Abnormal Behavior Detection Research Articles

IoT Intrusion Detection System based on Machine Learning Algorithms usingthe UNSW-NB15 dataset

The evolution of communications systems with the advent of IoT is leading to an increase in attacks against them. This is due to the fact that the security of connected objects in the IoT is an emerging area which still requires preventive solutions against various attacks. At the network security level, Intrusion Detection Systems (IDS) are used to analyze network data and detect abnormal behavior in the network. In this work, we implemented different machine learning models to build an intrusion detection system based on the UNSW NB15 dataset. To do this, we did data cleaning and feature engineering on the data in the pre-processing phase. Then we used various models such as logistic regression, support vector machine(SVM)classifier, decision tree, random forest, eXtremeGradient Boosting(XGBoost)in order to predict attacks. Finally, an intrusion detection system is trained on various machine learning algorithms and we selected the most effective model. Experiments were carried out on the UNSW-NB15 dataset and subsequently we compared other machine learning algorithms, and this meansthat the random forest model on important parameters has a clear advantage in the detection of rare abnormal behaviors

Correlation Mining-Based Strategies for Improving the Quality and Efficiency of Financial Data Center Operation, Maintenance, and Monitoring in Cloud-Native Models

Abstract At present, the daily operation and maintenance of large-scale data centers such as banks in China, due to a variety of reasons, often brings about the problem of unexpected events that are difficult to locate. In order to ensure that the systems running in the data center work efficiently, this paper proposes a method for improving the operation, maintenance, and monitoring of financial data centers based on the cloud-native model. First, we sequentially cleanse and process the financial center data to eliminate any negative impact and generate a time-trending correlation of financial attributes. We then apply association mining to data center operation and maintenance, using stock information as an example to analyze the operational results in stock trading transactions. The result of correlation mining is component B index (up)⇒ component A index (up), support = 12/100, confidence = 12/19, which indicates that in 100 trading days, the number of days that the component B index and the component A index rise together is 12 days, while the number of days that the component B rises alone is 19 days. In the case study examining the impact of association mining in stock trading, on March 15, 2022, the stock price experienced a rise from 11.456 to 11.498 within a mere 0.1s. The financial data operation and maintenance system, using association mining, identified this as “abnormal,” demonstrating the model’s successful detection of abnormal behavior.

Real-Time Detection of Abnormal Behavior of Escalator Passengers Based on YOLOv5s

Real-Time Detection of Abnormal Behavior of Escalator Passengers Based on YOLOv5s

Design of Abnormal Behavior Detection System Based on Multimodal Fusion

Design of Abnormal Behavior Detection System Based on Multimodal Fusion

Research on Employee Abnormal Behavior Detection Algorithm Based on Improved SSD

Research on Employee Abnormal Behavior Detection Algorithm Based on Improved SSD

Development of Abnormal Behavior Detection Technology for Distracted Driving Detection from Driver Driving images

Development of Abnormal Behavior Detection Technology for Distracted Driving Detection from Driver Driving images

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

Integrating Surrounding Vehicle Information for Vehicle Trajectory Representation and Abnormal Lane-Change Behavior Detection.

The detection of abnormal lane-changing behavior in road vehicles has applications in traffic management and law enforcement. The primary approach to achieving this detection involves utilizing sensor data to characterize vehicle trajectories, extract distinctive parameters, and establish a detection model. Abnormal lane-changing behaviors can lead to unsafe interactions with surrounding vehicles, thereby increasing traffic risks. Therefore, solely focusing on individual vehicle perspectives and neglecting the influence of surrounding vehicles in abnormal lane-changing behavior detection has limitations. To address this, this study proposes a framework for abnormal lane-changing behavior detection. Initially, the study introduces a novel approach for representing vehicle trajectories that integrates information from surrounding vehicles. This facilitates the extraction of feature parameters considering the interactions between vehicles and distinguishing between different phases of lane-changing. The Light Gradient Boosting Machine (LGBM) algorithm is then employed to construct an abnormal lane-changing behavior detection model. The results indicate that this framework exhibits high detection accuracy, with the integration of surrounding vehicle information making a significant contribution to the detection outcomes.

Public Place Crowd Transaction Monitoring System

Currently, the phenomenon of abnormal movement in public spaces by groups is becoming increasingly prominent, leading to issues concerning public flow and safety. The escalating problems of high crowd density, the presence of controlled dangerous items, and unexpected group activities highlight the necessity for timely detection in public settings. Timely identification of such scenarios will facilitate prompt responses and assistance from relevant government departments. Exploring how artificial intelligence technology can aid urban management personnel in effectively detecting abnormal group behaviors is crucial. Having the ability to swiftly and efficiently evacuate crowds in emergency situations holds significant practical importance. This paper employs deep learning methodologies to assist urban management personnel in efficiently monitoring crowd density and detecting abnormal behaviors. The aim is to maintain crowd density within reasonable limits and enable rapid and effective crowd evacuation in emergency situations. Detection of abnormal group behaviors typically involves methods based on global features, extracting feature patterns like optical flow from entire video segments and constructing corresponding histograms. Given that automatic classification of crowd patterns involves sudden and abnormal changes, a novel method is proposed to extract motion "textures" from dynamic STV (Space-Time Volume) blocks formed from real-time video streams.

The model of vessel trajectory abnormal behavior detection based on graph attention prediction and reconstruction network

The identification of atypical vessel behavior is a crucial factor in ensuring the safety of maritime navigation and enhancing the effectiveness of waterway oversight. The current approach to detecting vessel abnormal behavior lacks consideration for the inter-dependency among different time series and various characteristics associated with abnormal vessel behavior. Additionally, the subjective setting of anomaly detection threshold adversely affects the real-time performance of anomaly detection, resulting in poor detection accuracy. In order to tackle these issues, this paper explores the monitoring and detection mechanism of vessel abnormal behavior based on Graph Attention Prediction and Reconstruction Network. The proposed mechanism employs a sliding window to generate fixed data input. It effectively captures the inter-dependencies among vessel behavior characteristics. Additionally, it dynamically adjusts the threshold for identifying anomalies based on variations in the marine environment, utilizing the Peak Over Threshold (POT) method. In order to achieve real-time detection of abnormal vessel behavior in multivariate, multi-dimensional time series data, it is necessary to complete the task. The results of the paper are derived from an analysis of the AIS dataset encompassing vessel movements between Dalian and Yantai. The temporal scope of the dataset spans from November 1, 2021, to December 31, 2021. The detection accuracy, detection precision and recall rate are 98.29%, 92.44%, 87.09% respectively. The results indicate that there is an enhancement in the accuracy of detecting abnormal behavior in vessels, leading to a significant reduction in the blind area of VTS (Vessel traffic services) system monitoring.

A Contextually Supported Abnormality Detector for Maritime Trajectories

The analysis of maritime traffic patterns for safety and security purposes is increasing in importance and, hence, Vessel Traffic Service operators need efficient and contextualized tools for the detection of abnormal maritime behavior. Current models lack interpretability and contextualization of their predictions and are generally not quantitatively evaluated on a large annotated dataset comprising all expected traffic in a Region of Interest. We propose a model for the detection of abnormal maritime behaviors that provides the closest behaviors as context to the predictions. The normalcy model relies on two-step clustering, which is first computed based on the positions of the vessels and then refined based on their kinematics. We design for each step a similarity measure, which combined are able to distinguish boats cruising shipping lanes in different directions, but also vessels with more freedom, such as pilot boats. Our proposed abnormality detection model achieved, on a large annotated dataset extracted from AIS logs that we publish, an ROC-AUC of 0.79, which is on a par with State-of-the-Art deep neural networks, while being more computationally efficient and more interpretable, thanks to the contextualization offered by our two-step clustering.

CViT: A Convolution Vision Transformer for Video Abnormal Behavior Detection and Localization

CViT: A Convolution Vision Transformer for Video Abnormal Behavior Detection and Localization

Deep convolutional neural network based real-time abnormal behavior detection in social networks

In this study, we introduce a novel real-time approach for detecting abnormal behaviors in online social networks, leveraging both dynamic user activities and their associated profiles through Convolutional Neural Networks (CNN). Social networks, which serve as hubs for communication, discussion, and multimedia sharing, amass a plethora of user data. This vast reservoir of information, while invaluable for genuine interactions, is susceptible to exploitation by malicious entities. Despite numerous previously proposed detection methods, the challenge of ensuring security persists. Our distinctive framework, rigorously tested using an extensive dataset sourced from the web and executed via the CNN toolbox in MATLAB, consistently demonstrates an impressive 99.9% classification accuracy. This achievement not only underscores the method's effectiveness but also marks a significant stride towards proactively identifying and neutralizing potential threats in digital social platforms.

Intelligent recognition and behavior tracking of sea cucumber infected with Vibrio alginolyticus based on machine vision

The outbreak of aggregative diseases in the process of sea cucumber cultivation has brought huge economic losses to aquaculture farmers. It is of positive significance to realize intelligent detection of abnormal behavior to avoid the outbreak of aggregative diseases. Therefore, this paper researches the approaches of intelligent recognition and behavior tracking of sea cucumbers. Fusing the Coordinated Attention and Bi-directional Feature Pyramid Network, the DT-YOLOv5 intelligent recognition model is proposed to enhance the representation ability and feature extraction ability. A multi-object behavior tracking approach is presented based on the automatic frame-matching coordinates, which can track multiple objects and calculate the volumes of exercise. The experimental results show that the precision, recall and AP50:95 are 99.43%, 98.91% and 84.89%, respectively. This research provides a theoretical support for the detection of abnormal behavior of aquatic animals during intensive aquaculture and has potential practical application value for protecting the welfare of sea cucumbers and improving the intelligence level of aquaculture.

Big data driven vessel trajectory prediction based on sparse multi-graph convolutional hybrid network with spatio-temporal awareness

The revolutionary progress of deep learning and data mining technology has greatly contributed to the rapid development of maritime Internet of Things. In order to advance intelligent maritime traffic services, it is necessary to accurately predict the future trajectories of vessels, which is conducive to collision avoidance, maritime surveillance and abnormal behavior detection. In this work, a new method of vessel trajectory prediction based on sparse multi-graph convolutional hybrid network with spatio-temporal awareness is proposed, namely SMCHN model, which uses sparse spatial graph to capture the adaptive interactions between vessels and remove redundant interactions, and sparse temporal graph can be used to simulate the movement trends of vessels, bringing the movement behavior of vessels closer and closer to reality. In addition, the hybrid network is designed to fuse information from different sources by adjusting weights. Finally, the temporal convolutional network with gating mechanism is used to predict the future trajectories of vessels. Experimental results show that the SMCHN model improves 31%, 66% and 54% in short-term, medium-term and long-term vessel trajectory prediction compared with the optimal baseline model.

Facial Emotion Recognition for Photo and Video Surveillance Based on Machine Learning and Visual Analytics

Modern video surveillance systems mainly rely on human operators to monitor and interpret the behavior of individuals in real time, which may lead to severe delays in responding to an emergency. Therefore, there is a need for continued research into the designing of interpretable and more transparent emotion recognition models that can effectively detect emotions in safety video surveillance systems. This study proposes a novel technique incorporating a straightforward model for detecting sudden changes in a person’s emotional state using low-resolution photos and video frames from surveillance cameras. The proposed technique includes a method of the geometric interpretation of facial areas to extract features of facial expression, the method of hyperplane classification for identifying emotional states in the feature vector space, and the principles of visual analytics and “human in the loop” to obtain transparent and interpretable classifiers. The experimental testing using the developed software prototype validates the scientific claims of the proposed technique. Its implementation improves the reliability of abnormal behavior detection via facial expressions by 0.91–2.20%, depending on different emotions and environmental conditions. Moreover, it decreases the error probability in identifying sudden emotional shifts by 0.23–2.21% compared to existing counterparts. Future research will aim to improve the approach quantitatively and address the limitations discussed in this paper.

Retracted: Intelligent Transport Surveillance Memory Enhanced Method for Detection of Abnormal Behavior in Video

Retracted: Intelligent Transport Surveillance Memory Enhanced Method for Detection of Abnormal Behavior in Video

Abnormal Behavior Detection Based on Dynamic Pedestrian Centroid Model: Case Study on U-Turn and Fall-Down

With the increasing number of video surveillance cameras in public buildings, it has become challenging, yet significant to detect abnormal pedestrian behaviors in crowd management, to prevent crowd accidents. Although current advancements in human action recognition based on computer vision can help detect abnormal behaviors after their incidence, majority of them lack the ability to detect potential characteristics prior to the occurrence of real abnormal behaviors. Hence, in this study, we addressed this issue by proposing a novel dynamic centroid model (DCM) of a human body, and rebuilding pedestrian joint sub-segments from human skeleton key nodes obtained in camera images. We built a weighted centroid-combined force model based on Newton’s second law, considering acceleration, mass inertial of human body sub-segments, and internal constraints. Thereafter, pedestrian kinematic and dynamic parameters were analyzed, such as speed, trajectory, force. Furthermore, abnormal behavior detection criteria were constructed for typical abnormal-behavior cases: U-turn and fall-down. Comparative experiments between the proposed DCM and the state-of-the-art methods were conducted. The experimental results showed that the model was capable of detecting abnormal behaviors, with mean values of lead time of 277 ms in U-turn behavior, and 562 ms in fall-down behavior, prior to the captured occurrence of these two abnormal behaviors. Finally, a de-occlusion algorithm was designed and jointly used with DCM, validated by a fall-down detecting experiment including partial occlusion. Therefore, this study holds significant value for the prevention of abnormal pedestrian behaviors in public places.

Abnormal Behavior Detection in Online Exams Using Deep Learning and Data Augmentation Techniques

Massive open online courses (MOOCs) and other forms of distance learning have gained popularity in recent years. The success of remote online exam proctoring determines the integrity of the exam. Deep-learning-powered proctoring services have also grown in popularity. A large number of samples are needed for deep-learning training. The network’s generalization ability is poor due to insufficient training data or an uneven lack of variation. This study illustrates how to analyze students’ anomalous behavior by utilizing a YOLOv5 deep model trained using newly produced dataset. To overcome insufficient training data for deep-learning-related issues, this paper proposes a data-augmentation method based on semantic segmentation. The MobileNetV3 model was used to get an image semantic segmentation mask, which was used to get a binary mask, which in turn was used to replace the image background by using conditional subtraction with randomly selected background images. Finally, randomly pixel-based color augmentation was added to the resulting image. The behavioral detection model used in this study achieved 0.98 mean average precision (mAP) on the produced dataset, showing acceptable detection precision. The experimental findings indicate that the suggested augmentation method improves behavioral detection precision by more than 0.3%.

Detecting Abnormal Behaviors in Dementia Patients Using Lifelog Data: A Machine Learning Approach

In this paper, a proof-of-concept method for detecting abnormal behavior in dementia patients based on a single case study is proposed. This method incorporates the collection of lifelog data using affordable sensors and the development of a machine-learning-based system. Such an approach has the potential to enable the prompt detection of abnormal behavior in dementia patients within nursing homes and to send alerts to caregivers, which could potentially reduce their workload and decrease the risk of accidents and injuries. In a proof-of-concept experiment conducted on a single dementia patient in a Korean nursing home, the proposed system, specifically the multilayer perceptron model, demonstrated exceptional performance, achieving an accuracy of 0.99, a precision of 1.00, a recall of 1.00, and an F1 score of 1.00. While being cost-effective and adaptable to various nursing homes, these results should be interpreted as preliminary, being based on a limited sample. Future research is aimed at validating and improving the performance of the abnormal behavior detection system by expanding the experiments to include lifelog data from multiple nursing homes and a larger cohort of dementia patients. The potential application of this system extends beyond healthcare and medical fields, reaching into smart home environments and various other facilities. This study underscores the potential of this system to enhance patient safety, alleviate family concerns, and reduce societal costs, thereby contributing to the improvement of the quality of life for dementia patients.