检索结果-内蒙古大学图书馆

MV-DUO: multi-variate discrete unified optimization for psychological vital assessments

Neural Computing and Applications 2024年第31期36卷 19777-19793页

作者： Pethuraj, Mohamed Shakeel Burhanuddin, M.A. Dzakiyullah, Nur Rachman Department of Information System Faculty of Computer and Engineering Universitas Alma Ata Yogyakarta Indonesia Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka Durian Tunggal Melaka Malaysia

Psychological vital assessments are required for monitoring health conditions and observing body reactions toward diseases and medications. Wearable sensors play a vital role in sensing body vitals and presenting them as signals for computer-based analysis. The problem relies on the signal decoding due to its input stream that turns out to be discrete/ continuous. Therefore for addressing the above specific issue, this article introduces MV-DUO (Multi-Variate Discrete Unified Optimization) method. This method addresses the above problem from a multi-variate perspective by sensing differential signals across healthy and unhealthy conditions. The healthy and unhealthy conditions are trained using neural learning by augmenting/ ceasing external vital data. The unification is performed using single-point artificial ecosystem-based optimization for identifying discrete sequences collaborated with continuous signals. The single-point reference is grouped based on the maximum continuity fitness observed under various sensing intervals. In this process, the non-grouped sequences are identified as unhealthy or discrete for which additional detection training and classification are required. Considerably the changes between successive sensing intervals are used for variations detection from unified high-fitness groups. Those grouped instances are used for training new vital changes observed at distinct intervals. This improves detection accuracy under controlled errors. For the varying sensing intervals, the proposed method achieves 14.13% high accuracy, 8.29% high grouping rate, 10.77% less error, and 10.07% less detection time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： computer aided analysis

来源：评论

学校读者我要写书评

暂无评论

Path Authentication for Multiple Switches within First Communication Packets 6

Path Authentication for Multiple Switches within First Commu...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Anna, Koziol Agata Shen, Shan-Hsiang Shen, Chung-An Huang, Chin-Ya National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taiwan National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taiwan

ISBN: (纸本)9798350378511

This paper introduces a new approach to switch authentication within a network environment, addressing the challenges associated with multiple switch configurations. The proposed continuous authentication process is seamlessly integrated into the TCP handshake, leveraging public-private key encryption and challenge-based authentication methodologies. This novel solution aims to improve performance of traditional one-to-one authentication methods, both in terms of efficiency and security. The research demonstrates the efficiency gains achieved by the proposed authentication process through a comparative analysis with one-to-one solution based on the same authentication mechanism. The results reveal a significant reduction in authentication time, thanks to link latency reduction. The incorporation of public-private key encryption enhances the security, ensuring protection against unauthorized access and switch spoofing attempts. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in NSL-KDD Dataset Using Hybrid Self-Organizing Map Model

引用

computer Modeling in engineering & Sciences 2025年第4期143卷 639-671页

作者： Noveela Iftikhar Mujeeb Ur Rehman Mumtaz Ali Shah Mohammed J.F.Alenazi Jehad Ali Knowledge Unit of Systems and Technology University of Management and TechnologySialkot51310Pakistan Department of Computer Science University ofWahWah Cantt47010Pakistan Department of Computer Engineering College of Computer and Information Sciences(CCIS)King Saud UniversityRiyadh11451Saudi Arabia Department of AI Convergence Network Ajou UniversitySuwon16499Republic of Korea

Intrusion attempts against Internet of Things(IoT)devices have significantly increased in the last few *** devices are now easy targets for hackers because of their built-in security *** a Self-Organizing Map(SOM)hybrid anomaly detection system for dimensionality reduction with the inherited nature of clustering and Extreme Gradient Boosting(XGBoost)for multi-class classification can improve network traffic intrusion *** proposed model is evaluated on the NSL-KDD *** hybrid approach outperforms the baseline line models,Multilayer perceptron model,and SOM-KNN(k-nearest neighbors)model in precision,recall,and F1-score,highlighting the proposed approach’s scalability,potential,adaptability,and real-world ***,this paper proposes a highly efficient deployment strategy for resource-constrained network *** results reveal that Precision,Recall,and F1-scores rise 10%-30% for the benign,probing,and Denial of Service(DoS)*** particular,the DoS,probe,and benign classes improved their F1-scores by 7.91%,32.62%,and 12.45%,respectively.

关键词： Intrusion detection self-organizing map Internet of Things dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

CMCF-Net: An End-to-End Context Multiscale Cross-Fusion Network for Robust Copy-Move Forgery Detection

引用

IEEE Transactions on Multimedia 2024年 26卷 6090-6101页

作者： Xiong, Lizhi Xu, Jianhua Yang, Ching-Nung Zhang, Xinpeng Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Engineering Research Center of Digital Forensics Ministry of Education Nanjing210044 China Nanjing University of Information Science and Technology Software Engineering Nanjing210044 China National Dong Hwa University Department of Computer Science and Information Engineering Hualien974301 Taiwan Fudan University School of Computer Science Shanghai200433 China

Image copy-move forgery detection (CMFD) has become a challenging problem due to increasingly powerful editing software that makes forged images increasingly realistic. Existing algorithms that directly connect multiple scales of features in the encoder part may not effectively aggregate contextual information, resulting in poor performance. In this paper, an end-to-end context multiscale cross-fusion network (CMCF-Net) is proposed to detect image copy-move forgery. The proposed network consists of a multiscale feature extraction fusion (MSF) module and a multi-information fusion decoding (MFD) module. Multiscale information is efficiently extracted and fused in the MSF module utilizing stacked-scale feature fusion, which improves the network's forgery localization ability on objects of different scales. The MFD module employs contextual information combination and weighted fusion of multiscale information to guide the network in obtaining relevant clues from correlated information at multiple different scales. Experimental results and analysis have demonstrated that the proposed CMCF-Net achieves the best localization results with higher robustness. © 1999-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Know How Much Sensitive Precision and Recall Validity Measures Are? 27th

Know How Much Sensitive Precision and Recall Validity Measu...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mishra, Sumit Swain, Srinibas Prakash, Ved Department of Computer Science and Engineering Rajiv Gandhi Institute of Petroleum Technology Amethi Jais India Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati Guwahati India

ISBN: (纸本)9783031781650

For the performance evaluation of the clustering algorithm, evaluation metrics are used. For this purpose, the obtained set of clusters are compared with the actual set of clusters (or gold standard). Various evaluation metrics have been proposed in the past. One important question regarding these evaluation metrics is – how good are these metrics for evaluating the performance of the clustering algorithm? Wagner et al. have proposed some of the properties of these evaluation metrics. The evaluation metric should also have a high sensitivity value to capture the change in the clustering result/gold standard along with these properties. In this paper, we compute the sensitivity of two commonly used evaluation metrics – Precision and Recall. We also show that the sensitivity of Precision and Recall is polynomial with respect to the number of data-points. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Vulnerability Detection Method for Smart Contracts Based on Dynamic Meta Optimizer

引用

IEEE Internet of Things Journal 2025年第13期12卷 24904-24915页

作者： He, Daojing Gong, Wei Chan, Sammy Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Jiangxi University of Science and Technology School of Information Engineering Jiangxi Ganzhou China City University of Hong Kong Department of Electrical Engineering Hong Kong Hong Kong

With the increasingly complex blockchain technology environment and emerging security threats, the detection and prevention of vulnerabilities in blockchain smart contracts have become crucial for ensuring the healthy development of blockchain technology and avoiding substantial economic losses. Recently developed vulnerability detection methods for smart contracts suffer from the drawbacks of insufficient feature extraction and inadequate multitask detection. This paper proposes a multifaceted learning model, DLR, based on a dual-loop architecture of meta learning to address these issues by adopting model-agnostic meta-learning techniques. This model employs a syntax analyzer for targeted feature extraction, with graph information used as a supporting tool during the initial stage of feature engineering. Combined with an improved optimizer algorithm in the inner loop, the model can effectively learn and adjust based on the specific requirements of each task. In the outer loop, the model achieves efficient learning rate adjustment for multi-task learning by integrating the adaptive learning rate of the Adam optimizer with a global adjustment using simulated annealing strategy, thereby enhancing performance across diverse tasks. Experimental results demonstrate significant improvements in detection accuracy over state-of-the-art methods for three types of vulnerabilities, with our method achieving detection accuracies of 94.40%, 93.36%, and 94.33% for reentrancy, timestamp dependence, and integer overflow vulnerabilities, respectively. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Vehicle Detection on Express Roads Using YOLOv7 with Taguchi Parameter Optimization Method

引用

Sensors and Materials 2024年第4期36卷 1605-1625页

作者： Chen, Mei-Kuei Chang, Chun-Lung Lin, Cheng-Jian Chen, Wen-Jong Department of Industrial Education and Technology National Changhua University of Education Changhua County50007 Taiwan Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung City41170 Taiwan Department of Computer Science & Information Engineering National Chin-Yi University of Technology Taichung City41170 Taiwan

In road traffic management, high-speed vehicle detection is often affected by factors such as vehicle speed, weather, camera angle, and image resolution, making vehicle detection on express roads very challenging, Therefore, we propose a Taguchi-based You Only Look Once (YOLOv7) model, called T-YOLOv7, for vehicle detection on high-speed roads. The Taguchi method is used to optimize the combination of hyperparameters of YOLOv7. Experimental results show the precision rate, recall rate, and F1-score of the proposed T-YOLOv7 to be 82.2, 86.3, and 84.2%, respectively. Compared with the original YOLOv7, T-YOLOv7 has improved precision, recall, and F1-score by 12.1, 17.9, and 15.0 percentage points, respectively. Compared with YOLOv4, the improvements in precision, recall, and F1-score using T-YOLOv7 are 4.0, 2.4, and 3.3 percentage points, respectively. The experimental results also show that the proposed T-YOLOv7 is effective in adjusting hyperparameters through the Taguchi method and can be applied to real-time vehicle detection in real environments. © MYU K.K.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Mental Stress Detection with the Multimodal Data Using Ensemble Optimization Enabled Explainable Convolutional Neural Network

引用

Biomedical Materials and Devices 2025年 1-23页

作者： Shinde, Sumit Sudhakar Ghotkar, Archana Santosh Department of Computer Engineering Society for Computer Technology and Research’s Pune Institute of Computer Technology Savitribai Phule Pune University Maharashtra Pune India Department of Information Technology Society for Computer Technology and Research’s Pune Institute of Computer Technology Savitribai Phule Pune University Maharashtra Pune India

In recent years, modernization, physical work scenarios technology-wise, lifestyle, culture, and personal environments contribute to the stressed state of individuals. However, the early evaluation of long-term mental stress conditions is essential as it triggers several chronic disorders and affects the mental health of affected individuals. In traditional techniques, the multifaceted symptoms and comorbidities introduce difficulty in diagnosis, posing a risk of misdiagnosis. However, the existing techniques often failed to capture the relevant features and neglected to observe the notable shifts in various bio-signals caused by mental stress resulting in inaccurate detection. In addition, medical professionals are skeptical about the adoption of AI-assisted diagnosis due to their inability to be transparent in decision-making processes. In this regard, Explainable Artificial Intelligence (XAI) has surfaced to address the computational black box issue with AI systems by offering transparency and interpretability for model predictions. Consequently, this research proposes the Ensemble Optimization enabled Explainable Convolutional Neural Network (EO-ECNN) for mental stress detection by offering insights into its decision-making process which in turn enhances the system interpretability and transparency. The proposed model exploited the ECNN improves the effectiveness of the stress detection model in conjunction with Ensemble optimization, which combines the traits of the coyote’s and wolf’s individual and group huts, respectively. The high detection accuracy is made possible by the optimization that is being used, which increases the classifier’s slow convergence rate. The multimodal input data for the study still consist of text, images, and audio. The audio features are extracted with the help of the VGGish feature extractor, while the visual input is processed by Residual Network (ResNet). The experimental results demonstrate the superior performance of the multi

关键词： Convolutional neural network Ensemble optimization Explainable artificial intelligence Mental stress detection Residual network

来源：评论

学校读者我要写书评

暂无评论

Bidirectional attentional mechanism for Arabic chatbot

引用

International Journal of information technology (Singapore) 2024年第5期16卷 3109-3120页

作者： Youness, Farida Elshenawy, Ayman Makour, Mohamed Ashraf Systems and Computer Engineering Department Faculty of Engineering Al-Azhar University Cairo Egypt Software Engineering and Information Technology Department Faculty of Engineering and Technology Egyptian Chinees University Cairo Egypt

A chatbot is an intelligent agent that developed based on Natural language processing (NLP) to interact with people in a natural language. The development of multiple deep NLP models has allowed for the creation of a vector representation of words and sentences that captures meaning in context. In this paper, a generative Arabic chatbot is trained with the Sequence to Sequence (Seq2Seq) model based on encoder-decoder architecture. It utilizes both the bi-directional encoder types of Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM). The chatbot was trained using preprocessed dataset of 12 k conversations that were translated from English to Arabic. An attention layer was provided to the RNNs to focus on the important data between the input and output sequences. The obtained results showed that the proposed chatbot performed well with long sentences and elicited positive responses. In addition to that BiLSTM with attention performs better than BiGRU without attention. To assess the model, the Bilingual Evaluation Understudy (BLEU) Score is employed. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Arabic chatbot Attention mechanism Deep learning RNN

来源：评论

学校读者我要写书评

暂无评论

Integrated Crowd Counting System Utilizing IoT Sensors, OpenCV and YOLO Models for Accurate People Density Estimation in Real-Time Environments 1

Integrated Crowd Counting System Utilizing IoT Sensors, Open...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Jayasingh, Suvendra Kumar Naik, Pintu Swain, Satyaprakash Patra, Kumar Janardan Kabat, Manas Ranjan Institute of Management and Information Technology BPUT Department of Computer Science and Engineering Odisha Cuttack India Indian Institute of Technology Department of Computer Science and Engineering Jammu India

ISBN: (纸本)9798350361780

Real-time crowd monitoring plays a pivotal role in effectively managing public spaces and ensuring safety. This study investigates the fusion of IoT devices and the YOLO object detection model to accurately count crowds. IoT devices facilitate the instantaneous collection of data from cameras, while the YOLO model adeptly identifies individuals within recorded video frames. The study rigorously assesses the performance of three YOLO variants: YOLO V5, YOLO V8 and YOLO V8 NAS. Findings reveal that YOLO V8 NAS surpasses YOLO V5 and YOLO V8 in mean average precision (mAP), achieving an exceptional mAP of 95.1%. This heightened precision is attributed to the integration of Neural Architecture Search (NAS) into the YOLO V8 NAS model, fine-tuning its architecture specifically for crowd counting tasks. It analyzes various networking models proposed in earlier studies for analyzing crowded scenes in public spaces. It emphasizes the potential of a hybrid model involving an IP camera module and a Deep Neural Network for effective crowd sensing. In this setup, the IP camera captures video footage, while the DNN detects individuals and assesses crowd density based on the count of people recognized. This approach presents an encouraging solution for real-time crowd monitoring and management in public environments. © 2024 IEEE.

关键词： Face recognition

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：