Detection Algorithm Research Articles

Fault detection method for transmission line components based on lightweight GMPPD-YOLO

Abstract This paper designs a lightweight high-precision transmission line component detection model, named grouped dense, monotonic self-regularized, and partial faster convolution, pruning, and distillation optimized—you only look once (GMPPD-YOLO), in transmission line inspection. It addresses the issue of low detection accuracy of target detection algorithms due to the complex background, large differences in target shape, location, texture, etc, as well as diversified and smaller defects in insulator and vibration hammer images taken by unmanned aerial vehicles from multiple angles. To enhance the model’s feature extraction capabilities in complex backgrounds and across different scales, the grouped dense C3 dense feature extraction module was designed, enabling the model to more effectively handle diverse defect forms. Simultaneously, the monotonic self-regularized pyramid pooling–fast (MSPPF) module is proposed to enhance the model’s capability to process multi-scale information. Additionally, the partial-faster C3 feature awareness module is designed to improve feature fusion performance, enhancing the model’s ability to perceive features at different scales. Finally, channel pruning was used to reduce redundant parameters, and knowledge distillation was employed to compensate for the accuracy loss caused by pruning. This approach further compressed the model size while ensuring its detection performance. The experimental results demonstrate that compared to the original YOLOv5s algorithm, the proposed GMPPD-YOLO algorithm achieves a reduction in parameters by 68.4%, a decrease in Giga floating-point operations per second by 58.2%, and a reduction in the model size by 66.4%, while achieving an increase in precision by 1%, mAP50 by 1.1%, and mAP95 by 0.4%. This confirms the significant potential of the GMPPD-YOLO algorithm for deployment in real-time drone-based power transmission line inspections.

Correction: A Study of Novel Initial Fire Detection Algorithm Based on Deep Learning Method

Correction: A Study of Novel Initial Fire Detection Algorithm Based on Deep Learning Method

MFS-DBF: A trustworthy multichannel feature sieve and decision boundary formulation system for Obstructive Sleep Apnea detection

The fine identification of sleep apnea events is instrumental in Obstructive Sleep Apnea (OSA) diagnosis. The development of sleep apnea event detection algorithms based on polysomnography is becoming a research hotspot in medical signal processing. In this paper, we propose an Inverse-Projection based Visualization System (IPVS) for sleep apnea event detection algorithms. The IPVS consists of a feature dimensionality reduction module and a feature reconstruction module. First, features of blood oxygen saturation and nasal airflow are extracted and used as input data for event analysis. Then, visual analysis is conducted on the feature distribution for apnea events. Next, dimensionality reduction and reconstruction methods are combined to achieve the dynamic visualization of sleep apnea event feature sets and the visual analysis of classifier decision boundaries. Moreover, the decision-making consistency is explored for various sleep apnea event detection classifiers, which provides researchers and users with an intuitive understanding of the detection algorithm. We applied the IPVS to an OSA detection algorithm with an accuracy of 84% and a diagnostic accuracy of 92% on a publicly available dataset. The experimental results show that the consistency between our visualization results and prior medical knowledge provides strong evidence for the practicality of the proposed system. For clinical practice, the IPVS can guide users to focus on samples with higher uncertainty presented by the OSA detection algorithm, reducing the workload and improving the efficiency of clinical diagnosis, which in turn increases the value of trust.

Application of Deep Learning Model and Machine Learning Detection Algorithm for Gastric Cancer Patients Undergoing Chemotherapy

This work focused on exploring the application value of machine learning detection (MLD) algorithm and evidence-based nursing (EBN) in the chemotherapy (CHET) for gastric cancer (GC) patients. 100 GC patients who were treated in the Guang’an Traditional Chinese Medicine Hospital and needed postoperative CHET were recruited and randomly assigned to experimental (Exp) and control (Ctrl) groups, each including 50 patients. All participants received adjuvant CHET after gastrectomy. During CHET, participants in the Ctrl group were given routine nursing, while the experimental were given EBN in addition to routine nursing. Differences in self-rating anxiety scale (SAS), self-rating depress scale (SDS), QLQ-C30 life core questionnaire, and adverse reaction (AR) evaluation criteria were compared for participants in different groups after nursing. At the same time, all patients underwent computed tomography (CT) examination and all images were detected by MLD algorithm. After intervention, the SAS and SDS scores of patients in the Exp and Ctrl groups were 26.7±5.3 versus 33.6±6.61 and 30.07±5.58 versus 36.11±8.83, respectively. The total health status (THS) score of patients was 5.59±1.17 in Exp group and 4.53±0.96 in Ctrl group, showing P < 0.05. After intervention, great differences were observed in nausea/vomiting, decreased white blood cells (WBC), decreased haemoglobin (Hb), peripheral nerve paraesthesia (PNP), muscle and joint pain (MJP), hair loss, and other indicators between patients received EBN and routine nursing methods (P < 0.05). The MLD algorithm and EBN were of high application value in the nursing of CHET treatment for GC patients.

LDCNN: A new arrhythmia detection technique with ECG signals using a linear deep convolutional neural network.

The electrocardiogram (ECG) is a fundamental and widely used tool for diagnosing cardiovascular diseases. It involves recording cardiac electrical signals using electrodes, which illustrate the functioning of cardiac muscles during contraction and relaxation phases. ECG is instrumental in identifying abnormal cardiac activity, heart attacks, and various cardiac conditions. Arrhythmia detection, a critical aspect of ECG analysis, entails accurately classifying heartbeats. However, ECG signal analysis demands a high level of expertise, introducing the possibility of human errors in interpretation. Hence, there is a clear need for robust automated detection techniques. Recently, numerous methods have emerged for arrhythmia detection from ECG signals. In our research, we developed a novel one-dimensional deep neural network technique called linear deep convolutional neural network (LDCNN) to identify arrhythmias from ECG signals. We compare our suggested method with several state-of-the-art algorithms for arrhythmia detection. We evaluate our methodology using benchmark datasets, including the PTB Diagnostic ECG and MIT-BIH Arrhythmia databases. Our proposed method achieves high accuracy rates of 99.24% on the PTB Diagnostic ECG dataset and 99.38% on the MIT-BIH Arrhythmia dataset.

Development of a machine learning algorithm for fake news detection

With the extensive technological advancements and expansion, the persistent issues regarding the creation and rapid dissemination of fake news have become a prevalent and recurrent concern. The manipulation of news content has critical repercussions, such as causing public mistrust, fear, harm, and misinformation. Addressing that, this study developed a supervised machine learning algorithm that can accurately classify social media data as fake news. The methodology of the proposed fake news detection model involved five main components: data acquisition from Twitter, data preprocessing, data transformation, model development using Naïve Bayes, decision tree, and support vector machine (SVM) and model evaluation using accuracy, precision, recall and F1-score. The results revealed that decision tree recorded the highest accuracy for both textual data (100%) and metadata (94.54%) and consistently outperformed both Naïve Bayes and SVM in terms of precision, recall, and F1-score metrics, with a score of 100% for the classification of textual data-based datasets. Regarding the metadata-based classification, decision tree also demonstrated excellent performance, with the highest F1-score of 94% for fake news data. Meanwhile, SVM exhibited the highest precision and recall performance for the metadata-based classification. Overall, the application of the decision tree classifier was deemed the most effective in Twitter fake news detection.

SANAS-Net: spatial attention neural architecture search for breast cancer detection

<p>The utilization of mammography images plays a vital role in the prompt detection and treatment of breast cancer. Breast imaging techniques aid medical professionals in assessing the dimensions, morphology, and spatial orientation of breast lesions, facilitating the differentiation between benign and malignant conditions. Breast tissue can vary widely in terms of density, composition, and structure, leading to complexities in distinguishing between benign and malignant conditions. The primary contribution of this paper is the proposal of a spatial attention-based neural architecture search network (SANAS-Net) technique that incorporates a spatial attention mechanism, enabling the model to learn and prioritize key regions within mammograms (MMs). Multi-head attention is employed within the transformer blocks to effectively capture a wide range of spatial relations and feature interactions. Global contextual information was integrated into the transformer blocks by means of introducing positional embeddings. Several practical studies have been undertaken to verify the effectiveness of our methodology in identifying fully attentive networks that exhibit good performance in distinguishing between malignant and benign breast cancer cases. The experimental study reached a test accuracy of 89.95%, which is way higher than previously proposed algorithms for mammography imagebased breast cancer detection.</p>

Optimizing feature extraction for tampering image detection using deep learning approaches

Tamper image detection approach using deep learning involves, creating a model that can accurately identify and localize instances of image tampering, by employing advanced feature extraction methods, object detection algorithms, and optimization techniques that could be manipulated on need basis. Enhance the integrity of visual content by automating the detection of unauthorized alterations, to ensure the reliability of digital images across various applications and domains. The problem addressing the optimization feature extraction techniques involves the detection of subtle manipulations, handling diverse tampering techniques, and achieving robust performance across different types of images and scenarios. The proliferation of sophisticated image editing tools makes it challenging to detect tampered regions within images, necessitating proposed techniques for automated tamper image detection. The research work will focus on four different feature extraction algorithms such as non-negative factorization (NNF), singular value decomposition (SVD), explicit semantic analysis (ESA), principal component analysis (PCA), which are outsourced. Detecting tampered images through deep learning necessitates the meaningful selection and adjustment of several parameters to enhance the model's effectiveness. Integrating the feature extraction algorithm with the suggested methods effectively identifies critical features within the dataset, thereby improving the detection capabilities and achieving higher accuracy.

An intelligent approach to detect and predict online fraud transaction using XGBoost algorithm

The most popular payment method in recent years is the credit card. Due to the E-commerce industry’s explosive growth, the usage of credit cards for online purchases have been greatly increased as a result frauds has increased. Banks have been facing challenges to detect the credit card system fraud in recent years. Credit card fraud happens when the card was stolen for any unauthorized purposes or if the fraudster utilizes the credit card information for his own use. In order to prevent credit card fraud, it is essential to build detection measures. While detecting credit card theft with machine learning (ML), the features of credit card frauds play an important and they must be carefully selected. A fraud detection algorithm must be created in order to correctly locate and stop fraudulent activity as technology advances along with the amount of fraud cases. ML methods are essential for identifying fraudulent transactions. The implementation of fraud detection models is particularly difficult because of the sensitive nature of the data, the unbalanced class distributions, and the lack of data. In this work, an intelligent approach to detect and predict online fraud transaction using extreme gradient boosting (XGBoost) algorithm is described. The XGBoost model predicts whether a transaction is fraud or not. This model will achieve better performance interarm of recall, precision, accuracy and F1-score for credit card fraud detection.

An innovative approach for detecting buildings and construction anomalies in Zenata City

<p>Rapid urban development in Morocco has led to increased construction activities and significant environmental concerns. Recently Zenata city has undergone significant urban development, marking a crucial step in its trajectory toward a modern smart city. As a part of this growth, our research incorporates an innovative method within the You Only Look Once version 8 (YOLOv8) model, representing a significant advance over conventional methods. The YOLO algorithm has been updated with new features and improvements that infuse our work with a dash of innovation. YOLOv8 integration improves construction and irregular construction detection accuracy beyond what is possible with traditional applications. We trained our algorithm using orthophoto captured by DJI MATRICE 300 RTK drone split into georeferenced tiles and annotated using LabelImg software. Through this process, we were able to create a solid 742 image dataset for training, testing, and validation purposes related to construction. Utilizing drone imagery and the YOLOv8 object detection algorithm, buildings and construction irregularities are detected with high accuracy after 300 training epochs on Kaggle's GPU P100. Insights for early detection and effective building site management are provided by this all-encompassing strategy, which supports Zenata City's sustainable urban growth.</p><div> </div>

Improving image-based weld defects detection under interference information via a novel semantic supervision strategy

ABSTRACT Weld defects of skin-skeleton structures are invisible and image-based visual inspections using deep learning neural networks are in demand. The main limitation of previous detection algorithms is interference information in images. The reflective light and uneven brightness distribution hinder algorithms to achieve higher detection reliability. In this work, a novel supervision strategy for defects detection algorithms was proposed to break the limitation. A new semantic gate convolution block was developed to help the neural networks to distinguish between targets and interference. The block utilised semantic segmentation labels and a gate function to control the information transmitted to the detection output. Additionally, a new category-pixel-accuracy loss function was adopted to improve the effectiveness of semantic features. The new function reduced the effects of negative pixels to avoid over emphasis on semantic completeness, thus the ineffective features of interference could be eliminated. The results indicated that the back-propagated gradients from the supervision part taught the backbone networks to focus on correct objects instead of interference. To testify the validity of the current method, the algorithms was verified in burns and collapse defects. The detection accuracy under the new semantic supervision reached 99.1%, which was superior to common CNN.

Application of Big Data and Quantum Computing in the Secure Federated Internet of Things

Federated Internet of Things (IoT) presents both unprecedented opportunities and challenges in security and data management. This study explores the integration of big data analytics and Quantum Computing as potential solutions to address security concerns within the Federated IoT ecosystem. The study examines the implications of leveraging big data analytics to process and analyze the massive volume of data generated by IoT devices. Advanced analytics techniques, including machine learning and anomaly detection algorithms, are employed to enhance the detection and mitigation of security threats such as unauthorized access, data breaches and malicious attacks. Furthermore, the study investigates the role of Quantum Computing infrastructure in providing scalable and reliable resources for securely storing, processing and transmitting IoT data. By offloading computational tasks to quantum-based platforms, the aim is to alleviate the burden on edge devices while ensuring robust security measures are in place to safeguard sensitive information. A comprehensive review of existing literature and case studies identifies key challenges and opportunities in implementing big data and Quantum Computing solutions within the Federated IoT environment. The study also proposes potential frameworks and methodologies for integrating these technologies effectively, considering factors such as data privacy, scalability and interoperability. Overall, this research aims to advance secure IoT systems by leveraging big data analytics and cloud computing. By addressing security concerns proactively and adopting innovative approaches, the goal is to create a more resilient and trustworthy Federated IoT ecosystem, benefiting society at large.

Modeling contextual goals and detecting context conflicts from BDD-based user stories

Behavior-Driven Development (BDD) user stories are widely used in agile methods for capturing user requirements and acceptance criteria due to their simplicity and clarity. However, the concise structure of BDD-based user stories prevents capturing contextual information and connections between them, which help stakeholders understand requirements and uncover potential issues. The contextual goal models (CGMs) can provide explicit relationships between goals and contexts, but manually constructing models is effort-intensive. This paper proposes an automated approach called BUS2C to model contextual goals and detect context conflicts from BDD-based user stories. The aim is to improve requirements analysis by systematically eliciting goals and dependencies. BUS2C approach involves: (1) mapping BDD-based user story elements to CGMs, and (2) merging related models based on similarity. The context conflict detection algorithm checks if contexts associated with different goals are compatible using natural language metrics. We evaluated BUS2C approach through three experiments. First, we showed the effectiveness in merging scattered CGMs with common features. Second, we demonstrated the capability to construct CGMs from BDD-based user stories quickly, assisting modelers. Our merging method also produced models closer to manually built ones versus without merging. Third, we validated that the context conflict detection can successfully identify inconsistencies in small datasets, enhancing requirements quality. Further validation on larger datasets is needed. In conclusion, this work contributes automated techniques to systematically model and analyze contextual goals from BDD-based user stories. By providing unified goal understanding and detecting issues like conflicts, BUS2C approach aims to improve requirements analysis and support adaptive systems development.

Identifying alternately poisoning attacks in federated learning online using trajectory anomaly detection method.

Implicit poisoning in federated learning is a significant threat, with malicious nodes subtly altering gradient parameters each round, making detection difficult. This study investigates this problem, revealing that temporal analysis alone struggles to identify such covert attacks, which can bypass online methods like cosine similarity and clustering. Common detection methods rely on offline analysis, resulting in delayed responses. However, recalculating gradient updates reveals distinct characteristics of malicious clients. Based on this finding, we designed a privacy-preserving detection algorithm using trajectory anomaly detection. Singular values of matrices are used as features, and an improved Isolation Forest algorithm processes these to detect malicious behavior. Experiments on MNIST, FashionMNIST, and CIFAR-10 datasets show our method achieves 94.3% detection accuracy and a false positive rate below 1.2%, indicating its high accuracy and effectiveness in detecting implicit model poisoning attacks.

A Learnable and Explainable Wavelet Neural Network for EEG Artifacts Detection and Classification.

Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model's performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model's ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.

Active Security Surveillance and Object Detection

Active security surveillance and object detection have become crucial components in modern security systems, driven by advancements in computer vision and machine learning. These systems are designed to enhance real-time monitoring and threat detection across various environments, such as public spaces, transportation hubs, and critical infrastructure. Active security surveillance systems continuously scan and analyze video feeds or sensor data to identify potential security threats, unauthorized activities, or anomalies. They employ advanced algorithms for motion detection, facial recognition, and behavioural analysis, allowing for the rapid identification of suspicious activities or individuals. Object detection, a key element of these systems, involves the identification and classification of objects within a given scene. This is typically achieved through deep learning techniques, such as convolutional neural networks (CNNs), which can accurately detect and categorize objects like vehicles, weapons, or unattended bags. The integration of object detection with active surveillance enables more precise and automated responses to potential threats, reducing reliance on human operators and minimizing the risk of oversight. The adoption of active surveillance and object detection technologies has led to significant improvements in security management, offering enhanced situational awareness and faster response times. However, these technologies also raise concerns regarding privacy, data security, and ethical implications, particularly in their deployment in public and private spaces. Addressing these concerns requires careful consideration of data governance, transparency, and regulatory compliance to balance security needs with individual rights. As technology continues to evolve, ongoing research and development are essential to improving the accuracy, efficiency, and ethical deployment of active security surveillance and object detection systems.

Assessment of Small Object Detection Algorithm Based on Improved YOLOv5s

Assessment of Small Object Detection Algorithm Based on Improved YOLOv5s

Multiclass small target detection algorithm for surface defects of chemicals special steel

Multiclass small target detection algorithm for surface defects of chemicals special steel

Hyperspectral Imaging Technique to Characterize Digestate and Visualize Physical Impurities in Anaerobically Digested Biowaste.

Methods used to monitor anaerobic digestion (AD) indicators are commonly based on wet chemical analyses, which consume time and materials. In addition, physical disturbances, such as floating granules (FGs), must be monitored manually. In this study, we present an eco-friendly, high-throughput methodology that uses near-infrared hyperspectral imaging (NIR-HSI) to build a machine-learning model for characterizing the chemical composition of the digestate and a target detection algorithm for identifying FGs. A total of 732 digestate samples were used to develop and validate a model for calculating total nitrogen (TN), total organic carbon (TOC), total ammonia nitrogen (TAN), and chemical oxygen demand (COD), which are the chemical indicators of responses to disturbances in the AD process. Among these parameters, good model performance was obtained using the dried digestates data set, where the coefficient of determination (R2test) and the root-mean-square error (RMSEtest) were 0.82 and 1090 mg/L for TOC, and 0.86 and 690 mg/L for TN, respectively. Furthermore, the unique spectral features of the FGs in reactors with a lipid-rich substrate meant that they could also be identified by the HSI system. Based on these findings, developing NIR-HSI solutions to monitor the digestate properties in AD plants has great potential for industrial application.

Temporal Monitoring of Simulated Burials in an Arid Environment Using RGB/Multispectral Sensor Unmanned Aerial Vehicles

For the first time, RGB and multispectral sensors deployed on UAVs were used to facilitate grave detection in a desert location. The research sought to monitor surface anomalies caused by burials using manual and enhanced detection methods, which was possible up to 18 months. Near-IR (NIR) and Red-Edge bands were the most suitable for manual detection, with a 69% and 31% success rate, respectively. Meanwhile, the enhanced method results varied depending on the sensor. The standard Reed–Xiaoli Detector (RXD) algorithm and Uniform Target Detector (UTD) algorithm were the most suitable for RGB data, with 56% and 43% detection rates, respectively. For the multispectral data, the percentages varied between the algorithms with a hybrid of the RXD and UTD algorithms yielding a 56% detection rate, the UTD algorithm 31%, and the RXD algorithm 13%. Moreover, the research explored identifying grave mounds using the normalized digital surface model (nDSM) and evaluated using the normalized difference vegetation index (NDVI) in grave detection. nDSM successfully located grave mounds at heights as low as 1 cm. A noticeable difference in NDVI values was observed between the graves and their surroundings, regardless of the extreme weather conditions. The results support the potential of using RGB and multispectral sensors mounted on UAVs for detecting burial sites in an arid environment.