The necessity for precise and current data concerning the dynamics of land cover change in Indonesia is crucial for efforts to reduce natural vegetation cover due to agricultural expansion. The functionality of monitoring systems that incorporate Terra-MODIS is currently compromised by the limited availability of data for the immediate future. This study seeks to assess the potential of VIIRS satellite imagery in developing an early warning system for monitoring vegetation cover change in Indonesia. The Normalized Differential Open Area Index (NDOAI) computed from the 8-day’ VIIRS data was employed to detect changes in vegetation cover based on pixel-by-pixel subtraction in the NDOAI data time series. Evaluating the pixel-level accuracy of change detection is complicated due to the fact that we evaluate a change map at a coarser resolution than the Landsat-based reference map. The results revealed that increasing the threshold percentage is associated with improved accuracy. In change detection, there is often a trade-off between accuracy and sensitivity. A threshold that is too low may result in false positives, while a threshold that is too high may lead to missed changes. This study demonstrates that when a threshold value of less than 20% is applied, Landsat can identify vegetation cover changes at an earlier stage. Conversely, when a threshold value greater than 20% is employed, VIIRS will detect the change 4.5 days earlier than Landsat. Additionally, VIIRS is capable of detecting changes 25.4 days and 54.8 days faster than Landsat, respectively, when using thresholds of 40% and 75%.

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit (IMU) sensors installed as wearable device. The objective is to learn classification of multiple classes of human activities in real-time. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based, and distance-based, are employed to achieve the desired classification performance. A comparative study of these strategies has been presented in terms of classifiability and classification accuracies. The proposed system is shown to be computationally efficient, which is relevant in the context of limited computing resources on typical wearable devices. The trade-off between classification accuracy and computation complexity is analyzed for different algorithmic hyper-parameters and other system parameters. Extensive experimentation and simulation study have been conducted on a multi-user human activity data from the public do-main in order to validate the proposed learning paradigm.

For monitoring of chimeric antigen receptor (CAR) T-cell therapies antigen-based CAR detection methods are usually applied. However, for each target-antigen a separate detection system is required. Furthermore, when monitoring CAR T-cells in the blood of patients treated with bispecific antibodies or T-cell engagers (bsAbs/BiTEs) recognize the same antigen, these methods producing false-positive results in clinical diagnostics. Anti-CAR-linker monoclonal antibodies (mAbs) targeting the linker sequence between the variable domains of the antigen binding CAR fragment, promise an universal and unbiased CAR detection. To test this, we analyzed clinical specimens of all BCMA- and CD19 targeting CAR T-cell products currently approved for clinical use. We found a highly specific and sensitive CAR detection by using anti-CAR-linker mAb in blood cells from patients treated with Ide-cel, Tisa-cel, Axi-cel, Brexu-cel, and Liso-cel. For Ide-cel and Tisa-cel the sensitivity was significant lower compared to antigen-based CAR detection assays. Strikingly, the specificity of anti-CAR linker mAb was not affected by the simultaneous presence of bispecific blinatumomab or teclistamab for Axi-cel, Brexu-cel, Liso-cel or Ide-cel, respectively. Cilta-cel (containing an monomeric G4S-CAR linker) could not be detected by anti-CAR linker mAb. In conclusion, anti-CAR-linker mAbs are highly specific and useful for CAR T-cell monitoring but not universal applicable.

As cardiovascular diseases continue to be a leading cause of mortality, recent-ly, wearable devices for monitoring cardiac activity have gained much interest among medical community. This paper introduces an innovative ECG monitoring system based on a single – lead ECG machine enhanced with machine learning methods. The system only processes and analyses the ECG data, but also predict potential heart disease at an early stage. The wearable device was built on the ADS1298 and a microcontroller STM32L151xD. A server module based on REST API architecture style was designed to fa-cilitate interaction with web-based segment of the system. The module is responsible for receiving data in real time from microcontroller and their deliver to web – based segment. Algorithms for analyzing ECG signals have been developed, including band filter artifact removal, K-means clustering for signal segmentation, and PQRST analysis. Machine leaning methods as Isolation Forest have been employed for ECG anomaly detection. Moreover, a comparative analysis with various machine learning methods, including lo-gistic regression, random forest, SVM, XGBoost, decision forest and, CNNs was conducted to predict cardiovascular diseases. Convoluted Neural Networks (CNN) showed an accu-racy of 0.926, proving high effectiveness in ECG data process.

The paper aims at presenting the results obtained in the development of a system allowing the detection and monitoring of forest fires and the continuous comparison of their intensity when several events occur simultaneously, as usually happens in the European Mediterranean countries during the summer season. The system, called SFIDE (Satellite FIre DEtection), exploits a geostationary satellite sensor (SEVIRI on board of MSG satellite series). The algorithm was developed several years ago in the framework of a project (SIGRI) funded by the Italian Space Agency (ASI). This algorithm has been completely reviewed in order to enhance its efficiency by reducing false alarms rate preserving a high sensitivity. Due to the very low spatial resolution of SEVIRI images (4x4 km² at Mediterranean latitude) the sensitivity of the algorithm should be very high to detect even small fires. The improvement of the algorithm has been obtained by: introducing the sun elevation angle in the computation of the preliminary thresholds to identify potential thermal anomalies (hot spots), introducing a contextual analysis in the detection of clouds and in the detection of night-time fires. The results of the algorithm have been validated in the Sardinia region by using ground true data provided by the regional Corpo Forestale e di Vigilanza Ambientale (CFVA). A significant reduction of the commission error (less than 10%) has been obtained with respect to the previous version of the algorithm and also with respect to fire-detection algorithms based on low earth orbit satellites.

Sepsis still remains one of the most difficult conditions to diagnose as it presents unspecific clinical signs and symptoms, which makes early detection crucial. Our study aimed to enhance the accuracy of sepsis diagnosis by integrating multimodal monitoring technologies with traditional diagnostic methods. The research involved 121 newborns, comprising 39 cases of late-onset sepsis, 35 cases of early-onset sepsis, and 47 control subjects. Biosignals including pulse oximetry (PO), near-infrared spectroscopy (NIRS), and skin temperature (ST) were continuously monitored and an algorithm was developed using Python for identifying early signs of sepsis. The model demonstrated the ability to detect sepsis 6 to 48 hours in advance with an accuracy rate of 87.67% ± 7.42%. Sensitivity and specificity were recorded at 76% and 90%, respectively, with NIRS and ST having the most significant impact on predictive accuracy. Despite the promising results, limitations such as sample size, data variability, and potential biases were noted. The findings highlight the critical role of non-invasive biosensing methods in conjunction with traditional biomarkers and cultures, offering a robust framework for early sepsis detection and improved neonatal care. Further studies are recommended to validate these results across diverse clinical settings.

Without the use of medicine drones, users are responsible for transporting goods at a high cost. The goal of this patient monitoring system is to identify people's health and, if necessary, administer medicine. The transportation drone is capable of finding healthcare information in a 360-degree rotation within the transportation infrastructure. IoT: Drone doctors are critical for the transportation of small gadgets such as drug treatments, blood leakages, and vaccines in the critical conditions of a heart patient, in the event of failure of traffic location infrastructure, highway roads, or hospitals due to intense climate or site visitor congestion, and for the transportation of small gadgets such as drug treatments, blood leakages, and vaccines. When transmission is difficult, the self-maintaining drone is the format for quickly transporting drug treatments to the appropriate locations. The shipping drone equipped with an Ardupilot can drive in autopilot mode, which guides the drone to its destination. It has a 7-minute flying period and can deliver up to 2 kg of medicine. When the detected heartbeat is 94bpm and the fever range is 101 degrees, a method has been presented in which an IoT Drone Doctor (IDD) System distributes the first AID box to vulnerable patients and heart patients.

Objective tools to track medication adherence are lacking. A tool to monitor pill intake that can be implemented in mHealth apps without the need for additional devices was developed. We propose a pill intake detection tool that uses digital image processing to analyze images of a blister to detect the presence of pills. The tool uses the circular Hough transform as a feature extraction technique and is therefore primarily useful for the detection of pills with a round shape. This pill detection tool is composed of two steps. First, the registration of a full blister and storing of reference values in a local database. Second, the detection and classification of taken and remaining pills in similar blisters, to determine the actual number of untaken pills. In the registration of round pills in full blisters, 100% of pills in gray blisters or blisters with a transparent cover were successfully detected. In counting of untaken pills in partially opened blisters, 95.2% of remaining and 95.1% of taken pills were detected in gray blisters, while 88.2% of remaining and 80.8% of taken pills were detected in blisters with a transparent cover. The proposed tool provides promising results for the detection of round pills. However, the classification of taken and remaining pills need to be further improved, in particular for the detection of pills with non-oval shapes.

Context: Anomaly detection in a data center is a challenging task, having to consider different services on various resources. Current literature shows the application of artificial intelligence techniques to either log files or monitoring data: the former created by services at run time, while the latter produced by specific sensors directly on the physical or virtual machine. Objectives: We propose a model that exploits information both in log files and monitoring data to identify patterns and detect anomalies over time. Methods: The key idea is to use on one side natural language processing solutions to detect problems at service level, extracting words that represent anomalies. Clustering and topic modeling techniques have been used to identify patterns and group them with respect to topics. On the other side time series anomaly detection technique has been applied to sensors data in order to combine problems found in the log files with problems stored in the monitoring data. Results: We have tested our approach on a real data center equipped with log files and monitoring data that can characterize the behaviour of physical and virtual resources in production. We have observed a correspondence between anomalies in log files and monitoring data, e.g. an increase in memory usage or machine load. The results are extremely promising. Conclusion: Our model requires to integrate site administrators' expertise in order to consider all critical scenario in the data center and understand results properly.

This paper introduces the improvements in the natural frequency based Structural Health Monitoring (SHM) by applying bio-inspired optimization methods and the vision-based monitoring system for the effective damage detection. This paper proposes a natural frequency extraction method using the motion magnification based vision monitoring system with bio-inspired optimization techniques to estimate the damage location and depth in a cantilever beam. The proposed optimization techniques are inspired by natural processes and biological evolution including Genetic Algorithms, Particle Swarm Optimization, Sea Lion Optimization, and Coral Reefs Optimization. To verify the performances of each bio-inspired optimization methods, the eigenvalues of a two-bay truss structure are used for estimating the damaged elements. Then, using the proposed video motion magnification method, the natural frequency for each of undamaged and damaged cantilever beam have been extracted and compared with the LDV sensor to verify the proposed vision-based monitoring system. The performance of each bio-inspired optimizer for the damage detection has been compared. As a result, Coral Reefs Optimization has showed the lowest average error, around 1%, in the damage detection using natural frequency.

Whole cell biosensors could serve as eco-friendly and cost-effective alternatives for detecting potentially toxic bioavailable heavy metals in aquatic environments. However, they often fail to meet practical requirements due to an insufficient limit of detection (LOD) and high background noise. In this study, we designed a synthetic genetic circuit specifically tailored for detecting ionic mercury, which we applied to environmental samples collected from artisanal gold mining sites in Peru. We developed two distinct versions of the biosensor, each utilizing a different reporter protein: a fluorescent biosensor (Mer-RFP) and a colorimetric biosensor (Mer-Blue). Mer-RFP enabled real-time monitoring of the culture’s response to mercury samples using a plate reader, whereas Mer-Blue was analysed for colour accumulation at the endpoint using a specially designed, low-cost camera set up for harvested cell pellets. Both biosensors exhibited negligible baseline expression of their respective reporter proteins and responded specifically to HgBr2 in pure water. Mer-RFP demonstrated a linear detection range from 1 nM to 1 μM, whereas Mer-Blue showed a linear range from 2 nM to 125 nM. Our biosensors successfully detected a high concentration of ionic mercury in the reaction bucket where artisanal miners produce a mercury-gold amalgam. However, they did not detect ionic mercury in the water from active mining ponds, indicating a concentration lower than 3.2 nM Hg2+ -a result consistent with chemical analysis quantitation. Furthermore, we discuss the potential of Mer-Blue as a practical and affordable monitoring tool, highlighting its stability, reliance on simple visual colorimetry, and the possibility of sensitivity expansion to organic mercury.

In this study, we explored the application of deep learning techniques for credit card fraud detection, aiming to improve the performance and reliability of anomaly detection methods in financial transactions. We first utilized the Isolation Forest algorithm, achieving a detection accuracy of 26% for the top 1000 transactions. Subsequently, we experimented with the Autoencoder algorithm, an unsupervised deep neural network model, which enhanced the detection accuracy to 33.6% in the best case despite some fluctuations. The results demonstrate deep learning models' strong feature extraction capability and adaptability, highlighting their potential to surpass traditional methods. However, the high imbalance in the dataset, with only 0.17% of transactions being fraudulent, poses a significant challenge. This study underscores the necessity for further experimentation and optimization of network structures and hyperparameters to achieve more stable and efficient fraud detection. The findings provide valuable insights and reference points for future research in financial fraud detection using deep learning methodologies.

There are numerous challenges involved in the diagnosis and treatment of lung cancer. Globally, majority of people suffers from cancerous disease involving throat cancer, lung cancer, stomach cancer, cancerous brain tumor. Among these the most common ones is the lung cancer or lung carcinoma. The leading cause of the lung cancer is the smoking. Around 80% to 90% of deaths are caused due to Non-small cell lung cancer (NSCLC). The inadequate diagnostic techniques and low chances for the survival of lung cancer patients results from the lack of an early prognosis and incompetency in traditional therapies. However, such challenges involved in the prognosis and treatment of lung cancer are on decline with the progression in magnetic nanoparticle (MNP) technology. Many break-through discoveries and inventions have been made in the field of cancer therapy by using magnetic nanoparticles. The implication of nanotechnology has led to the recent advancement in nanomedicine field. This has encouraged the improvement in different therapeutic and diagnosis strategies employing nanotechnology. The generation of immense technological benefits for nanoparticles systems has been accredited to its remarkable nanoscale physico-chemical properties. This in turns provides the early detection of lung cancer and active drugs delivery for an improved theranostics strategy. The present review provides a general idea of the current progression in the therapeutic and prognosis purpose of magnetic nanoparticles. Further, we disclose the development in the lung cancer theranostics by functionalization of magnetic nanoparticles. The established importance of magnetic nanoparticles in the theranostics centers for lung cancer has been revealed in this paper. The challenges existing in the theranostics of lung cancer are addressed through the functioning of magnetic nanoparticles in the process.

Chip pad alignment inspection is of great importance in the industrial field. However, due to the fact that chip pads are usually small, problems such as misdetection and missed detection often occur. When applying deep learning methods for chip pad detection, it is necessary to ensure accurate detection of small target chips while meeting the requirements of lightweight detection models for industrial needs. To solve the above problems, this paper proposes a lightweight model based on improved YOLOv5s. Firstly, the feature extraction part is improved to increase the network's focus on the target. Secondly, the feature fusion layer is improved to double the resolution of the prediction head, and the context-aware network is designed to enhance the context-capture ability of key features of small targets. Finally, SIoU is adopted as the loss function to improve the speed and accuracy of the regression frame. The experimental results show that the improved YOLOv5s algorithm improves the detection accuracy by 2.3% and reduces the network parameters by 81.8% compared to the original algorithm. The improved algorithm is combined with image processing techniques to design correction methods for alignment anomalies and realize real-time alignment anomaly correction in industry.

Pipelines are widely used for transportation of hydrocarbon fluids over millions of miles over the world. The structures of the pipelines are designed to withstand several environmental loading conditions to ensure safe and reliable distribution from point of production to the shore or distributions deport. However, leaks in pipeline networks are one of the major causes of innumerable losses in pipeline operators and nature. Incidents of pipeline failure can result in serious ecological disasters, human casualties and financial loss. In order to avoid such menace and maintain safe and reliable pipeline infrastructure, substantial research efforts have been devoted to implementing pipeline leak detection and localisation using different approaches. This paper discusses on pipelines leakage detection technologies and summarises the state-of-the-art achievements. Different leakage detection and localisation in pipeline systems are reviewed and their strengths and weaknesses are highlighted. Comparative performance analysis is performed to provide a guide in determining which leak detection method is appropriate for particular operating settings. In addition, research gaps and open issues for development of reliable pipeline leakage detection systems are discussed.

We introduce a novel microscopic image dataset augmented with segmentation and detection labels specifically designed for microplastic analysis in sewage environments. Recognizing the increasing concern over microplastics — particles of synthetic polymers smaller than 5mm — and their detrimental effects on marine ecosystems and human health, our research focuses on enhancing detection and analytical methodologies through advanced computer vision and deep learning techniques. The dataset comprises high-resolution microscopic images of microplastics collected from sewage, meticulously labeled for both segmentation and detection tasks, aiming to facilitate accurate and efficient identification and quantification of microplastic pollution. In addition to dataset development, we present example deep learning models optimized for segmentation and detection of microplastics within complex sewage samples. The models demonstrate significant potential in automating the analysis of microplastic contamination, offering a scalable solution to environmental monitoring challenges. Furthermore, we ensure the accessibility and reproducibility of our research by making the dataset and model codes publicly available, accompanied by detailed documentation on GitHub and LabelBox. The dataset and example deep learning models are publicly available at the following GitHub link. https://anonymous.4open.science/r/Microplastics-in-Sewage-1BEF

Monitoring is an essential component in ecosystem management and leveraging existing data sources for multiple species of interest can be one effective way to enhance information when making management decisions. Here we analyzed juvenile Chinook Salmon (Oncorhynchus tshawytscha) bycatch data that has been collected by the recently established Enhanced Delta Smelt Monitoring program (EDSM), a survey designed to estimate the abundance and distribution of the San Francisco Estuary’s (estuary) endangered Delta Smelt (Hypomesus transpacificus). Two key aspects of the EDSM program distinguish it from other fish surveys in the estuary: a stratified random sampling design and the spatial scale of its sampling effort. We integrated the EDSM dataset with other existing surveys in the estuary and used an occupancy model to assess detection probability differences across gear types. We saw no large-scale differences in size selectivity, and while detection probability varied among gear types, cumulative detection probability for EDSM was comparable to other surveys due to the program’s use of replicate tows. Based on our occupancy model and sampling effort in the estuary during spring of 2017 and 2018, we highlighted under-sampled regions that saw improvements in monitoring coverage due to EDSM. Our analysis also revealed that each sampling method has its own benefits and constraints. Although the use of random sites with replicates as conducted by EDSM can provide more statistically robust abundance estimates relative to traditional methods, the use of fixed stations and simple methods such as beach seine may provide a more cost-effective way of monitoring salmon occurrence in certain regions of the estuary. Stronger inference on salmon abundance and distribution can be made by leveraging the strengths of each survey’s method. Careful consideration of these trade-offs is crucial as the management agencies of the estuary continue to adapt and improve their monitoring programs.

This paper describes the proposal and development of a proof of concept (PoC) for a data logger system designed for operation and fault detection in bench testing of combustion engines. The main objective was to develop a data logger system that collects data on vibration, sound, temperature, and CO2 levels to identify ignition and combustion faults, thereby contributing to reducing greenhouse gas emissions (GHG). The paper presents (i) the proposal and development and (ii) the open-source code: proof of concept for a data logger system focused on detecting faults and monitoring the operational condition of benchtop combustion engines. The results indicate the feasibility of the PoC for data acquisition and dataset creation for Research and Development purposes.

The number of connected IoT devices is increasing significantly due to their many benefits, including automation, improved efficiency and quality of life, and waste reducing. However, these devices have several vulnerabilities that have led to the rapid growth in the number of attacks. Therefore, several machine learning-based Intrusion Detection Systems (IDS) tools have been developed to detect intrusions and suspicious activity to and from a host (HIDS - Host IDS) or, in general, within the traffic of a network (NIDS - Network IDS). The proposed work performs a comparative analysis and an ablative study among recent machine learning-based NIDS to develop a benchmark of the different proposed strategies. The proposed work compares both shallow learning algorithms, such as Decision Trees, Random Forest, Naïve Bayes, Logistic Regression, XGBoost, and Support Vector Machine, and deep learning algorithms, such as DNN, CNN, and LSTM, whose approach is relatively new in the literature. The algorithms are evaluated on the KDD-99, NSL-KDD, UNSW-NB15, and IoT-23 datasets. The results show that the NIDS tools based on deep learning approaches achieve better performance in detecting network anomalies than shallow learning approaches.

Methane is the main cause of sewer explosion accidents, and the available monitoring methods mainly use portable gas sensors for on-site detection. However, these methods cannot grasp the dynamic changes in methane in a sewer in real time or make better predictions of methane explosion accidents. Here, we present a low-power online monitoring system for sewer methane in order to ensure the safety of urban sewers. A low-power ultrasonic gas sensor was used to monitor the methane content in biogas. Due to the impacts of changes in CO2, temperature, and humidity in the sewer on the ultrasonic methane measurement results, a corresponding compensation method was proposed. The effectiveness of the compensation method was verified through experiments, which measured the methane concentration under different influences, and the methane values measured before and after compensation were compared. The power consumption was only 1.28 mW if the system worked in intermittent operation mode, and it could operate for about 1.5 years by selecting a lithium battery with a capacity of 5 A · H. The experimental results showed that the gas detection accuracy could meet the commercial requirements and had a high compensation for the impacts of carbon dioxide, temperature, and humidity.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

A high performance Driver State Monitoring (DSM) application for the detection of driver drowsiness is presented in this paper. It relies on the usage of an Ensemble of Regression Trees (ERTs) machine learning method that aligns 68 facial landmarks. Special focus is given on the acceleration of the frame processing using reconfigurable hardware. Reducing the frame processing latency saves time that can be used to apply frame-to-frame facial shape coherency rules. False face detection and false shape estimations can be ignored for higher robustness and accuracy in the operation of the DSM application without reducing the frame processing rate that can reach 65 frames per second. The sensitivity and precision in yawning recognition can reach 93% and 97%, respectively. The implementation of the employed DSM algorithm in reconfigurable hardware is challenging since the kernel arguments require large data transfers and the degree of data reuse in the computational kernel is low. Due to this, unconventional hardware acceleration techniques have been employed that can also be useful for the acceleration of several other applications.

The Pygmy hog (Porcula Salvania), till recently, classified as a critically endangered suid, is facing the threat of extinction globally due to habitat degradation. Efforts are being made to protect the pygmy hogs from extinction and breed them in captivity under Pygmy Hog Conservation Pro-gramme (PHCP). However, very little information is available on the reproductive physiology of pygmy hogs. Therefore, the present study aimed to standardize enzyme immunoassays (EIAs) for monitoring pregnancy and reproductive status using progesterone and testosterone metabolites. A total of 785 faecal samples were collected from five females and two males over a period of one year from PHCP Research and Breeding Centre, Guwahati, Assam. High-pressure liquid chro-matography (HPLC) analysis revealed the presence of immunoreactive progesterone and testos-terone metabolites in faeces. Mating was observed in all the five females and four of them gave birth successfully. We were able to detect pregnancy using faecal progesterone metabolites. Based on mating and parturition, the mean gestation period was estimated to be 153.25 days from four females. The breeding centre recorded 172 births between 1996 and 2000 and found strong sea-sonality in births and most of the births were between May and June. Faecal testosterone metabo-lites were significantly higher in the breeding season than the non-breeding season. This is the first study and will help in future breeding programs in other captive breeding centres and reproduc-tive monitoring of reintroduced populations.

In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional Convolutional Neural Networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.

In this work, an IoT system with edge computing capability is proposed facilitating postoperative surveillance of patients who have undergone knee surgery. The main objective is to reliably identify whether a set of orthopedic rehabilitation exercises are executed correctly, which is critical since, it is often necessary to supervise patients during the rehabilitation period so as to avoid injuries or long recovery periods. The proposed system leverages Internet of Things (IoT) paradigm, in combination with Deep Learning and Edge Computing to classify the extend-flex movement of one’s knee via embedded Machine Learning (ML) classification algorithms. The contribution of the proposed work is multilayered. Furthermore as an outcome of this work a dataset of labeled knee movements is freely available on https://www.kaggle.com/datasets/billskarm/knee-range-of-motion to the research community. It also provides real time movement detection with an accuracy reaching 100%, which is achieved with a ML model trained to fit a low cost, off the shelf, Bluetooth Low Energy platform. The proposed Edge Computing approach allows predictions to be performed on-device rather than solely relying on a cloud service. This yields critical benefits in terms of wireless bandwidth and power conservation, drastically enhancing device autonomy, while delivering reduced event detection latency. In particular, the “on device” implementation is able to yield a drastic 99,9% wireless data transfer reduction, a critical 39% prediction delay reduction and a valuable 17% increase of prediction event. Finally, enhanced privacy comprises another significant benefit from the implemented Edge Computing ML model as sensitive data can be processed on-site and only events or predictions are shared with the medical personnel.

This paper describes a multi-channel in-situ monitoring system developed to better understand defect formation signatures in metal additive manufacturing. Three high-speed imaging modes coupled with an image computer capable of processing and storing these data streams allowed an examination of defect formations signatures and mechanisms. It was found that defects later detected in X-ray computed tomography (CT) scans were related to regions with anomalous heat signatures and powder bed morphology. Automated defect detection algorithms based on these defect signatures captured 80% of defects greater than 300 µm.

Knowledge of the spatio-temporal occurrence of avalanche activity is critical for avalanche forecasting and hazard mapping. We present a near-real time automatic avalanche monitoring system that outputs detected avalanche polygons within roughly 10 min after Sentinel- 1 SAR data download. Our avalanche detection algorithm has an average probability of detection of 67.2 % with a false alarm rate averaging 45.9, with maximum POD's over 85 % and minimum FAR's of 24.9 % compared to manual detection of avalanches. The high variability in performance stems from the dynamic nature of snow in the Sentinel-1 data. After tuning parameters of the detection algorithm, we processed five years of Sentinel-1 images acquired over a 150 x 100 km large area in Northern Norway, with the best setup. Compared to a dataset of field-observed avalanches, 77.3 % were manually detectable. Using these manual detections as benchmark, the avalanche detection algorithm achieved an accuracy of 79 % with high POD's in cases of medium to large wet snow avalanches. For the first time, we can present a dataset of spatiotemporal avalanche activity over several winters from a large region. This unique dataset allows for research into the relationship between avalanche activity and triggering meteorological factors, mapping of avalanche prone areas and near-real time avalanche activity monitoring to assist public avalanche forecasting. Currently, the Norwegian Avalanche Warning Service is using our processing system for pre-operational use in three regions in Norway.

Fiber-based flexible sensors have promising applications potential in human motion and healthcare monitoring, owing to their merits of lightweight, flexibility, and easy processing. Now, high-performance elastic fiber-based strain sensors with high sensitivity, large working range and excellent durability are in great demand. Herein, we have easily and quickly prepared a highly-sensitive, durable fiber-based strain sensor by dip-coating of highly-stretchable polyurethane (PU) elastic fiber in MXene/ waterborne polyurethane (WPU) dispersion solution. Benefiting from the electrostatic repulsion force between the negatively charged WPU and MXene sheets in the mixed solution, very homogeneous and stable MXene/WPU dispersion was successfully obtained and the interconnected conducting networks were correspondingly formed in coated MXene/WPU shell layer, which makes as-prepared strain sensor exhibit a gauge factor of over 960, a large sensing range of over 90% and detection limit as low as 0.5% strain. As elastic fiber and mixed solution have the same polymer constitute, tight bonding of MXene/WPU conductive composite on PU fibers was achieved, enabling the as-prepared strain sensor endure over 2500 stretching-releasing cycles and thus show good durability. Full-scale human motion detection was also performed by the strain sensor, and a body posture monitoring, analysis, and correction prototype system was developed via embedding the fiber-based strain sensors into sweater, strongly indicating the great application prospect in exercise, sports and healthcare.

Lamb wave-based structural health monitoring is widely acknowledged as a reliable 11 method for damage identification, classification, localization and quantification. However, due to 12 the complexity of Lamb wave signals, especially after interacting with structural components and 13 defects, interpreting these waves and extracting useful information about the structure's health is 14 still a major challenge. However, deep learning-based strategy offers a great opportunity to address 15 such challenges as the algorithm can operate directly on raw discrete time-domain signals. Unlike 16 traditional methods, which often require careful feature engineering and preprocessing, deep learn-17 ing can automatically extract relevant features from the raw data. This paper proposes an autoen-18 coder based on a bidirectional long short-term memory network with maximal overlap discrete 19 wavelet transform layer to detect the signal anomaly and determine the location of the damage in 20 the composite structure. This approach has the potential to greatly enhance our ability to detect and 21 locate structural damage in composite structures, thereby increasing safety and efficiency.

Even if the field of medicine has made great strides in recent years, infectious diseases caused by novel viruses that damage the respiratory system continue to plague people all over the world. This type of virus is very dangerous, especially for people who deal with serious long-term breathing problems, like triggering asthma, pneumonia, or bronchitis infections. Thus, this paper demonstrates a new Secure Machine Learning Monitoring System for a model for virus detection. Our proposed model makes use of 4 basic emerging technologies, Internet of Things (IoT), Wireless Sensor Networks (WSN), Cloud Computing (CC), and Machine Learning (ML), to detect dangerous types of viruses that infect people or animals causing panic worldwide and deregulating human daily life. The proposed system is a robust system that could be established in various buildings, like hospitals, entertainment halls, universities, etc., and will provide accuracy, speed, and privacy for data collected in the detection of viruses.

The task of unsupervised anomalous sound detection (ASD) is challenging for detecting anomalous sounds from a large audio database without any annotated anomalous training data. Many unsupervised methods were proposed, but previous works have confirmed that the classification-based models far exceeds the unsupervised models in ASD. In this paper, we adopt two classification-based anomaly detection models: (1) Outlier classifier is to distinguish anomalous sounds or outliers from the normal; (2) ID classifier identifies anomalies using both the confidence of classification and the similarity of hidden embeddings. We conduct experiments in task 2 of DCASE 2020 challenge, and our ensemble method achieves an averaged area under the curve (AUC) of 95.82% and averaged partial AUC (pAUC) of 92.32%, which outperforms the state-of-the-art models.

Traffic sign detection plays a pivotal role in autonomous driving systems. The intricacy of the detection model necessitates high-performance hardware. Real-world traffic environments exhibit considerable variability and diversity, posing challenges for effective feature extraction by the model. Therefore, it is imperative to develop a detection model that is not only highly accurate but also lightweight. In this paper, we proposed YOLO-ADual, a novel lightweight model. Our method leverages the C3Dual and Adown lightweight modules as replacements for CPS and CBL modules in YOLOv5. The Adown module effectively mitigates feature loss during downsampling while reducing computational costs. Meanwhile, C3Dual optimizes the processing power for kernel feature extraction, enhancing computation efficiency while preserving network depth and feature extraction capability. Furthermore, the inclusion of the CBAM module enables the network to focus on salient information within the image, thus augmenting its feature representation capability. Our proposed algorithm achieves a [email protected] of 70.1% while significantly reducing the number of parameters and computational requirements to 51.83% and 64.73% of the original model, respectively. Compared to various lightweight models, our approach demonstrates competitive performance in terms of both computational efficiency and accuracy.

Pig farms management is involved in multiple factors such as environmental conditions, animal behavior, weight gaining and others. In all those scenarios, it is fundamental to detect each individual and its development as it grows to reach the shipment phase. Therefore, the objective of this study was to apply an automatic individual pig detection algorithm using Deep Learning Techniques, in frames taken from videos recorded during the weaning phase in real production conditions of small and medium producers in tropical conditions in Colombia. The weaning phase was selected because individual detection in each cage is more difficult due to environmental adaptations that piglets undergo after nursing. Piglets tend to cluster together during this phase, making image processing more challenging compared to the fattening phase, where animals are more isolated. The You Only Look Once (YOLOv7) algorithm and VGG Image Annotator were used to detect individuals in two pens separated by gender. All animal postures, lighting conditions were considered. The Precision, Recall and mAP metrics were used to assess the model performance with different confidence values. A precision of 98.3% in a threshold of 0.9 was reached, Recall of 98.5% in a threshold of 0.85. Data augmentation techniques were important to increase the dataset and to have a more realistic model for individuals’ detection. The method used allowed us to identify all the complete pigs’ bodies under different posture and lighting situations.

The analysis of the radon-seismicity relationship has been carried out so far in the Vrancea (Ro-mania) seismic zone, with monitoring stations positioned on tectonic faults. The article analyzes the evolution of radon under the conditions of the existence of deep and surface seismicity and the presence of mud volcanoes along with live fires caused by gases emitted from the soil. The monitoring area was extended to the Black Sea and the area of the Făgăraș Câmpulung fault, where a special radon detection system was set up, which was proposed for patenting. A case study is the effect of the earthquakes in Turkey (7.8 R and 7.5 R on 2023/02/06) on the seismically active areas in Romania in terms of gas emissions (radon, CO2). The main analysis methods on radon (we also included CO2) are applied to integrated time series and the use of anomaly detection algorithms. Data analysis shows that the effects of global warming introduce deviations in seasonal gas emissions compared to previous years. This makes it difficult to analyze the data and correlate them with seismicity. The main conclusions related to the development of a radon monitoring network and in general the emission of gases in seismic areas refer to the importance of the choice of equipment, the monitoring location and the installation method.

Continuous in-home monitoring of older adults living alone aims to improve their quality of life and independence, by detecting early signs of illness and functional decline or emergency conditions. To meet requirements for technology acceptance by seniors (unobtrusiveness, non-intrusiveness, privacy-preservation), this study presents and discusses a new smart sensor system for the detection of abnormalities during daily activities, based on ultra-wideband radar providing rich, not privacy-sensitive, information useful for sensing both cardiorespiratory and body movements, regardless of ambient lighting conditions and physical obstructions (through-wall sensing). The radar sensing is a very promising technology, enabling the measurement of vital signs and body movements at a distance, and thus meeting both requirements of unobtrusiveness and accuracy. In particular, impulse-radio ultra-wideband radar has attracted considerable attention in recent years thanks to many properties that make it useful for assisted living purposes. The proposed sensing system, evaluated in meaningful assisted living scenarios by involving 30 participants, exhibited the ability to detect vital signs, to discriminate among dangerous situations and activities of daily living, and to accommodate individual physical characteristics and habits. The reported results show that vital signs can be detected also while carrying out daily activities or after a fall event (post-fall phase), with accuracy varying according to the level of movements, reaching up to 95% and 91% in detecting respiration and heart rates, respectively. Similarly, good results were achieved in fall detection by using the micro-motion signature and unsupervised learning, with sensitivity and specificity greater than 97% and 90%, respectively.

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a Deep Neural Network-based Model for automated people detection, tracking, and inter-people distances estimation in the crowd, using common CCTV security cameras. The proposed DNN model along with an inverse perspective mapping technique leads to a very accurate people detection and social distancing monitoring in challenging conditions, including people occlusion, partial visibility, and lighting variations. We also provide an online infection risk assessment scheme by statistical analysis of the Spatio-temporal data from the moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infection. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The efficiency of the proposed methodology is evaluated on the Oxford Town Centre dataset, with superior performance in terms of accuracy and speed compared to three state-of-the-art methods.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

With increasing research focus on industrial anomaly detection, numerous methods have emerged in this domain. Notably, memory bank-based approaches, coupled with kNN distance metrics, have demonstrated remarkable performance in anomaly detection (AD) and anomaly segmentation (AS). However, upon examination of the Back to the Feature (BTF) method applied to the Mvtec-3D AD dataset, it was observed that while it exhibited exceptional segmentation performance, its detection performance was lacking. To address this discrepancy, this study base improves the implementation of BTF, especially the improvement of the anomaly score metric. It posits that different "clusters" necessitate distinct k values in kNN distance metrics. For simplify, this assumption is distilled into the proposition that AD and AS tasks impose differing requirements on the k value in kNN distance metrics. Consequently, the paper introduces the BTM method, which utilizes distinct distance metrics for AD and AS tasks. This innovative approach yields superior AD and AS performance (I-AUROC 93.0%, AURPO 96.9%, P-AUROC 99.5%), representing a substantial enhancement over the BTF method (I-AUROC 5.7% ↑, AURPO 0.5% ↑, P-AUROC 0.2% ↑).

Currently there are fewer depth models applied to pepper picking detection, while the existing generalized neural networks have problems such as large model parameters, long training time, and low model accuracy.In order to solve the above problems, this paper proposes a Yolo-chili target detection algorithm for chili pepper detection. First, the classical target detection algorithm yolov5 is used as a benchmark model, and an adaptive spatial feature pyramid structure combining the attention mechanism and the idea of multi-scale prediction is introduced to improve the model's detection effect on occluded peppers and small target peppers. Secondly, a three-channel attention mechanism module is introduced to improve the algorithm's long-distance recognition ability and reduce the interference of redundant testers. Finally, the quantized pruning method is used to reduce the model parameters and realize the lightweight processing of the model. Applying the method to the homemade chili pepper dataset, the AP value of chili pepper reaches 93.11%; the accuracy rate is 93.51% and the recall rate is 92.55%.The experimental results show that yolo-chili is able to achieve accurate and real-time pepper detection under complex orchards.

This study demonstrates the efficacy of structured pruning and architectural fine-tuning on the YOLOv7-tiny model for eye state detection, emphasizing optimization for real-time applications. Structured pruning significantly reduced the model's complexity and storage size while maintaining high detection accuracy, as evidenced by stable precision, recall, and [email protected] metrics across iterations. Further fine-tuning adjusted the model's width and depth, optimizing efficiency and processing speed without compromising performance. These optimizations yielded YOLOv7-tiny variants that are both computationally efficient and accurate, suitable for resource-constrained environments. The findings highlight the critical role of model optimization in deploying effective neural networks for specific detection tasks in real-time scenarios.

Turbidity is an important water quality parameter, especially for drinking water. The ability to actively monitor the turbidity level in Drinking Water Distribution Systems is of critical importance to the safety and wellbeing of the public. Traditional turbidity monitoring methods involve manual collection of water samples at set locations and times followed by laboratory analysis, which are labor intensive and time consuming. Fiber-optic measurement permits real-time, in-situ turbidity monitoring. But the current technology is based on plastic fibers, which suffer from high optical attenuation and hence are unsuitable for large-scale remote monitoring. In this paper, we report the demonstration of a fiber-optic turbidity sensor based on multi-mode glass fibers. The system uses a single fiber to both deliver laser light into the water sample and collect the back-scattered light for detection. A balanced-detection scheme is utilized to remove the common-mode noise to enhance the turbidity sensitivity. Highly linear turbidity responses are obtained and a turbidity resolution as low as 0.1 NTU is achieved. The test unit is also shown to have excellent reproducibility against repeated measurements and good stability against temperature changes. Turbidity measurement in real environmental matrices such as tap water and pond water is also reported with an assessment of the impact of flow rate. This work demonstrates the feasibility of future large scale distributed fiber-optic turbidity monitoring networks.

The application of 3D LiDAR technology has become increasingly extensive in tunnel monitoring due to the large density and high accuracy of the acquired spatial data. The proposed processing method aims at circle tunnels and provides a clear workflow to automatically process raw point data and easily interpretable results to analyze tunnel health state. The proposed automatic processing method employs a series of algorithms to extract point cloud of a single tunnel segment without obvious noise from entire raw tunnel point cloud mainly by three steps: axis acquisition, segments extraction and denoising. Tunnel axis is extracted by fitting boundaries of the tunnel point cloud rejection in plane with RANSAC algorithm. With guidance of axis, the entire preprocessed tunnel point cloud is segmented by equal division to get a section of tunnel point cloud which corresponds to a single tunnel segment. Then the noise in every single point cloud segment is removed by clustering algorithm twice, based on distance and intensity. Finally, clean point clouds of tunnel segments are processed by effective deformation extraction processor to get ovality and three-dimensional deformation nephogram.

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.

Computer vision is a rapidly developing field that focuses on highly sophisticated picture analysis, manipulation, and comprehension. Its objective is to analyze what is happening in front of a camera and utilize that understanding to control a computer or robotic system or to present users with fresh visuals that are more enlightening or appealing than the original camera images. Computer vision technologies make it feasible for new user interfaces, augmented reality gaming, biometrics, automobile, photography, movie creation, Web search, and many more applications. This essay seeks to explain how computer vision can be utilized to play blackjack successfully.

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, it is aimed to reduce the dangerous effects of drone use through early detection of drones.The state of the art of the study is evaluation of deep learning approaches such as pre trained YOLOv8 drone detection for security issues. In this study, dataset collected by Mehdi Özel for a UAV competition are sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605 and a considerable precision-recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.

Generating a range-wide population status of the diamondback terrapin (Malaclemys terrapin spp.) is challenging due to a combination of species ecology and behavior, and limitations associated with traditional sampling methods. Visual counting of emergent heads offers an efficient, non-invasive and promising method for generating abundance estimates of terrapin populations across broader spatial scales and can be used to explain spatial variation in population size. We conducted repeated visual head count surveys at 38 predetermined sites along the shoreline of Wellfleet Bay in Wellfleet, Massachusetts. We analyzed the count data using a hierarchical modeling framework designed specifically to analyze repeated count data: the so-called N-mixture model. This approach allows for simultaneous modeling of imperfect detection to generate estimates of true terrapin abundance. We found detection probability was lowest when skies were overcast and when wind speed was highest. Site specific abundance varied but we found that abundance estimates were, on average, higher in unexposed sites compared to exposed sites. We demonstrate the utility of pairing visual head counts and N-mixture models as an efficient method for estimating terrapin abundance and show how the approach can be used to identifying environmental factors that influence detectability and distribution.

Rigid-body visual tracking is an active research field with many practical applications including visual surveillance and intelligent transport system. In this paper, we define a new problem domain, called visual growth tracking, to track different parts of an object that grow non-uniformly over space and time for application in image-based plant phenotyping. The paper introduces a novel method to detect and track each leaf of a plant for automated leaf stage monitoring. The method has four phases: optimal view selection, plant architecture determination, leaf tracking and generation of a leaf status report. The proposed method uses a graph theoretic approach to reliably detect and track individual leaves by overcoming the challenge of leaf-losses based on temporal image sequence analysis for automatically generating the leaf status report containing the following phenotypes, i.e., the emergence timing of each leaf, total number of leaves present at any time, the day on which a particular leaf stopped growing, and the length and relative growth rate of individual leaves. The proposed method demonstrates high accuracy in detecting leaves and tracking them through the early vegetative stages of maize plants based on experimental evaluation on a publicly available benchmark dataset.

Addressing real-time aircraft target detection in microsatellite-based visible light remote sensing video imaging requires considering the limitations of imaging payload resolution, complex ground backgrounds, and the relative positional changes between the platform and aircraft. These factors lead to multi-scale variations in aircraft targets, making high-precision real-time detection of small targets in complex backgrounds a significant challenge for the detection algorithms. Hence, this paper introduces a real-time aircraft target detection algorithm for remote sensing imaging using an improved lightweight attention mechanism that relies on the YOLOv7 framework (SE-CBAM-YOLOv7). The proposed algorithm replaces the standard convolution (Conv) with a lightweight convolutional SEConv to reduce the computational parameters and accelerate the detection process of small aircraft targets, thus enhancing real-time onboard processing capabilities. Besides, the SEConv-based SPPCSPC (Spatial Pyramid Pooling and Connected Spatial Pyramid Convolution) module extracts image features. It improves detection accuracy while the feature fusion section integrates the CBAM hybrid attention network, forming the CBAMCAT module. Furthermore, it optimizes small aircraft target features in channel and spatial dimensions, improving the model's feature fusion capabilities. Experiments on public remote sensing datasets reveal the proposed SE-CBAM-YOLOv7 improves detection accuracy by 3% and mAP value by 4.2% compared to YOLOv7, significantly enhancing the detection capability for small-sized aircraft targets in satellite remote sensing imaging.

We report the development of an extrinsic self-healing coating system that shows no fluorescence from the intact coating, yellowish fluorescence in cracked regions, and greenish fluorescence in healed regions, thus allowing the separate monitoring of cracking and healing of coatings. This fluorescence monitoring self-healing system consisted of a top coating, an epoxy matrix resin containing mixed dye-loaded in single microcapsule. The dye-loaded microcapsules consisted of a poly(urea-formaldehyde) shell encapsulating a healing agent containing MAT-PDMS and styrene, a photo-initiator and a mixture of two dyes, one that fluoresces only in the solid state (DCM) and a second that fluoresces dramatically increased in the solid than solution state (4-TPAE). A mixture of the healing agent, photo-initiator and the two dyes was yellow due to fluorescence from DCM. On UV curing of this mixture, however, the color changed from yellow to green and the fluorescence intensity increased due to fluorescence from 4-TPAE in the solid state. When a self-healing coating embedded with microcapsules containing the DCM/4-TPAE dye mixture was scratched, the damaged region exhibited a yellowish color that changed to green after healing. Thus, the self-healing system reported here allows the separate monitoring of cracking and healing based on changes in fluorescence color.

A novel fiber optic sensing technology for high frequency dynamics detection is proposed in this paper, specifically tailored for structural health monitoring applications based on strain wave analysis, including both passive impact identification and active Lamb wave monitoring. The sensing solution relies on a fiber optic-based interferometric architecture associated to an innovative coherent detection scheme, which retrieves in a completely passive way the high-frequency phase information of the received optical signal. The optical fiber can be arranged into different configurations in order to meet the requirement of the specific application, the sensor sensitivity being maximized while still ensuring a limited gauge length if a local measure is required. For the active Lamb wave monitoring, this results in a sensing fiber arranged in multiple loops glued on an aluminum thin panel in order to increase the phase signal relative only to the sensing points of interest. Instead, for passive impact identification, the sensitivity is simply increased by exploiting a longer gauge length glued to the structure. The fiber optic coherent (FOC) sensor detects the strain waves emitted by a piezoelectric transducer placed on the aluminum panel or generated by an impulse hammer, respectively. The FOC sensor measurements have been compared with both a numerical model based on Finite Elements and traditional piezoelectric sensors, confirming a very good agreement between experimental and simulated results for both the active and passive impact monitoring scenarios.

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.

Electrical impedance tomography (EIT) can monitor the real-time hemodynamic state of a conscious and spontaneously breathing patient noninvasively. However, cardiac volume signal (CVS) extracted from EIT images has a small amplitude and is sensitive to motion artifacts (MAs). This study aimed to develop a new algorithm to reduce MAs from the CVS for more accurate heart rate (HR) and cardiac output (CO) monitoring in patients undergoing hemodialysis based on the source consistency between the electrocardiogram (ECG) and the CVS of heartbeats. Two signals were measured at different locations on the body through independent instruments and electrodes, but the frequency and phase were matched when no MAs. As the number of motions per hour (MI) increased over 30, the proposed algorithm had a correlation of 0.83 and a precision of 1.65 beats per minute (BPM) compared to the conventional statical algorithm of a correlation of 0.56 and a precision of 4.04 BPM. For CO monitoring, the precision and upper limit of the mean ∆CO were 3.41 and 2.82 liters per minute (LPM), respectively, compared to 4.05 and 3.82 LPM of the statistical algorithm. The developed algorithm could reduce MAs and improve HR/CO monitoring accuracy and reliability, particularly in high-motion environments.

Background: The World Health Organization identifies lung and prostatic cancers as solid tumors with significant global lethality, both being auxotrophic cancers for L-arginine aminoacid. The aim of the study: The study aims to detect L-arginase-expressing bacteria from various soil environments in Egypt using 16S rRNA and characterize its anticancer activity. Methodology: A hundred samples of Egyptian grassland soil were gathered at a depth of 11–20 cm, close to wheat mills. Using fast plate assay screening and spectrophotometric analysis, the presence of bacteria generating L-arginase was verified. The major soil bacterial isolates were identified by morphological characterization, biochemical responses, and 16SrRNA sequencing methods. The anticancer activity of the test enzyme was assessed using MTT assay. Results: On the MAA medium, only the bacterial isolates capable of using L-arginine as the only metabolic source for carbon and nitrogen were cultivated. Bacillus cereus DSM 360 was shown to be the prevailing bacterial isolate generating L-arginase using molecular detection and biochemical reactions. When Co+2, Ni+2, and Mn+2 metal ions were present as co-factors, bacterial L-arginase demonstrated remarkable anticancer action against auxotrophic tumors for L-arginine. The total protein content was 0.349 mg, while total enzyme activity was 8.174 U with 61% enzyme recovery. As well as the specific activity reached 23.4212 U/mg. Using the mass spectrometer, the molecular weight of the bacterial L-arginase was revealed to be 37 KDa. The bacterial L-arginase's IC50 values were 3.12 U/ml for the lung cancer cell line, 3.91 U/ml for prostatic cancer cell line, 0.91 U/ml for acute promyelocytic leukemia cancer cell line and 2.73 U/ml for kidney cancer cell line. The enzyme under test showed kinetic characteristics of 7.36 mmol/l and 6.14 μmol/min for Km and Vmax, respectively. The half-life time (T1/2) was 90.17 min at 50°С, while being 86.53 min at 60°С. The test enzyme was thermostable at 60°С for 1 hour. Conclusion: The study showed a potential strategy by identifying and determining a newly discovered bacterial L-arginase enzyme as an anticancer agent in Egypt's soil settings.

Seismic monitoring in areas where induced earthquakes could occur is a challenging topic for seismologists due to generally very low signal to noise ratio. Therefore, the seismological com-munity is devoting several efforts to the development of high-quality networks around the areas where fluid injection and storage and geothermal activities take place, also following the national induced seismicity monitoring guidelines. The use of advanced data-mining strategy, such as template matching filters, auto-similarity search and deep-learning approaches is recently further fostering such a monitoring enhancing the seismic catalogues and lowering the magnitude of completeness of these areas. In this framework, we carried out an experiment where a small-aperture seismic array was installed around the gas reservoir of Collalto, in North Italy. The continuous velocimetric data, acquired for 25 days, were analysed through the application of the optimized auto-similarity search technique FAST. The array was conceived as a cost-effective network, aimed at integrating, right above the gas storage site, the permanent high-resolution Collalto Seismic Network. The analysis allowed to detect micro-events down to magnitude Ml=-0.4 within a distance of ~15km from the array. Our results confirmed that the system based on the array installation and the FAST data-analysis might contribute to lower the magnitude of completeness around the site of about 0.7.

Weak signal spectral detection is a serious problem in many applications, especially the target possesses certain frequency band and under low signal-to-noise ratio (SNR). A kind of novel technique based on pre-whitening scale-transformation symmetric bistable parallel stochastic resonance (SR) is proposed to solve the problem. Firstly, the pre-whitening can ensure the even distribution of the receiving signal to fit the requirement of SR processing. Secondly, the scale- transformation can help to utilize the weak signal improvement property especially under low frequency band more effectively. Thirdly, the symmetric bistable parallel SR can try to reduce the variance of the clutter and additive noise fluently. Fourthly, by subtracting the steady state re-sponse of the selected symmetric bistable SR system from the parallel SR output, the weak signal spectral detection objective can be realized successfully. Simulation results based on the real sea clutter radar data guarantee the effectiveness and applicability of the proposed symmetric bistable PSR processing approach.

A multimodal detection system with complementary capabilities for efficient detection was developed for impurity detection. The system consisted of a visible light camera, a multispectral camera, image correction and registration algorithms. It can obtain spectral feature and color feature at the same time, and has higher spatial resolution than a single spectral camera. This system was applied to detect impurities in Pu ’er tea to verify its high efficiency. The spectral and color features of each pixel in the images of Pu ’er tea were obtained by this system and used for pixel classification. The experimental results show that the accuracy of Support Vector Machine (SVM) model based on combined features is 93%, which is 7% higher than that based on only spectral features. By applying median filtering algorithm and contour detection algorithm to the label matrix extracted from pixel-classified images, 8 impurities except hair were detected successfully. Moreover, taking advantage of the high resolution of visible light camera, small impurities can be clearly imaged. By comparing the segmented color image with the pixel-classified image, small impurities such as hair could be detected successfully. Finally, it is proved that the system can obtain multiple images to allow a more detailed and comprehensive understanding of the detected items, and has excellent ability to detect small impurities.

Buildings are rapidly becoming more digitized, to a large extent due to developments in IoT. This will provide many opportunities but also a number of challenges. One of the central challenges in the process of digitizing buildings is the ability to monitor the building’s status effectively. This monitoring is essential for various services that rely on information about the presence and activities of individuals within different areas of the building. Occupancy information, including people counting, occupancy detection, location tracking, and activity detection, plays a vital role in the management of smart buildings. In this article, our primary focus is on the use of Passive Infrared (PIR) sensors for gathering occupancy information. PIR sensors are among the most widely used sensors for this purpose due to their consideration of privacy concerns, cost-effectiveness, and low processing complexity compared to many others. Despite numerous literature review articles in the field of occupancy information, there currently isn’t a specialized literature review dedicated to occupancy information derived specifically from PIR sensors.Therefore, this study analyzes articles that specifically explore the application of PIR sensors for occupancy information. This article provides a comprehensive literature review of PIR sensor technology from 2015 to 2023, with a focus on applications in people counting, activity detection, and localization (traking and location). It consolidates findings from a number of articles that have explored and enhanced the capabilities of PIR sensors in these interconnected domains. This review thoroughly examines the application of various techniques, machine learning algorithms, and configurations for PIR sensors in indoor building environments, emphasizing not only the data processing aspects but also their advantages, limitations, and efficacy in producing accurate occupancy information.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects. The paper seeks to offer a thorough analysis of the present state and potential future advancements of PIR sensor technology in efficiently monitoring and understanding occupancy information by classifying and analyzing improvements in these domains.

Road cracks significantly affect the serviceability and safety of roadways, especially in mountainous terrain. Traditional inspection methods, such as manual detection, are excessively time-consuming, labor-intensive, and inefficient. Additionally, multi-function detection vehicles equipped with various sensors are expensive and not suitable for mountainous roads due to poor conditions. To address these challenges, this study proposes a customized Unmanned Aerial Vehicles (UAV) inspection system designed for automatic crack detection. The system focuses on enhancing autonomous capabilities in mountainous terrains by incorporating embedded algorithms for route planning, autonomous navigation, and automatic crack detection. The slide window method is proposed to enhance the autonomous navigation of UAV flights by generating path planning in mountainous roads. This method compensates for GPS/IMU positioning errors, particularly in GPS-denied or GPS-drift scenarios. Moreover, the YOLOv8 algorithm is introduced to conduct autonomous crack detection from UAV imagery in the offboard module. To validate our UAV inspection system's performance, we conducted several experiments to assess its accuracy, robustness, and efficiency. The experimental results demonstrate that our UAS inspection system accurately estimates the flight trajectory along the mountainous road for autonomous navigation. Furthermore, the experimental detection results also demonstrate that the YOLOv8 algorithm achieves higher recognition accuracy compared to the YOLOv5, and YOLOv7-tiny algorithms, exceeding 3.1%,and 6.8% of mAP, respectively. In summary, the UAV inspection system proposed in this study can provide a useful tool and technological guidance for the regular inspection of mountainous roads.

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an Electroencephalography (EEG) based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM) the K Nearest Neighbor (KNN) the Naive Bayes (NB) the Decision Tree (DT) and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake, and drowsy). Segmentation into 10-second intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries.

This paper introduces the AltumView Sentinare smart activity sensor for senior care and patient monitoring. The sensor uses an AI chip and deep learning algorithms to monitor the activity of people, collect activity statistics, and notify caregivers when emergencies such as falls are detected. To protect privacy, only skeleton (stick figure) animations are transmitted instead of videos. The sensor is highly affordable, accessible, and versatile. It was a CES 2021 Innovation Award Honoree, and has been selected by Amazon as one of only three fall detection devices integrated into its Alexa Together urgent response service, and has received very positive reviews from Amazon customers. It has also been used in different senior care settings in about ten different countries. The paper presents the main features of the system, the evidences and lessons learned from its practical applications, and future directions.

Over the past couple of decades, Global positioning system (GPS) technology has been utilized to collect large-scale data from travel surveys. As the precise spatiotemporal characteristics of travel could be provided by GPS devices, the issues of traditional travel survey, such as misreporting and non-response, could be addressed. Considering the defects of dedicated GPS devices (e.g., need much money to buy devices, forget to take devices to collect data, limit the simple size because of the number of devices, etc.), and the phenomenon that the smartphone is becoming one of necessities of life, there is a great chance for the smartphone to replace dedicated GPS devices. Although, several general reviews have been done about smartphone-based GPS travel survey in the literature review section in some articles, a systematic review from smartphone-based GPS data collection to travel mode detection has none. The included studies were searched from six databases. The purpose of this review is to critically assess the current literature on the existing methodologies of travel mode detection based on GPS raw data collected by smartphones. Meanwhile, according to the systematic comparison among different methods from data-preprocessing to travel mode detection, this paper could carefully provide the Strengths and Weaknesses of existing methods. Furthermore, it is the crucial step to develop the methodologies and applications of GPS raw data collected by smartphones.

Pig behavior is an integral part of health and welfare management, as pigs usually reflect their inner emotions through behavior change. The livestock environment plays a key role in pigs' health and wellbeing. A poor farm environment increases the toxic GHGs, which might deteriorate pigs' health and welfare. In this study a computer-vision-based automatic monitoring and tracking model was proposed to detect short-term pigs' physical activities in a compromised environment. The ventilators of the livestock barn were closed for an hour, three times in a day (07:00-08:00, 13:00-14:00, and 20:00-21:00) to create a compromised environment, which increases the GHGs level significantly. The corresponding pig activities were observed before, during, and after an hour of the treatment. Two widely used object detection models (YOLOv4 and Fast-er R-CNN) were trained and compared their performances in terms of pig localization and posture detection. The YOLOv4, which outperformed the Faster R-CNN model, coupled with a Deep-SORT tracking algorithm to detect and track the pig activities. The results showed that the pigs became more inactive with the increase in GHG concentration, reducing their standing and walking activities. Moreover, the pigs also shortened their sternal-lying posture increasing the lateral lying posture duration at higher GHG concentration. The high detection accuracy (mAP: 98.67%) and tracking accuracy (MOTA: 93.86% and MOTP: 82.41%) signify the models’ efficacy in monitoring and tracking pigs' physical activities non-invasively.

In this research, a model is presented to detect and monitor the rotor bar’s condition of large motors. This proposed model uses two diagnostic methods MCSA and ZCT, to extract the fault components. The input of the proposed model is only the motor current at two levels of 80% and 100% of the nominal motor load, which by using the two methods MCSA and ZCT and making changes in how to use them can be the disadvantages of other methods such as incorrect detection of rotor bars in Large motors with variable load, the harmonical stator voltage (or the presence of the drives) and asymmetric conditions. The extracted components are classified using neural network, instead of experimental and human resources constraints. Using this classification algorithm is high accuracy and the ability to implement in conventional processors. The proposed model has been trained andtested using currents of real large motor data and 96.87% accuracy using neural network to detect faults and monitor the online status of the rotor bars. On the other hand, the proposed model has been implemented in the industrial environment (FiroozkoohCement Factory) and has been able to correctly determine the rotor bars of 4 large suspicious motors announced by the factory technicians.

This study presents an advanced defect detection approach for solar cells using the YOLOv10 deep learning model. Leveraging a comprehensive dataset of 10,500 solar cell images, annotated with 12 distinct defect types, our model integrates Compact Inverted Blocks (CIB) and Partial Self-Attention (PSA) modules to enhance feature extraction and classification accuracy. Training on the Viking cluster with state-of-the-art GPUs, our model achieved remarkable results, including a mean Average Precision ([email protected]) of 98.5%. Detailed analysis of the model's performance revealed exceptional precision and recall rates for most defect classes, notably achieving 100% accuracy in detecting black core, corner, fragment, scratch, and short circuit defects. Even for challenging defect types such as thick line and star crack, the model maintained high performance with accuracies of 94% and 96%, respectively. The recall-confidence and precision-recall curves further demonstrate the model's robustness and reliability across varying confidence thresholds. This research not only advances the state of automated defect detection in photovoltaic manufacturing but also underscores the potential of YOLOv10 for real-time applications. Our findings suggest significant implications for improving the quality control process in solar cell production.

Adenomyosis, a benign gynecological condition characterized by the infiltration of endometrial tissue into the myometrium, poses significant challenges to women's reproductive health. Recently, the landscape of adenomyosis diagnosis transformed significantly, thanks to advancements in imaging technologies such as transvaginal ultrasound and magnetic resonance imaging. This lead to a noticeable shift in the demographic profile of patients diagnosed with adenomyosis, including younger women of reproductive age who frequently present with a diverse array of symptoms. Approximately 20% of women are affected by adenomyosis. Adenomyosis manifests with various subtypes, distinct epidemiological profiles, symptomatology, and treatment responses, necessitating tailored approaches for optimal management. Despite its clinical significance, adenomyosis remains understudied, resulting in a significant disparity in research and literature compared to other gynecological conditions. The severity of adenomyosis is compounded when coexisting with endometriosis, particularly deep infiltrating endometriosis (DIE), leading to exacerbated fertility issues and severe symptomatology. The wide range of symptoms, including adverse pregnancy outcomes such as pre-eclampsia, highlights its wider impact and emphasizes the need for increased awareness of the condition. Furthermore, Adenomyosis is frequently associated with treatment failure in endometriosis, contributing to dienogest resistance, elevated discontinuation rates, and persistent pain post endometriosis surgery. Additionally, the lack of specific treatments tailored to adenomyosis poses a considerable challenge in clinical management.

Acoustic emission monitoring (AEM) has emerged as an effective technique for detecting wire-breaks resulting from, e.g., stress corrosion cracking, and its application on prestressed concrete bridges is increasing. The success of this monitoring measure depends crucially on a carefully designed sensor layout. For this the attenuation of elastic waves within the structure’s material is determined ideally in-situ through object-related measurements with a reproducible signal source, typically a rebound-hammer. This assumes that the attenuation coefficients derived from rebound-hammer tests are comparable to those from wire-breaks, thus allowing their results to be directly applied to wire-break detection without further adjustments. This study challenges this assumption by analysing attenuation behaviour through an extensive dataset. Employing time-domain and frequency analysis, the research generates attenuation profiles from laboratory experiments and in-situ measurements across various girders and bridge structures, extracting the slope and standard deviation of the residuals. While generally validating this approach, the findings highlight differences in attenuation behaviour from among wire-break signals and rebound-hammer impulses, whereby the latter potentially underestimates the relevant attenuation of wire-breaks by approximately 20 %. Consequently, a transfer factor is proposed to adjust object-related measurement results for wire-break scenarios, including a variance of 1.0 dB/m to cover a 95 % confidence interval for sample scattering. Moreover, the anisotropic attenuation behaviour across different structures was studied, showing that transverse attenuation consistently exceeds the longitudinal, significantly influenced by structural features such as voids. In prefabricated concrete bridges with in-situ-cast concrete slabs, transverse signal transmission remains unhindered across multiple elements. Finally, the results provide a valuable reference for the design of sensor layouts in bridge monitoring, particularly benefiting scenarios where direct in-situ experiences are lacking.

Underwater visual detection technology plays a pivotal role in fields such as marine exploration. With the increasing demand for underwater monitoring, the quest for efficient and reliable methods for underwater target recognition has become particularly significant. To address this requirement, this study developed an innovative underwater object detection architecture based on YOLOv8, named YOLOv8-MU, aimed at significantly enhancing detection accuracy.By integrating the LarK module proposed in UniRepLKNet to optimize the backbone network, YOLOv8-MU aims to achieve a larger receptive field without increasing the model’s depth. Further, this research introduces C2fSTR, an innovative method that combines Swin Transformer with the C2f module. Additionally, we have incorporated the SPPFCSPC_EMA module, which combines Cross-Stage Partial Fast Spatial Pyramid Pooling (SPPFCSPC) with attention mechanisms, significantly improving the detection accuracy and robustness of various biological targets. Moreover, by introducing a fusion block based on DAMO-YOLO into the neck of the model, we further enhanced the model’s capability in multi-scale feature extraction. Finally, the adoption of the MPDIoU loss function, designed around vertex distance, effectively tackles the challenges of localization accuracy and boundary clarity in underwater organism detection. Experimental results on the URPC2019 dataset demonstrate that the YOLOv8-MU model achieved an [email protected] of 78.4%, marking improvements of 5.6%, 1.1%, and 4.0% over YOLOv5s, YOLOv7, and YOLOv8n respectively, indicating the leading performance (SOTA) of this method. On the other hand, further evaluation on the URPC2020 dataset confirmed the generalization capability of the YOLOv8-MU architecture, with its [email protected] reaching 80.4%, surpassing various models including YOLOv5x and YOLOv8n, showcasing the wide applicability of our proposed improved model architecture.

Deadlock is a real problem that can cause expensive, time-dependent hang-ups or failures in distributed computing systems. Some studies have been conducted with deadlock detection and resolution in generalized request computing models, most of these studies are based on the diffusing computation scheme, where forward and backward propagated probe and reply messages respectively are diffused between dependent processes. The replies carry the dependency information between processes for the initiator. Using this dependency information initiator can detect and resolve the deadlock cycle. It has been proven in the literature that a deadlock cycle length distribution is skewed with a large majority of cycles (90%) having length two. Based on this fact an improved algorithm is proposed for handling deadlock detection in distributed computing systems under the distributed request model where each process has several requests at a time. The improved algorithm depends mainly on message propagation and timeout policy. Probe and reply messages are propagated between the initiator and its successors only to detect deadlock cycles between them. Global timeout policy is used to detect potential deadlock cycles with large length distribution. The proposed algorithm can handle concurrent executions. Simulation experiments are performed to see the effectiveness of the improved algorithm. It is found that the improved algorithm compares favorably with other existing algorithms and it shows better results for several performance metrics especially in reducing deadlock latency and execution time.

A stable driver state is essential in the process of manually transition control, which inevitably occurs in Level 3 automated driving situations. To this end, this paper proposed a CNN algorithm-based driver state monitoring system that uses multi-sensor data such as driver's face image, biometric information, and vehicle behavior information as input. This system calculates the probability of drowsiness for each of the four time periods using a convolutional neural network (CNN) based on ToF camera-based eye blinking, ECG information (pulse rate) embedded in the steering wheel, and vehicle information (steering angle data). In order to build a reliable and high-quality training dataset (Ground Truth) for the CNN algorithm, a baseline was established by matching the driver's face image with the electrocardiogram (ECG) and electroencephalogram (EEG) changes in the drowsy and normal states. In a simulation test of the proposed CNN algorithm using more than 20,000 driver image data acquired using a driving simulator, the TNR was 94.8% and the accuracy was 94.2%. Our proposed method is expected to minimize human errors that may occur when switching control by monitoring inappropriate driver state (drowsiness) in real time.

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.

Agriculture is pivotal in national economies, with pest detection significantly influencing food quality and quantity. Pest classification remains challenging in automated agriculture monitoring systems, exacerbated by the non-uniform pest scales and the scarcity of high-quality datasets. In this study, we constructed a pest dataset by acquiring domain-agnostic images from the Internet and resizing them to a standardized 299x299 pixel format. Additionally, we employed diffusion models to generate supplementary data. While Convolutional Neural Networks (CNNs) are prevalent for prediction and classification, they often lack effective global information integration and discriminative feature representation. To address these limitations, we propose the RS Transformer, an innovative model that combines elements like the Region Proposal Network, Swin Transformer, and ROI Align. Additionally, we introduce the Randomly Generated Stable Diffusion Dataset (RGSDD) to augment the availability of high-quality pest datasets. Extensive experimental evaluations demonstrate the superiority of our approach compared to both two-stage models (SSD and Faster R-CNN) and one-stage models (YOLOv3, YOLOv4, YOLOv5m, YOLOv8, and DETR). We rigorously assess performance using metrics such as mean Average Precision (mAP), F1Score, Recall, and mean Detection Time (mDT). Our research contributes to advancing pest detection methodologies in automated agriculture systems, promising improved food production and quality.

The autonomous displacement and displacement measurement functions of the maglev ruler are performed by the mover core. The stability of the four magnetic field in air gaps and the levitation position of the maglev ruler is one of the key factors for the stability of the thrust force on the power core, and it is also one of the key factors for ensuring the precision of the maglev ruler. There is cross-coupling between the two ends of the mover core of the maglev ruler, resulting in a strongly coupled, nonlinear, multi-input and multi-output system for the levitating system of the maglev ruler. This paper establishes a mathematical model for the levitating system of the maglev ruler, and designs a levitating control system for the maglev ruler based on ADRC control algorithm to achieve decoupling and disturbance suppression. Through simulation analysis and experimental testing of the levitating system with starting and disturbance, it is proved that the levitating control system of the maglev ruler has good dynamic characteristics, static characteristics, and robustness.

Achieving effective control over microbial contamination necessitates the precise and concurrent identification of numerous pathogens. In this research, we have devised a remarkably sensitive duplex droplet digital PCR (dddPCR) reaction system to simultaneously detect Pseudomonas aeruginosa (P. aeruginosa) and Pseudomonas fragi (P. fragi). Employing comparative genomics, we identified four genes of P. fragi. By specific analysis, RS22680 gene was selected as the detection target of P. fragi and LasR gene was chosed as P. aeruginosa, which were applied to construct a dddPCR reaction. In terms of specificity, sensitivity and anti-interference ability, the constructed dddPCR detection system was verified and analyzed. The assay showed excellent sensitivity and applicability, as evidenced by a limit of detection of 100 CFU/mL. When the concentration of natural background bacteria in milk or fresh meat was 100 times that of the target detection bacteria, the method was still capable of completing the absolute quantification. In the simulation of actual sample contamination, P. aeruginosa could be detected after 3 h of enrichment culture, and P. fragi could be detected after 6 h. The established ddPCR detection system exhibits exceptional performance, serving as a foundation for the simultaneous detection of various pathogenic bacteria in food products.

Rapid and accurate detection of road cracks is of great significance for road health monitoring, but currently this work is mainly completed through manual site surveys. Low-altitude UAV remote sensing can obtain images with centimeter or even subcentimeter ground resolution, which provides a new efficient and economical approach for rapid crack detection. Nevertheless, crack detection networks face challenges such as edge blurring and misidentification due to the heterogeneity of road cracks and the complexity of the background. To address these issues, we propose a real-time edge reconstruction crack detection network (ERNet) which adopts multi-level information aggregation to reconstruct crack edges and improve the accuracy of segmentation between the target and background. To capture global dependencies across spatial and channel levels, we propose an efficient bilateral decomposed convolutional attention module (BDAM) that combines depth separable convolution and dilated convolution to capture global dependencies across spatial and channel levels. To enhance the accuracy of crack detection, we use a coordinate-based fusion module that integrates spatial, semantic, and edge reconstruction information. In addition, we propose an automatic measurement of crack information for extracting the crack trunk and its corresponding length and width. Experimental results demonstrate that our network achieves the best balance between accuracy and inference speed.

The optimal functionality and dependability of mechanical systems are important for the sustained productivity and operational reliability of industrial machinery which has direct impact on it’s longevity and profitability. Therefore, failure of a mechanical system or any of it component would be detrimental to production continuity and availability. Consequently,this study proposes a robust diagnostic framework for analyzing the blade conditions of shot blast industrial machinery. The framework involves analyzing the spectral characteristics of the vibration signals generated by Industrial Shot Blast. Additionally, a peak detection algorithms is introduced to identify and extract the unique features present in the peak magnitudes of each signal spectrum. A feature importance algorithm is then deployed as the feature selection tool, and these selected features are fed into 10 machine learning classifier, with Extreme gradient boosting (XGB) as the core classifier. Results show that the XGB classifier achieved the best accuracy of 98.05%, with a cost-efficient computational cost of 0.83 seconds. Other global assessment metrics were also implemented in the study to further validate the model.

Mobile inspections conducted by intelligent tunnel robots are instrumental in broadening the inspection reach, economizing on inspection expenditures, and augmenting the operational efficiency of inspections. Despite differences from fixed surveillance, mobile-captured traffic videos have complex backgrounds and device conditions that interfere with accurate traffic event identification, warranting more research. This paper proposes an improved algorithm based on YOLOv9 and DeepSORT for intelligent event detection in edge computing mobile device using the intelligent tunnel robot. The enhancements comprise the integration of the Temporal Shift Module to boost temporal feature recognition and the establishment of logical rules for identifying diverse traffic incidents in mobile video imagery. Experimental results show that our fused algorithm achieves a 93.25% accuracy rate, an inprovement of 1.75% over the baseline. The algorithm is also applicable to inspection vehicles, drones, and autonomous vehicles, effectively enhancing the detection of traffic events and improving traffic safety.

Mulberry leaves, when infected by pathogens, can suffer significant yield loss or even death if early disease detection and timely spraying are not performed. To enhance the detection performance of mulberry leaf diseases in natural environments and to precisely locate early small lesions, we propose a high-precision, high-efficiency disease detection algorithm named YOLOv8-RFMD. Based on improvements to You Only Look Once version 8 (YOLOv8), we first proposed the Multi Dimension Feature Attention (MDFA) module, which integrates important features at the pixel-level, spatial and channel dimensions. Building on this, we designed the RFMD Module, which consists of the Conv-BatchNomalization-SiLU (CBS) module, Receptive-Field Coordinated Attention (RFCA) Conv, and MDFA, replacing the Bottleneck in the model’s Residual block. We then employed Adown down sampling structure to reduce the model size and computational complexity. Finally, to improve the detection precision of small lesion features, we replaced the complete intersection over union (CIOU) loss function with the Normalized Wasserstein Distance (NWD) loss function. Results show that the YOLOv8-RFMD model achieves an mAP50 of 94.3% and an mAP50:95 of 67.8% on experimental data, representing increases of 2.9% and 4.3% respectively compared to the original model. The model size is reduced by 0.53 MB to just 5.45 MB, and the number of floating-point operations is reduced by 0.3 G to only 7.8 G. The improved model meets the deployment requirements of mobile embedded devices and can provide a theoretical reference for the automated spraying operations of mulberry leaves.

Extracellular vesicles (EVs) hold enormous potential in the diagnosis and treatment of diseases, benefit from their roles in intercellular signaling, as well as their plentiful presence and stability in body fluids. However, conventional EV isolation methods are labor-intensive, and harvest EVs with low purity and compromised recovery. In addition, the drawbacks, such as limited sensitivity and specificity of traditional EV analysis methods hinder the application of EVs in clinical use. Therefore, it is urgent to develop effective and standardized methods for isolating and detecting EVs. Microfluidics technology is a powerful and rapidly developing technology that has been introduced as a potential solution for the above bottlenecks. It holds the advantages of high integration, short analysis time, low consumption of samples and reagents. In this review, we summarize the traditional techniques alongside microfluidic-based methodologies for the isolation and detection of EVs. We emphasize the separation advantages of microfluidic technology in enhancing EV capture efficiency and precise targeting, while summarizing its analytical role in targeted detection and discussing the significance of EV detection in the tumor microenvironment, providing a direction for achieving automated and high-throughput EV detection in clinical samples.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

Breast cancer remains a major public health concern, and early detection can result in more treatment options, which are crucial for improving survival rates. Metabolomics offers the potential to develop blood-based screening and diagnostics tools that are less invasive and more cost-effective. However, the inherent complexity of metabolomic datasets makes identifying the most diagnostically relevant biomarkers a difficult task, with multiple studies demonstrating lim-ited agreement on the specific metabolites and pathways involved. This study aims to identify a set of biomarkers for early diagnosis of breast cancer using metabolomics data. Plasma samples from 185 breast cancer patients and 53 controls (CHTN) were analyzed. We utilized univariate Naïve Bayes, L2-regularized Support Vector Machines, and Principal Component Analysis (PCA), along with feature engineering techniques, to select the most informative features. Multiple ma-chine learning models, including Support Vector Machines, Multidimensional Scaling, Logistic Regression, and Ensemble Learning were utilized for classification. The best-performing feature set comprised 4 biomarkers and 2 demographic variables, achieving an accuracy of 98%, demon-strating the potential for a robust, cost-effective, non-invasive breast cancer screening and diagnostic tool.

The proposed research methodology aims to design a generally implementable framework for providing a house owner/member with the immediate notification of an on-going theft (unauthorized access to their premises). For this purpose, a rigorous analysis of existing systems was undertaken to identify research gaps. The problems found with existing systems were that they can only identify the intruder after the theft, or cannot distinguish between human and non-human objects. Wireless Sensors Networks (WSNs) combined with the use of Internet of Things (IoT), Cognitive Internet of Things, Internet of Medical Things, and Cloud Computing are expanding smart home concepts and solutions, and their applications. The primary objective of the present research work was to design and develop IoT and cloud computing based smart home solutions. In addition, we also propose a novel smart home anti-theft system that can detect an intruder, even if they have partially/fully hidden their face using clothing, leather, fiber, or plastic materials. The proposed system can also detect an intruder in the dark using a CCTV camera without night vision facility. The fundamental idea was to design a cost-effective and efficient system for an individual to be able to detect any kind of theft in real-time and provide instant notification of the theft to the house owner. The system also promises to implement home security with large video data handling in real-time.

In recent years, with the development of the Internet of Things and distributed computing, the "server-edge device" architecture has been widely deployed. This study focuses on leveraging autoencoder technology to address the binary classification problem in network intrusion detection, aiming to develop a lightweight model suitable for edge devices. Traditional intrusion detection models face two main challenges when directly ported to edge devices: inadequate computational resources to support large-scale models and the need to improve the accuracy of simpler models. To tackle these issues, this research utilizes Extreme Learning Machine for its efficient training speed and compact model size to implement autoencoders. Two improvements over the latest related work are proposed: First, to improve data purity and ultimately enhance detection performance, this study partitions the data into multiple regions based on the prediction results of these autoencoders. Second, leveraging autoencoder characteristics to investigate further the data within each region. We used the public dataset NSL-KDD to test the behavior of the proposed mechanism. The experimental results show that when dealing with multi-class attacks, the model's performance was significantly improved, the accuracy and the F1-score are improved by 3.5% and 2.9%, respectively maintaining its lightweight nature.

Forest fires are part of a set of natural disasters that have always affected regions of the world typically characterized by a tropical climate with long periods of drought. However, due to climate change in recent years, other regions of our planet have also been affected by this phenomenon, never seen before. One of them is certainly the Italian peninsula, and especially the regions of southern Italy. For this reason, the scientific community, as well as remote sensing one, is highly concerned in developing reliable techniques to provide useful support to the competent authorities. In particular, three specific tasks have been carried out in this work: (i) fire risk prevention, (ii) active fire detection, and (iii) post-fire area assessment. To accomplish these analyses, the capability of a set of spectral indices, derived from spaceborne remote sensing (RS) data, is assessed to monitor the forest fires. The spectral indices are obtained from Sentinel-2 multispectral images of the European Space Agency (ESA), which are free of charge and openly accessible. Moreover, the twin Sentinel-2 sensors allow to overcome some restrictions on time delivery and observation repeat time. The performance of the proposed analyses were assessed experimentally to monitor the forest fires occurred in two specific study areas during the summer of 2017: the volcano Vesuvius, near Naples, and the Lattari mountains, near Sorrento (both in Campania, Italy).

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tool and the left-handed tool. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. For gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

The human eye is a vital source of collecting information worldwide via daily observation. The computer science area recognizes it in research as a human-computer interaction. Human blink is an integral part of this observation as a research topic. Several studies have been conducted on eye blinking and left-right eye movements. Previous studies conducted on the eye blink consider the availability of hardware devices high in the budget, high Precision, and low light expo-sure, unlike our study, which uses low-budget devices as simple as a webcam and more versatile usable techniques, incredibly both dim and high light to name a few. This study offers the observational approach via ResNet101v2, VGG-19, and Convolution Neural Network (CNN) architectures. Outperforming both VGG-19 and CNN in this study, ResNet101v2 achieves an impressive accuracy of 98.2%. In contemporary times, deep learning in AI is taking an advanced form. This study attempts to provide a new insight into the real-world implementation of the eye blink.

Exposure to malachite green (MG) may pose great health risks to humans, thus it is of prime importance to develop fast and robust methods to quantitatively screen the presence malachite green in environment. Herein application of extractive electrospray ionization mass spectrometry (EESI-MS) has been extended to the trace detection of MG within lake water and aquiculture water, due to the intensive use of MG as biocide in fisheries. This method has the advantage of obviating offline liquid-liquid extraction or tedious matrix separation prior to the measurement of malachite green in native aqueous medium. The experimental results indicate that the extrapolated detection limit for MG was ~3.8 ug L-1 (S/N=3) in lake water samples and ~ 0.5 ug L-1 in ultrapure water under optimized experimental conditions. The signal intensity of MG showed good linearity over the concentration range of 10–5000 ug L-1. Measurement of practical water samples fortified with MG at 0.01 and 0.1 mg L-1 gave a good validation of the established calibration curve. The average recoveries of malachite green in lake water and Carassius carassius fish farm effluent water were 114.9% (6.6% RSD) and 85.4% (9.2% RSD), respectively. Overall, the established EESI-MS/MS method has been demonstrated suitable for sensitive and rapid (<2 min per sample) quantitative detection of malachite green in various aqueous media, indicating its potential for online real-time monitoring of real life samples.

In an era of rapid technological improvements, state-of-the-art methodologies and tools dedicated to protecting and promoting our cultural heritage should be developed and extensively employed in the contemporary built environment and lifestyle. At the same time, sustainability principles underline the importance of the continuous use of historic or vernacular buildings as part of the building stock of our society. Adopting a holistic, integrated, multi-disciplinary strategy can bridge technological innovation with conserving and restoring heritage buildings. The paper presents ongoing research and results of the application of Machine Learning methods for the remote monitoring of the built environment of the historic cluster in Cypriot cities. This study is part of an integrated, multi-scale, and multi-discipline study of heritage buildings towards the creation of an online HBIM platform for urban monitoring.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors and complexity of character interactions.Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy.To address the dataset complexity and multi-targeting problems, feature extraction is optimized and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students raising their hands, reading, writing, playing cell phones, looking down, and lying on the table in high-definition images. And the accuracy and robustness of this network are verified.Compared with small target detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network has better detection performance and can efficiently deal with the behavior recognition of multiple students.

In emergency situations, ensuring standardized Cardiopulmonary Resuscitation (CPR) actions is crucial. However, current Automated External Defibrillators (AEDs) lack methods to determine whether CPR actions are performed correctly, leading to inconsistent CPR quality. To address this issue, we introduce a novel method called Deep Learning-based CPR Action Standardization (DLCAS). This method involves three parts. First, it detects correct posture using OpenPose to recognize skeletal points. Second, it identifies a marker wristband with our CPR-Detection algorithm and measures compression depth, count and frequency using a depth algorithm. Finally, we optimize the algorithm for edge devices to enhance real-time processing speed. Extensive experiments on our custom dataset have shown that the CPR-Detection algorithm achieves a mAP0.5 of 97.04%, while reducing parameters to 0.20M and FLOPs to 132.15K. In a complete CPR operation procedure, the depth measurement solution achieves an accuracy of 90% with a margin of error less than 1 cm, while the count and frequency measurements achieve 98% accuracy with a margin of error less than 2 counts. Our method meets the real-time requirements in medical scenarios, and the processing speed on edge devices have increased from 8fps to 25fps.

The intentional damages to local Cultural Heritage sites carried out in recent months by the Islamic State have received wide coverage from the media worldwide. Earth Observation data provide important information to assess these damages in such non-accessible areas, and automated image processing techniques would be needed to speed up the analysis if a fast response is desired. This paper shows the first results of applying fast and robust change detection techniques to sensitive areas, based on the extraction of textural information and robust differences of brightness values related to pre- and post-disaster satellite images. A map highlighting potentially damaged buildings is derived, which could help experts at timely assessing the damages to the Cultural Heritage sites of interest. Encouraging results are obtained for two archaeological sites in Syria and Iraq.

This article utilizes the Canny edge extraction algorithm based on contour curvature and the cross-correlation template matching algorithm to extensively study the impact of high-repetition-rate CO2 pulsed Laser on the target extraction and tracking performance of the infrared imaging detector. It establishes a quantified dazzling pattern for lasers on infrared imaging systems. By conducting laser dazzling and damage experiments, a detailed analysis of the normalized correlation between target and dazzling images is performed to quantitatively describe laser dazzling effects. Simultaneously, an evaluation system, including target distance and laser power evaluation factors, is established to determine the dazzling level and whether the target is recognizable. The research results reveal that laser power and target position are crucial factors affecting the detection performance of infrared imaging-guided weapon systems under laser dazzling. Different laser powers are required to successfully interfere with the recognition algorithm of infrared imaging-guided weapons at different distances. And laser dazzling will produce a lot of false edge information, which seriously affects the performance of pattern recognition algorithm. In laser damage experiments, the detector experienced functional damage, with a quarter of the image displaying as completely black. The energy density threshold required for functional damage to the detector is approximately 3 J/cm2. The dazzling assessment conclusions also apply to evaluating damage results. Finally, the proposed evaluation formula aligns with experimental results, objectively reflecting the actual impact of laser dazzling on the target extraction and tracking performance of infrared imaging systems. This study provides an in-depth and accurate analysis for understanding the influence of lasers on the performance of infrared imaging-guided weapons.

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

Digital photogrammetry has attracted widespread attention in the field of geotechnical and geological survey due to its low-cost, ease of use and contactless mode. In this work, with the purpose of studying the progressive block surficial detachments of a landslide we developed a monitoring system based on fixed multi-view time-lapse cameras. Thanks to a new-developed photogrammetric algorithm based on the comparison of photo sequences through a structural similarity metric and the computation of the disparity map of two convergent views we can quickly detect the occurrence of collapse events, determine their location and calculate the collapse volume. With the field data obtained at the Perarolo landslide site (Belluno Province, Italy), we have preliminary tested the effectiveness of the algorithm and its accuracy in the volume calculation. The method of quickly and automatically obtaining collapse information proposed in this paper can extend the potentials of landslide monitoring system based on videos or photo sequence and it will be of great significance for further research on the link between the frequency of collapse events and the driving factors.

YOLOv8, as an efficient object detection method, can swiftly and precisely identify objects within images. However, traditional algorithms encounter difficulties when detecting small targets in remote sensing images, such as missing information, background noise, and interactions among multiple objects in complex scenes, which may affect performance. To tackle these challenges, we propose an enhanced algorithm optimized for detecting small objects in remote sensing images, named HP-YOLOv8. Firstly, we design the C2f-D-Mixer (C2f-DM) module as a replacement for the original C2f module. This module integrates both local and global information, significantly improving the ability to detect features of small objects. Secondly, we introduce a feature fusion technique based on attention mechanisms, named Bi-Level Routing Attention in Gated Feature Pyramid Network (BGFPN). This technique utilizes an efficient feature aggregation network and reparameterization technology to optimize information interaction between different scale feature maps, and through the Bi-level Routing Attention (BRA) mechanism, it effectively captures critical feature information of small target objects. Finally, we propose the Smooth Mean Perpendicular Distance Intersection over Union (SMPDIoU) loss function. The method comprehensively considers the shape and size of detection boxes, enhances the model's focus on the attributes of detection boxes and provides a more accurate bounding box regression loss calculation method. To demonstrate our approach's efficacy, we conduct comprehensive experiments across the RSOD, NWPU VHR-10, and VisDrone2019 datasets. The experimental results show that the HP-YOLOv8 achieves 95.11%, 93.05%, and 53.49% in the [email protected] metric, and 72.03%, 65.37%, and 38.91% in the more stringent [email protected]:0.95 metric, respectively.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.

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

Outliers seriously affect the accuracy in geometric model fitting. Previous works in coping with outliers involve threshold selection and scale estimation. However most scale estimators suppose the inlier distribution as a Gaussian model, which usually poorly meets the cases in geometric model fitting. Outliers, considered as the points with big residuals to all the true models, share common items with big values in quantized residual preferences, thus making the outliers gather away from the inliers in quantized residual preference space. In this paper we make use of this outlier consensus in quantized residual preference space by extending the usage of energy minimization to combine the model error and the spatial smoothness in quantized residual preference space for outlier detection. The energy minimization based outlier detection process follows an alternate sampling and labeling framework. After the outlier detection, an ordinary energy minimization method is employed to optimize the inlier labels, which also follows the framework of alternate sampling and labeling. The experimental results in this study show that the energy minimization based outlier detection method can detect most of the outliers in the data. Furthermore, the proposed energy minimization based inlier segmentation process segments the inliers into different models quite accurately. Overall, the performance of the proposed method is better than most of the state-of-the-art methods.

Fire detection from satellite sensors relies on an accurate estimation of the unperturbed state of a target pixel, from which an anomaly can be isolated. Methods for estimating the radiation budget of a pixel without fire depend upon training data derived from the location's recent history of brightness temperature variation over the diurnal cycle, which can be vulnerable to cloud contamination and the effects of weather. This study proposes a new method that utilises the common solar budget found at a given latitude in conjunction with an area's local solar time to aggregate a broad-area training dataset, which can be used to model the expected diurnal temperature cycle of a location. This training data is then used in a temperature fitting process with the measured brightness temperatures in a pixel, and compared to pixel-derived training data and contextual methods of background temperature determination. Results of this study show similar accuracy between clear-sky medium wave infrared upwelling radiation and the diurnal temperature cycle estimation compared to previous methods, with demonstrable improvements in processing time and training data availability. This method can be used in conjunction with brightness temperature thresholds to provide a baseline for upwelling radiation, from which positive thermal anomalies such as fire can be isolated.

With increasing power and speed of laser welding, in-process monitoring has become even more crucial to ensure process stability and weld quality. Due to its low cost and installation flexibility, acoustic process monitoring is a promising method and has demonstrated its effectiveness. Since its feasibility has been the focus of existing studies, the temporal resolution of acoustic emissions (AE) has not yet been addressed despite its utmost importance for realizing real-time systems. Aiming to provide a benchmark for further development, this study investigates the relationship between duration and informativeness of AE signals during high power (3.5kW) and high speed (12m/min) laser beam butt welding. Specifically, the informativeness of AE signals is evaluated based on the accuracy of detecting and quantifying joint gaps for various time windows of signals, yielding numerical comparison. The obtained results show that signals can be shortened up to a certain point without sacrificing their informativeness, encouraging to optimize the signal duration. Our results also suggest that large gaps (> 0.3mm) induce unique signal characteristics in AE, which are clearly identifiable from 1 ms signal segments, equivalent to 0.2mm weld seam.

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.