Abnormal Detection System Research Articles

PADrone: Pre-flight Abnormalities Detection on Drone via Deep RF Sensing

Drone delivery is envisioned to be the delivery mode of the future due to its capability to provide autonomous, end-to-end delivery. Such rapid growth of the drone market necessitates careful checks on drone flight delivery, as a failure in any of a drone’s parts can result in an overestimation of the drone’s battery life, an unexpected increase in delivery time, or even a drone crash. Prior works utilize onboard sensors to detect potential drone failures during flight, which is a reactive approach where the problem may have already occurred. In this work, we propose PADrone , a pre-flight and an automated drone abnormality detection system that leverages contactless radio frequency– (RF) based vibration sensing. PADrone utilizes an end-to-end deep learning pipeline to differentiate various abnormalities in motors, propellers, and other drone’s parts, by leveraging their unique vibration fingerprints . PADrone uses a frequency-modulated continuous wave radar-based RF system to capture these unique drone vibrations using an RF bandwidth of 150 MHz in the industrial, scientific, and medical band (5.8 GHz). Our real-world evaluations show that PADrone can classify various drone abnormalities with an average accuracy of 97.5%.

TimbreSense: Timbre Abnormality Detection for Bel Canto with Smart Devices

With the rise of mobile devices, bel canto practitioners increasingly utilize smart devices as auxiliary tools for improving their singing skills. However, they frequently encounter timbre abnormalities during practice, which, if left unaddressed, can potentially harm their vocal organs. Existing singing assessment systems primarily focus on pitch and melody and lack real-time detection of bel canto timbre abnormalities. Moreover, the diverse vocal habits and timbre compositions among individuals present significant challenges in cross-user recognition of such abnormalities. To address these limitations, we propose TimbreSense, a novel bel canto timbre abnormality detection system. TimbreSense enables real-time detection of the five major timbre abnormalities commonly observed in bel canto singing. We introduce an effective feature extraction pipeline that captures the acoustic characteristics of bel canto singing. By applying temporal average pooling to the Short-Time Fourier Transform (STFT) spectrogram, we reduce redundancy while preserving essential frequency-domain information. Our system leverages a transformer model with self-attention mechanisms to extract correlation and semantic features of overtones in the frequency domain. Additionally, we employ a few-shot learning approach involving pre-training, meta-learning, and fine-tuning to enhance the system’s cross-domain recognition performance while minimizing user usage costs. Experimental results demonstrate the system’s strong cross-user domain recognition performance and real-time capabilities.

In-home Gait Abnormality Detection through Footstep-Induced Floor Vibration Sensing and Person-Invariant Contrastive Learning.

Detecting gait abnormalities is crucial for assessing fall risks and early identification of neuromusculoskeletal disorders such as Parkinson's and stroke. Traditional assessments in gait clinics are infrequent and pose barriers, particularly for disadvantaged populations. Previous efforts have explored sensor-based approaches for in-home gait assessments, yet they face limitations such as visual obstructions (cameras), limited coverage (pressure mats), and the need for device carrying (wearables and insoles). To overcome these limitations, we introduce an in-home gait abnormality detection system using footstep-induced floor vibrations, enabling low-cost, non-intrusive, device-free gait health monitoring. The main research challenge is the high uncertainty in floor vibrations due to gait variations among people, making it challenging to develop a generalizable model for new patients. To address this, we analyze time-frequency-domain features of floor vibration data during specific gait phases and develop a feature transformation method through contrastive learning to address the between-people gait variation challenge. Our method transforms the features from vibrations to an embedding space where samples from different people stay close to each other (robust to people variation) while normal and abnormal gait samples are far apart (sensitive to gait abnormality). After that, gait abnormalities are detected by a downstream classifier after feature transformation. We evaluated our approach through a real-world walking experiment with 21 participants and achieved an 85% to 95% mean accuracy in detecting various gait abnormalities. This novel method overcomes prior limitations in in-home gait assessments, offering accessible gait abnormality detection without the need for intrusive devices or labels for new patients.

GastroNet: A CNN based system for detection of abnormalities in gastrointestinal tract from wireless capsule endoscopy images

Gastrointestinal disorders are a class of prevalent disorders in the world. Capsule endoscopy is considered an effective diagnostic modality for diagnosing such gastrointestinal disorders, especially in small intestinal regions. The aim of this work is to leverage the potential of deep convolutional neural networks for automated classification of gastrointestinal abnormalities from capsule endoscopy images. This method developed a deep learning architecture, GastroNetV1, an automated classifier, to detect abnormalities in capsule endoscopy images. The gastrointestinal abnormalities considered are ulcerative colitis, polyps, and esophagitis. The curated dataset consists of 6000 images with “ground truth” labeling. The input image is automatically classified as ulcerative colitis, a polyp, esophagitis, or a normal condition by a web-based application designed with the trained algorithm. The classifier produced 99.2% validation accuracy, 99.3% specificity, 99.3% sensitivity, and 0.991 AUC. These results exceed that of the state-of-the-art systems. Hence, the GastroNetV1 could be used to identify the different gastrointestinal abnormalities in the capsule endoscopy images, which will, in turn, improve healthcare quality.

Abnormal behavior monitoring enhanced smart university stadium under the background of “Internet plus”

AbstractWith the rapid development of the Internet of Things and 5G technology, smart university gymnasiums have become more and more important. However, it has become increasingly difficult for university gymnasium management, especially to detect abnormal behavior with dense crowds under limited venue space. To handle this issue, this paper designs an Artificial Intelligence Internet of Things (AIoT) abnormal behavior detection system which consists of the 5G camera, 5G transmission network and cloud platform. The 5G camera captures and transmits the video to the cloud platform by exploiting the 5G wireless sensor network. In the cloud platform, a hybrid variational autoencoder backbone which exploits the pre‐trained VGG16 and Transformer model is deployed to detect abnormal behaviors. Moreover, by introducing adversarial training mechanisms, the robustness of the proposed model is effectively improved. The experimental results on our self‐built gymnasium abnormal behavior dataset show that the proposed model can correctly identify most of the abnormal behaviors in the gymnasium compared to other models.

SAGA: Stability-Aware Gait Analysis in constraint-free environments

Background:Gait abnormality detection is a challenging task in clinical practice. The majority of the current frameworks for gait abnormality detection involve the individual processes of segmentation, feature estimation, feature learning, and similarity assessment. Since each component of these modules is fixed and they are mutually independent, their performance under difficult circumstances is not ideal. We combine those processes into a single framework, a gait abnormality detection system with an end-to-end network. Methods:It is made up of convolutional neural networks and Deep-Q-learning methods: one for coordinate estimation and the other for classification. In a single joint learning technique that may be trained together, the two networks are modeled. This method is significantly more efficient for use in real life since it drastically simplifies the conventional step-by-step approach. Results:The proposed model is experimented on MATLAB R2020a. While considering into consideration the stability factor, our proposed model attained an average case accuracy of 95.3%, a sensitivity of 96.4%, and a specificity of 94.1%. Significance:Our paradigm for quantifying gait analysis using commodity equipment will improve access to quantitative gait analysis in medical facilities and rehabilitation centers while also allowing academics to conduct large-scale investigations for gait-related disorders. Numerous experimental findings demonstrate the effectiveness of the proposed strategy and its ability to provide cutting-edge outcomes.

Pedestrian Abnormal Behavior Detection System Using Edge–Server Architecture for Large–Scale CCTVEnvironments

As the deployment of CCTV cameras for safety continues to increase, the monitoring workload has significantly exceeded the capacity of the current workforce. To overcome this problem, intelligent CCTV technologies and server-efficient deep learning analysis models are being developed. However, real-world applications exhibit performance degradation due to environmental changes and limited server processing capacity for multiple CCTVs. This study proposes a real-time pedestrian anomaly detection system with an edge–server structure that ensures efficiency and scalability. In the proposed system, the pedestrian abnormal behavior detection model analyzed by the edge uses a rule-based mechanism that can detect anomalies frequently, albeit less accurately, with high recall. The server uses a deep learning-based model with high precision because it analyzes only the sections detected by the edge. The proposed system was applied to an experimental environment using 20 video streams, 18 edge devices, and 3 servers equipped with 2 GPUs as a substitute for real CCTV. Pedestrian abnormal behavior was included in each video stream to conduct experiments in real-time processing and compare the abnormal behavior detection performance between the case with the edge and server alone and that with the edge and server in combination. Through these experiments, we verified that 20 video streams can be processed with 18 edges and 3 GPU servers, which confirms the scalability of the proposed system according to the number of events per hour and the event duration. We also demonstrate that the pedestrian anomaly detection model with the edge and server is more efficient and scalable than the models with these components alone. The linkage of the edge and server can reduce the false detection rate and provide a more accurate analysis. This research contributes to the development of control systems in urban safety and public security by proposing an efficient and scalable analysis system for large-scale CCTV environments.

Abnormal Traffic Detection System Based on Feature Fusion and Sparse Transformer

This paper presents a feature fusion and sparse transformer-based anomalous traffic detection system (FSTDS). FSTDS utilizes a feature fusion network to encode the traffic data sequences and extracting features, fusing them into coding vectors through shallow and deep convolutional networks, followed by deep coding using a sparse transformer to capture the complex relationships between network flows; finally, a multilayer perceptron is used to classify the traffic and achieve anomaly traffic detection. The feature fusion network of FSTDS improves feature extraction from small sample data, the deep encoder enhances the understanding of complex traffic patterns, and the sparse transformer reduces the computational and storage overhead and improves the scalability of the model. Experiments demonstrate that the number of FSTDS parameters is reduced by up to nearly half compared to the baseline, and the success rate of anomalous flow detection is close to 100%.

Involvement of radiographers in the interpretation and reporting of general radiographic images

Globally, radiographers play an important role in the diagnosis and treatment of injuries and diseases. Radiographers have ample opportunities to encounter a wide variety of radiographic images throughout their training and careers. For this reason, radiographers are in a better position to communicate their radiographic observations to the referring clinician. However, there is a lack of clarity on the level of radiographers’ involvement in the interpretation and reporting of general radiographic images. Therefore, this educational article has identified and reviewed the three levels of involvement: abnormality detection system (red dot system), preliminary clinical evaluation (commentary reporting), and clinical reporting as identified from the literature. This information is important to the radiography profession and stakeholders in African countries planning to extend the role of a radiographer in image interpretation and reporting on general radiographic images.

Research on Abnormal Behavior Detection Technology for Simmental Cattle

This paper mainly studies the abnormal behavior detection technology of Simmental cattle, aiming to establish an efficient and reliable abnormal behavior detection system, so as to detect abnormal situations in time and take corresponding measures to deal with potential problems. At the same time, by establishing a dataset for the abnormal behavior of Simmental cattle, the study uses deep learning algorithms to accurately capture the existence, location and key body parts of Simmental cattle, and accurately identify abnormal behaviors such as convulsions and falls. The application of abnormal behavior detection technology to animal husbandry to achieve contactless, automated, and efficient monitoring of Simmental cattle behavior can provide advanced and comprehensive intelligent health management solutions for animal husbandry and promote the wide application of intelligent management in animal husbandry. Real-time monitoring, early warning and fine management of Simmental cattle behavior can effectively reduce the risk of disease transmission and improve the production safety of farms.

Diagnostic accuracy of artificial intelligence-enabled vectorcardiography versus myocardial perfusion SPECT in patients with suspected or known coronary heart disease.

The present study evaluated with myocardial perfusion SPECT (MPS) the diagnostic accuracy of an artificial intelligence-enabled vectorcardiography system (Cardisiography, CSG) for detection of perfusion abnormalities. We studied 241 patients, 155 with suspected CAD and 86 with known CAD who were referred for MPS. The CSG was performed after the MPS acquisition. The CSG results (1) p-factor (perfusion, 0: normal, 1: mildly, 2: moderately, 3: highly abnormal) and (2) s-factor (structure, categories as p-factor) were compared with the MPS scores. The CSG system was not trained during the study. Considering the p-factor alone, a specificity of >78% and a negative predictive value of mostly >90% for all MPS variables were found. The sensitivities ranged from 17 to 56%, the positive predictive values from 4 to 38%. Combining the p- and the s-factor, significantly higher specificity values of about 90% were reached. The s-factor showed a significant correlation (p=0.006) with the MPS ejection fraction. The CSG system is able to exclude relevant perfusion abnormalities in patients with suspected or known CAD with a specificity and a negative predictive value of about 90% combining the p- and the s-factor. Since it is a learning system there is potential for further improvement before routine use.

Artificial intelligence based abnormal detection system and method for wind power equipment

The existing traditional monitoring methods are not ideal for identifying abnormal states in remote real-time monitoring of power system equipment due to adverse weather conditions such as haze and snow. The traditional monitoring methods for wind power equipment mainly rely on manual inspections and regular maintenance, which have problems such as high labor costs, low monitoring efficiency, and low monitoring accuracy. In order to improve the effectiveness of anomaly recognition for power system equipment, this paper proposes a remote real-time monitoring anomaly recognition method for power system equipment based on artificial intelligence technology. Firstly, this article uses pan tilt cameras to capture real-time images of power system equipment and transmit them to a remote monitoring center. The remote monitoring center captures real-time images of the equipment in the video stream and performs real-time image preprocessing. Then, the variational mode decomposition method is used to extract the abnormal state features of power system equipment in the image, and this feature is input into the support vector machine as a training sample to achieve real-time recognition of abnormal state of power system equipment. This article was also conducting fault diagnosis for four sets of wind turbines in the experimental section. According to the experimental results, it can be concluded that the rotational speed of wind turbine 1 increased from around 12 rpm to around 30 rpm during the day. During the day, the temperature of wind turbine 2 increased from around 25 °C to around 40 °C, while wind turbine 3 remained in a stopped state and the current speed decreased to 0. Wind turbine 4 also decreased from around 10 rpm to 0 during the day. From this, it can be concluded that the wind power equipment anomaly detection system based on artificial intelligence can clearly determine the abnormal situation of wind turbines. The wind power equipment anomaly detection system based on artificial intelligence can timely and accurately identify the abnormal situation of WPE, and can provide a new wind power equipment anomaly detection method based on artificial intelligence for the wind power industry. This can provide more accurate and reliable support for the operation and maintenance of wind power equipment, and also provide practice and exploration for the application of artificial intelligence in the industrial field.

Chromosome analysis method based on deep learning: Counting chromosomes and detecting abnormal chromosomes

Karyotype analysis is a cytogenetic test method that counts chromosomes and evaluates their structural abnormalities. However, since the processes of counting chromosomes and determining structural abnormalities are mostly performed manually, the analysis is time-consuming and labor-intensive, and the results may vary depending on the expert who performs the analysis. Therefore, studies for automating karyotype analysis have been conducted; however, most have focused on the detection of dicentric chromosomes among abnormal chromosome classes and counting the number of chromosomes. Therefore, this study proposes an automated chromosome analysis system that applies an object detection method based on deep learning to simplify chromosome analysis and derive effective results. The proposed analysis system consists of a chromosome counting system and an abnormal chromosome detection system. Additionally, to further improve the performance of the automated chromosome analysis system, convolutional spatial pooling attention and squeeze and excitation block are applied. In each proposed system, the object detection-based deep learning model detects a chromosome with a probability of 99.32%, and a chromosome abnormality with a probability of approximately 75.71%.

A newly developed deep learning-based system for automatic detection and classification of small bowel lesions during double-balloon enteroscopy examination

BackgroundDouble-balloon enteroscopy (DBE) is a standard method for diagnosing and treating small bowel disease. However, DBE may yield false-negative results due to oversight or inexperience. We aim to develop a computer-aided diagnostic (CAD) system for the automatic detection and classification of small bowel abnormalities in DBE.Design and methodsA total of 5201 images were collected from Renmin Hospital of Wuhan University to construct a detection model for localizing lesions during DBE, and 3021 images were collected to construct a classification model for classifying lesions into four classes, protruding lesion, diverticulum, erosion & ulcer and angioectasia. The performance of the two models was evaluated using 1318 normal images and 915 abnormal images and 65 videos from independent patients and then compared with that of 8 endoscopists. The standard answer was the expert consensus.ResultsFor the image test set, the detection model achieved a sensitivity of 92% (843/915) and an area under the curve (AUC) of 0.947, and the classification model achieved an accuracy of 86%. For the video test set, the accuracy of the system was significantly better than that of the endoscopists (85% vs. 77 ± 6%, p < 0.01). For the video test set, the proposed system was superior to novices and comparable to experts.ConclusionsWe established a real-time CAD system for detecting and classifying small bowel lesions in DBE with favourable performance. ENDOANGEL-DBE has the potential to help endoscopists, especially novices, in clinical practice and may reduce the miss rate of small bowel lesions.

Abnormal traffic detection system in SDN based on deep learning hybrid models

Software defined network (SDN) provides technical support for network construction of smart cities. However, the openness of SDN is also prone to more network attacks. Traditional abnormal traffic detection algorithms are complex and time-consuming, so it is difficult to find abnormalities in the network in time and unable to satisfy the requirements of abnormal traffic detection in the SDN environment. Therefore, we propose an abnormal traffic detection system based on deep learning hybrid model. The system adopts a hierarchical detection method. Firstly, it completes the rough detection of abnormal traffic in the network according to the statistical information of switch ports and then uses wavelet transform and deep learning technology to extract multi-dimensional features of all traffic data flowing through suspicious switches, so as to realize the fine detection of abnormal traffic from the surface. The experimental results show that the proposed detection method based on port information can quickly locate the source of abnormal traffic. Compared with the traditional abnormal traffic detection method in SDN, the fine detection method based on multi-dimensional features improves the accuracy by 1.7 %, the recall rate by 1.6 %, and the false positive rate by 91.3 %.

Design of Abnormal Behavior Detection System Based on Multimodal Fusion

The application of intelligent video surveillance systems can reduce the workload of staff, save human resources, and timely handle abnormal situations, reducing losses. Abnormal behavior detection based on multimodal fusion is a key part of intelligent video surveillance systems and a hot research topic in the field of pattern recognition. Its application prospects are very broad. Firstly, the dual stream residual convolutional neural network was studied. Based on the convolutional neural network model, the dual stream convolutional neural network model and residual convolutional neural network model were studied; Then, research the overall solution and related technologies, based on the multimodal fusion process, and study techniques such as RGB images, optical flow images, and bone images; Finally, the Resnet34 model was used for training and simulation, and the simulation results showed that the Resnet34 model has superiority. Applying deep residual structures to dual stream CNN has better recognition performance.

Deep learning-based optimization method for detecting data anomalies in power usage detection devices

Abstract In this paper, the self-attention layer of a graph convolutional neural network is first constructed to output the important information in the network structure. The migration learning network model is established, and the sample data are preprocessed and trained sequentially. The final processing results are used as the initial data for abnormal power consumption detection. Introduce Bayes’ theorem to optimize the hyperparameters of the model. The optimized model is applied in the abnormal power consumption detection system to identify abnormal power consumption events and provide specific processing solutions. Through the detection of the system, it was found that the voltage of the test user dropped from a 100V cliff to about 20V in late November, which was determined by the system to be a power consumption abnormality, and, therefore, an operation and maintenance order was issued. The site survey revealed that the data was in line with the system detection. Calculating the power consumption information of another user, the phase voltage of this user stays around 85-100V, far below 150V, so the undercounting of power is verified for the user, and the amount of power that should be recovered is 201.22kW.

Abnormal noise identification of engines based on wavelet packet transform and bispectrum analysis

Abnormal noise is the most prominent problem for motorcycles and affects the consumers’ purchasing desire and driving experience and the enterprise’s competitiveness. Usually, the noise from a newly assembled engine is detected by manual auscultation (MA) to determine if the engine is operating normally. However, MA is also affected by subjective and objective factors with severe labor intensity, and its accuracy greatly fluctuates. Importantly, MA cannot be applied in a corporation with mass production and high-quality requirements. To improve the efficiency and accuracy of motorcycle engine quality inspection and achieve intelligent production, an online engine abnormal noise detection method was proposed based on wavelet packet transform (WPT) and bispectrum analysis (BA); this method improved the accuracy and stability of the identification of the abnormal noise engine and reduced the cost of the check. First, the acoustic signal of the engine of the motorcycle was acquired by using a free-field microphone. Second, the background noise of signals was eliminated by using the wavelet correlation coefficient (WCC) theory, and the signal features were extracted by applying WPT and BA. Third, the feature vectors were normalized before being used as support vector machine (SVM) samples. Fourth, an appropriate kernel function and parameters were selected to train the vector machine using the training sets. Finally, the testing sets were used to inspect the accuracy of the vector machines. The result showed that the training accuracy is 95% and the testing accuracy is 97.5 of the samples were suitable by using the method of wavelet packet transform-bispectrum analysis-support vector machines (WPT-BA-SVM). WPT-BA-SVM effectively identified engine fault types and provided the theoretical foundation for the establishment of an engine abnormal noise online detection system.

M-MultiSVM: An efficient feature selection assisted network intrusion detection system using machine learning

The intrusions are increasing daily, so there is a huge amount of privacy violations, financial loss, illegal transferring of information, etc. Various forms of intrusion occur in networks, such as menacing networks, computer resources and network information. Each type of intrusion focuses on specified tasks, whereas the hackers may focus on stealing confidential data, industrial secrets and personal information, which is then leaked to others for illegal gains. Due to the false detection of attacks in the security and changing environmental fields, limitations like data lagging on actual attacks and sustaining financial harms occur. To resolve this, automatic abnormality detection systems are required to secure the required computing ability and to analyze the attacks. Hence, an efficient automated intrusion detection system using machine learning methodology is proposed in this research paper. Initially, the data are gathered from CSE-CIC-IDS 2018 and UNSW-NB15 datasets. The acquired data are pre-processed using Null value handling and Min-Max normalization. Null value handling is used to remove missing values and irrelevant parameters. Min-Max normalization adjusted the unnormalized data in the pre-processing stage. After pre-processing, the class imbalance problem is reduced by using the Advanced Synthetic Minority Oversampling Technique (ASmoT). ASmoT aims to balance the class and reduce imbalance class problems and overfitting issues. The next phase is feature extraction, which is performed by Modified Singular Value Decomposition (M-SvD). M-SvD extracts essential features such as basic features, content features and traffic features from the input. The extracted features are optimized by the Opposition-based Northern Goshawk Optimization algorithm (ONgO). These optimal features are able to produce optimal output. After feature selection, the different types of attacks are classified by a hybrid machine learning model called Mud Ring assisted multilayer support vector machine (M-MultiSVM) and finally, the hyperparameters are tuned by the Mud Ring optimization algorithm. Thus, the proposed M-MultiSVM model can efficiently detect intrusion in the network. The performance metrics show that the proposed system achieved 99.89 % accuracy by using the CSE-CIC-IDS 2018 dataset; also, the proposed system achieved 97.535 % accuracy by using the UNSW-NB15 dataset.

Driver abnormal behavior detection system using two-stage object detection

Driver abnormal behavior detection system using two-stage object detection