检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Chen, Xiu-Zhi Li, Mu-Chuan Chen, Yen-Lin National Taipei University of Technology Dept. of Computer Science & Information Engineering Taipei Taiwan

ISBN: (纸本)9798350324136

Re-identification has become a crucial issue in computer vision today as it allows for tracking objects in both continuous and discontinuous scenarios. Despite achieving perfect detection results, anchor-based trackers encountered difficulties in effectively learning re-identification features, due to various issues. This research proposes strategies aimed at improving the capability of anchor-based trackers to learn high-quality re-identification (re-ID) features. The model developed through our strategies can extract more distinct features and achieve almost 0.57 Multiple Object Tracking Accuracy (MOTA) on MOT20, even under a limited training dataset. This result indicates that our proposed strategies hold potential for improving the performance of anchor-based trackers. © 2024 IEEE.

关键词： Anchor-Based Tracker Re-Identification Smart City Surveillance

来源：评论

学校读者我要写书评

暂无评论

Modular Deep Reinforcement Learning: Enhancing Flexibility through Agent Splitting

Modular Deep Reinforcement Learning: Enhancing Flexibility t...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tian, Chong Rawat, Danda B. Howard University Dept. of Electrical Engineering & Computer Science WashingtonDC United States

ISBN: (纸本)9798350362480

Deep reinforcement learning (DRL) has shown remarkable success in tackling complex tasks by learning representations directly from raw data. However, as DRL agents become increasingly sophisticated, they often face challenges in adapting to new tasks or environments due to their monolithic structure. In this paper, we prove that by decomposing the agent into modular components, we enable more efficient adaptation as well as more efficient than that of the singular DRL agent on tackling complex tasks. Overall, our work contributes to advancing the field of DRL by introducing a flexible and scalable framework for agent decomposition. By enabling the creation of modular agents, we empower DRL systems to efficiently adapt to changing environments, learn new tasks with minimal intervention, and achieve higher levels of performance and versatility. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Secured Release through an Agile Security Growth Framework 29

Secured Release through an Agile Security Growth Framework

引用

29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024

作者： Bhattacharya, Saikath Williams, Laurie Singh, Munindar P. Electrical Engineering and Computer Science Milwaukee School of Engineering Milwaukee United States Dept. of Computer Science North Carolina State University Raleigh United States

ISBN: (纸本)9798986576138

Software development teams need to produce and assess secure software products so that they can perform critical functionality. Because no software product can ever be "perfectly secure, " development teams need to decide when a software product is "secure enough" to be released, that is, to make a decision on the product’s release readiness. The goal of this paper is to aid software practitioners in predicting whether a software product is "secure enough" to be released through the evolution and evaluation of software security growth models (SSGM). In this paper, we adapt and evolve software reliability growth models (SSGMs) for the purpose of SSGM using empirical software vulnerability analysis. We quantitatively compare the quality of agile software versions by comparing the security correction and detection process over testing time and software testing cost. The framework is generic to incorporate software vulnerability data into different time frames and multiple agile software versions. We evaluated our SSGM using data from Google Chromium, which uses an agile process with releases every 50 days. © Conference Proceedings of the 29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Experimental Thermal Model-Based SOC Estimation Algorithm for Lithium-Ion Phosphate Batteries Considering Internal Temperature

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第12期73卷 2289-2296页

作者： Kim, Dong Hwan Ko, Jeong Soo Kim, Do Hyeon Lim, Jong-Hun Lim, Je Yeong Lee, Jaein Lee, Byoung Kuk Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Advanced Defense Science & Technology Research Institute Agency for Defense Development Korea Republic of

This paper proposes a method for estimating the State of Charge (SOC) of lithium iron phosphate (LFP) batteries based on an experimental thermal model that considers internal battery temperatures. The proposed algorithm involves selecting a thermal model and suggesting methods for extracting parameters from the chosen model. Using the proposed thermal model, the algorithm compensates for temperature differences in cold and hot environments, thereby correcting the internal temperature to estimate SOC accurately. The effectiveness of the proposed algorithm is verified by estimating the SOC of electric vehicle LFP batteries and comparing the accuracy before and after correction. Copyright © The Korean Institute of Electrical Engineers.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

HAR-CLET: A Novel Conv-LSTM with Extra Tree Classifier for Human Activity Recognition

HAR-CLET: A Novel Conv-LSTM with Extra Tree Classifier for H...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Choudhury, Nurul Amin Soni, Badal National Institute of Technology Silchar Dept. of Computer Science and Engineering Assam Silchar India

ISBN: (纸本)9798350350821

In this paper, we propose a novel ensemble of Convolutional Neural Network-Long Short-Term Memory with an Extra Tree Classifier for automatic feature engineering in the spatiotemporal domain and classification of different human activities collected using inbuilt smartphone sensors. Prominent sensor-based HAR systems are trained and validated in extracted features of datasets collected in a controlled and simulated environment, which can adversely impact the reliability in real-world scenarios. Our approach utilizes unsimulated data from diverse users collected using inbuilt smartphone sensors in real world environment. Also, the proposed model was effectively trained and tested with multiple standard public datasets for validation and benchmarking with diverse evaluation metrics. With effective parameter tuning and lightweight feature extraction architecture, the proposed model achieved an average performance accuracy of 99 % with their own generated dataset, mHealth and MotionSense dataset, in comparatively optimized computational time compared to the benchmark models. © 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

A Multi-Routing Paths' Exploration Algorithm for Multi-paired Communicating Vehicles' Data Transmission Offloading using the Multi-access Edge Computing Architecture 4

A Multi-Routing Paths' Exploration Algorithm for Multi-paire...

引用

4th European Conference on Communication systems, ECCS 2024

作者： Huang, Chung-Ming Tsai, Cheng-Han National Cheng Kung University Dept. of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350377927

This work proposed a novel method for multiple communicating paired vehicles' data transmission offloading using the Multi-access Edge Computing (MEC) technique. When two paired communicating vehicles are communicating with each other through cellular network's Base Stations (BSs), the data transmission can be offloaded to the Cellular Vehicle-to-Vehicle (C-V2V) path that exists between these two vehicles using 5G NR's sidelink communication;these two paired communicating vehicles can switch back to the Cellular Vehicle-to-Infrastructure (C-V2I) communication to communicate with each other when the corresponding C-V2V path is broken. Using the proposed method, the MEC architecture serves as a centralized computing mechanism to determine the availability of k-hop C-V2V paths for paired communicating vehicles' data transmission offloading. Each vehicle periodically reports its context, such as position, speed, driving direction, and C-V2V sidelinks' Channel Busy Ratios (CBRs), to the MEC server to derive feasible k-hop C-V2V data transmission offloading paths. The simulation result demonstrates that the proposed method has (i) better throughput compared to the method of relying solely on C-V2I communication through BSs and (ii) better throughput, higher offloading fraction and lower average data loss rate comparing with the other k-hop-limited CV2V data transmission offloading method. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

PREDICTING SHORT-TERM TRAFFIC WITH RANDOM FOREST: A GRANULAR DATA APPROACH

PREDICTING SHORT-TERM TRAFFIC WITH RANDOM FOREST: A GRANULAR...

引用

2025 International Conference on Energy, Power, Environment, Control and Computing, ICEPECC 2025

作者： Mustafa, Ahmad Khattak, Khurram Shehzad Khan, Zawar Hussain Dept. of Computer Systems Engineering University of Engineering and Technology Peshawar Peshawar Pakistan College of Computer Science and Engineering University of Ha’il Ha’il Saudi Arabia

ISBN: (纸本)9781837243235

Accurate short-term traffic flow prediction is critical for improving the efficiency of Intelligent Transportation systems (ITS), particularly in heterogeneous traffic environments. This paper presents a data-driven model based on the Random Forest (RF) algorithm to predict traffic flow using high-resolution data collected over a week. The dataset encompasses individual vehicle speed, vehicle classification (car, bicycle, motorbike, bus), timestamp, flow rate, peak hour factor, traffic density, time and distance headway, and density range, recorded from 9 AM to 5 PM over seven consecutive days. Six days of data are used for training the RF model, with Thursday’s traffic flow serving as the test case. The dataset features high-dimensional, heterogeneous traffic attributes, enabling the model to capture non-linear and complex interactions effectively. Our results demonstrate that the RF model effectively captures complex, non-linear relationships in the data, delivering highly accurate predictions with an R-squared value of 0.997. This study contributes to advancing machine learning applications in traffic management, emphasizing the importance of feature selection in enhancing model performance. Future research will investigate the inclusion of additional factors such as weather conditions and external events to further refine prediction accuracy. © The Institution of engineering & Technology 2025.

关键词： Highway traffic control

来源：评论

学校读者我要写书评

暂无评论

Survey on Ethical Challenges of Implementing AI in Healthcare 7

Survey on Ethical Challenges of Implementing AI in Healthcar...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Lalwani, Nikita Ur Rahim, Muhammad Abdul Basit Anand, Aravind Shaik, Sumair Pasha Moghe, Gauri Shashank Datta, Debarati California State University Long Beach Dept. of Computer Engineering and Computer Science Long Beach United States

ISBN: (纸本)9798350350890

In today's world, Artificial Intelligence (AI) and its usage concerning human tasks have become an integral part of our daily lives. Humans depend upon AI to provide faster and more efficient solutions. In the world of medicine, where every decision made by a doctor, physician, or consultant directly impacts the lives of those being treated or diagnosed, AI is making its way to help efficiently provide such results as the intelligence of a human being. Healthcare systems around the world are now making use of AI to help provide humane solutions using algorithms and Machine Learning (ML). Fallacies or inaccuracies in the arena of healthcare can have horrendous outcomes for the patient on whom the procedure is being carried out. Sometimes, certain ethics could be traded off by the system, such as confidentiality, autonomy, justice, and biased decisions leading to false results and victim blaming, which directs the masses into not trusting AI-related healthcare solutions. This situation can lead to mishaps like 'AI winter,' where the public could start disbelieving the results of AI solutions. This survey review makes an effort to analyze and address these pertinent ethical issues underlying the requirement for algorithmic translucency, concealment, and safeguarding the interests of all those involved. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Immersive Sound Effects System Based on Dynamic Spatial Perception and Architectural Response 9

An Immersive Sound Effects System Based on Dynamic Spatial P...

引用

Joint 9th International Conference on Digital Arts, Media and Technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Lai, Wen-Hsing Ma, Chia-Hao Wang, Siou-Lin National Kaohsiung University of Science and Technology Dept. of Computer and Communication Engineering Kaohsiung Taiwan

ISBN: (纸本)9798350318241

This paper achieves the conversion of monaural audio into spatially immersive stereo audio through the use of binaural speech synthesis and Pyroomacoustics. It integrates dynamic spatial perception with the acoustic response of architectural spaces to recreate immersive audio experiences in desired environments like concert halls. The system encompasses diverse options for motion trajectory generation and architectural space modeling within its interface, allowing users to customize and merge various environmental spatial effects and surround modes, delivering an unparalleled auditory encounter. © 2024 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authentication System Based on Zero Knowledge Proof for IoT Devices 2

Lightweight Authentication System Based on Zero Knowledge Pr...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Khandait, Ashish Umesh Pattanshetti, Tanuja R. Coep Technological University Pune Dept. of Computer Science and Engineering Maharashtra Pune India

ISBN: (纸本)9798350388916

In the rapidly expanding field of the Internet of Things, ensuring secure and efficient communication between IoT devices and servers is crucial. This paper henceforth designs a lightweight authentication system under the Zero Knowledge Proof (ZKP) protocol, utilizing the HMAC hashing algorithm for the improvement of security measures put in place. This system is designed to enable the authentication of IoT devices without sending their actual password, thus avoiding risks due to password interception at the point of authentication. For instance, if using the phrase "God is great"as the password, one can get it hashed into HMAC with this method and still be assured that it is secure even if proof is intercepted. Simulations in the simulator shall evaluate the system's effectiveness and performance. Performance metrics include accuracy, response time, memory consumption, latency, and throughput. The presented results intend to serve lightweight device authentication mechanisms for IoT devices such that the trustworthiness of IoT devices is achieved without hampering their performance. The presented results are also shown to outperform conventional methods. © 2024 IEEE.

关键词： Authentication Protocol

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：