A Novel Spatio-Temporal Violence Classification Framework Based on Material Derivative and LSTM Neural Network

Lejmi, Wafa; Khalifa, Anouar Ben; Mahjoub, Mohamed Ali

doi:10.18280/ts.370501

Cited by 11 publications

(7 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recognition depends on the eye and mouth information to the same extent. It can be seen from this that the facial feature information relied on is different when recognizing the different emotional facial expressions of college students and primary school students [ 49 ].…”

Section: Discussionmentioning

confidence: 99%

Educational Psychology Analysis Method for Extracting Students’ Facial Information Based on Image Big Data

Zhang

2022

Occupational Therapy International

View full text Add to dashboard Cite

At present, most of the research on academic emotions focuses on the concept, current situation, and relevance. There are not many researches on the application of artificial intelligence-based neural network facial expression recognition technology in practical teaching. With reference to image-based big data, this research integrates the application of artificial intelligence facial expression recognition technology with the research on educational theory and applies information technology to the actual teaching process, in order to promote the optimization of the teaching process and improve the learning effect. Method. A Hadoop cluster consisting of 3 nodes is built on the Linux system, and the environment required for Opencv execution is compiled for each node, which provides support for subsequent parallel optimization, feature extraction, feature fusion, and recognition of student facial images. The image data type and input and output format based on MapReduce framework are designed, and the image data is optimized by means of serialized files. The color features, texture features, and Sift features of students’ facial images and common distractors were analyzed. A parallel extraction framework of student facial image features is designed, and based on this, the student facial image feature extraction under Hadoop platform is implemented. This paper proposes a dynamic sequential facial expression recognition method that combines shallow and deep features with an attention mechanism. The relative position of facial landmarks and local area texture features based on FACS represent shallow-level features. At the same time, the structure of ALexNet is improved to extract the deep features of sequence images to express high-level semantic features. The effectiveness of the facial expression recognition system is improved by introducing three attention mechanisms: self-attention, weight-attention, and convolutional attention. Results/Discussion. Through the analysis of the teaching effect, we found that when teachers can obtain the correct student’s academic mood, they can intervene on the students’ positive academic mood. The purpose of the intervention is to improve the positive academic emotions of students. After the students receive the intervention, their academic emotions are also improved and are positively correlated with their academic performance. Through the analysis of teaching effect, the research can achieve the predetermined goal. From the specific teaching effect of this study, it is concluded that in classroom teaching, teachers should devote energy to intervene in students’ positive academic emotions, in order to improve students’ positive academic emotions, which will improve students’ academic performance and teaching.

show abstract

Section: Discussionmentioning

confidence: 99%

Educational Psychology Analysis Method for Extracting Students’ Facial Information Based on Image Big Data

Zhang

2022

Occupational Therapy International

View full text Add to dashboard Cite

show abstract

“…In 2020s, the social networking, which uses the semanticbased text analysis, becomes a hot topic in the field of computer science [2]. Various accurate text mining models have emerged, including convolutional neural network (CNN) and long short-term memory (LSTM) model [3][4][5][6][7][8][9][10][11][12]. However, these traditional classification models cannot be directly used for training and applying directly to process the HE files because the HE files are much longer and richer in contents, and the whole HE dataset is more imbalanced than common social network texts (e.g., Tweets) [13].…”

Section: Introductionmentioning

confidence: 99%

Semantic-Based Classification of Long Texts on Higher Education in China

Chun¹,

Fei²

2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

The development level of higher education (HE) is an important indicator of the development level and development potential of a country. The HE-related document is the mirror to reflect the develop process of the HE. The research of high education (HE) has been developing rapidly in China, resulting in a huge number of texts, such as relevant policies, speech drafts, and yearbooks. The traditional manual classification of HE texts is inefficient and unable to deal with the huge number of HE texts. Besides, the effect of direct classification is rather poor because HE texts tend to be long and exist as an imbalanced dataset. To solve these problems, this paper improves the convolutional neural network (CNN) into the HE-CNN classification model for HE texts. Firstly, Chinese HE policies, speech drafts, and yearbooks (1979–2020) were downloaded from the official website of Chinese Ministry of Education. In total, 463 files were collected and divided into four classes, namely, definition, task, method, and effect evaluation. To handle the huge number of HE texts, the Twitter-latent Dirichlet allocation (LDA) topic model was employed to extract word frequency and critical information, such as age and author, enhancing the training effect of CNN. To address the dataset imbalance problem, CNN parameters were optimized repeatedly through comparative experiments, which further improve the training effect. Finally, the proposed HE-CNN model was found more effective and accurate than other classification models.

show abstract

“…In order to address the violent human actions identification issue in videos, Carneiro-et-al. [3] concentrated on implementing a multistream-based learning model. A method that operates on the HOG properties of video frames was proposed [4] in one of the most recent studies on this topic.…”

Section: Literature Reviewmentioning

confidence: 99%

Real time Violence and Weapon detection and Alert System

More,

Patil,

Pattanshetti

2024

Preprint

View full text Add to dashboard Cite

With the proliferation of surveillance systems and the increasing need for public safety, real-time violence detection has emerged as a crucial research area. This project presents a novel approach to real-time violence detection leveraging the power of deep learning through the integration of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory Networks (LSTM) and weapon detection using You Only Look Once algorithm. The proposed system not only accurately identifies violent activities and weapons in video streams but also promptly issues alerts for timely intervention. The proposed system aims to address the challenges associated with accurately and swiftly identifying violent activities and weapons in video streams, making it applicable to diverse settings such as public spaces. The CNN component of the model is designed to automatically extract relevant spatial features from video frames, enabling the network to discern patterns associated with violent actions. Simultaneously, the Bi-LSTM network is employed to capture temporal dependencies and dynamic sequences within the video stream, allowing the model to understand the evolution of events over time. The fusion of spatial and temporal information enhances the robustness and accuracy of violence detection, especially in complex scenarios where contextual information is crucial. To further augment the system's capabilities, we use the You Only Look Once (YOLO) for weapon detection. YOLO is a state-of-the-art object detection algorithm that operates in real-time with high accuracy. By incorporating YOLO into our system, we enhance its ability to not only detect violent activities but also identify the presence of weapons in the scene. This additional functionality adds a crucial layer of security and enables authorities to respond more effectively to potential threats. Overall, the combined approach of CNN, Bi-LSTM, and YOLO offers a comprehensive solution for real-time violence detection in video streams, with the added capability of weapon detection. This integrated system contributes to enhancing public safety and security in various settings, including public spaces, by enabling timely intervention and response to potential threats.

show abstract

A Novel Spatio-Temporal Violence Classification Framework Based on Material Derivative and LSTM Neural Network

Cited by 11 publications

References 74 publications

Educational Psychology Analysis Method for Extracting Students’ Facial Information Based on Image Big Data

Educational Psychology Analysis Method for Extracting Students’ Facial Information Based on Image Big Data

Semantic-Based Classification of Long Texts on Higher Education in China

Real time Violence and Weapon detection and Alert System

Contact Info

Product

Resources

About