检索结果-内蒙古大学图书馆

Abnormal behaviors recognition in crowd environments based on semi-supervised deep learning and hierarchical approach

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第12期15卷 3925-3943页

作者： Asl, Vahid Fazel Karasfi, Babak Masoumi, Behrooz Keyvanpour, Mohammad Reza Department of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Computer Engineering Alzahra University Tehran Iran

This paper tackles the complexity of detecting abnormal behavior by focusing on temporal patterns, such as social force and optical flow, rather than spatial patterns. The CycleGAN system trains on normal behaviors, ensuring that abnormal behaviors are not reproduced during testing. Hierarchical supervised learning and transfer learning techniques are applied to recognize abnormal behaviors. Given the scarcity of abnormal patterns, geometric techniques are employed to augment these patterns, followed by training with temporal models. Experimental results on the UCSD and UMN datasets demonstrate that the proposed method significantly outperforms existing approaches, achieving average AUCs of 99.90% on Ped1, 99.89% on Ped2, and 99.82% on UMN. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Determination of the time location points and investigation of the body sensor network using RATDMA and PATDMA

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9043-9055页

作者： Mohammed Mustafa, M. Kalpana Devi, S. Althaf Ali, A. Gunavathie, M.A. Department of Information Technology Sri Krishna College of Engineering & Technology Coimbatore India Department of Computer Science and Engineering RV University Bengaluru India Andhra Pradesh India Department of Information Technology Panimalar Engineering College Chennai India

Wireless body sensor networks have gained significant importance across diverse fields, including environmental monitoring, healthcare, and sports. This research is concentrated on sports applications, specifically exploring the viability of a wireless body area network tailored for high-performing athletes. The paper is divided into three sections. First, the design of the node location that is used for real-time monitoring of a sportsperson in which the node position, such as the human thigh, foot, arm, wrist, and chest, was estimated and the best position was selected. Second, the accuracy of an application when related to the other schemes such as TDMA with ZigBee and RA-TDMA & PA-TDMA was done. The reliability using RA-TDMA performed well and showed approximately 98% reliability. Finally, the features of wireless communiqués that affect the presentation of the network for RA-TDMA were estimated, such as delay and jitter. These findings collectively contribute to advancing the understanding of optimizing wireless body sensor networks for sports applications, with notable achievements including the identification of the arm as the optimal sensor placement, achieving a 98% success rate, and surpassing alternative techniques in network performance parameters like packet delivery rate. © 2024 – IOS Press.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection in surveillance videos through LSTM auto-encoding and local minima assistance

引用

Discover Internet of Things 2025年第1期5卷 1-25页

作者： Sengonul, Erkan Samet, Refik Abu Al-Haija, Qasem Alqahtani, Ali Alsemmeari, Rayan A. Alghamdi, Bandar Alturki, Badraddin Alsulami, Abdulaziz A. Department of Computer Engineering Ankara University Ankara06100 Turkey Department of Cybersecurity Faculty of Computer & Information Technology Jordan University of Science and Technology PO Box 3030 Irbid22110 Jordan Department of Networks & Communications Engineering College of Computer Science & Information Systems Najran University Najran61441 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Abnormal event detection in video surveillance is critical for security, traffic management, and industrial monitoring applications. This paper introduces an innovative methodology for anomaly detection in video data, encompassing three primary stages: preprocessing, feature learning, and anomaly detection. We employ background subtraction and noise reduction during preprocessing to refine the data. The feature-learning stage involves training an LSTM autoencoder to capture the essential features of normal video sequences. For anomaly detection, we map video data to a lower-dimensional space (latent code) and compare it against the distribution of codes from normal sequences. We determine regularity scores and identify local minima points exceeding a specified threshold while scrutinizing shadows between adjacent maxima to confirm and pinpoint anomalies. When tested on the CUHK Avenue and UMN datasets, our methodology demonstrated performance with AUCs of 93.8% and 94.1%, respectively, outperforming several baseline models. Our results show the high precision of our method that can detect anomalies, highlighting its potential advantages that it can achieve for enhancing systems of surveillance. © The Author(s) 2025.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

A Post-Stroke Rehabilitation System With Compensatory Movement Detection Using Virtual Reality and Electroencephalogram Technologies

引用

IEEE Access 2024年 12卷 61418-61432页

作者： Shih, Chi-Huang Lin, Pei-Jung Chen, Yen-Lin Chen, Shu-Ling National Chin-Yi University of Technology Department of Computer Science and Information Engineering Taichung411030 Taiwan Feng Chia University Department of Information Engineering and Computer Science Taichung40724 Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Hungkuang University Department of Nursing Taichung43302 Taiwan

Stroke is a leading cause of global population mortality and disability, imposing burdens on patients and caregivers, and significantly affecting the quality of life of patients. Therefore, in this study, we aimed to explore the application of virtual reality technology in physical therapy by using immersive interactive training and designing rehabilitation modes for individual and group settings. We also aimed to provide patients with stroke with a comprehensive home-based rehabilitation and treatment plan, ultimately enhancing training effectiveness. Patients can engage in home-based rehabilitation through this system and undergo functional, mirror, and constraint-induced therapies tailored to different task contents. Simultaneously, using brain-computer interface technology, an emotion analysis mechanism was designed to map the patients' brainwave signal data onto a two-dimensional space of positive-negative valence arousal;this approach can enable remote physical therapists to discern the patients' emotional states during the rehabilitation process through virtual spaces, facilitating timely adjustments to rehabilitation tasks. Moreover, to prevent compromised effectiveness owing to improper training postures leading to compensation, the system offers real-time identification and recording, promptly issuing alerts when compensation occurs. The system provides a multiuser virtual rehabilitation space, enabling timely corrections and data observations, offering patients with stroke a home-based rehabilitation program, thereby realizing a localized aging care model. © 2013 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Novel Reliable and Trust Objective Function for RPL-Based IoT Routing Protocol

引用

computers, Materials & Continua 2025年第2期82卷 3467-3497页

作者： Mariam A.Alotaibi Sami S.Alwakeel Aasem N.Alyahya Department of Computer Engineering College of Computer ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Science and Information Technology Shaqra UniversityShaqra11961Saudi Arabia

The Internet of Things (IoT) integrates diverse devices into the Internet infrastructure, including sensors, meters, and wearable devices. Designing efficient IoT networks with these heterogeneous devices requires the selection of appropriate routing protocols, which is crucial for maintaining high Quality of Service (QoS). The Internet engineering Task Force’s Routing Over Low Power and Lossy Networks (IETF ROLL) working group developed the IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) to meet these needs. While the initial RPL standard focused on single-metric route selection, ongoing research explores enhancing RPL by incorporating multiple routing metrics and developing new Objective Functions (OFs). This paper introduces a novel Objective Function (OF), the Reliable and Secure Objective Function (RSOF), designed to enhance the reliability and trustworthiness of parent selection at both the node and link levels within IoT and RPL routing protocols. The RSOF employs an adaptive parent node selection mechanism that incorporates multiple metrics, including Residual Energy (RE), Expected Transmission Count (ETX), Extended RPL Node Trustworthiness (ERNT), and a novel metric that measures node failure rate (NFR). In this mechanism, nodes with a high NFR are excluded from the parent selection process to improve network reliability and stability. The proposed RSOF was evaluated using random and grid topologies in the Cooja Simulator, with tests conducted across small, medium, and large-scale networks to examine the impact of varying node densities. The simulation results indicate a significant improvement in network performance, particularly in terms of average latency, packet acknowledgment ratio (PAR), packet delivery ratio (PDR), and Control Message Overhead (CMO), compared to the standard Minimum Rank with Hysteresis Objective Function (MRHOF).

关键词： IoT LLNs RPL objective function OF MRHOF OF0 routing metrics reliability trustworthiness

来源：评论

学校读者我要写书评

暂无评论

Robust steganographic approach using generative adversarial network and compressive autoencoder

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Qasaimeh, Malik Qtaish, Alaa Abu Aljawarneh, Shadi Department of Computer Information Systems Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan Department of Software Engineering co-joint with the Department of Cyber Security Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan

Nowadays, social media applications and websites have become a crucial part of people’s lives;for sharing their moments, contacting their families and friends, or even for their jobs. However, the fact that these valuable data are transferred via the Internet and open channels, which are vulnerable to attacks and espionage, requires using defense methods to improve the security of data transmission. Recently, the progress of Deep Learning (DL) inspired researchers to use it with security methods such as steganography, the art of hiding secret data in unrelated content. DL and steganography combined enhanced the hiding properties, especially in the Coverless Image Steganography (CIS) methods. In this paper, we propose a Compressive Coverless Image Steganography (CCIS) model, which is a generated-based CIS, to improve the capacity and robustness of Steganography. This model uses the compressive autoencoder to compress the message, thus increasing the capacity, and uses the Generative Adversarial Network (GAN) to generate a stego image from the compressed vector, thus enhancing concealment ability, besides using a regression model and optimization method to extract the data. Another version was designed to enable sending binary messages by replacing the compressive autoencoder network with a robust mapping rule. Experiments show that the proposed model could improve the characteristics of Steganography. Furthermore, the proposed model could extract binary messages with 256 bits from attacked stego images with 99% recovery accuracy. Thus, capacity and robustness were enhanced using our model with both images and text as secret messages. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An optimization driven deep belief network model for crop yield prediction in IoT based smart agriculture

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Patel, Jaideep Chandel, Sonal Telang Sonker, Abhilash Department of Computer Science Engineering Sagar Institute of Research and Technology Bhopal India Department of Computer Science Engineering Indian Institute of Information Technology Bhopal India Department of Information Technology Madhav Institute of Technology & Science Gwalior India

Crop yield Prediction based on environmental, soil, water, and crop parameters has been an active area of research in agriculture. Many studies have shown that these parameters can have a significant impact on crop yields, and that accurate predictions of crop yields can be made by considering them together. Despite the progress made in crop yield prediction, several challenges still remain, such as the lack of high-quality and diverse data, the high cost of technology, and the lack of domain knowledge for certain crops and regions. Thus, Crop yield forecasting models can reasonably estimate yields, but better yield forecasting performance is still desirable. Thus, in order to enhance the accuracy of crop yield prediction in IoT, a novel optimization driven deep belief neural network model is developed in this study. IoT sensors can collect data on various environmental factors such as temperature, humidity, soil moisture, as well as crop parameters such as growth stage and leaf area index. These data can then be used to train a proposed deep learning-based model, namely an optimization driven deep belief neural network (DBNN) along with an effective crocodile optimization algorithm, to predict crop yields. To improve the performance of DBNN, adaptive crocodile optimization (ACO) algorithm is used. Using this algorithm, weight parameters of DBNN are chosen optimally. Results of the article depict that the proposed model achieve accuracy of 97.26%. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

MOHSQO: Multi objective harmony search algorithm based QoS optimization in delay tolerant networks

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Sonkar, Nidhi Pandey, Sudhakar Kumar, Sanjay Department of Computer Science and Engineering National Institute of Technology Warangal Hanamkonda India Department of Information Technology National Institute of Technology Raipur Raipur India

Delay Tolerant Networks (DTNs) have the ability to make communication possible without end-to-end connectivity using store-carry-forward technique. Efficient data dissemination in DTNs is very challenging problem due to compromising in Quality-of-Service (QoS) metrics such as delivery ratio, end-to-end delay and overhead ratio. That means, if an algorithm is design to find highest delivery ratio, then the algorithm does not bother about delay and overhead ratio. Researchers tried to improve the performance of network but, none of them had given satisfactory results to make a balance between all QoS metrics. In this paper, we have proposed a novel approach to optimize the performance of the network using Multi objective harmony search algorithm by creating a balance between all QoS metrics. Harmony search algorithm considers number of QoS parameters simultaneously. We have used characteristics of the node (Speed, residual energy, buffer capacity and encounters) to select the optimum forwarder node so that we can balance the performance metrics for network optimization. We have used ONE (Opportunistic Network Environment) simulator to simulate the proposed method and compared with exiting techniques. By analyzing the results, we can say that proposed method has the optimum performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Delay tolerant networks

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年 13卷 90316-90332页

作者： Huang, Huang Asemi, Adeleh Universiti Malaya Faculty of Computer Science Information Technology Department of Software Engineering Kuala Lumpur Malaysia

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domainspecific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting," arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains—Laptops, Restaurants, Tweets, and Finance—this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Lumbar Vertebrae Using Meijering U-Net(MU-Net)on Spine Magnetic Resonance Images

引用

computer Modeling in engineering & Sciences 2025年第1期142卷 733-757页

作者： Lakshmi S V V Shiloah Elizabeth Darmanayagam Sunil Retmin Raj Cyril Department of Computer Science and Engineering College of Engineering GuindyAnna UniversityChennai600025India Department of Information Technology Madras Institute of TechnologyAnna UniversityChrompetChennai600044India

Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people *** to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the *** semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar *** is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation *** work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra ***-colour mask images were generated and used as ground truth for training the *** work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley *** proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.

关键词： computer aided diagnosis(CAD) magnetic resonance imaging(MRI) semantic segmentation lumbar vertebrae deep learning U-Net model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：