Abnormal Behavior Detection Research Articles

Abnormal behavior detection algorithm based on multi-branch convolutional fusion neural network

Abnormal behavior detection algorithm based on multi-branch convolutional fusion neural network

A Multiscale Fusion YOLOV3-Based Model for Human Abnormal Behavior Detection in Special Scenarios

Urban public security incidents are prone to occur. Better understanding of pedestrian abnormal behavior and trajectory in crowded places is conducive to crowd management and safety monitoring. A novel pedestrian abnormal behavior detection model (PABDM) is proposed to identify crowd behavior under abnormal scenarios. This model originated from a multiscale fusion you only look once (YOLO) version 3 (V3) algorithm and was trained using the PASCAL visual object classes (VOC) in combination with an abnormal pedestrian data set (APD), denoted as VOC+APD. Compared with YOLOV3-VOC, single-stage detectors (SSD)-VOC, and SSD-VOC+APD, the proposed model has notable advantages in prediction accuracy and detection efficiency. The results show that the network loss function of the model tends to be stable after 500 epochs, and its detection accuracy is 6% higher than the average accuracy of the compared models. This proposed model also effectively solves the problem of missing detection caused by edge target, fuzzy target, and small target in abnormal state human detection. The research results are of great significance for real-time crowd monitoring in complex scenes.

Dual Stream Conditional Generative Adversarial Network Fusion for Video Abnormal Behavior Detection

Deep learning has been successfully applied to video anomaly detection. However, the way that deep network learn spatio-temporal features autonomously will ignore the specificity of different pattern features. Therefore, this paper focuses on how to efficiently learn deep appearance feature, introduces the idea of learning appearance information by predicting future frame, and proposes dual stream conditional generative adversarial network fusion for video abnormal behavior detection. The video frame and its corresponding optical flow image are transferred to the conditional generative adversarial network to learn the motion feature representation. In addition, inputting the video frame and its corresponding future frame to the network to generate the appearance representation complementary to motion feature. The model is only trained with normal events, therefore it is not able to generate abnormal events accurately. During the test, for the foreground moving targets, the images generated by the model are compared with the ground truth to obtain a two-stream anomaly probability distribution model based on the mean square error used to achieve the purpose of region anomaly detection. Experiments on the public datasets show that the proposed method can effectively detect and locate abnormal behaviors in the video.

The nocturnal life of the great scallops (Pecten maximus, L.): First description of their natural daily valve opening cycle.

Valvometry techniques used to monitor bivalve gaping activity have elucidated numerous relationships with environmental fluctuations, along with biological rhythms ranging from sub-daily to seasonal. Thus, a precise understanding of the natural activity of bivalves (i.e., not exposed to stressful environmental variations) is necessary as a baseline for detecting abnormal behaviors (deviations). This knowledge is also needed to reliably interpret observations of bivalve gaping behavior and associated biological processes (e.g., respiration, nutrition) acquired over time-limited periods. With this in mind, we investigated the natural daily gaping activity of the great scallop (Pecten maximus) by continuously monitoring 35 individuals in several individual tanks and in situ (Bay of Saint-Brieuc, Brittany, France) using fully autonomous Hall effect sensors. Our results revealed a circadian cycle (τ = 24.0h) in scallop gaping activity. Despite significant inter-individual variability in mean opening and cycle amplitude, almost all individuals (87.5%) exhibited nocturnal activity, with valves more open at night than during the day. A shift in light regime in the tanks triggered an instantaneous change in opening pattern, indicating that light levels strongly determine scallop activity. Based on the opening status of scallops, we also identified several gaping behaviors deviating from the regular daily pattern (lack of rhythmicity, high daytime opening), potentially reflecting physiological weakness. While further long-term studies are required to fully understand the natural activity of scallops, these findings pave the way for studies focused on the scallop response to external factors and introduce further research into the detection of abnormal behaviors. Coupling observations of diel valve gaping cycles with other daily variations in organismal and environmental parameters could help explain mechanisms driving the growth patterns of scallops observed in their shell striations. From a technical perspective, our field-based monitoring demonstrates the suitability of autonomous valvometry sensors for studying mobile subtidal bivalve activity in remote offshore environments.

A Review of Abnormal Behavior Detection in Activities of Daily Living

Abnormal behavior detection (ABD) systems are built to automatically identify and recognize abnormal behavior from various input data types, such as sensor-based and vision-based input. As much as the attention received for ABD systems, the number of studies on ABD in activities of daily living (ADL) is limited. Owing to the increasing rate of elderly accidents in the home compound, ABD in ADL research should be given as much attention to preventing accidents by sending out signals when abnormal behavior such as falling is detected. In this study, we compare and contrast the formation of the ABD system in ADL from input data types (sensor-based input and vision-based input) to modeling techniques (conventional and deep learning approaches). We scrutinize the public datasets available and provide solutions for one of the significant issues: the lack of datasets in ABD in ADL. This work aims to guide new researchers to better understand the field of ABD in ADL and serve as a reference for future study of better Ambient Assisted Living with the growing smart home trend.

A method for detecting abnormal behavior of ships based on multi-dimensional density distance and an abnormal isolation mechanism.

Abnormal ship behavior detection is essential for maritime navigation safety. Most existing abnormal ship behavior detection methods only build A ship trajectory position outlier detection model; however, the construction of a ship speed outlier detection model is also significant for maritime navigation safety. In addition, in most existing methods for detecting a ship's abnormal behavior based on abnormal thresholds, one unsuitable threshold leads to the risk of the ship not being minimized as much as possible. In this paper, we proposed an abnormal ship behavior detection method based on distance measurement and an isolation mechanism. First, to address the problem of traditional trajectory compression methods and density clustering methods only using ship position information, the minimum description length principle based on acceleration (AMDL) algorithm and Multi-Dimensional Density Clustering (MDDBSCAN) algorithm is used in this study. These algorithms not only considered the position information of the ship, but also the speed information. Second, regarding the issue of the difficulty in determining the anomaly threshold, one method for determining the anomaly threshold based on the relationship between the velocity weights and noise points of the MDDBSCAN algorithm has been introduced. Finally, due to the randomness issue of the selected segmentation value in iForest, a strategy of selectively constructing isolated trees was proposed, thus further improving the efficiency of abnormal ship behavior detection. The experimental results on the historical automatic identification system data set of Xiamen port prove the practicality and effectiveness of our proposed method. Our experiment results show that the proposed method achieves an improvement of about 10% over the trajectory outlier detection based on the local outlier fraction method, about 14% over the isolation-based online anomalous trajectory method in terms of the accuracy of ship position information anomaly detection, and about 3% over the feature fusion method in terms of the accuracy of ship speed anomaly detection. This method improves algorithm efficiency by about 5% compared to the traditional isolation forest anomaly detection algorithm.

Human Behavior Recognition of Video Surveillance System Based on Neural Network

Video surveillance system is widely used in modern society. Human behavior recognition based on neural network uses computer vision and image processing technology to analyze and judge the behavior of different objects in surveillance video. In order to improve the recognition accuracy of human behavior, this paper makes an in-depth study on the design of video surveillance system and target tracking using the relevant algorithms of neural network. In this paper, the application of relevant neural network algorithms and the technology of character behavior recognition are analyzed by means of experimental method comparison and algorithm comparison. The experimental data shows that in the detection of abnormal behavior, the highest accuracy rate of human behavior recognition is 90% by using the improved hu invariant moment model.

Abnormal Crowd Behavior Detection Using Optimized Pyramidal Lucas-Kanade Technique

Abnormal behavior detection is challenging and one of the growing research areas in computer vision. The main aim of this research work is to focus on panic and escape behavior detections that occur during unexpected/uncertain events. In this work, Pyramidal Lucas Kanade algorithm is optimized using EMEHOs to achieve the objective. First stage, OPLKT-EMEHOs algorithm is used to generate the optical flow from MIIs. Second stage, the MIIs optical flow is applied as input to 3 layer CNN for detect the abnormal crowd behavior. University of Minnesota (UMN) dataset is used to evaluate the proposed system. The experimental result shows that the proposed method provides better classification accuracy by comparing with the existing methods. Proposed method provides 95.78% of precision, 90.67% of recall, 93.09% of f-measure and accuracy with 91.67%.

Detection of abnormal human behavior using deep learning

The complete human body or the various limb postures are involved in human action. These days,Abnormal Human Activity Recognition (Abnormal HAR) is highly well noticed and surveyed in manystudies. However, because of complicated difficulties such as sensor movement, positioning, and so on,as well as how individuals carry out their activities, it continues to be a difficult process. Identifyingparticular activities benefits human-centric applications such as postoperative trauma recovery, gesturedetection, exercise, fitness, and home care help. The HAR system has the ability to automate orsimplify most of the people’s everyday chores. HAR systems often use supervised or unsupervisedlearning as their foundation. Unsupervised systems operate according to a set of rules, whereassupervised systems need to be trained beforehand using specific datasets. This study conducts detailedliterature reviews on the development of various activity identification techniques currently being used.The three methods—wearable device-based, pose-based, and smartphone sensor—are examined in thisinquiry for identifying abnormal acts (AAD). The sensors in wearable devices collect data, whereas thegyroscopes and accelerometers in smartphones provide input to the sensors in wearable devices. Tocategorize activities, pose estimation uses a neural network. The Anomalous Action Detection Dataset(Ano-AAD) is created and improved using several methods. The study examines fresh datasets andinnovative models, including UCF-Crime. A new pattern in anomalous HAR systems has emerged,linking anomalous HAR tasks to computer vision applications including security, video surveillance,and home monitoring. In terms of issues and potential solutions, the survey looks at vision-based HAR

Driver Behavior Classification: A Systematic Literature Review

Driver behavior is receiving increasing attention as a result of the staggering number of road accidents. Many road safety reports regard human behavior as the most important factor in the likelihood of accidents. The detection and classification of aggressive or abnormal driver behavior is an essential requirement in the real world to avoid deadly road accidents and to protect road users. The automatic detection of the driver’s behavior aids in the prevention of dangerous situations for the driver and all other participants in the driving environment, as well as the implementation of corrective measures. This paper presents a systematic literature review (SLR) of the classification of driver behavior. The study aim is to highlight and analyze the different types of driver behavior, data sources, datasets, features, and artificial intelligence techniques used to classify driver behavior and its performance. Based on the results obtained from the analysis of the selected works, we aim to identify the key contributions and challenges of studying driver behavior classification and propose potential avenues for further directions for practitioners and researchers.

An investigation of videos for abnormal behavior detection

The identification of abnormal behavior has several applications. There are several ways, ranging from classical to deep learning based. It may be used to monitor campuses, banks, transportation, and airports. In many circumstances, the context determines whether real-life events are common or unusual. Recent video surveillance anomaly detection systems are good enough, but they come at a significant computational cost and require particular hardware resources. When it comes to real-time anomaly detection, extra emphasis must be paid on lowering model complexity, which causes computational and memory demands. This study attempts to find real-world abnormalities in CCTV recordings, such as violence, detention, property destruction, assault, burglary, blast and theft. The impact of these abnormalities on public safety is enormous. The study also provides a low-cost algorithm for detecting crowd irregularities. The proposed model uses the convolutional neural network based on DenseNet121 as the feature extractor. Our suggested framework has an AUC of 86.63 percent on the UCF-Crime dataset and obtains new stateof-the-art performance

Workload-Aware Scheduling Using Markov Decision Process for Infrastructure-Assisted Learning-Based Multi-UAV Surveillance Networks

In modern networking research, infrastructure-assisted unmanned autonomous vehicles (UAVs) are actively considered for real-time learning-based surveillance and aerial data-delivery under unexpected 3D free mobility and coordination. In this system model, it is essential to consider the power limitation in UAVs and autonomous object recognition (for abnormal behavior detection) deep learning model performance in infrastructure/towers. To overcome the power limitation of UAVs, this paper proposes a novel aerial scheduling algorithm between multi-UAVs and multi-towers where the towers conduct wireless power transfer toward UAVs. In addition, to take care of the high-performance learning model training in towers, the training data from UAVs should be fairly delivered to towers because larger data delivery will make huge computation overhead whereas the less data delivery will introduce overfitting. Therefore, fair data distribution from UAVs to their associated towers is essentially required. Therefore, this paper proposes a novel workload-aware scheduling algorithm between multi-towers and multi-UAVs for joint power-charging from towers to their associated UAVs and training data delivery from UAVs to their associated towers. For computing the workload-aware optimal scheduling decisions in each unit time, our solution approach for the given scheduling problem is designed based on Markov decision process (MDP) to deal with (i) time-varying low-complexity computation and (ii) pseudo-polynomial optimality. As shown in performance evaluation results, our proposed algorithm ensures (i) sufficient times for resource exchanges between towers and UAVs, (ii) the most even and uniform data collection during the processes compared to the other algorithms, and (iii) the performance of all towers converges to optimal levels.

Abnormal behavior detection of solitary elderly people using floor vibration

Abnormal behavior detection of solitary elderly people using floor vibration

Machine Learning-Based Intelligent Video Surveillance in Smart City Framework

The proposed method of using Machine Learning in Motion Detection and Pedestrian Tracking-assisted Intelligent Video Surveillance Systems (ML-IVSS) can be seen as an application of intelligent fusion techniques. ML-IVSS combines the power of motion detection, pedestrian tracking, and machine learning to create a more accurate and efficient surveillance system for smart cities. By fusing these techniques, ML-IVSS can effectively detect unusual behaviors such as trespassing, interruption, crime, or fall-down, and provide accurate depth data from surveillance footage to protect residents. Intelligent fusion techniques can help improve the accuracy and effectiveness of surveillance systems in smart cities, making them safer and more secure for residents. Combination channel models are used at first, and an object area with prominent features is selected for surveillance. Scaled modification and extraction of features are carried out on the presumed object's region. Identifying the low-level characteristic is the first step in incorporating it into neural architectures for deep feature learning. A smart CCTV data set is used to evaluate the proposed method's performance. According to the numerical analysis, the proposed ML-IVSS model outperforms other traditional approaches in terms of abnormal behaviour detection (98.8%), prediction (97.4%), accuracy (96.9%), F1-score (97.1%), precision (95.6%), and recall (96.2%).

STC-NLSTMNet: An Improved Human Activity Recognition Method Using Convolutional Neural Network with NLSTM from WiFi CSI

Human activity recognition (HAR) has emerged as a significant area of research due to its numerous possible applications, including ambient assisted living, healthcare, abnormal behaviour detection, etc. Recently, HAR using WiFi channel state information (CSI) has become a predominant and unique approach in indoor environments compared to others (i.e., sensor and vision) due to its privacy-preserving qualities, thereby eliminating the need to carry additional devices and providing flexibility of capture motions in both line-of-sight (LOS) and non-line-of-sight (NLOS) settings. Existing deep learning (DL)-based HAR approaches usually extract either temporal or spatial features and lack adequate means to integrate and utilize the two simultaneously, making it challenging to recognize different activities accurately. Motivated by this, we propose a novel DL-based model named spatio-temporal convolution with nested long short-term memory (STC-NLSTMNet), with the ability to extract spatial and temporal features concurrently and automatically recognize human activity with very high accuracy. The proposed STC-NLSTMNet model is mainly comprised of depthwise separable convolution (DS-Conv) blocks, feature attention module (FAM) and NLSTM. The DS-Conv blocks extract the spatial features from the CSI signal and add feature attention modules (FAM) to draw attention to the most essential features. These robust features are fed into NLSTM as inputs to explore the hidden intrinsic temporal features in CSI signals. The proposed STC-NLSTMNet model is evaluated using two publicly available datasets: Multi-environment and StanWiFi. The experimental results revealed that the STC-NLSTMNet model achieved activity recognition accuracies of 98.20% and 99.88% on Multi-environment and StanWiFi datasets, respectively. Its activity recognition performance is also compared with other existing approaches and our proposed STC-NLSTMNet model significantly improves the activity recognition accuracies by 4% and 1.88%, respectively, compared to the best existing method.

Multi-homed abnormal behavior detection algorithm based on fuzzy particle swarm cluster in user and entity behavior analytics

User and entity behavior analytics (UEBA) is an anomaly detection technique that identifies potential threat events in the enterprise's internal threat analysis and external intrusion detection. One limitation of existing methods in UEBA is that many algorithms use deterministic algorithms only for one category labeling and only compare with other samples within this category. In order to improve the efficiency of potential threat identification, we propose a model to detect multi-homed abnormal behavior based on fuzzy particle swarm clustering. Using the behavior frequency-inverse entities frequency (BF-IEF) technology, the method of measuring the similarity of entity and user behavior is optimized. To improve the iterative speed of the fuzzy clustering algorithm, the particle swarm is introduced into the search process of the category centroid. The entity's nearest neighbor relative anomaly factor (NNRAF) in multiple fuzzy categories is calculated according to the category membership matrix, and it is combined with boxplot to detect outliers. Our model solves the problem that the sample in UEBA is evaluated only in one certain class, and the characteristics of the particle swarm optimization algorithm can avoid clustering results falling into local optimal. The results show that compared with the traditional UEBA approach, the abnormal behavior detection ability of the new method is significantly improved, which can improve the ability of information systems to resist unknown threats in practical applications. In the experiment, the accuracy rate, accuracy rate, recall rate, and F1 score of the new method reach 0.92, 0.96, 0.90, and 0.93 respectively, which is significantly better than the traditional abnormal detections.

A New Method of Pedestrian Abnormal Behavior Detection Based on Attention Guidance

In public places, some behavior that violates public order and endangers public safety is defined as abnormal behavior. Moreover, it is a necessary auxiliary means to maintain public order and safety by detecting abnormal behavior in a large number of surveillance videos. However, due to the small proportion of abnormal behavior in video data, the extreme imbalance of data seriously restricts the effectiveness of detection. So, weakly supervised learning has become the most suitable and effective detection method. However, existing weakly supervised methods rarely take the locality and slightness of abnormal behavior into account and ignore the details of extracted features. Based on this, an attention-directed abnormal behavior detection model is proposed. In the two common prediction and reconstruction abnormal behavior detection methods based on weak supervision, suitable attention mechanisms are introduced, respectively, and two corresponding attention-directed networks are proposed. In addition, aiming at the problem of inaccurate thresholds for abnormal behavior division, the loss function of the model is improved and a new abnormal behavior evaluation method is proposed. Experiments were carried out on three classical datasets (the USCD Ped1, USCD Ped2, and CUHK Avenue dataset) for abnormal behavior detection. The best results for the area under the curve (AUC) indicator reached 82.7%, 94.5%, and 87.3%, respectively, which are better than many existing literature results.

CUDM: A Combined UAV Detection Model Based on Video Abnormal Behavior

The widespread use of unmanned aerial vehicles (UAVs) has brought many benefits, particularly for military and civil applications. For example, UAVs can be used in communication, ecological surveys, agriculture, and logistics to improve efficiency and reduce the required workforce. However, the malicious use of UAVs can significantly endanger public safety and pose many challenges to society. Therefore, detecting malicious UAVs is an important and urgent issue that needs to be addressed. In this study, a combined UAV detection model (CUDM) based on analyzing video abnormal behavior is proposed. CUDM uses abnormal behavior detection models to improve the traditional object detection process. The work of CUDM can be divided into two stages. In the first stage, our model cuts the video into images and uses the abnormal behavior detection model to remove a large number of useless images, improving the efficiency and real-time detection of suspicious targets. In the second stage, CUDM works to identify whether the suspicious target is a UAV or not. Besides, CUDM relies only on ordinary equipment such as surveillance cameras, avoiding the use of expensive equipment such as radars. A self-made UAV dataset was constructed to verify the reliability of CUDM. The results show that CUDM not only maintains the same accuracy as state-of-the-art object detection models but also reduces the workload by 32%. Moreover, it can detect malicious UAVs in real-time.

Skeleton-Based Abnormal Behavior Detection Using Secure Partitioned Convolutional Neural Network Model.

Theabnormal behavior detection is the vital for evaluation of daily-life health status of the patient with cognitive impairment. Previous studies about abnormal behavior detection indicate that convolution neural network (CNN)-based computer vision owns the high robustness and accuracy for detection. However, executing CNN model on the cloud possible incurs a privacy disclosure problem during data transmission, and the high computation overhead makes difficult to execute the model on edge-end IoT devices with a well real-time performance. In this paper, we realize a skeleton-based abnormal behavior detection, and propose a secure partitioned CNN model (SP-CNN) to extract human skeleton keypoints and achieve safely collaborative computing by deploying different CNN model layers on the cloud and the IoT device. Because, the data outputted from the IoT device are processed by the several CNN layers instead of transmitting the sensitive video data, objectively it reduces the risk of privacy disclosure. Moreover, we also design an encryption method based on channel state information (CSI) to guarantee the sensitive data security. At last, we apply SP-CNN in abnormal behavior detection to evaluate its effectiveness. The experiment results illustrate that the efficiency of the abnormal behavior detection based on SP-CNN is at least 33.2% higher than the state-of-the-art methods, and its detection accuracy arrives to 97.54%.

AREP: an adaptive, machine learning-based algorithm for real-time anomaly detection on network telemetry data

Abnormal behaviour detection is an essential task of real-time monitoring to secure the reliable operation of ICT infrastructures. This paper presents AREP, an adaptive, long short-term memory-based machine learning algorithm for real-time anomaly detection on network telemetry data. AREP is an improved version of Alter-Re^2, the direct predecessor algorithm developed by our research team. AREP introduces automatic tuning of its two key parameters and includes an offset compensation component to increase accuracy. Unfortunately, AREP and its predecessors perform well only on time series showing specific patterns. Thus, we propose also a data type classification method to identify patterns on which AREP performs best. Moreover, we use an extended range of metrics in our performance evaluations, including area under the curve (AUC). AUC computation is based on receiver operating characteristic (ROC) curves. However, generating ROC curves is not straightforward due to the inherent adaptive threshold technique used by AREP and its predecessors, so we had to develop a novel ROC curve generation approach for these algorithms. We show through rigorous experiments that on network time series following specific data patterns AREP overperforms its predecessors and produces similar or even better performance than other state-of-the-art algorithms.