检索结果-内蒙古大学图书馆

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Chinnasamy Subashini. B Nijanthan Nijanthan Madasamy Raja. G Devulapally Swetha Sreenivasulu Reddy L Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Data Science and Business Systems School of Computing SRMIST India Computer Science and Engineering Paavai Engineering College Namakkal Tamilnadu India Information Technology Paavai Engineering College Namakkal Tamilnadu India Dept. of Computer Science and Engineering Vaagdevi Engineering College Telangana India Department of Mathematics School of Advanced Sciences Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

The rapid advancement of Blockchain technology has led to its widespread application in several domains of digital activities, such as e-government concerns and monetary security. This article presents a smart contract-based Blockchain solution for protecting intellectual property rights in new product development. The proposed solution effectively tackles the challenges associated with the confidentiality of personally identifiable information, efficiency in storing transaction-related information, as well as cooperation and monitoring in IPR. Initially, we create a mathematical model based on smart contract enabled Blockchain and intelligent contracts. Subsequently, we develop algorithms for Blockchain generation, and intelligent contracts. The system is suitable for protecting IPR in a blockchain network, by implementation of distributed identity authentication and real-time extensible storage. These features enhance the security and expandability of circuit copyright protection based on blockchain technology. The experimental results demonstrate that the suggested algorithm has decreased the cost for communication and enhanced the effectiveness of storing information and administration. Furthermore, it demonstrates resilience against many common attacks such as double-spending assaults, while maintaining low cost and overhead. Additionally, it exhibits a superior level of security in comparison to three other competing algorithms.

关键词： Patents Technological innovation Costs Smart contracts Intellectual property Product development Blockchains Security Protection Resilience

来源：评论

学校读者我要写书评

暂无评论

Feedback Control Based on Trust for Varied Automation Transparency

Feedback Control Based on Trust for Varied Automation Transp...

引用

Advances in computer science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Ceres Dbritto Joel Lopes Krishnan Bandyopadhyay Nandan Banerji Ishani Mishra Ankit Kandpal Independent Reseacher St Louis USA Independent Reseacher Redmond USA Department of Medical Electronics Engineering Dayananda Sagar College of Engineering Bengaluru Karnataka Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Department of Computer Science and Engineering New Horizon college of Engineering Bengaluru Karnataka India Department of ECE Bipin Tripathi Kumaon Institute of Technology Dwarahat Almora India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Interactions between people and automation depend heavily on human confidence in the latter. Lack of trust can cause people to not use automation, while too much trust can cause them to put their faith in a flawed autonomous system, which could have detrimental effects on them. Transparency and trust in automation are vital for the usefulness and security of human-robotization frameworks. The majority of the research that has been done on the trust that human operators have in robotics and automation has been an ongoing variable that has received little attention. paid to how trust changes over time. In order to fill this research void, we offer a study that examines how trust is dynamic. Using real-time trust measurements, we first discovered options to quantify trust of entirety, which we described as a metric that considers trust throughout the entire human-automation interaction experience. In this study, a feedback control strategy for powerfully changing mechanization straightforwardness and transparency concurring on client trust is analysed. The proposed approach tweaks mechanical way of behaving and correspondence by incorporating an input control component with a trust assessment model. The adequacy of the feedback control framework in improving errand execution and trust adjustment under different levels of computerization straightforwardness and transparency is checked utilizing MATLAB reenactments.

关键词： Measurement Robust control Automation Computational modeling Mathematical models Robustness Real-time systems Feedback control Security MATLAB

来源：评论

学校读者我要写书评

暂无评论

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective

Rethinking Adversarial Attacks in Reinforcement Learning fro...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tianyang Duan Zongyuan Zhang Zheng Lin Yue Gao Ling Xiong Yong Cui Hongbin Liang Xianhao Chen Heming Cui Dong Huang Department of Computer Science The University of Hong Kong Hong Kong China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong China School of Computer Science Fudan University China School of Computer and Software Engineering Xihua University Chengdu China Department of Computer Science and Technology Tsinghua University Beijing China School of Transportation and Logistics Southwest Jiaotong University Chengdu China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in real-world applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing attack methods targeting individual sampled actions have limited impacts on the overall policy distribution, particularly in continuous action spaces. To address these limitations, we propose the Distribution-Aware Projected Gradient Descent attack (DAPGD). DAPGD uses distribution similarity as the gradient perturbation input to attack the policy network, which leverages the entire policy distribution rather than relying on individual samples. We utilize the Bhattacharyya distance in DAPGD to measure policy similarity, enabling sensitive detection of subtle but critical differences between probability distributions. Our experiment results demonstrate that DAPGD achieves SOTA results compared to the baselines in three robot navigation tasks, achieving an average 22.03% higher reward drop compared to the best baseline.

关键词： Uncertainty Navigation Perturbation methods Signal processing Robot sensing systems Deep reinforcement learning Probability distribution Robustness Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Reconfiguration in Network Function Virtualization: Toward Service Function Chain Optimization

引用

IEEE Transactions on Network and Service Management 2025年

作者： Assis, Karcius D. R. Almeida, Raul C. Baghban, Hojjat Santos, Alex F. Boutaba, Raouf Electrical and Computer Engineering Department Salvador Brazil University of Waterloo David R. Cheriton School of Computer Science Canada Department of Electronics and Systems Recife Brazil Chang Gung University Department of Artificial Intelligence Taiwan Chang Gung University College of Intelligent Computing Taiwan Center of Science and Technology in Energy and Sustainability Brazil Postgraduate Program in Computer Science Bahia Brazil

Network Function Virtualization (NFV), as a promising paradigm, speeds up the service deployment by separating network functions from proprietary devices and deploying them on common servers in the form of software. Any service in NFV-enabled networks is achieved as a Service Function Chain (SFC) which consists of a series of ordered Virtual Network Functions (VNFs). However, migration of VNFs for more flexible services within a dynamic NFV-enabled network is a key challenge to be addressed. Current VNF migration studies mainly focus on single VNF migration decisions without considering the sharing and concurrent migration of VNF instances. In this paper, we assume that each deployed VNF is used by multiple SFCs and deal with the optimal placement for the contemporaneous migration of VNFs based on the actual network situation. We formalize the VNF migration and SFC reconfiguration problem as a mathematical model, which aims to minimize the VNF migration between nodes or the total number of core changes per node. The approach is a two-stage MILP based on optimal order to solve the reconfiguration. Extensive evaluation shows that the proposed approach can reduce the change in terms of location or number of cores per node in a 6-node and 14-node networks while ensuring network latency compared with the model without reconfiguration. © 2004-2012 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

An Intelligent System for Prediction of Depression based on Facial Emotions and Textual Data

An Intelligent System for Prediction of Depression based on ...

引用

Intelligent Systems (ETIS), Emerging Technologies for

作者： Akhil Chandran Miniyadan Prathibha P G Nithya G P Resna R Department of Information Technology College of Engineering Thalassery Kerala India Department of Computer Science BITS Pilani Dubai Campus Dubai United Arab Emirates

ISBN: (数字)9798331507541

ISBN: (纸本)9798331507558

Globally, a significant portion of the population experiences depression or stress due to a range of factors at various stages of life. In contemporary society, the fast-paced nature of daily life contributes to the gradual development of depression, as ongoing stress accumulates over time. Artificial Intelligence based systems contribute significantly to the healthcare systems by providing timely intervention and automating the decision-making process. Deep learning-based algorithms are capable of recognizing facial expressions and identifying as well as predicting an individual's mental state. In this research article we propose a depression detection system based on deep learning. In the proposed system, a combination of facial expression and text data are used to predict whether a person is depressed or not. We utilize Convolutional Neural Network (CNN) for the extraction of features for the detection and prediction for depression. The proposed model was tested on FER dataset along with a Patient Health Questionnaire also known as PHQ-9 for the psychological analysis. With experiments our system obtained an accuracy of 92% with FER dataset.

关键词： Deep learning Accuracy Data analysis Psychology Human factors Depression Feature extraction Convolutional neural networks Intelligent systems Video recording

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Induced Selective Identification of Dopamine Using Doped Carbon Quantum Dots

Machine Learning Induced Selective Identification of Dopamin...

引用

International Conference on Electronics, Materials engineering and Nano-technology (IEMENTech)

作者： Ruma Das Abhirup Paria P. K. Giri Department of Applied Science (Physics) Haldia Institute of Technology Haldia India Department of Computer Science & Engineering (Artificial Intelligence & Machine Learning) Haldia Institute of Technology Haldia India Department of Physics & Centre for Nanotechnology Indian Institute of Technology Guwahati Guwahati India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

The present work highlights the selective identification of dopamine (DA) with machine learning (ML) classification. Dopamine is an essential organic neurotransmitter that acts a dynamic role. With the inhouse experimental da-ta, the ML models are trained with more than thirty classification algorithms for the efficient selection of DA among various metal ions and biomolecules that exist in human body fluids. The experimental data was collected by measuring the turn-off photoluminescence intensity of nitrogen-doped car-bon quantum dots in the presence of various metal ions and biomolecules. A promising agreement between predicted result and experimental consequences endorses the effectiveness of the proposed ML prediction. Additionally, confusion matrices and receiver operating characteristic (ROC) are introduced to validate the outcomes by visual analysis.

关键词： Visualization Biological system modeling Quantum dots Metals Molecular biophysics Machine learning Photoluminescence Ions Classification algorithms Sensors

来源：评论

学校读者我要写书评

暂无评论

Secured and Privacy-Preserving GPU-Based Machine Learning Inference in Trusted Execution Environment: A Comprehensive Survey

Secured and Privacy-Preserving GPU-Based Machine Learning In...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Arunava Chaudhuri Shubhi Shukla Sarani Bhattacharya Debdeep Mukhopadhyay Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Centre for Computational and Data Sciences Indian Institute of Technology Kharagpur Kharagpur India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

With the rapid advancement of machine learning (ML) models and their widespread application across various sectors such as intrusion detection, medical diagnosis, natural language processing, and autonomous driving, these technologies have achieved remarkable success. However, this progress has also raised significant concerns about ensuring the security of ML models and protecting both private training data and model outputs from getting exposed in a shared cloud environment. To address these challenges, researchers have proposed various methodologies to create privacy-preserving, secure, and trustworthy model execution environments to prevent adversarial attacks. This study provides a comprehensive review of Trusted Execution Environment (TEE) implementations across different hardware accelerators. It also offers an overview of modern techniques for preserving privacy and security in execution environments, while identifying critical research gaps that require attention. In essence, this survey is an important resource for researchers, providing insights into recent methodologies and guiding them to focus on pressing research challenges.

关键词： Surveys Deep learning Training Privacy Data privacy Training data Data models Stability analysis Security Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

JANE: Joint Angle Networks Assisting 3D Human Pose Estimation

JANE: Joint Angle Networks Assisting 3D Human Pose Estimatio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jinhuan Wang Yuzhen Zhao Xujie Song Wenzhou Chen Qi Xuan Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology HangZhou China Department of Computer Science and Technology Hangzhou Dianzi University HangZhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

3D human pose estimation (HPE) is crucial due to its extensive applications. While current 3D HPE methods focus on human skeleton topology for accuracy, they often overlook joint angle information, which is vital in 2D-to-3D pose lifting. This paper introduces the Joint Angle Network (JANE) model to leverage joint angle features from 2D poses. We propose an angle graph convolution module to extract joint angle features and a multi-stage parallel fusion module to integrate these features with input image data. Experiments on Human3.6M show that our method improves accuracy by 8.7% and 2.6% over non-spatiotemporal baselines using 2D ground truth and 2D pose detectors, respectively.

关键词： Visualization Solid modeling Three-dimensional displays Accuracy Convolution Pose estimation Feature extraction Transformers Topology Speech processing

来源：评论

学校读者我要写书评

暂无评论

Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network

Cognitive Congestion Alleviation Framework in IoT-Enabled WS...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： R. Mohandas Sudha Y Narmatha P P.Venkata Prasad N. Manikandan Department of Electronics & Communication Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Presidency University Bangalore Karnataka India Department of Computer Science and Engineering Sri Sairam College of Engineering Bangalore Karnataka India Department of Electrical and Electronics Engineering Chaitanya Bharathi Institute of Technology Hyderabad Telangana India Department of Business Administration Kalasalingam Academy of Research and Education Kalasalingam Business School Krishnankoil Viruthunagar India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The rapid advancement of Intelligent Transportation Systems (ITS) has heightened the importance of reliable, real-time data transmission in Wireless Sensor Networks (WSNs). However, congestion in data-heavy Internet of Things (IoT)-enabled networks remains a critical challenge, impacting communication efficiency and decision-making in ITS. In high-density IoT-ITS applications, traditional congestion control methods are insufficient to address the complexity and dynamics of data flows. Existing solutions often fail to adapt in real time to varying traffic loads, leading to delays and data loss. There is a strong need for a congestion alleviation framework capable of intelligently prioritizing data while dynamically managing network resources to ensure seamless information exchange in large-scale deployments. This study presents a Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network (V-CapMiAN-Parr), which combines the Vectorized Adaptive Capsule Neural Network (V-AdCapNet) and Multi-instance Attention Network (MAN), fine-tuned by the Parrot Optimizer (ParrOpt). This integration aims to effectively detect, mitigate, and prevent congestion through an advanced capsule-based attention mechanism with adaptive optimization. The suggested V-CapMiAN-Parr framework demonstrated significant improvements in congestion control, achieving data throughput efficiencies above 99.7%, packet delivery rates above 99.5%, and network reliability reaching 99.2% under high traffic loads. The model's adaptive weighting mechanism ensures real-time responsiveness and reliability, crucial for next-gen ITS applications. The V-CapMiAN-Parr framework effectively addresses congestion issues in IoT-enabled WSNs, providing a robust, scalable solution for ITS applications. This cognitive framework's advanced data prioritization and adaptive optimization capabilities are well-suited for enhancing the performanc

关键词： Wireless communication Wireless sensor networks Adaptive systems Transportation Telecommunication traffic Real-time systems Internet of Things Data communication Optimization Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Jia, Nanshan Yuan, Chenfei Wu, Yuhang Zheng, Zeyu Department of Industrial Engineering & Operations Research University of California Berkeley United States United States Department of Computer Science and Technology Tsinghua University China

The fast development of Large Language Models (LLMs) offers growing opportunities to further improve sequential recommendation systems. Yet for some practitioners, integrating LLMs to their existing base recommendation systems raises questions about model interpretability, transparency and related safety. To partly alleviate challenges from these questions, we propose guided embedding refinement, a method that carries out a guided and interpretable usage of LLM to enhance the embeddings associated with the base recommendation system. Instead of directly using LLMs as the backbone of sequential recommendation systems, we utilize them as auxiliary tools to emulate the sales logic of recommendation and generate guided embeddings that capture domain-relevant semantic information on interpretable attributes. Benefiting from the strong generalization capabilities of the guided embedding, we construct refined embedding by using the guided embedding and reduced-dimension version of the base embedding. We then integrate the refined embedding into the recommendation module for training and inference. A range of numerical experiments demonstrate that guided embedding is adaptable to various given existing base embedding models, and generalizes well across different recommendation tasks. The numerical results show that the refined embedding not only improves recommendation performance, achieving approximately 10% to 50% gains in Mean Reciprocal Rank (MRR), Recall rate, and Normalized Discounted Cumulative Gain (NDCG), but also enhances interpretability, as evidenced by case studies. © 2025, CC BY.

关键词：

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：