Behavior Recognition Research Articles

Abnormal Behavior Recognition Based on 3D Dense Connections.

Abnormal behavior recognition is an important technology used to detect and identify activities or events that deviate from normal behavior patterns. It has wide applications in various fields such as network security, financial fraud detection, and video surveillance. In recent years, Deep Convolution Networks (ConvNets) have been widely applied in abnormal behavior recognition algorithms and have achieved significant results. However, existing abnormal behavior detection algorithms mainly focus on improving the accuracy of the algorithms and have not explored the real-time nature of abnormal behavior recognition. This is crucial to quickly identify abnormal behavior in public places and improve urban public safety. Therefore, this paper proposes an abnormal behavior recognition algorithm based on three-dimensional (3D) dense connections. The proposed algorithm uses a multi-instance learning strategy to classify various types of abnormal behaviors, and employs dense connection modules and soft-threshold attention mechanisms to reduce the model's parameter count and enhance network computational efficiency. Finally, redundant information in the sequence is reduced by attention allocation to mitigate its negative impact on recognition results. Experimental verification shows that our method achieves a recognition accuracy of 95.61% on the UCF-crime dataset. Comparative experiments demonstrate that our model has strong performance in terms of recognition accuracy and speed.

Intelligent Surveillance of Airport Apron: Detection and Location of Abnormal Behavior in Typical Non-Cooperative Human Objects

Most airport surface surveillance systems focus on monitoring and commanding cooperative objects (vehicles) while neglecting the location and detection of non-cooperative objects (humans). Abnormal behavior by non-cooperative objects poses a potential threat to airport security. This study collects surveillance video data from civil aviation airports in several regions of China, and a non-cooperative abnormal behavior localization and detection framework (NC-ABLD) is established. As the focus of this paper, the proposed framework seamlessly integrates a multi-scale non-cooperative object localization module, a human keypoint detection module, and a behavioral classification module. The framework uses a serial structure, with multiple modules working in concert to achieve precise position, human keypoints, and behavioral classification of non-cooperative objects in the airport field. In addition, since there is no publicly available rich dataset of airport aprons, we propose a dataset called IIAR-30, which consists of 1736 images of airport surfaces and 506 video clips in six frequently occurring behavioral categories. The results of experiments conducted on the IIAR-30 dataset show that the framework performs well compared to mainstream behavior recognition methods and achieves fine-grained localization and refined class detection of typical non-cooperative human abnormal behavior on airport apron surfaces.

Retraction Note: Artificial intelligence and automatic recognition application in B2C e-commerce platform consumer behavior recognition

Retraction Note: Artificial intelligence and automatic recognition application in B2C e-commerce platform consumer behavior recognition

Recognition of aggressive driving behavior under abnormal weather based on Convolutional Neural Network and transfer learning

Objectives Aggressive driving behavior can lead to potential traffic collision risks, and abnormal weather conditions can exacerbate this behavior. This study aims to develop recognition models for aggressive driving under various climate conditions, addressing the challenge of collecting sufficient data in abnormal weather. Methods Driving data was collected in a virtual environment using a driving simulator under both normal and abnormal weather conditions. A model was trained on data from normal weather (source domain) and then transferred to foggy and rainy weather conditions (target domains) for retraining and fine-tuning. The K-means algorithm clustered driving behavior instances into three styles: aggressive, normal, and cautious. These clusters were used as labels for each instance in training a CNN model. The pre-trained CNN model was then transferred and fine-tuned for abnormal weather conditions. Results The transferred models showed improved recognition performance, achieving an accuracy score of 0.81 in both foggy and rainy weather conditions. This surpassed the non-transferred models’ accuracy scores of 0.72 and 0.69, respectively. Conclusions The study demonstrates the significant application value of transfer learning in recognizing aggressive driving behaviors with limited data. It also highlights the feasibility of using this approach to address the challenges of driving behavior recognition under abnormal weather conditions.

Research on the Human Motion Recognition Method Based on Wearable.

The accurate analysis of human dynamic behavior is very important for overcoming the limitations of movement diversity and behavioral adaptability. In this paper, a wearable device-based human dynamic behavior recognition method is proposed. The method collects acceleration and angular velocity data through a six-axis sensor to identify information containing specific behavior characteristics in a time series. A human movement data acquisition platform, the DMP attitude solution algorithm, and the threshold algorithm are used for processing. In this experiment, ten volunteers wore wearable sensors on their bilateral forearms, upper arms, thighs, calves, and waist, and movement data for standing, walking, and jumping were collected in school corridors and laboratory environments to verify the effectiveness of this wearable human movement recognition method. The results show that the recognition accuracy for standing, walking, and jumping reaches 98.33%, 96.67%, and 94.60%, respectively, and the average recognition rate is 96.53%. Compared with similar methods, this method not only improves the recognition accuracy but also simplifies the recognition algorithm and effectively saves computing resources. This research is expected to provide a new perspective for the recognition of human dynamic behavior and promote the wider application of wearable technology in the field of daily living assistance and health management.

Thermal preference prediction through infrared thermography technology: Recognizing adaptive behaviors

The recognition of thermal adaptation behaviors is a crucial and noninvasive method for accurately and swiftly predicting the thermal preferences of occupants. This is instrumental in enhancing the energy efficiency, indoor personnel comfort, and overall productivity of office buildings. This study employed deep-learning models to analyze a thermal adaptive behavior video dataset captured by Infrared thermography (IRT) cameras to predict the thermal preferences of occupants. A large-scale infrared thermography dataset was developed for recognizing thermal adaptive behaviors using 9650 video samples. Two adaptive behavior recognition models for infrared videos were developed by leveraging neural network models: Two-Stream Inflated 3D ConvNet (I3D) and SlowFast (SF) networks. These models achieved the average prediction accuracies of 83.53 % and 88.56 %, respectively. Notably, both models exhibited a recognition time of milliseconds, facilitating the real-time recognition of thermal adaptive behaviors. This study offers vital technical and theoretical underpinnings for developing decision-making solutions for smart buildings based on noninvasive thermal preference prediction.

A study of falling behavior recognition of the elderly based on deep learning

A study of falling behavior recognition of the elderly based on deep learning

Frontal person image generation based on arbitrary‐view human images

AbstractFrontal person images contain the richest detailed features of humans, which can effectively assist in behavioral recognition, virtual dress fitting and other applications. While many remarkable networks are devoted to the person image generation task, most of them need accurate target poses as the network inputs. However, the target pose annotation is difficult and time‐consuming. In this work, we proposed a first frontal person image generation network based on the proposed anchor pose set and the generative adversarial network. Specifically, our method first classify a rough frontal pose to the input human image based on the proposed anchor pose set, and regress all key points of the rough frontal pose to estimate an accurate frontal pose. Then, we consider the estimated frontal pose as the target pose, and construct a two‐stream generator based on the generative adversarial network to update the person's shape and appearance feature in a crossing way and generate a realistic frontal person image. Experiments on the challenging CMU Panoptic dataset show that our method can generate realistic frontal images from arbitrary‐view human images.

부와 모 간의 양육태도, 훈육방식, 유아 문제행동 인식 차이 비교 연구

The purpose of this study is to provide understanding and information on the parenting of fathers and mothers according to changes in modern society by comparing and analyzing the differences in parenting attitudes, discipline methods, and recognition of children's problem behavior between fathers and mothers. The questionnaires of 167 pairs of 334 fathers and mothers were selected and analyzed as the final subject of this study. As a result of the study, the father had an affectionate and autonomous parenting attitude, and the mother had a controlling and rejecting parenting attitude. In terms of disciplinary methods, both parents often used logical explanation disciplinary methods. The permissive discipline method showed more wealth. Regarding the recognition of infant problem behavior, both parents recognized that hostile-aggressive behavior was the most problematic behavior, and hyperactivity-distracted behavior was perceived as more problematic by mothers than by fathers. The results of this study are expected to provide basic information about fathers and mothers' parenting in response to changes in modern society.

A Cross-Domain Abnormal Behavior Recognition Model and Application Based on Transfer Learning

A Cross-Domain Abnormal Behavior Recognition Model and Application Based on Transfer Learning

An Overview of Behavioral Recognition

Human behavior recognition has become a popular research topic in the field of computer vision. With the introduction of deep learning and attention mechanisms, this field has been further promoted. However, issues such as dataset acquisition and preprocessing operations on multimodal datasets, modeling of long time information in videos, and fusion of temporal and spatial information still exist. In this paper, we first outline some video action recognition datasets and related preprocessing techniques, including frame extraction, optical flow extraction, and skeletal feature acquisition. Then, the relevant models are classified and parsed according to their characteristics and the types of input data modalities. In addition, we evaluate the performance of the models on several benchmark datasets to gain a deeper understanding of the model development process. Finally, we summarized the current challenges faced in the field of video behavior recognition, including model timeliness, data set subjectivity and effective fusion of multi-modal features, and proposed possible future improvement directions in order to provide more ideas and methods for subsequent research.

Triboelectric based smart ceramic tiles

With the exponential development of the Internet of Things (IoTs), big data, and artificial intelligence (AI), smart home technologies have become crucial to people's lives and the construction of smart cities, driving an increasing demand for distributed sensors. In this work, we have for the first time successfully fabricated smart ceramic tiles (SCTs) that integrate electrodes with ceramic tiles using a layer-by-layer temperature gradient sintering method. These SCTs, which are based on triboelectric nanogenerator (TENG) technology, not only demonstrate high sensitivity and good stability, but also offer the potential for high concealment by adjusting glaze composition and color. Under various motion triggers, the SCTs produced high-discrimination electrical output signals, which proves their potential in behavior recognition. Extreme environmental tests further confirmed the SCTs' superior responsiveness. A wireless security monitoring system for SCT sensing, which was developed using IoT chips, enables remote monitoring via mobile devices. This study not only demonstrates the commercial feasibility of SCTs but also highlights their immense potential for imperceptible monitoring within the smart home domain.

Development of a Device and Algorithm Research for Akhal-Teke Activity Level Analysis

This study demonstrated that wearable devices can distinguish between different levels of horse activity, categorized into three types based on the horse’s gaits: low activity (standing), medium activity (walking), and high activity (trotting, cantering, and galloping). Current research in activity level classification predominantly relies on deep learning techniques, known for their effectiveness but also their demand for substantial data and computational resources. This study introduces a combined acceleration threshold behavior recognition method tailored for wearable hardware devices, enabling these devices to classify the activity levels of horses directly. The approach comprises three sequential phases: first, a combined acceleration interval counting method utilizing a non-linear segmentation strategy for preliminary classification; second, a statistical analysis of the variance among these segments, coupled with multi-level threshold processing; third, a method using variance-based proximity classification for recognition. The experimental results show that the initial stage achieved an accuracy of 87.55% using interval counting, the second stage reached 90.87% with variance analysis, and the third stage achieved 91.27% through variance-based proximity classification. When all three stages are combined, the classification accuracy improves to 92.74%. Extensive testing with the Xinjiang Wild Horse Group validated the feasibility of the proposed solution and demonstrated its practical applicability in real-world scenarios.

Driver behaviour recognition based on recursive all‐pair field transform time series model

AbstractTo standardize driver behaviour and enhance transportation system safety, a dynamic driver behaviour recognition method based on the Recurrent All‐Pairs Field Transforms (RAFT) temporal model is proposed. This study involves the creation of two datasets, namely, Driver‐img and Driver‐vid, including driver behaviour images and videos across various scenarios. These datasets are subject to preprocessing using RAFT optical flow techniques to enhance the cognitive process of the network. This approach employs a two‐stage temporal model for driver behaviour recognition. In the initial stage, the MobileNet network is optimized and the GYY module is introduced, which includes residuals and global average pooling layers, thereby enhancing the network's feature extraction capabilities. In the subsequent stage, a bidirectional GRU network is constructed to learn driver behaviour video features with temporal information. Additionally, a method for compressing and padding video frames is proposed, which serves as input to the GRU network and enables intent prediction 0.2 s prior to driver actions. Model performance is assessed through accuracy, recall, and F1 score, with experimental results indicating that RAFT preprocessing enhances accuracy, reduces training time, and improves overall model stability, facilitating the recognition of driver behaviour intent.

Efficient recognition of fish feeding behavior: A novel two-stage framework pioneering intelligent aquaculture strategies

In the domain of aquaculture, the act of feeding fish is a pivotal factor influencing both the growth of the fish and the associated cultivation costs. The implementation of intelligent feeding strategies is a crucial prerequisite for maintaining fish health and minimizing costs, with the accurate discernment of fish feeding behavior serving as the fundamental basis for the realization of such strategies. Addressing the issues of high data redundancy and substantial noise content inherent in the datasets utilized by existing identification models, as well as the intricate design and suboptimal execution efficiency of the model structures, this study introduces a two-stage framework for discriminating fish feeding behavior. In the initial stage, a re-parameterizable multi-scale object detection model is established, facilitating the acquisition of the spatial distribution of fish schools. This process effectively eliminates redundant data and noise, decouples the training and inference processes of the model, equivalently transforms the complex network training weights, and simplifies the inference process of the model. An analysis of the dataset characteristics is conducted, leading to the optimization of the model detector’s design and a reduction in both the model parameters and computational requirements. In the subsequent stage, responding to the key data characteristics of the spatial distribution of fish schools, a lightweight behavior recognition model is designed. This model enables the rapid and accurate identification of fish feeding behavior. A plethora of experimental results demonstrate that the proposed method can achieve a high recognition accuracy (Acc 83.33%) while operating under the constraints of minimal model parameters and computations (6.45M Params, 8.135G FLOPs). This provides a robust model foundation for the industrial application of the algorithm, underscoring the significant potential of the proposed method in advancing intelligent feeding strategies in aquaculture.

Attitudes Toward Unhealthy Relationship Behaviors and Boundary-Setting: Variation Among High School Students.

Teen dating violence (TDV) is common during adolescence and has lasting negative impacts on those who experience it. Yet, there is limited research exploring how well teens recognize unhealthy behaviors and communicate boundaries, both crucial aspects in preventing TDV. This study aimed to investigate how demographic characteristics (i.e., gender, age, sexual identity, and race/ethnicity) relate to adolescents' abilities to recognize unhealthy relationships and willingness to communicate boundaries. Participants (N = 873) completed online surveys during school hours on demographic characteristics (e.g., gender), recognition of unhealthy relationship behaviors, communicating boundaries, and navigating breakups. We found that girls, participants who identify as a sexual minority (e.g., lesbian), and White participants demonstrated significantly higher recognition of controlling behaviors compared to boys and their heterosexual and non-White counterparts, respectively, but there was no significant difference in identifying abusive behaviors such as shouting, yelling, and insulting a partner. Older participants (i.e., ages 16-18) were significantly more likely to recognize controlling and abusive behaviors as unhealthy compared to younger participants (i.e., 13-15). Further, we found that girls and older participants were significantly more willing to communicate boundaries in relationships than boys and their younger counterparts. Our findings align with prior research emphasizing the necessity for prevention strategies that raise awareness of controlling behaviors that can escalate to more severe forms of TDV and equip adolescents with the means to establish and communicate personal boundaries.

Student Classroom Teaching Behavior Recognition Based on DSCNN Model in Intelligent Campus Education

Student Classroom Teaching Behavior Recognition Based on DSCNN Model in Intelligent Campus Education

Preclinical and clinical evidence of the association of colibactin-producing Escherichia coli with anxiety and depression in colon cancer

BACKGROUND The association between the intestinal microbiota and psychiatric disorders is becoming increasingly apparent. The gut microbiota contributes to colorectal carcinogenesis (CRC), as demonstrated with colibactin-producing Escherichia coli (CoPEC). AIM To evaluate the association between CoPEC prevalence and anxiety- and depressive-like behaviors with both preclinical and clinical approaches. METHODS Patients followed after a CRC surgery and for whom the prevalence of CoPEC has been investigated underwent a psychiatric interview. Results were compared according to the CoPEC colonization. In parallel C57BL6/J wild type mice and mice with a CRC susceptibility were chronically infected with a CoPEC strain. Their behavior was assessed using the Elevated Plus Maze test, the Forced Swimming Test and the Behavior recognition system PhenoTyper®. RESULTS In a limited cohort, all patients with CoPEC colonization presented with psychiatric disorders several years before cancer diagnosis, whereas only one patient (17%) without CoPEC did. This result was confirmed in C57BL6/J wild-type mice and in a CRC susceptibility mouse model (adenomatous polyposis colimultiple intestinal neoplasia/+). Mice exhibited a significant increase in anxiety- and depressive-like behaviors after chronic infection with a CoPEC strain. CONCLUSION This finding provides the first evidence that CoPEC infection can induce microbiota-gut-brain axis disturbances in addition to its procarcinogenic properties.

Assessment of sustainable baits for passive fishing gears through automatic fish behavior recognition

Low-impact fishing gear, such as fish pots, could help reduce human’s impact on coastal marine ecosystems in fisheries but catch rates remain low and the harvest of resources used for baiting increases their environmental cost. Using black seabreams (Spondyliosoma cantharus) as target species in the Bay of Biscay, we developed and assessed the efficiency of biodegradable biopolymer-based baits (hereafter bio-baits) made of cockles (Cerastoderma edule) and different biopolymer concentrations. Through a suite of deep and machine learning models, we automatized both the tracking and behavior classification of seabreams based on quantitative metrics describing fish motion. The models were used to predict the interest behavior of seabream towards the bait over 127 h of video. All behavior predictions categorized as interested to the bait were validated, highlighting that bio-baits have a much weaker attractive power than natural bait yet with higher activity after 4 h once natural baits have been consumed. We also show that even with imperfect tracking models, fine behavioral information can be robustly extracted from video footage through classical machine learning methods, dramatically lifting the constraints related to monitoring fish behavior. This work therefore offers new perspectives both for the improvement of bio-baits and automatic fish behavior recognition.

Video Abnormal Behavior Recognition and Trajectory Prediction Based on Lightweight Skeleton Feature Extraction.

Video action recognition based on skeleton nodes is a highlighted issue in the computer vision field. In real application scenarios, the large number of skeleton nodes and behavior occlusion problems between individuals seriously affect recognition speed and accuracy. Therefore, we proposed a lightweight multi-stream feature cross-fusion (L-MSFCF) model to recognize abnormal behaviors such as fighting, vicious kicking, climbing over the wall, et al., which could obviously improve recognition speed based on lightweight skeleton node calculation, and improve recognition accuracy based on occluded skeleton node prediction analysis in order to effectively solve the behavior occlusion problem. The experiments show that our proposed All-MSFCF model has a video action recognition average accuracy rate of 92.7% for eight kinds of abnormal behavior recognition. Although our proposed lightweight L-MSFCF model has an 87.3% average accuracy rate, its average recognition speed is 62.7% higher than the full-skeleton recognition model, which is more suitable for solving real-time tracing problems. Moreover, our proposed Trajectory Prediction Tracking (TPT) model could real-time predict the moving positions based on the dynamically selected core skeleton node calculation, especially for the short-term prediction within 15 frames and 30 frames that have lower average loss errors.