检索结果-内蒙古大学图书馆

LiDAR Technology for Human Activity Recognition: Outlooks and Challenges

IEEE Internet of Things Magazine 2023年第2期6卷 143-150页

作者： Rinchi, Omar Ghazzai, Hakim Alsharoa, Ahmad Massoud, Yehia Missouri University of Science and Technology Electrical and Computer Engineering Department Rolla United States Thuwal Saudi Arabia

The smart and autonomous learning and recognition of human activities will certainly lead to an incredible progression for several applications and services in public healthcare, education, entertainment, safety and security, and more. With the recent advances in artificial intelligence, signal processing, and computational capabilities, light detection and ranging (LiDAR) technology can play an instrumental role to revamp current human activity recognition (HAR) systems. In this magazine, we investigate the potential of using LiDAR sensors as a novel technology enabling complex and real-time HAR applications. We first overview the HAR categories and the existing state-of-the-art technologies: video-based cameras, depth sensors, wearable devices, and WiFi. Afterward, we delve into the integration of LiDAR technology to perform HAR applications. Then, we discuss the advantages and drawbacks of utilizing LiDAR technology for HAR and compare it with the existing techniques. Finally, we discuss the challenges that need to be addressed to enable advanced LiDAR-based HAR applications. © 2018 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Polynomial-time Combinatorial Algorithm for General Max–Min Fair Allocation

引用

Algorithmica 2024年第2期86卷 485-504页

作者： Ko, Sheng-Yen Chen, Ho-Lin Cheng, Siu-Wing Hon, Wing-Kai Liao, Chung-Shou Department of Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu30013 Taiwan Department of Electrical Engineering National Taiwan University Taipei106 Taiwan Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan

In the general max–min fair allocation problem, there are m players and n indivisible resources, each player has his/her own utilities for the resources, and the goal is to find an assignment that maximizes the minimum total utility of resources assigned to a player. The problem finds many natural applications such as bandwidth distribution in telecom networks, processor allocation in computational grids, and even public-sector decision making. We introduce an over-estimation strategy to design approximation algorithms for this problem. When all utilities are positive, we obtain an approximation ratio of c1-ϵ, where c is the maximum ratio of the largest utility to the smallest utility of any resource. When some utilities are zero, we obtain an approximation ratio of (1 + 3 c^ + O(δc^ 2)) , where c^ is the maximum ratio of the largest utility to the smallest positive utility of any resource. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Edge-assisted indexing for highly dynamic and static data in mixed reality connected autonomous vehicles

引用

Intelligent and Converged Networks 2024年第2期5卷 167-179页

作者： Daniel Mawunyo Doe Dawei Chen Kyungtae Han Haoxin Wang Jiang Xie Zhu Han Department of Electrical and Computer Engineering University of HoustonHoustonTX 77004USA InfoTech Labs Toyota Motor North America Research and DevelopmentMountain ViewCA 94043USA Department of Computer Science Georgia State UniversityAtlantaGA 30302USA Department of Electrical and Computer Engineering University of North Carolina at CharlotteCharlotteNC 28223USA

The integration of Mixed Reality(MR)technology into Autonomous Vehicles(AVs)has ushered in a new era for the automotive industry,offering heightened safety,convenience,and passenger ***,the substantial and varied data generated by MR-Connected AVs(MR-CAVs),encompassing both highly dynamic and static information,presents formidable challenges for efficient data management and *** this paper,we formulate our indexing problem as a constrained optimization problem,with the aim of maximizing the utility function that represents the overall performance of our indexing *** optimization problem encompasses multiple decision variables and constraints,rendering it mathematically infeasible to solve ***,we propose a heuristic algorithm to address the combinatorial complexity of the *** heuristic indexing algorithm efficiently divides data into highly dynamic and static categories,distributing the index across Roadside Units(RSUs)and optimizing query *** approach takes advantage of the computational capabilities of edge servers or RSUs to perform indexing operations,thereby shifting the burden away from the vehicles *** algorithm strategically places data in the cache,optimizing cache hit rate and space utilization while reducing *** quantitative evaluation demonstrates the superiority of our proposed scheme,with significant reductions in latency(averaging 27%-49.25%),a 30.75%improvement in throughput,a 22.50%enhancement in cache hit rate,and a 32%-50.75%improvement in space utilization compared to baseline schemes.

关键词： mixed reality autonomous vehicles data indexing edge computing query optimization

来源：评论

学校读者我要写书评

暂无评论

SAFE AND ROBUST WATERMARK INJECTION WITH A SINGLE OOD IMAGE 12

SAFE AND ROBUST WATERMARK INJECTION WITH A SINGLE OOD IMAGE

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Yu, Shuyang Hong, Junyuan Zhang, Haobo Wang, Haotao Wang, Zhangyang Zhou, Jiayu Department of Computer Science and Engineering Michigan State University United States Department of Electrical and Computer Engineering University of Texas Austin United States

Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increasingly crucial. A major stream of watermarking strategies implants verifiable backdoor triggers by poisoning training samples, but these are often unrealistic due to data privacy and safety concerns and are vulnerable to minor model changes such as fine-tuning. To overcome these challenges, we propose a safe and robust backdoor-based watermark injection technique that leverages the diverse knowledge from a single out-of-distribution (OoD) image, which serves as a secret key for IP verification. The independence of training data makes it agnostic to third-party promises of IP security. We induce robustness via random perturbation of model parameters during watermark injection to defend against common watermark removal attacks, including fine-tuning, pruning, and model extraction. Our experimental results demonstrate that the proposed watermarking approach is not only time- and sample-efficient without training data, but also robust against the watermark removal attacks above. Codes are available: https://***/illidanlab/Single_oodwatermark. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Logistic Regression based Sentiment Analysis System: Rectify

Logistic Regression based Sentiment Analysis System: Rectify

引用

2024 IEEE International Conference on Big Data and Machine Learning, ICBDML 2024

作者： Singh, Harsh Pratap Singh, Nagendra Mishra, Anuprita Sen, Santosh Kumar Swarnkar, Mamta Pandey, Deepak Shri Vaishnav Vidyapeeth Vishwavidyalaya Department of Computer Science and Engineering Indore India Trinity College of Engineering & Technology Department of Electrical Engineering Karimnagar India IES College of Technology Department of Electrical and Electronics Engineering Bhopal462044 India IES University Department of Electrical and Electronics Engineering Bhopal426044 India Corporate institute of Science and Technology Department of Computer Science and Engineering Bhopal505001 India MANIT Department of Computer Science and Engineering Bhopal India TIT Department of EEE Bhopal India

ISBN: (纸本)9798350374100

The detection of various reactions using computer vision, machine learning, and artificial intelligence is a rapidly growing field of research. In this paper, we present a sentiment analysis model based on the Python, NLTK (natural language toolkit) libraries, and machine learning algorithms that can detect multiple reactions from the public on a single platform. The proposed Sentiment Analysis System deals with the very usual problem faced by different companies, manufacturers, and sellers about knowing the customer review for their product. The model classifies the public reviews and the normal text as positive, negative, or neutral. This proposed system is categorised into two parts, one being a field-specific sentiment analysis and the other being a generalised system that can judge any particular word or sentence to be either positive, negative, or neutral. The proposed model is also capable of representing a huge dataset (input as a csv file) in the form of a graph, which can be easily understood by the desired person, and the graphical representation is possible with the Matplotlib library of Python. The model's performance is evaluated using several metrics, such as precision, recall, and others. The model's accuracy and efficiency make it a promising tool for sentiment analysis, which can be used by anyone in any field. In conclusion, the system can work for any specific field provided the data set, and the generalized way can help out with random sentences, and the model's potential can be boosted with some further research. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

SMT-based Layout Synthesis for Silicon-based Quantum Computing with Crossbar Architecture 24

SMT-based Layout Synthesis for Silicon-based Quantum Computi...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Huang, Sheng-Tan Jiang, Ying-Jie Fang, Shao-Yun Cheng, Chung-Kuan Department of Electrical Engineering National Taiwan University of Science and Technology Taiwan Department of Computer Science and Engineering University of California San Diego United States

ISBN: (纸本)9798400710773

With the announcement of the most advanced silicon spin quantum-bit (qubit) chip by Intel, silicon-based quantum circuit manufacturing technology has shown the superior potential to realize quantum computing to other technologies because of the mature semiconductor manufacturing technologies and the compatibility with electronics. Due to the bottleneck in scalability caused by interconnections in silicon-based quantum circuits, crossbar architectures serve as one of the most promising solutions for circuitry implementation. This paper proposes the first satisfiability modulo theories (SMT) formulation to optimally solve the layout synthesis problem by simultaneously performing scheduling, mapping, and routing for silicon-based quantum systems with a specific crossbar architecture. The experiments demonstrate that the proposed method can effectively generate layout synthesis results with minimal usage of swap and shuttle gates within the shortest circuit depths, and the solutions greatly outperform those derived from a state-of-the-art work. © 2024 Copyright is held by the owner/author(s).

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Real-time Resource Management Mechanism for Mobile IoT Devices in 5G-enabled Edge Computing 13

Real-time Resource Management Mechanism for Mobile IoT Devic...

引用

13th International Conference on computer Technologies and Development, TechDev 2024

作者： Alqahtani, Abdullah M. Jazan University Collage of Engineering and Computer Science Department of Electrical and Electronic Engineering Saudi Arabia

ISBN: (纸本)9798331539771

The time-sensitive Internet of Things (IoT) applications within 5G and edge computing environments presents unique challenges in network resource management. Current systems struggle with efficiently managing the high-density and variable conditions typical in such mobile networks. This study aims to address these challenges by introducing the Federated Learning-Enhanced Resource Management System for Mobile IoT networks (FLERMS-IoT). The proposed FLERMS-IoT system incorporates a novel federated learning framework that incorporates localized data processing at the edge to reduce latency and bandwidth usage. It includes algorithms that adaptively manage computational and network resources. The core of the system is a dual-module approach that dynamically adjusts to network conditions, enhancing both stability and scalability. Empirical evaluations demonstrate significant enhancements in resource utilization efficiency, with FLERMS-IoT achieving 90% in high-density scenarios and 85% in variable network conditions in comparison with 5GTFF, JCSR, and SKUNK. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Efficient Classification of Rice Varieties Using Optimized Convolutional Neural Networks 8

Efficient Classification of Rice Varieties Using Optimized C...

引用

8th IEEE International Conference on Information and Communication Technology, CICT 2024

作者： Pathak, Abhishek Kumar Singh, Ankit Kumar Bhatia, Vimal Singh, Puneet Indian Institute of Technology Department of Electrical Engineering Indore India Motihari College of Engineering Department of Computer Science and Engineering India

ISBN: (纸本)9798331531539

Rice type classification is a crucial task in agri-cultural automation, aimed at improving quality control and ensuring market standards. This study presents a deep learning-based approach using a optimized Convolutional Neural Network (CNN) model implemented with PyTorch to classify five rice varieties: Arborio, Basmati, Ipsala, Jasmine, and Karacadag. Our proposed model diverges from conventional methods that rely heavily on complex machine learning algorithms or pretrained CNN architectures like MobileNetV2, VGG16, EfficientNetB0 etc., which require a large number of parameters and layers, re-sulting in increased computational complexity. Through proposed approach, we achieved a remarkable 99.81% validation accuracy and a minimal validation loss of 0.01 % with a significantly reduced model size 30.76 MB. The simplicity of the proposed CNN architecture not only enhances computational efficiency but also maintains high accuracy, making it a viable solution for rice type classification in practical applications. This study demonstrates that a fine-tuned CNN model can outperform more complex models, providing an efficient and effective alternative for agricultural classification tasks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Confidentiality Preserving Data Sharing for Life Cycle Assessment in Process Industries 29

Confidentiality Preserving Data Sharing for Life Cycle Asses...

引用

29th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2024

作者： Perera, Hansani Atmojo, Udayanto Dwi Vyatkin, Valeriy Aalto University Department of Electrical Engineering and Automation Espoo Finland Luleå Tekniska Universitet Department of Computer Science Computer and Space Engineering Sweden

ISBN: (纸本)9798350361230

The pulp and paper industry faces significant en-vironmental challenges, such as air pollution, greenhouse gas emissions, and wastewater discharge, requiring smarter and more sustainable operations. Regulatory bodies are imposing stringent measures to mitigate these impacts, prompting the industry to adopt sustainable practices and technologies. Life Cycle Assessment (LCA) models are crucial in this effort, pro-viding a comprehensive evaluation of environmental impacts and aiding decision making for sustainable manufacturing. However, organisations prioritise the confidentiality of their sensitive data, which can hinder collaborative efforts and LCA calculations. This paper addresses organisational requirements for improving confidentiality, tamper-proof data transfer, and ensuring data sovereignty. The ongoing proof-of-concept introduces a novel approach in LCA, employing Secure Multiparty Computation (SMPC) and data spaces to enable confidentiality-preserving LCA. Our solution ensures data sovereignty and accurate LCA calculations, promoting sustainable practices across the value chain. This paper lays the foundation for a collaborative data platform that meets the critical needs of confidentiality, security, and sustainability in the process manufacturing industry. © 2024 IEEE.

关键词： Life cycle assessment

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Imitation Learning Based Energy Management of a Microgrid With Hybrid Energy Storage and Real-Time Pricing

引用

IEEE Internet of Things Journal 2025年第12期12卷 19801-19817页

作者： Gao, Shuhua Xu, Yizhuo Zhang, Zhaoqian Wang, Zhengfang Zhou, Xiaoyu Wang, Jing Shandong University School of Control Science and Engineering Jinan250100 China The Hong Kong Polytechnic University Department of Electronic and Information Engineering Hong Kong Hong Kong National University of Singapore Department of Electrical and Computer Engineering Singapore117583 Singapore Second Construction Limited Company of China Construction Eighth Engineering Division Jinan Shandong China

Microgrids equipped with hybrid energy storage systems (ESSs) are increasingly critical for balancing the intermittency of renewable energy sources (RESs) and the fluctuations in demand. This paper introduces a novel Multi-Agent Imitation Learning (MAIL) framework for real-time energy management in microgrids, particularly under real-time pricing conditions. The approach leverages a problem decomposition strategy, which separates the energy management task into two phases: first, optimal actions for each ESS are estimated using individual agents, each employing a deep neural network (DNN) trained to emulate an ideal mixed-integer linear programming (MILP) solver;then, a one-step online optimization reacts to these decisions to optimize the remaining system components holistically. Rigorous proofs establish the equivalence of the decomposed subproblems to the original optimization problem, ensuring integrity and effectiveness. Comparative simulation studies with real-world data reveal that our MAIL framework offers significant cost advantages and superior training efficiency relative to both traditional single and emerging multi-agent reinforcement learning (RL) methods. Notably, the operational costs achieved through our approach are markedly lower than those of its counterparts, closely approximating the theoretical minimum. This underscores the method's proficiency and its potential as an effective solution for microgrid energy management. Moreover, the MAIL strategy's multi-agent design allows for straightforward scalability to more extensive systems involving multiple ESSs and shows promising potential for cooperative management across interconnected microgrids. © 2014 IEEE.

关键词： Costs

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：