease is interesting, with its own arrangement of development properties and hereditary changes. This paper presents the lung knob division and disease characterization by proposing an enhancement calculation. The general technique of the created approach includes four stages, such as pre-processing, division, highlight extraction, and the order. From the outset, the CT picture of the lung is taken care of to the division. When the division is done, the highlights are extricated through morphological and measurable and surface highlights like LOOP and LGP. At long last, the extricated highlights are given to the order step. Here, the characterization is done dependent on the Deep Belief Network (DBN) which is prepared by utilizing the proposed Chicken-Sine Cosine Algorithm (CSCA) which distinguish the lung tumor, giving two classes in particular, knob or non-knob. The presentation assessment of lung knob division and malignant growth grouping dependent on CSCA is figured utilizing three measurements to be specific, precision, affectability, and the explicitness.

This study presents a novel semi-supervised deep learning method utilizing 3D TOF-MRA images for the detection of brain aneurysms, employing landmark-based techniques that mimic radiologist practices to enhance detection accuracy and efficiency.

This work presents an approach for detecting mathematical formulas in scanned document images. The proposed approach is end-to-end trainable. Since many OCR engines cannot reliably work with the formulas, it is essential to isolate them to obtain the clean text for information extraction from the document. Our proposed pipeline comprises a hybrid task cascade network with deformable convolutions and a Resnext101 backbone. Both of these modifications help in better detection. We evaluate the proposed approaches on the ICDAR-2017 POD and Marmot datasets and achieve an overall accuracy of 96% for the ICDAR-2017 POD dataset. We achieve an overall reduction of error of 13%. Furthermore, the results on Marmot datasets are improved for the isolated and embedded formulas. We achieved an accuracy of 98.78% for the isolated formula and 90.21% overall accuracy for embedded formulas. Consequently, it results in an error reduction rate of 43% for isolated and 17.9% for embedded formulas.

This paper presents a novel architecture for detecting mathematical formulas in document images, which is an important step for reliable information extraction in several domains. Recently, Cascade Mask R-CNN networks have been introduced to solve object detection in computer vision. In this paper, we suggest a couple of modifications to the existing Cascade Mask R-CNN architecture: First, the proposed network uses deformable convolutions instead of conventional convolutions in the backbone network to spot areas of interest better. Second, it uses a dual backbone of ResNeXt-101, having composite connections at the parallel stages. Finally, our proposed network is end-to-end trainable. We evaluate the proposed approach on the ICDAR-2017 POD and Marmot datasets. The proposed approach demonstrates state-of-the-art performance on ICDAR-2017 POD at a higher IoU threshold with an f1-score of 0.917, reducing the relative error by 7.8%. Moreover, we accomplished correct detection accuracy of 81.3% on embedded formulas on the Marmot dataset, which results in a relative error reduction of 30%.

Intrusion Detection Systems (IDS) plays a part in modern cyber security, as a result of the increasing need for cyber security systems in the “real” world due to the increasing number of cyber attacks, more sophisticated systems are required in order to prevent these attacks - an IDS can provide this protection. Due to the sophistication of these systems, they must be properly understood, developed and analyzed - research papers can be used as a tool to improve IDS systems. This paper is composed of two main sections: a survey and a taxonomy, providing information, reviews and interpretations from relevant papers, a timeline of important papers, a discussion on the future of IDS and a classification on IDS and how to apply this.

Determination of the presence in the blood of antibodies specific to the causative agent of a particular disease (serodiagnosis) is an effective approach in medical analytical chemistry. Serodiagnostics performed in the lateral flow immunoassay format (immunochromatography) meet the modern requirements for point-of-care testing and are supported by existing technologies of large-scale diagnostic tests production—thus raising increased attention in a tense epidemiological situation. For traditional lateral flow serodiagnostics formats, a large number of nonspecific immunoglobulins in the sample significantly reduces the degree of detectable binding. To overcome these limitations, an assay based on the formation of immobilized antigen— specific antibody—labeled antigen complexes detection was proposed. However, the requirements for its implementation, providing maximum sensitivity, have not been established. This article describes the mathematical model for the above assay. The influence of the ratio of reagent concentrations on the analysis results is considered. It is noted that the formation of specific antibody complexes with several labeled antigens is the main limiting factor in reducing the detection limit, and methods are proposed to minimize this factor. Recommendations for the choice of the assay conditions, following from the analysis of the model, are confirmed experimentally.

In the next decade, further digitalisation of the entire wind energy project lifecycle is expected to be a major driver for reducing project costs and risks. In this paper, a literature review on the challenges related to implementation of digitalisation in the wind energy industry is first carried out, showing that there is a strong need for new solutions that enable co-innovation within and between organisations. Therefore, a new collaboration method called the WeDoWind Ecosystem is developed and demonstrated. The method is centred around specific "challenges", which are defined by "challenge providers" within a topical "space" and made available to participants via a digital platform. The data required in order to solve a particular "challenge" is provided by the "challenge providers" under the confidentiality conditions they specify. The method is demonstrated via a case study, the EDP Wind Turbine Fault Detection Challenge. Six submitted solutions using diverse approaches are evaluated. Two of the methods perform significantly better than EDP’s existing method in terms of Total Prediction Costs (saving up to €120,000). The WeDoWind Ecosystem is found to be a promising solution for enabling co-innovation in wind energy, providing a number of tangible benefits for both challenge and solution providers.

Lane detection is a foundational technology for autonomous driving systems. It involves identifying the boundaries of lanes on the road and ensuring the vehicle stays within these boundaries. Accurate lane detection is crucial for safety, navigation and traffic management. This paper presents an artificial intelligent based autonomous road lane detection and navigation system for vehicles. The system can detect and analyze road lanes accurately and efficiently in real-time, with frame rates of up to 17 FPS. By utilizing image processing techniques, the system can identify the location and boundaries of road lanes and obstacles on the road and provide accurate and reliable navigation guidance to the driver. The system is integrated with sensors and actuators to provide comprehensive autonomous navigation. The efficiency of the proposed system is demonstrated using accuracy of lane detection on straight and curve lanes covering frames per second and motor of the speed as parameters for assessment. Results show that the proposed system detects lane as entire lane detection, partial lane detection and no detection status on different settings.

Metal-organic framework (MOF) is a porous hybrid material of metal ions connected by organic bridging ligands. The coordination bonds link the metal ions, metal-ion clusters, and organic ligands to create the MOFs, and the materials are a distinctive class of crystalline frameworks. These porous materials possess relatively large surface area, tunable pore sizes, various functionalities, and high thermal stability. Therefore, diverse area of research including electrochemical sensor development utilizes distinctive and engineered MOFs materials. The review critically analyzes the strategy adopted for synthesizing a variety of MOFs materials. The role of these engineered materials in the fabrication of a miniaturized device demonstrates the detection of various emerging water contaminants in an aqueous medium. The studies demonstrated an understanding of the insights of sensor and device development. Moreover, the challenges encountered utilizing the MOFs in the electrochemical sensor development are precisely included, along with future perspectives of these studies.

Objective: Design and validate a wireless, low-cost, easy-to-use, mobile, dry-electrode headset for scalp electroencephalography (EEG) recordings for closed-loop brain-computer (BCI) interface and internet-of-things (IoT) applications. Approach: The EEG-based BCI headset was designed from commercial off-the-shelf (COTS) components using a multi-pronged approach that balanced interoperability, cost, portability, usability, form factor, reliability, and closed-loop operation. Main Results: The adjustable headset was designed to accommodate 90\% of the population. A patent-pending self-positioning dry electrode bracket allowed for vertical self-positioning while parting the user's hair to ensure contact of the electrode with the scalp. In the current prototype, five EEG electrodes were incorporated in the electrode bracket spanning the sensorimotor cortices bilaterally, and three skin sensors were included to measure eye movement and blinks. An accelerometer provides monitoring of head movements. The EEG amplifier operates with 24 bits resolution up to 500 Hz sampling frequency, and can communicate with other devices using 802.11 {b/g/n/WiFi}. It has high SNR and CMRR (121 dB and 110 dB, respectively), and low input noise. In closed-loop BCI mode, the system can operate at 40 Hz, including real-time adaptive noise cancellation and 512 MB of processor memory. It supports LabVIEW as backend coding language and JS, CSS, HTML as front-end coding languages, and includes training and optimization of Support Vector Machine (SVM) neural classifiers. Extensive bench testing supports the technical specifications and human subject pilot testing of a closed-loop BCI application to support upper-limb rehabilitation provides proof-of-concept validation for device use at both the clinic and at home. Significance: The low-cost, accessibility, usability, interoperability, and programmability of the proposed closed-loop BCI system provides a low-cost solution for BCI and neurorehabilitation research and IoT applications.

Early detection of wildfires has been limited using the sun-synchronous orbit satellites due to their low temporal resolution and wildfires’ fast spread in the early stage. NOAA’s geostationary weather satellites GOES-R can acquire images every 15 minutes at 2km spatial resolution, and have been used for early fire detection. However, advanced processing algorithms are needed to provide timely and reliable detection of wildfires. In this research, a deep learning framework, based on Gated Recurrent Units (GRU), is proposed to detect wildfires at early stage using GOES-R dense time series data. GRU model maintains good performance on temporal modelling while keep a simple architecture, makes it suitable to efficiently process time-series data. 36 different wildfires in North and South America under the coverage of GOES-R satellites are selected to assess the effectiveness of the GRU method. The detection times based on GOES-R are compared with VIIRS active fire products at 375m resolution in NASA’s Fire Information for Resource Management System (FIRMS). The results show that GRU-based GOES-R detections of the wildfires are earlier than that of the VIIRS active fire products in most of the study areas. Also, results from proposed method offer more precise location on the active fire at early stage than GOES-R Active Fire Product in mid-latitude and low-latitude regions.

This study investigated the influence of land-use and precipitation change and variability on Lake Victoria’s water-level fluctuations. Extreme precipitation events, corresponding to extreme water-levels, over the lake and its catchment area were identified and their return periods estimated by fitting them into a generalized extreme value (GEV) distribution. Using general circulation models from the 6^th phase of the Coupled Model Intercomparison Project (CMIP6)’s Detection & Attribution Model Intercomparison Project (DAMIP), an assessment of the potential contribution of human-induced climate change on the observed precipitation patterns over the study area was done. The greatest precipitation anomalies for the period 1900-2020 were recorded in 1961’s October-December (OND) season and 2019’s June-August (JJA) and OND seasons, corresponding to the period when the highest water-levels were recorded in Lake Victoria. While land-use change in the study domain was observed, extended and unusually heavy June to December 2019 precipitation bore the greatest responsibility for the 2019/2020 high water-levels in Lake Victoria. The OND precipitation event of 2019 was a 1-in-52-year event compared to the 1961’s 1-in-693 years. Differences in return periods at various parts of the lake imply a high spatial climate variability within the lake itself. An analysis of the fraction of attributable risk (FAR) showed natural variability to have a greater influence on the JJA and OND precipitation patterns over Lake Victoria than human-induced climate change. However, variability over the land area of the study domain was mainly driven by human-induced climate change rather than natural variability, implying a unique climate system over Lake Victoria. Findings from the current study enhance the understanding of Lake Victoria’s water budget and motivate for further research to inform effective strategies on the planning and use of Lake Victoria’s water resources in a changing climate.

We discuss two methods to detect the presence and location of a person in a small-scale room and compare the performances. The first method is Direct Intersection, which determines a coordinate point based on the intersection of spheroids defined by observed distances of high-intensity reverberations. The second method, Sonogram analysis, overlays all channel’s room impulse responses to generate an intensity map for the observed environment. We demonstrate that the former method has lower computation complexity and higher accuracy for small numbers of channels, while the latter performs more robustly.

A Mild traumatic brain injury (mTBI) or concussion has become a public health problem in the United State. Sports and recreational activities are major sources of concussions; with the most incidents connected to American football. Recently, many companies and research institutions have started studying concussions and introduced some means of protection and some alarming systems of strong jolts. The major detection and protection system currently available on the market is the electronic helmet (e-helmet) composed of measurement devices to record head impact acceleration. The most commonly used devices in e-helmets are accelerometers to measure linear acceleration and gyroscopes for rotational/angular acceleration. Using smart textiles for concussion detection is currently uncommon and limited due to the lack of literature studying their voltage related errors. Actually, there are few works that characterize some voltage-force related errors for such type of sensors but for small impact forces and under bench testing while the behavior of those sensors was not described for higher ranges of applied forces and in field situations. This paper previews some common techniques used in e-helmets for concussion detection and highlights electronic textiles and smart fabric sensors that could be very useful for these applications. It discusses and validates the general behavior of such type of sensors under high impact forces and on field testing instead of bench testing, and also it characterizes the effect of increasing the thickness of the sensing element layer on the sensor. A custom-made pressure sensor was created of some available fabrics to be embedded within the padding of a football helmet to quantify the impacting force to the head. The sensor is mainly composed a Semi Conductive Polymer Composite SCPC layer with modifiable thickness that was modified three times with 0.2, 0.4, and 1.6mm to characterize the general behavior of the sensor due to a high amount of impacts and correlated with the thickness. A pendulum system was built to test the pressure sensors, while a special camera and an open-source video analysis software, Tracker was used to track the pendulum bob. The speed and the acceleration of the pendulum bob were measured, then the impact force was calculated and a voltage-force response was obtained. The results showed that no meaningful improvement occurs by small increase in the thickness but better sensor behavior could be obtained by significant increment to observe any difference. Despite that at a very high impacts, the suggested sensor with Velostat layers is not giving the real voltage readings that reflect the actual applied forces but it gives a helpful information that illustrate the distribution of the force through identification the place of the highest and lowest voltage readings regardless of the exact values of those readings. However, the proposed smart textile pressure sensor could be applicable in future e-helmet designs with additional research-based improvements especially on the structure of the sensing element layer to be able to withstand such high impacts which in turns improves the overall sensor performance and accurately measures pressure in concussion-inducing ranges.

Multi-floor environments are usually ignored while designing an autonomous robot for indoor cleaning applications. However, for efficient operation in such environments, the ability of a robotic platform to traverse staircases is crucial. Staircase detection and localization is highly important for planning the traversal on staircases. This paper describes a deep learning approach using Convolutional Neural Networks (CNNs) based Robot Operation System (ROS) to staircase detection and localization. We use an object detection network to detect staircases in images. We also localize these staircases using a contour detection algorithm to detect the target point, a point close to the center of the first step, and the angle of approach to the target point. Experiments are performed with data obtained from images captured on different types of staircases at different view points/angles. Results show that the approach is very accurate in identifying the presence of the staircase in the working environment and is also able to locate the target point with good accuracy.

The goal of background reconstruction is to recover the background image of a scene from a sequence of frames showing this scene cluttered by various moving objects. This task is fundamental in image analysis, and is generally the first step before more advanced processing, but difficult because there is no formal definition of what should be considered as background or foreground and the results may be severely impacted by various challenges such as illumination changes, intermittent object motions, highly cluttered scenes, etc. We propose in this paper a new iterative algorithm for background reconstruction, where the current estimate of the background is used to guess which image pixels are background pixels and a new background estimation is performed using those pixels only. We then show that the proposed algorithm, which uses stochastic gradient descent for improved regularization, is more accurate than the state of the art on the challenging SBMnet dataset, especially for short videos with low frame rates, and is also fast, reaching an average of 52 fps on this dataset when parameterized for maximal accuracy using GPU acceleration and a Python implementation.

Porcine parvovirus 8 (PPV8), a novel virus in the Parvoviridae family, was first identified in 2022 in lung samples of domestic pigs from China. Retrospective analyses showed that it had been circulating in China since 1998, but no other countries had reported its presence so far. A recent study conducted in South America did not detect any PPV8-positive samples in that region. Here we report the detection of PPV8 in Hungarian and Slovakian pig farms and the estimated prevalence of the virus in Hungary. Altogether 2230 serum, 233 oral fluid, and 115 processing fluid samples were systematically collected from 23 Hungarian and 2 Slovakian pig farms between 2020 and 2023. A real-time quantitative PCR method was developed to detect the viral genome. Our results revealed the presence of PPV8 on 65% of the Hungarian farms and on both Slovakian farms included in our study, marking its first detection in Europe. Oral fluid samples showed the highest positivity rates, reaching up to 100% in some herds. The viral genome was successfully detected in serum and processing fluid samples too, but with significantly lower prevalence rates of 4% and 5%, respectively. Genetic analysis of 11 partial VP2 sequences demonstrated high similarity to the original Chinese strain but with unique amino acid mutations, suggesting possible local evolution of the virus. Our study presents the first scientific evidence of PPV8 infection outside of China and offers a comprehensive assessment of its prevalence in the Hungarian pig population. Further research is required to understand its potential impact on swine health.

In the first part of this article, we discuss and generalize the complete convergence introduced by Hsu and Robbins (1947) to the r-complete convergence introduced by Tartakovsky (1998). We also establish its relation to the r-quick convergence first introduced by Strassen (1967) and extensively studied by Lai (1976). Our work is motivated by various statistical problems, mostly in sequential analysis. As we show in the second part, generalizing and studying these convergence modes is important not only in probability theory but also to solve challenging statistical problems in hypothesis testing and changepoint detection for general stochastic non-i.i.d. models.

Predictive maintenance (PM) algorithms are widely applied for detecting operational anomalies on industrial processes to trigger maintenance before a possible breakdown; however, much less focus has been devoted to the use of such PM predictions as feedback in automated process control mechanisms. They usually integrate preventive solutions to protect the machines, usually causing downtimes. The premise of this study is to develop a holistic adaptive process scheduling mechanism that incorporates PM analysis as a safety component to optimize the operation mode of an industrial process toward preventing breakdowns while maintaining its availability and operational state, thereby reducing downtimes. As PM is largely a data-driven approach; hence, relies on the setup, we first compare different PM approaches and identify a one-class support vector machine (OCSVM) as the best performing option for the anomaly detection on our setup. Then, we propose a novel pipeline to integrate maintenance predictions into a real-time adaptive process scheduling mechanism. It schedules for the most suitable operation, i.e., optimizing for machine health and process efficiency, according to the abnormal readings. To demonstrate the pipeline on action, we implement our approach on a small-scale conveyor belt system utilizing our Internet of Things (IoT) framework. The results show that our PM-based adaptive process control provides an efficient process with less or no downtime. We also conclude that a PM approach does not provide sufficient efficiency without its integration into an autonomous planning process.

Automobile proving ground is important for the research of vehicles which is used for the vehicle dynamics, durability testing, braking testing, etc. However, the roads in automobile proving ground will inevitably be damaged with the extension of the service life. In most previous researches, equipment similar to laser cross-section was used to detect pavement quality, the principle of which was to reflect pavement quality by detecting road surface roughness. This method ignores the elastic deformation of the roads itself when the vehicle is traveling on it and hardly compensate for the amendment. Therefore, this article presents a new method based on force sensor to reduce the impact of elastic deformation such as wheel tyre deformation, pavement deformation, and wheel rim deformation. In which, force sensors mounted on the wheels collect the three-dimensional dynamic load of the wheel.The presented method has been tested with two sets of cobblestone road load data, and the results show that The　incentives imposed by the test vehicle on the target road are 88.3%, 91.0%, and 92.05% of the incentives imposed by the test vehicle on the standard road in three dimensions, respectively. It is clear that the proposed method has strong potential effectiveness to be applied for lose detection of the special road application.

This paper presents a novel segmentation algorithm specially developed for applications in 3D point clouds with high variability and noise, particularly suitable for heritage building 3D data. The method can be categorized within the segmentation procedures based on edge detection. In addition, it uses a graph-based topo-logical structure generated from the supervoxelization of the 3D point clouds, which is used to make the clo-sure of the edge points and to define the different segments. The algorithm provides a valuable tool for generating results that can be used in subsequent classification tasks and broader computer applications dealing with 3D point clouds. One of the characteristics of this segmentation method is that it is unsupervised, which makes it particularly advantageous for heritage applications where labelled data is scarce. It is also easily adaptable to different edge point detection and supervoxelization algorithms. Finally, the results show that the 3D data can be segmented into different architectural elements, which is important for further classification or recognition. Extensive testing on real data from historic buildings demonstrates the effectiveness of the method. The results show superior performance compared to three other segmentation methods, both globally and in the segmentation of planar and curved zones of historic buildings.

Disease detection and prediction have been one of the most frequent uses of machine learning models in the last decade, and Parkinson's disease is no exception. It is common for people in their old age to have one form of disease or another depending on the circumstances in which they find themselves. This study analyzed and evaluated various supervised machine learning models to detect the presence of Parkinson's disease in elderly individuals. An extreme gradient boosting model, along with other models, such as naïve Bayes, random forest, K-nearest neighbor, and support vector machine (SVM), was implemented to determine the best outcome. The extreme gradient boosting (XGBoost) model is a powerful boosting machine learning technique, particularly in terms of speed and accuracy. The results showed that the XGBoost model, which is an optimized version of the other boosting models, is capable of projecting the presence of Parkinson's disease with very high accuracy compared to other algorithms. The implemented classification algorithm extreme gradient boosting method achieved approximately 98 % accuracy, 97.5 % precision, 100.0 % recall, and 98.7% f1-score which are high compared with the results found in the existing literature.

Process safety plays a vital role in the modern process industry. To prevent undesired accidents caused by malfunctions or other disturbances in complex industrial processes, considerable attention has been paid to data-driven fault detection techniques. To explore the underlying manifold structure, manifold learning methods including Laplacian eigenmaps, locally linear embedding, and Hessian eigenmaps have been utilized in data-driven fault detection. However, only the partial local structure information is extracted from the aforementioned methods. In this paper, these typical manifold learning methods are synthesized to find the underlying manifold structure from different angles. A more comprehensive local structure is discovered under a unified framework by constructing an objection optimization function for dimension reduction of the process data. The proposed method takes advantage of different manifold learning methods. Based on the proposed dimension reduction method, a new data-driven fault detection method is developed. Hotelling’s T2 and Q statistics are established for the purpose of fault detection. Experiments on an industrial benchmark Tennessee Eastman process and a real blast furnace ironmaking process are carried out to demonstrate the superiority and effectiveness of the proposed method.

Coronavirus Disease-19 (COVID-19) is presently wreaking havoc on public health and socio-economic development. Besides the upper and lower respiratory tract involvement, gastrointestinal symptoms are also reported in COVID-19 patients through gut-lung axis. Finding its way through the feces of infected individuals and other sources, the genetic material of SARS-CoV-2 (ssRNA) is reported widely in wastewater and is being used as a fingerprint for its detection. With millions of cases arriving every day, there is a need to level up the testing speed efficiency. Due to the restricted sampling potential of testing laboratories, clinical testing is unable to track all the symptomatic and asymptomatic cases. Wastewater-based epidemiology (WBE) bestows an auxiliary monitoring tool that will contribute in community level screening. Sample collection, concentration, RNA extraction, quantification and data analysis are the main steps involved in implementation of WBE that can be relied upon as an alarm call for an upcoming wave, emergence of a new variant or any future pandemic. WBE can be a cheaper and more practical alternative to high end and sophisticated clinical testing for community transmission detection. Worldwide, there are more than 300 reports entailing the occurrence of SARS-CoV-2 in wastewater exhibiting unique temporal trends with five of them in India. This review aims to address the present knowledge on surveillance of SARS-CoV-2 in wastewater and its implications.

With advancements in digital technologies such as 5G communications, big data, and cloud computing, the components of network operation systems have become increasingly complex, significantly complicating system monitoring and maintenance. Correspondingly, automated log anomaly detection has become a crucial means to ensure stable network operation and protect them from malicious attacks or failures. Conventional machine learning and deep learning methods assume consistent distributions between the training and testing data, adhering to a closed-set recognition paradigm. Nevertheless, in realistic scenarios, systems may encounter new anomalies that were not present in the training data, especially in log anomaly detection. Inspired by evidential learning, we propose a novel anomaly detector called LogEDL, which supervises training of the model through an evidential loss function. Unlike traditional loss functions, the evidential loss function not only focuses on correct classification, but also quantifies the uncertainty of predictions. This enhances the robustness and accuracy of the model in handling anomaly detection tasks, while achieving functionality similar to open-set recognition. To evaluate the proposed LogEDL method, we conduct extensive experiments on three datasets, i.e., HDFS, BGL, and Thunderbird, to detect anomalous log sequences. Experimental results demonstrate that our proposed LogEDL achieves state-of-the-art performance in anomaly detection.

Ophthalmological services face global inadequacies, especially in low- and middle-income countries, which are marked by a shortage of both practitioners and equipment. This study employed a portable slit-lamp microscope with video capabilities and cloud storage for a more equitable global diagnostic resource distribution. To enhance accessibility and quality of care, this study targeted corneal opacity, a global cause of blindness. To boost the online diagnosis efficiency, an AI pipeline was developed using anterior segment videos to detect corneal opacity. First, we extracted image frames from videos and learned them using a Convolutional Neural Network(CNN) model. Second, we manually annotated to extract only the corneal margins, adjusted the contrast with CLAHE, and learned using the CNN model. Finally, we performed semantic segmentation of the cornea using the annotated data. The results showed an accuracy of 0.8 for image frames, and 0.96 for corneal margins. Dice and IoU were 0.94 for semantic segmentation of corneal margins. While corneal opacity detection from video frames seemed challenging in the early stages of this study, manual annotation, corneal extraction, and CLAHE contrast adjustment significantly improved accuracy. Integrating manual annotation into the AI pipeline through semantic segmentation achieved a high accuracy in detecting corneal opacity.

The rapid and sensitive detection of pathogenic bacteria is becoming increasingly important for the timely prevention of contamination and treatment of infections. Biosensors based on nucleic acid aptamers integrat-ed with optical, electrochemical, and mass-sensitive analytical techniques have garnered intense interest for their versatility, cost-efficiency, and ability to exhibit high affinity and specificity in binding bacterial bi-omarkers, toxins, and whole cells. This review emphasizes the development of aptamers, their structural op-timization, and their use in bacterial sensing applications. Moreover, we explore barriers and develop per-spectives in applying aptamer-based bacterial detection.

With the continuous development of deep learning, the application of object detection based on deep neural network in the coal mine has been expanding. Simultaneously, as the production applications demand higher recognition accuracy, most research chooses to enlarge the depth and parameters of the network to improve accuracy. However, due to the limited computing resources in the coal mining face, it is challenging to meet the computation demands of a large number of hardware resources. Therefore, this paper proposes a lightweight object detection algorithm designed specifically for coal mining face, referred to as CM-YOLOv8. The algorithm introduces adaptive predefined anchor boxes tailored to the coal mining face dataset to enhance the detection performance of various targets. Simultaneously, a pruning method based on the L1 norm is designed, significantly compressing the model's computation and parameter volume without compromising accuracy. The proposed algorithm is validated on the coal mining dataset DsLMF+, achieving a compression rate of 40% on the model volume with less than a 1% drop in accuracy. Comparative analysis with other existing algorithms demonstrates its efficiency and practicality in coal mining scenarios. The experiments confirm that CM-YOLOv8 significantly reduces the model's computational requirements and volume while maintaining high accuracy.

Langya Henipavirus (LayV) is a new zoonotic Henipavirus reported in 2022. Patients infected by LayV show common cold symptoms, such as fever, fatigue, and cough. Non-fatal cases associated with this virus have been reported in Henan and Shandong provinces in China. Should human-to-human transmission occur, it has the potential to be a pandemic like SARS-CoV-2. LayV is an enveloped negative-sense RNA virus. Its polymerase (encoded by the L gene) is considered a conserved target shared within Henipavirus viruses, allowing for qPCR detection, in which primers play a pivotal role. For the development of a diagnostic kit, we designed three primer sets targeting the L gene and evaluated their detection of plasmids carrying part of the L gene. Primer sets 1 and 2 were found to be suitable for further sensitivity, specificity, and efficiency testing. Both primer sets were able to amplify PCR products in the presence of human saliva, and both the melt curve analysis and gel electrophoresis showed distinct peaks and bands, supporting the specificity of the qPCR primers. Based on standard curve analysis, both primers detected as low as approximately 1000 copies of the L gene. Given the specificity and robustness to work in the presence of saliva, the primers can be used for pandemic-preparedness in LayV detection.

In the industrial field, the 3D target detection algorithm PointPillars has gained popularity. Improving target detection accuracy while maintaining high efficiency has been a significant challenge. To address the issue of low target detection accuracy in the PointPillars 3D target detection algorithm, this paper proposes an algorithm based on feature enhancement to improve the backbone network. The algorithm enhances preliminary feature information of the Backbone network by modifying it based on PointPillars with the aid of channel attention and spatial attention mechanisms. To address the inefficiency caused by the excessive number of subsampled parameters in PointPillars, FasterNet (a lightweight and efficient feature extraction network) is utilized for downsampling and forming different scale feature maps. To prevent the loss and blurring of extracted features resulting from the use of inverse convolution, we utilize the lightweight and efficient up-sampling modules Carafe and Dysample for adjusting resolution. Experimental results indicate improved accuracy under all difficulties of the KITTI dataset, demonstrating the superiority of the algorithm over PointPillars.

CdZnTe (CZT) is a new type of compound semiconductor that has emerged in recent years. Compared to other semiconductor materials, it possesses an ideal bandgap, high density, and high electron mobility, rendering it an excellent room-temperature composite semiconductor material for X-ray and γ-ray detectors. Due to the exceptional performance of CZT material, detectors manufactured using it exhibit high energy resolution, spatial resolution, and detection efficiency. They also have the advantage of operating at room temperature. CZT array detectors, furthermore, demonstrate outstanding spatial detection and three-dimensional imaging capabilities. Researchers worldwide have conducted extensive studies on this subject. This paper, building upon this foundation, provides a comprehensive analysis of CZT crystals and CZT array detectors, summarizes existing research to offer valuable insights for envisioning new detector methodologies.

Pathological Brain Detection (PBD) is a crucial field aimed at identifying and diagnosing structural or functional abnormalities in the brain related to neurological, neurodegenerative, or psychiatric disorders. This detection process typically employs medical imaging technologies such as MRI, CT, or PET scans, along with neurological evaluations, blood tests, and other diagnostic tools. Early detection is essential for effective treatment, improving prognosis, and enhancing the quality of life for affected individuals. Each common computational method provides unique insights into brain pathologies. Despite significant advancements in technology and methodology, PBD faces challenges such as variability in brain anatomy, the complexity of disorders, data quality, standardization issues, interpretability of models, and ethical concerns. Addressing these challenges necessitates collaboration among researchers, clinicians, and policymakers to develop robust and ethical methods for improving the detection and diagnosis of brain disorders.

In this research, 117,718 ionospheric perturbations, with a space size (t) of 20–300 s but no limit on amplitude (A) have been automatically searched globally by a software from ion density data measured by the DEMETER satellite for more than 6 years. The influence of the solar activity on the ionosphere has been firstly examined and the results have presented that the solar activities can globally enhance ionospheric irregularities but rarely induce plasma variations more than 100%. A statistical work has been performed on ion PERs to check their dependence on local time and it is shown that there are 24.8% perturbations appeared in daytime (10:30 LT) and 75.2% ones in nighttime (22:30 LT). Ionospheric fluctuations with an absolute amplitude A < 10% tend to be background variations and the percentages of positive perturbations with small A < 20% are 64% in daytime and 26.8% in nighttime, respectively, but this number is revers for mid-large amplitude PERs. There is a demarcation point in space size t = 120 s and occurrence probabilities of day PERs are always higher than that of nighttime ones before this point while this trend is contrary after this point. Distributions of PER according to various amplitudes or space scales have been characterized by typical seasonal variations either in daytime or in nighttime. The EIA only exists in dayside equinox and winter occupying two lowlatitude crests with lower Np. The huge WSA appears in all periods except for dayside summer full of PERs with enhanced amplitude, especially in winter night. The WN-like structure can be obviously figured out in all seasons showing absolutely space large-scales. In the meanwhile, several magnetic anomalous zones of planetary scale non-dipole fields, such as the SAMA, Northern Africa anomaly, and so on, have been also successfully detected by extreme negative ion perturbations in this time.

During a multi-detector computed tomography (MDCT) examination, it is crucial to efficiently organize, store, and transmit medical images in DICOM standard, which requires significant hardware resources and memory. Our project processed large amounts of DICOM images by classifying them based on cross-section views that may carry important information about a possible diagnosis. We ensured that images were retained and saved in PNG format to optimize hardware resources while preserving patient confidentiality. Furthermore, we have developed a graphical, user-friendly interface that allows physicians to visualize specific regions of interest in a patient's brain where changes may indicate disease. Our proposed method enables quick classification of medical images into predefined classes of confirmed diseases of brain parenchyma, contributing to swift decision-making for further diagnosis for more precisely evaluating and characterizing brain changes, and it can lead to the rapid application of adequate therapy, which may result in better outcomes.

Traditional underground pipeline inspection primarily relies on closed-circuit television (CCTV) systems, capturing visual data of deformations within sewer systems for manual assessment of their types and severity. However, these methods heavily rely on human expertise, which leads to subjective detection with limited accuracy. Moreover, they lack the capability for quantitative analysis of deformation extent, hindering accurate assessments and limiting overall inspection effectiveness. To address these challenges, this paper proposes a method for quantitatively detecting geometric deformations in underground pipe corridors using laser point cloud data. The approach, employing laser scanning with a 3D scanner, enables objective detection of internal pipeline deformations and quantitative assessment of blockage levels. In comparison to traditional CCTV-based methods, this approach offers advantages in objectivity and quantification, thereby improving detection reliability, accuracy, and overall efficiency.

In recent years, significant advancements in the field of machine learning have influenced the domain of image restoration. While these technological advancements present prospects for improving the quality of images, they also present difficulties, particularly the proliferation of manipulated or counterfeit multimedia information on the internet. The objective of this paper is to provide a comprehensive review of existing inpainting algorithms and forgery detections, with a specific emphasis on techniques that are designed for the purpose of removing objects from digital images. In this study, we will examine various techniques encompassing conventional texture synthesis methods, as well as those based on neural networks. Furthermore, we will explore the artifacts associated with the identification of modified photos and present the artifacts frequently introduced by the inpainting procedure and assess the state-of-the-art technology for detecting such modifications. Lastly, we shall look at the available datasets and how the methods compare with each other. Having covered all of the above, the final outcome of this study is to provide a comprehensive perspective on the abilities and constraints to detect images for which an inpainting object removal method was applied.

The rate of accidents in Morocco is experiencing a significant increase. Automatic license plate detection and recognition (ALPR) is an essential road safety technology. It facilitates applications such as traffic control, law enforcement, and toll collection by allowing for the automated recognition of vehicles on the road. In this study, we incorporated ShuffleNet V2 into the end-to-end YOLOV5 object detection system. The objective was to develop a model capable of identifying Moroccan license plates with an accuracy of 87%. The proposed model is intended to attain a high processing performance of 60 frames per second (FPS) while maintaining a low weight of 1.3 megabytes (MB) and a parameter count of 0.44 million floating point operations (MGFLOP). Our model maintains superior performance and is highly compatible with embedded systems compared to other models utilized in the same context.

Nanoparticle-assisted polymerase chain reaction (nanoPCR) is a novel method for rapid detection of pathogens. A sensitive and specific multiple nanoPCR assay was developed for simultaneous detection of three subgroups avian leucosis virus (ALV). In this study, three pairs of primers that were designed based on gp85 gene sequences of subgroup A, B and J, optimizations were carried out for better performance of the nanoPCR assay and remarkably improved the detection limit of the assay. The detection limit of the assay was 101copies/μl, which was 100-fold more sensitive than conventional PCR assays. The nanoPCR assay amplified the specific 336 bp, 625 bp and 167 bp fragments of ALV-A, -B and –J respectively and no cross-reactivity were found with the genomic DNA or cDNA of Newcastle disease virus, avian infectious laryngotracheitis virus, Marek's disease virus, infectious bronchitis vaccine, infectious bursal disease virus and avian encephalomyelitis Virus. To evaluate the detection ability of the assay, 186 clinical samples were detected by nanoPCR and the detection results were further confirmed by sequencing. The sequencing results were 100% in coincidence with the nanoPCR detection results, suggesting the possibility of clinical application of the newly developed nanoPCR assay. Taking all the results together, a highly specific and sensitive nanoPCR was successfully developed, which could be useful for rapid diagnosis of ALV in poultry farming.

Food safety is a significant issue that affects people worldwide and is tied to their lives and health. The issue of pesticide residues in food is just one of many issues related to food safety, which leave residues in crops and are transferred through the food chain to human consumption. Foods contaminated with pesticide residues pose a serious risk to human health, including carcinogenicity, neurotoxicity and endocrine disruption. Although traditional methods including gas chromatography, high-performance liquid chromatography, chromatography and mass spectrometry can be used to achieve quantitative analysis of pesticide residues, the disadvantages of these techniques, such as being time-consuming and costly and requiring specialist staff, limit their application. Therefore, there is a need to develop rapid, effective and sensitive equipment for the quantitative analysis of pesticide residues in food. Microfluidics is rapidly emerging in a number of fields due to its outstanding strengths. This paper summarizes the application of microfluidic techniques to pyrethroid, carbamate, organochlorine and organophosphorus pesticides, as well as to commercial products. Meanwhile, the paper also outlines the development of microfluidics in combination with 3D printing technology and nanomaterials for the detection of pesticide residues in food.

This study reports the design of a dielectric resonator (DR) metasurface-based terahertz biosensor for rapid and accurate detection of different kinds of viruses (H1N1, SARA-COV-2, etc.). The characterization of the sensor is done by analyzing its absorbance properties with and without the presence of the H1N1 virus layer of different concentrations and electrical properties in the frequency range of 2.4 THz to 3 THz. A full-wave EM model of the sensor is designed using CST MWS software. The geometrical parameters of the proposed biosensor, as well as its dielectric constant of the virus swab, are varied to achieve good performance with an absorption level close to 1 (100%). A significant change in the resonating pick-up frequency owing to the variation in the effective refractive index of the realized sensor ensures the detection and classification of the different concentrations of the same or different viruses. The presented design could be used for the rapid detection of viruses with the added advantages of contactless, label-free, and accurate identification of different concentrations of viruses.

Diffusion in recent decades of Cannabis sativa L. varieties with low concentrations of tetrahydrocannabinol (THC) is leading to a specialization in the whole sector, requiring innovative techniques for input optimization according to the variety and the growing environment. The continuous agricultural evolution aims at increasing the sustainability of cultivation systems, pushing toward precision technologies application for inputs management. Cannabis monitoring can benefit from Unmanned Aerial Systems applications combined with image thresholding techniques for reliable and effective near-real-time plant detection and numbering. The work compares and evaluates the potential of two threshold segmentation techniques for Cannabis plant detection and counting in two experimental fields in Italy on a multitemporal scale, bringing such techniques in competition with machine learning for object detection. The Otsu segmentation technique demonstrated more reliable performances at the early stage of cultivation with an accuracy of 0.95. The Canopy Height Model technique showed increasing performances during the growing season. Future works will compare thresholding segmentation techniques with machine learning (ML) approaches and their potential as a supporting tool for ML image annotation.

This study compares the performance of existing studies on multimodal emotion recognition, and proposes a model that fuses two modalities with the speaker's text and voice signals as input values and detects depression. Based on the DAIC-WOZ dataset, voice features were extracted using CNN, text features were extracted using Transformers, and two modalities were fused through a tensor fusion network. We also build a model to detect whether the speaker is depressed or not using LSTM in the final layer. This study suggests the possibility of increasing access to mental illness diagnosis by enabling patients to detect depression on their own in daily conversations. If the model proposed in this study is developed and the voice conversation system is connected, it will be easier for patients who cannot visit the hospital periodically or who are reluctant to visit the hospital to check their condition and seek recovery. Furthermore, it can be expanded to multi-label classification for various mental diseases and used as a simple self-mental disease diagnosis tool.

The increasing use of deep learning techniques to manipulate images and videos, commonly referred to as "deepfakes," is making more and more challenging to differentiate between real and fake content. While various deepfake detection systems have been developed, they often struggle to detect deepfakes in real-world situations. In particular, these methods are often unable to effectively distinguish images or videos when these are modified using novel techniques which have not been used in the training set. In this study, we carry out an analysis of different deep learning architectures in an attempt to understand which is more capable of better generalizing the concept of deepfake. According to our results, it appears that Convolutional Neural Networks (CNNs) seem to be more capable of storing specific anomalies and thus excel in cases of datasets with a limited number of elements and manipulation methodologies. The Vision Transformer, conversely, is more effective when trained with more varied datasets, achieving more outstanding generalization capabilities than the other methods analysed. Finally, the Swin Transformer appears to be a good alternative for using an attention-based method in a more limited data regime. All the analyzed architectures seem to have a different way to look at deepfakes but since in a real-world environment, the generalization capability is essential, based on the carried out experiments the Vision Transformer seems to provide superior performances.

(1) Background: As Patient-reported outcome measures face challenges with low response rate on surveys, different incentive mechanism have been proposed to achieve a higher response rate. However, it seems that monetary incentives are the only mechanism with proven effect. Nevertheless, it is less likely to be used than other mechanisms due to the monetary cost. (2) Methods: In this research work, a cryptographic scheme for rewarding patients with cryptographic tokens is developed and implemented on the Ethereum test network. (3) Results: The model is able to distribute decentralised tokens to patients who complete the PROMs in a fair, private, decentralised approach. The token can be further used by patients to exchange more healthcare services, encouraging more patients to participate in PROMs. At the same time, an IER detection method is built to improve the quality of PROMs, avoiding the healthcare provider paying for meaningless PROMs from patients who barely participate for incentives. (4) Conclusions: This work provides an privacy-preserving incentive model to increase the response rate for PROMs surveys. Our model prevents patients providing invalid responses to gain rewards.

American Sign Language is a popular language for deaf individuals. Communication is made easier for these people through sign language. However, in a digital era like today, there is a need for these people to be able to communicate online, and even get help from technology to communicate in person with non sign language speakers. This research will present a program able to translate American sign language to plain English. This study aims to use the OpenCV library to recognize hand signals, also a trained model to identify images so that the program can then translate them to words and letters. The program uses a data set of over 2000 images which will be in this case the largest data set available. With over 90\% of accuracy it results in a basic computer program with the largest data set available that would make possible for users to communicate with a wide variety of words and expressions.

Carton detection is an important technique in the automatic logistics system and can be applied to many applications such as the stacking and unstacking of cartons, the unloading of cartons in the containers. However, there is no public large-scale carton dataset for the research community to train and evaluate the carton detection models up to now, which hinders the development of carton detection. In this paper, we present a large-scale carton dataset named Stacked Carton Dataset (SCD) with the goal of advancing the state-of-the-art in carton detection. Images are collected from the Internet and several warehouses, and objects are labeled using per-instance segmentation for precise localization. There are total of 250,000 instance masks from 16,136 images. Naturelly, a suite of benchmarks are established with several popular detectors. In addition, we design a carton detector based on RetinaNet by embedding our proposed Offset Prediction between Classification and Localization module (OPCL) and Boundary Guided Supervision module (BGS). OPCL alleviates the imbalance problem between classification and localization quality which boosts AP by 3.1%∼4.7% on SCD at the model level while BGS guides the detector to pay more attention to boundary information of cartons and decouple repeated carton textures at the task level. To demonstrate the generalization of OPCL to other datasets, we conduct extensive experiments on MS COCO and PASCAL VOC. The improvements of AP on MS COCO and PASCAL VOC are 1.8%∼2.2% and 3.4%∼4.3% respectively. Source dataset is available here.

In this review paper, an overview of the application of n-type 4H-SiC Schottky barrier diodes (SBDs) as radiation detectors is given. We have chosen 4H-SiC SBDs among other semiconductor devices such as PiN diodes or metal-oxide-semiconductor (MOS) structures, as significant progress has been achieved in radiation detection applications of SBDs in the last decade. Here, we present the recent advances at all key stages in the application of 4H-SiC SBDs as radiation detectors, namely: SBDs fabrication, electrical characterization of SBDs, and their radiation response. Main achievements are highlighted, and main challenges are discussed.

Early detection improves prognosis in pancreatic ductal adenocarcinoma (PDAC) but is challenging as lesions are often small and poorly defined on contrast-enhanced computed tomography scans (CE-CT). Deep learning can facilitate PDAC diagnosis, however current models still fail to identify small (&lt;2cm) lesions. In this study, state-of-the-art deep learning models were used to develop an automatic framework for PDAC detection, focusing on small lesions. Additionally, the impact of integrating surrounding anatomy was investigated. CE-CT scans from a cohort of 119 pathology-proven PDAC patients and a cohort of 123 patients without PDAC were used to train a nnUnet for automatic lesion detection and segmentation (nnUnet_T). Two additional nnUnets were trained to investigate the impact of anatomy integration: (1) segmenting the pancreas and tumor (nnUnet_TP), (2) segmenting the pancreas, tumor, and multiple surrounding anatomical structures (nnUnet_MS). An external, publicly available test set was used to compare the performance of the three networks. The nnUnet_MS achieved the best performance, with an area under the receiver operating characteristic curve of 0.91 for the whole test set and 0.88 for tumors &lt;2cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.

Blockchain-based currencies or cryptocurrencies have become a global phenomenon known to most people as a disruptive technology, and a new investment vehicle. However, due to their decentralized nature, regulating these markets has presented regulators with difficulties in finding a balance between nurturing innovation, and protecting consumers. The growing concerns about illicit activity have forced regulators to seek new ways of detecting, analyzing, and ultimately policing public blockchain transactions. Extensive research on machine learning, and transaction graph analysis algorithms has been done to track suspicious behaviour. However, having a macro view of a public ledger is equally important before pursuing a more fine-grained analysis. Benford’s law, the law of first digit, has been extensively used as a tool to discover accountant frauds (many other use cases exist). The basic motivation that drove our research presented in this paper was to test he applicability of the well established method to a new domain, in this case the identification of anomalous behavior using Benford’s law conformity test to the cryptocurrency domain. The research focused on transaction values in all major cryptocurrencies. A suitable time-period was identified that was long enough to sport sufficiently large number of observations for Benford’s law conformity tests and was also situated long enough in the past so that the anomalies were identified and well documented. The results show that most of the cryptocurrencies that did not conform to Benford’s law had well documented anomalous incidents, the first digits of aggregated transaction values of all well known cryptocurrency projects were conforming to Benford’s law. Thus the proposed method is applicable to the new domain.

The zoonotic disease anthrax caused by the endospore-forming bacterium Bacillus anthracis is very rare in Germany. In the state of Bavaria, the last case occurred in July of 2009 resulting in four dead cows. In August of 2021, the disease reemerged after heavy rains, killing one gestating cow. Notably, both outbreaks affected the same pasture, suggesting a close epidemiological connection. B. anthracis could be grown from blood culture and the presence of both virulence plasmids (pXO1 and pXO2) were confirmed by PCR. Also, recently developed diagnostic tools enabled rapid detection of B. anthracis cells and nucleic acids directly in clinical samples. The complete genome of the strain isolated from blood, designated BF-5, was DNA-sequenced and phylogenetically grouped within the B.Br.CNEVA clade that is typical for European B. anthracis strains. The genome was almost identical to BF-1, the isolate of 2009, separated only by three single nucleotide polymorphisms on the chromosome, one on plasmid pXO2 and three indel-regions. Further, B. anthracis DNA was detected by PCR from soil-samples taken from spots, where the cow had fallen onto the pasture. New tools based on phage receptor binding proteins enabled the microscopic detection and isolation of B. anthracis directly from soil-samples. These environmental isolates were genotyped and found to be SNP-identical to BF-1. Therefore, it seems that the BF-5 genotype is currently the prevalent one at the affected premises. The contaminated area was subsequently disinfected with formaldehyde.

Klebsiella pneumonia (K. pneumoniae) is a Gram-negative bacterium that causes nosocomial infections in the lung, bloodstream, and urinary tract. Therefore, detecting K. pneumoniae in early time is important in preventing severe infections. However, clinical detection of K. pneumoniae requires a long time of agar plate culture. Nucleic acid detection like qPCR is precise but requires expensive equipment. Recent research reveals that collateral cleavage activity of CRISPR-LbCas12a has been applied in nucleic acid detection. In this study, PCR combined with CRISPR-LbCas12a targeting the K. pneumoniae system was established. This system showed excellent detection specificity and sensitivity in both bench work and clinical samples. Due to its advantages, its application can meet different detection requirements in health centers where qPCR is not accessible.

The rapid infiltration of fake news is a flaw to the otherwise valuable internet, a virtually global network that allows for the simultaneous exchange of information. While a common, and normally effective, approach to such classification tasks is designing a deep learning-based model, the subjectivity behind the writing and production of misleading news invalidates this technique. Deep learning models are unexplainable in nature, making the contextualization of results impossible because it lacks explicit features used in traditional machine learning. This paper emphasizes the need for feature engineering to effectively address this problem: containing the spread of fake news at the source, not after it has become globally prevalent. Insights from extracted features were used to manipulate the text, which was then tested on deep learning models. The original unknown yet substantial impact that the original features had on deep learning models was successfully depicted in this study.

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

The end of 2019 marked a bushfire crisis for Australia that affected more than 100000km2 of land and destroyed more than 2000 houses. Here, we propose a method of in-orbit bushfire detection with high efficiency to prevent a repetition of this disaster. An LEO satellite constellation is first developed through NSGA-II (Nondominated Sorting Genetic Algorithm II), optimising for coverage over Australia. Then edge computing is adopted to run a bushfire detection algorithm using several constellation satellites as edge nodes to reduce fire detection time. A geostationary satellite is used for inter-satellite communications, such that an image taken by a satellite can be distributed among several satellites for processing. The geostationary satellite also maintains a constant link to the ground, so that a bushfire detection can be reported back without any significant delay. Overall, this system is able to detect fires that span more than 5m in length, and can make detections in 1.39s per image processed. This is faster than any currently available bushfire detection method.

Identifying fake news on the media has been an important issue. This is especially true considering the wide spread of rumors on the popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

Traditional applications of Interferometric Synthetic Aperture Radar (InSAR) data involved inverting an interferogram stack to determine the average displacement velocity. While this approach has useful applications in continuously deforming regions, much information is lost by simply fitting a line through the time series. Thanks to regular acquisitions across most of the the world by the ESA Sentinel-1 satellite constellation, we are now in a position to explore opportunities for near-real time deformation monitoring. In this paper we present a simple statistical approach for detecting offsets and gradient changes in InSAR time series. Our key assumption is that 5 years of Sentinel-1 data is sufficient to calculate the population standard deviation of the detection variables. Our offset detector identifies statistically significant peaks in the first, second and third difference series. The gradient change detector identifies statistically significant movements in the second derivative series. We exploit the high spatial resolution of Sentinel-1 data and the spatial continuity of geophysical deformation signals to filter out false positive detections that arise due to signal noise. When combined with near-real time processing of InSAR data these detectors, particularly the gradient change, could be used to detect incipient ground deformation associated with geophysical phenomena, for example from landslides or volcanic eruptions.

Generic object detection is one of the most important and flourishing branches of computer vision and has real-life applications in our day to day life. With the exponential development of deep learning-based techniques for object detection, the performance has enhanced considerably over the last 2 decades. However, due to the data-hungry nature of deep models, they don't perform well on tasks which have very limited labeled dataset available. To handle this problem, we proposed a transfer learning-based deep learning approach for detecting multiple pigs in the indoor farm setting. The approach is based on YOLO-v2 and the initial parameters are used as the optimal starting values for train-ing the network. Compared to the original YOLO-v2, we transformed the detector to detect only one class of objects i.e. pigs and the back-ground. For training the network, the farm-specific data is annotated with the bounding boxes enclosing pigs in the top view. Experiments are performed on a different configuration of the pen in the farm and convincing results have been achieved while using a few hundred annotated frames for fine-tuning the network.

Wideband signal detection is an important problem in wireless communication. With the rapid development of deep learning (DL) technology, some DL-based methods are applied to wireless technology, and the effect is obvious. In this paper, we propose a novel neural network for multi-type signal detection that can locate signals and recognize signal types in wideband spectrogram. Our network utilizes the key point estimation to locate the rough centerline of signal region and identify class. Then, several regressions are carried out to achieve properties, such as local offset and border offsets of bounding box, which is further synthesized for a more fine location. Experimental results demonstrate that our method performs more accurate than other DL-based object detection methods previously employed for the same detection task. Specifically, our method runs obviously faster than existing methods, and abandons the anchor generation, which makes it more favorable for real-time applications.

Critical Infrastructures and associated real time Informational systems need some security protection mechanisms that will be able to detect and respond to possible attacks. For this reason, Anomaly Detection Systems (ADS), as part of a Security Information and Event Management (SIEM) system, are needed for constantly monitoring and identifying potential threats inside an Information Technology (IT) System. Typically, ADS collect information from various sources within a CI system using security sensors or agents and correlate those information so as to identify anomaly events. Such sensors though in a CI setting (factories, power plants, remote locations) may be placed in open areas and left unattended thus becoming targets themselves of security attacks. They can be tampering and malicious manipulated so that they provide false data that may lead an ADS or SIEM system to falsely comprehend the CI current security status. In this paper, we describe existing approaches on security monitoring in critical infrastructures and focus on how to collect security sensor - agent information in a secure and trusted way. We then introduce the concept of hardware assisted security sensor information collection that improve the level if trust (by hardware means) and also increase the responsiveness of the sensor. Thus, we propose a Hardware Security Token (HST) that when connected to a CI Host, it acts as a secure anchor for security agent information collection. We describe the HST functionality, its association with a host device, its expected role and its log monitoring mechanism. We also provide information on how security can be established between the Host device and the HST.Then, we introduce and describe the necessary Host components that need to be established in order to guarantee a high security level and correct HST functionality. We, also provide a realization-implementation of the HST overall concept in a FPGA SoC evaluation board and describe how the HST implementation can controlled. Finally, we provide indicative use case scenarios of how the HST can be used in practice to provide a variety of different security services beyond acting as a secure ADS sensor.

Standard Ethernet (IEEE 802.3 and the TCP/IP protocol suite) is gradually applied in industrial control system (ICS) with the development of information technology. It breaks the natural isolation of ICS, but contains no security mechanism. A modified intrusion detection system (IDS), which is strongly correlated to specific industrial scenario, is necessary for modern ICS. On the one hand, this paper outlines attack models, including infiltration attacks and our creative forging attack. On the other hand, we proposes a hierarchical IDS, which contains a traffic prediction model and an anomaly detection model. The traffic prediction model, which is based on autoregressive integrated moving average (ARIMA), can forecast the traffic of ICS network in the short term and precisely detect the infiltration attacks according to abnormal changes in traffic pattern. The anomaly detection model using one-class support vector machine (OCSVM) is able to detect malicious control instructions by analyzing the key field in EtherNet/IP packets. The experimental results show that the hierarchical IDS has an outstanding performance in detecting infiltration attacks and forging attack compared with other two innovative IDSs.

We demonstrate, for the first time, a highly sensitive detection of 4-methylimidazole (4-MeI), a carcinogenic material, by applying an electric field enhancement technique using a terahertz (THz) metamaterial at the THz region. The THz metamaterials were fabricated with a metal array using an electric-field-coupled inductor-capacitor (ELC) resonator structure, and FDTD simulation showed good agreement with experimental results. We measured the THz spectra of the metamaterials to detect 4-MeI concentrations of 0, 1, 2, 5, 10, 15, and 20 mg/L. The resonance frequency of the metamaterial was shifted by approximately 8 GHz and transmittance at the resonance frequency increased to 2 x 10-3 as the concentration was increased, up to 20 mg/L. Our study provides new insight into application of metamaterials to detect carcinogen using a THz technique.

This paper is devoted to change-point detection using only the ordinal structure of a time series. A statistic based on the conditional entropy of ordinal patterns characterizing the local up and down in a time series is introduced and investigated. The statistic requires only minimal a priori information on given data and shows good performance in numerical experiments.

A novel virus with distinct genome features was discovered by high throughput sequencing in a symptomatic blackcurrant plant. The virus tentatively named as blackcurrant virus A (BCVA) has distinct genome organization and molecular features bridging genera in the order Tymovirales. The genome consists of 7106 nucleotides excluding the poly(A) tail. Five open reading frames were identified with the first encoding a putative viral replicase with methyl transferase (MTR), AlkB, helicase and RNA dependent RNA polymerase (RdRp) domains. The other four putative proteins exhibit no significant homology to other virus proteins. The genome organization downstream of the replicase resembles that of members of the order Tymovirales with an unconventional triple gene block (TGB) movement protein arrangement. Phylogenetic analysis using replicase conserved motifs loosely placed BCVA within the Betaflexiviridae whereas it was evolutionarily distant to existing members of the family when using the putative TGBp 1-like and coat protein sequences. Our analysis strongly suggests that BCVA is a novel virus that should be classified as a species in a new genus in the Betaflexiviridae or a new family in the order Tymovirales.

Fire is a serious security threat that can lead to casualties, property damage, and environmental damage. However, despite the availability of object detection algorithms, challenges persist in detecting fires and smoke. These challenges include slow convergence speed, poor performance in detecting small targets, and high computational cost limiting deployments. In this paper, Fire smoke and human detection based on ConvNeXt and Mixed encoder (FCM-DETR), an end-to-end object detection algorithm based on Deformable DETR, is proposed. Firstly, we introduce ConvNeXt to take the place of Resnet, which greatly reduces the amount of computation and improves the ability to extract irregular flame features. Secondly, to effectively process multi-scale features, the original encoder is decoupled into two modules. Then Mixed encoder, an innovative encoder structure, is proposed, resulting in excellent performance of multi-scale fire and smoke features fusion. What can’t be overlooked is that the encoder block is compatible with any DETR-based models. Finally, the convergence speed is accelerated and the mean of average precision is improved by applying a novel loss function called Powerful IoU v2. The experimental results indicate that our model achieves the best detection accuracy compared to other models, with mAP reaching 66.7%, mAPs and Accuracyfire achieving impressive 50.2% and 98.05%, respectively.

Based on recent popular money priming research results, which conclude that money makes self-sufficient (e.g. less interest in other people), we assumed that people are less interested in finding out whether others are lying or telling the truth. In a laboratory experiment, 163 students (85 women, 78 men, M_Age = 23.08, ranging from 18 to 36 years) were primed by actively handling money (versus paper sheets). Afterwards, they classified 24 video statements as true or deceptive (senders describing their most/least favorite movie), rated their classification confidence for each decision and then answered control questions. Results revealed no influence of priming condition on judgmental bias, classification accuracy, and classification confidence. Also the level of self-reported motivation to find out who lied or told the truth did not differ between conditions. Higher motivation was correlated to higher classification confidence. Additionally, and in line with Reinhard (2010) and Reinhard et al. (2011), higher classification accuracy correlated to a higher use of verbal content cues for classification decisions. Thus, while we were able to replicate these findings, our results contradict the assumption of a money prime influence on lie detection ability. Concluding, our results make self-sufficiency in this context questionable and offer next steps for research.

Leakages in the water distribution networks (WDNs) are real problems for utilities and other governmental agencies. Timely leak detection and location identification has been a challenge. In this paper, an integrated approach to geospatial and infrared image processing method was used for robust leak detection. The method combines drops in flow, pressure, and chlorine residuals to determine potential water leakage locations in the WDN using Geographic Information System (GIS) techniques. GIS layers were created from the hourly values of these three parameters for the city of Sharjah provided by Sharjah Electricity, Water and Gas Authority (SEWA). These layers are then analyzed for locations with dropped values of each of the parameters and are overlaid with each other. In the case where there were no overlaying locations between flow and pressure, further water quality analysis was avoided, assuming no potential leak. In the case where there are locations with drops in flow and pressure layers, these overlaying locations are then examined for drops in chlorine values. If overlaying locations are found, then these regions are considered potential leak locations. Once potential leak locations are identified, a specialized remote sensing technique can be used for precise leak location. This study also demonstrated the suitability of using an infrared camera for leak detection in a laboratory-based setup. This paper concludes that the following methodology can help water utility companies in the timely detection of leaks, saving money, time, and effort.

Unmanned Aerial Vehicles (UAVs) image object detection has great application value in military and civilian fields. However, the objects in the captured images from UAVs have problems of large scale variation, complex backgrounds, and a large proportion of small objects. To resolve these problems, a multi-scale object detector based on coordinate and global information aggregation is proposed, named CGMDet. Firstly, a Coordinate and Global Information Aggregation Module (CGAM) is designed by aggregating local, coordinate, and global information, which can obtain features with richer context information. Secondly, a Multi-Feature Fusion Pyramid Network (MF-FPN) is proposed, which can better fuse features of different scales and obtain features containing more context information through repeated use of feature maps, to better detect multi-scale targets. Moreover, more location information of low-level feature maps is integrated to improve the detection results of small targets. Furthermore, we modified the bounding box regression loss of the model to make the model more accurately regress the bounding box and faster convergence. Finally, the proposed CGMDet was tested on VisDrone and UAVDT datasets and mAP0.5 of 50.9% and 48% was obtained, respectively. At the same time, our detector achieved the best results compared to other detectors.

Nanotechnology and polymer engineering are steering towards a new development to invade deleterious mysteries. In the last few decades, polymer engineering has grabbed researchers’ attention and similarly, polymeric network-engineered structures have been vastly studied. Prior to therapeutic application, early and quick detection analyses are critical. Therefore, developing nanoscale sensors to manage the acute expression of feeble states and malignancies to draw therapeutic lines demands advanced nanoengineering. In spite of nano-therapeutics have emerged as an alternative approach to tackling strenuous diseases. Also, studies have shown highly biocompatible biomedical engineering has emerged with sheer progression. Moreover, hydrogels have emerged as a three-dimensional (3D) polymeric network that consists of hydrophilic natural or synthetic polymers. The resemblance of hydrogels with tissue structure makes it more unique to study inquisitively. Preceding studies have shown a vast spectrum of synthetic and natural polymer deployment in the field of biotechnology and molecular diagnostics. This review explores recent studies on synthetic and natural polymer engineered hydrogel-based biosensors and their applications in multipurpose diagnostics and therapeutics. We reviewed the latest studies on hydrogel-engineered biosensors, exclusively DNA-based and DNA hydrogels fabricated biosensors.

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to detect objects, namely lost/forgotten items to inform the passengers, and aggressive items to monitoring if violent actions may arise between passengers. For object detection algorithms was used public datasets (COCO and TAO) to train state-of-the-art algorithms, such as YOLOv5. For violent action detection was used the MoLa InCar dataset to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN and TSM. At the end an embedded automotive solution was used to demonstrate both methods running in real-time.

This paper provides a concise review of remote sensing of ocean fronts and its applications in marine ecology and fisheries, with a particular focus on the most popular front detection algorithms/techniques: Canny (1986), Cayula and Cornillon (1990, 1992, 1995), Miller (2004, 2009), Shimada et al. (2005), Belkin and O’Reilly (2009), and Nieto et al. (2012). A case is made for feature-based approach in marine ecology and fisheries that emphasizes fronts as major structural and circulation features of the ocean realm that play key roles in various aspects of marine ecology.

Bioimpedance measurements are used increasingly in health applications because bioelectric parameters have been associated with anatomical and physiological properties, thus enabling to distinguish medical conditions. For bone fracture diagnostics, nevertheless, there is no established non-invasive method. Ex vivo studies and In vivo bioimpedance procedures, both invasive and non-invasive, on mammalians long bones are associated with promising results. In this work, out of a total of 568 papers, we reviewd 59 articles that mention long bone integrity by electric properties, be it Bioimpedance Analysis, Electrical Impedance Spectroscopy or Electrical Impedance Tomography. The papers are described in three sections, “Ex vivo measurements”, “In vivo invasive measurements” and “In vivo non-invasive measurements”. This review allows to establish the basics to planning the development of new technology to detect bone fracture via bioimpedance measurements.

This paper presents the results of an experimental investigation about target detecting with passive sonar in Persian Gulf. Detecting propagated sounds in the water is one of the basic challenges of the researchers in sonar field. This challenge will be complex in shallow water (like Persian Gulf) and noise less vessels. Generally, in passive sonar the targets are detected by sonar equation (with constant threshold) which increase the detection error in shallow water. Purpose of this study is proposed a new method for detecting targets in passive sonars using adaptive threshold. In this method, target signal (sound) is processed in time and frequency domain. For classifying, Bayesian classification is used and prior distribution is estimated by Maximum Likelihood algorithm. Finally, target was detected by combining the detection points in both domains using LMS adaptive filter. Results of this paper has showed that proposed method has improved true detection rate about 27% compare other the best detection method.

The safe and reliable operation of autonomous vehicles in complex and dynamic environments is heavily dependent upon exteroceptive and proprioceptive sensors. A LiDAR system generates accurate 3D point clouds, which are crucial for the detection, classification, and tracking of multiple targets. LiDAR data, however, presents significant challenges due to its density, noise, and varying sampling rates. In this study, various clustering and MTT techniques for LiDAR point clouds will be identified and classified within the context of autonomous driving to assess the state-of-the-art methods’ key challenges and their performances. We have categorized clustering and MTT methods used in AV applications, identified research gaps and challenges and analyzed existing algorithms and their challenges in detail. Researchers and practitioners in the field of autonomous driving will find this review to be a valuable resource.

An energy model that correlates fan airflow, head, speed, and system power input is essential to detect device faults and optimize control strategies in fan systems. Since the application of variable frequency drives (VFDs) makes the motor efficiency data published by manufacturers inapplicable, the fan efficiency and drive (belt-motor-VFD) efficiency must be identified for each individual system to obtain accurate energy models. The objectives of this paper are to identify an energy model of existing VFD-motor-fan systems using available experimental data and demonstrate its applications in loose belt fault detection and virtual airflow meter development for optimal control. First, an approach is developed to identify the fan head, fan efficiency and drive efficiency curves using available fan head, speed, and system power input as well as temporarily measured airflow rate without measuring shaft power. Then the energy model is identified for an existing VFD-motor-fan system. Finally, the identified model is applied to detect the slipped belt faults and develop the virtual airflow meter. The experiment results reveal that the developed approach can effectively obtain the energy model of VFD-motor-fan systems and the model can be applied to effectively detect slipped belt faults and accurately calculate the fan airflow rate.

The aim of this study was to determine the extent to which the Tyme Wear smart shirt is as reliable and valid in detecting personalized ventilatory thresholds when compared to the Parvo Medics TrueOne 2400. In this validation study, 19 subjects were recruited to conduct two graded exercise test (GXT) trials. Each GXT trial was separated by seven to ten days of rest. During the GXT, gas exchange and heart rate data were collected by the TrueOne 2400 (TRUE) in addition to the ventilation data collected by the Tyme Wear smart shirt (S-PRED). Gas exchange data from TRUE was used to detect VT1 and VT2. TRUE and S-PRED VT1 and VT2 were compared to determine the reliability and validity of the smart shirt. Of the 19 subjects, data from 15 subjects were used during analysis. S-PRED exhibited excellent (ICC &gt; 0.90) reliability for detection of VT1 and VT2 utilizing time point and workload and moderate (0.90 &gt; ICC &gt; 0.75 ) reliability utilizing heart rate. TRUE exhibited excellent reliability for detection of VT1 and VT2 utilizing time point, workload, and heart rate. When compared to TRUE, S-PRED appears to underestimate the VT1 workload (p &gt; 0.05) across both trials and heart rate (p &lt; 0.05) for trial 1. However, S-PRED appears to underestimate VT2 workload (p &lt; 0.05) and heart rate (p &lt; 0.05) across both trials. The result from this study suggests that the Tyme Wear smart shirt is less valid but is comparable in reliability when compared to the gold standard. Moreover, despite the underestimation of S-PRED VT1 and VT2, the S-PRED detected personalized ventilatory thresholds will provide an adequate training workload for most individuals. In conclusion, the Tyme Wear smart shirt provides easily accessible testing to establish threshold-guided training zones but does not devalue the long-standing laboratory equivalent.

A new type of gold nanoparticles was synthesized by using benzoyl pyrazolone as a capping agent. The synthesized AuNPs exhibited a spherical shape and a monodisperse and fluorescence emission characteristic peak at 650 nm. The AuNPs –BMPBP was demonstrated as sensitive and selective fluorescent chemosensor for detection of Al ³⁺ ion. In the presence of Al ³⁺ ion, the fluorescent emission of BMPBP-AuNPs at 650 nm, increased with an increasing concentration of Al ³⁺ ion with a low detection limit (2 µM), the proposed method provided to apply determination of Al ³⁺ ion of tap water with satisfactory results.

The constant increase in volume and wide variety of available Internet of Things (IoT) devices leads to highly diverse software and hardware stacks, which opens new avenues for exploiting previously unknown vulnerabilities. The ensuing risks are amplified by the inherent IoT resource constraints both in terms of performance and energy expenditure. At the same time, IoT devices often times generate or collect sensitive, real-time data used in critical application scenarios (e.g. health monitoring, transportation, smart energy, etc.). All these factors combined make IoT networks a primary target and potential victims for malicious actors. In this paper, we present a brief overview of existing attacks and defense strategies against urban IoT networks. The goal of this work is twofold: First, it presents a summary of some of the common attack vectors and the corresponding solutions available in the research literature. Then, the paper lays out a theoretical plan and a corresponding pipeline of steps (i.e. development and implementation process) for the design and application of the solutions encountered throughout the course of the research efforts. The end goal of following this plan is the deployment of the proposed IoT security measures in a real-world urban IoT infrastructure.

According to the risk investigations of being involved in an accident, alcohol-impaired driving is one of the major causes of motor-vehicles accidents. Preventing highly intoxicated persons from driving would potentially save many lives. This paper proposes a lightweight in-vehicle alcohol detection that processes the data generated from 6-alcohol sensors (MQ-3 Alcohol Sensors) using an optimizable shallow neural network (O-SNN). The experimental evaluation results exhibit a high-performance detection system scoring a 99.8% of detection accuracy with a very short inferencing delay of 2.22 µ seconds. Hence, the proposed model can be efficiently deployed and used to discover in-vehicle alcohol with high accuracy and low inference overhead as a part of the driver alcohol detection system for safety (DADSS) system aiming at massive deployment of alcohol sensing systems that could potentially save thousands of lives annually.