检索结果-内蒙古大学图书馆

Intelligent Battery Management System for Electric Vehicle with IoT-based Monitoring, AI-Driven Multiple Fault Diagnosis and Energy Optimization 3

Intelligent Battery Management System for Electric Vehicle w...

引用

3rd international conference on Electronics and Renewable systems, ICEARS 2025

作者： Arun Kumar, P. Shalini, S. Sneha, R. Vasunthra, P. Suganyadevi, S. M Kumarasamy College of Engineering Department of Ece Karur India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509675

Battery related issues have a significant effect on both the performance and safety of electric vehicle (EV). Overheating Battery Lifespan is meant to be reduced by simply the dangers of overheating, as they can even cause thermal runaway, as well as from over and deep revolution. Besides, EV batteries have poor performance even in extreme temperatures, capacity loss, and internal defects. In order to cope with these problems, a proposed IoT based EV battery monitoring and fault detection system provides the real time analysis to promptly notify the battery health. Built in IoT sensors are integrated in this system which monitors critical parameters constantly i.e. temperature, voltage, current and charge levels. For 95-98% battery parameters monitoring accuracy, the collected data is transferred to a centralized cloud platform for real time cloud processing. The system utilizes advanced edge computing techniques and continuous monitoring capable of detecting a fault with 95-98% probability. Electrochemical processes are analyzed with 90-95% accuracy using predictive analytics and machine learning algorithms to ensure optimal battery performance. Moreover, the system achieves energy efficiency of more than 95% through power management and control mechanisms. In 95% of the cases, intelligent charging algorithms will prevent overcharging. This cutting-edge technology dramatically improves EV battery safety, longevity as well as efficiency, assuring reliability and sustainability. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Through the Looking Glass—The 2025 Edition: Trends in solid-state circuits from ISSCC

引用

IEEE Solid-State Circuits Magazine 2025年第1期17卷 97-118页

作者： Mirabbasi, Shahriar Fujino, Laura C. University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada University of Toronto Department of Electrical and Computer Engineering TorontoONM5S 1A1 Canada

The international Solid-State Circuits conference (ISSCC) is the flagship conference of the IEEE Solid-State Circuits Society. The theme for ISSCC 2025 is "The Silicon Engine Driving the Artificial Intelligence (AI) Revolution." This theme further highlights how today’s IC research and development can contribute to the solid-state foundation upon which AI is rapidly evolving and pervasively entering people’s lives. ISSCC 2025 is the 72nd edition of ISSCC and is more than ever focused on innovation, in particular, innovative solutions that facilitate the efficient implementation of AI algorithms. To enhance and support the widespread use of AI, ISSCC 2025 promotes and shares new circuit ideas that advance the state of the art in IC design and further equip AI systems with improved functionality and efficiency. © 2025 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

A Novel Channel Selection and Classification in Motor Imagery for Brain Computer Interface Using Meta Heuristic algorithms

A Novel Channel Selection and Classification in Motor Imager...

引用

international conference on Smart systems and Wireless Communication, SSWC 2024

作者： Devarakonda, Nagaraju Kamarajugadda, Raviteja Anandarao, Sarvani School of Computer Science and Engineering VIT-AP University Amaravathi India Department of Information Technology Lakireddy Bali Reddy College of Engineering Mylavaram India Department of Computer Science and Engineering SRM University AP Amaravati India

ISBN: (纸本)9789819613472

A vital input for a task using the brain in BCI (Brain Computer Interface) applications is the motor imagery (MI) signal from the brain. Users of BCI systems can operate external equipment by using their brain activity, using motor imagery as a control method. Innumerous Electroencephalography (EEG) channels are used to gather nerve impulses from the brain, which are the most prevalent input for Brain Computer Interface systems while they are minimally invasive, flexible, and low in price. The computational overhead is increased by multichannel BCI systems’ high-dimensional data, which causes processing to be slower and to cost more money. EEG details are regularly gathered from over 100 different brain regions;therefore, it is essential to use channel selection algorithms to choose the ideal channels for a given circumstance. However, the primary objective of choosing the channel in EEG data analysis is to lessen the computer intricacy, improve the precision of classification by eliminating over fitting, and save setup time. In this study, we suggested a remora optimization technique that was inspired by nature to lessen the computational load brought on by several channels. Using predetermined criteria, a number of channel selection evaluation techniques, whether classification-based methods used or not it extracted the proper channel subsets. In order to determine the greatest classification accuracy, the classification procedures were utilized in the end. Three publicly available EEG datasets are used to validate the experiment (BCI Competition IV-1,2a, Competition III-3a), and it resulted in superior classification accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

M-Patch: Adversarial Patch-based Physical Attack against Multi-modal Fusion Detectors 24

M-Patch: Adversarial Patch-based Physical Attack against Mul...

引用

3rd international conference on algorithms, Data Mining, and Information Technology, ADMIT 2024

作者： Chen, Yixin Zheng, Haibin Chen, Jinyin Huang, Haojie College of Information Engineering Zhejiang University of Technology China Institute of Cyberspace Security Zhejiang University of Technology China

ISBN: (纸本)9798400718120

As reliance on multimodal fusion object detection models grows in critical tasks, ensuring their robustness and security is essential before deployment. However, research on adversarial attacks in multimodal target detection is still in its early stages, making it crucial for evaluating and improving system resilience. To address these challenges, we propose M-Patch, an adversarial patch-based attack method specifically designed for multimodal fusion object detection models. M-Patch can execute attacks in both digital and physical environments and is applicable to various multimodal detection models. In digital tests, M-Patch achieved success rates exceeding 60%, with a notable 97.6% success rate against the MFEIF+YOLOv3 multimodal detection model. Physical experiments further validated the patch’s effectiveness, demonstrating strong attack results. More importantly, M-Patch reveals significant vulnerabilities in multimodal systems, offering a practical and efficient approach to enhancing their security. © 2024 Copyright held by the owner/author(s).

关键词： adversarial attack

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach Based on Contract Parameters for Cost Forecasting in Construction 7th

A Machine Learning Approach Based on Contract Parameters for...

引用

7th international conference on Industrial and Logistics systems, SIL 2024

作者： Ben Talha, Maroua Houari, Fatima-Zahrae Benghabrit, Asmaa Rhazi, Mohamed Sayf Eddine INDUSLAB ONRST ENSMR Rabat Casablanca Morocco Laboratory of Applied Mathematics and Business Intelligence ENSMR Rabat Casablanca Morocco JACOBS Engineering S.A Casablanca Morocco

ISBN: (纸本)9783031873089

The construction industry, characterized by its inherent complexity, is a cornerstone of economic growth and development. In the era of Construction 4.0, accurate cost estimation within this sector is essential for successful project planning and execution. This research aims to predict construction project costs using real data from 203 projects, incorporating contract parameters provided by an engineering consulting firm. Among the eleven machine learning algorithms tested, the Partial Least Squares regression model emerged as the most effective. It achieved the highest ranking in the TOPSIS analysis, demonstrating a coefficient of determination of 91% for the test set. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

Data Protection in Enhanced EXplainable Digital Twins: Insights from Hybrid AI 2

Data Protection in Enhanced EXplainable Digital Twins: Insig...

引用

2nd international conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Gupta, Prashant K. Mazumdar, Bireshwar Dass Pillai, Subash Nataraja School of Computer Science & Engineering Technology Bennett University Uttar Pradesh Greater Noida India Division of Agricultural Physics ICAR-Indian Agricultural Research Institute Pusa Campus New Delhi110012 India

ISBN: (纸本)9798331530389

Deep Learning (DL) based artificial intelligence (AI) is becoming pervasive in almost all the day to day applications. These DL algorithms require large amounts of data, which can be easily collected nowadays by deploying sensors in the environment of the system under observation. These DL algorithms however, suffer from drawbacks such as being criticised as 'black-boxes', being biased to generating predictions based on past data and ignoring the human expertise. Hence, an architecture of Enhanced eXplainable Digital Twins (EXDTs) was proposed. EXDTs remove 'black-boxness' of DL algorithms by using the XAI approaches. Further, the digital twins (DTs) underlying the EXDTs are constructed through the sensor data and depict the real-time simulatability. Also, to improve the explainability and use the human expertise/experience, EXDTs use the domain experts' qualitative data. EXDTs are a class of Hybrid AI systems, that use the numeric data for underlying DL algorithms and subjective knowledge of the domain expert. This multimodal data in EXDTs opens up new attacks fronts for data manipulation and change the EXDTs' outputs. In this manuscript, we discuss about the data protection in EXDTs, by simulating various types of attacks and suggesting possible ways the system can counter them. We feel our proposed framework is useful for the involved stakeholders in various domains like precision agriculture, healthcare, manufacturing, etc. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Critical Review of Automated Traffic Signal systems Leveraging IoT and Machine Learning 2

Critical Review of Automated Traffic Signal Systems Leveragi...

引用

2nd international conference in Civil engineering for a Sustainable Planet, ICCESP 2024

作者： Abhijith, R.P. Christy, Freeda Simi, M.R. Renju, C.M. Dept. of Civil Engineering Kalasalingam Academy of Research and Education India Dept. of Civil Engineering Mahaguru Institute of Technology India Dept. of Civil Engineering Marian Engineering College India

ISBN: (数字)9780784486047

ISBN: (纸本)9780784486047

The integrated use of Internet of Things (IoT) and machine learning (ML) in automated traffic signal systems marks a significant leap forward in optimizing urban traffic flows. By leveraging real-time data gathered from interconnected devices and applying advanced machine learning algorithms, these systems can dynamically adjust traffic signals to enhance efficiency and alleviate congestion. This technological innovation underscores the transformative potential of incorporating state-of-the-art technologies into urban traffic management practices. However, despite the promising advantages offered by IoT and machine learning, several implementation challenges are also be addressed. That includes ensuring the secure and reliable transmission of the data across interconnected devices, managing the scalability of the system to accommodate varying traffic volumes and urban environments, and effectively handling the complexity of real-time decision-making processes. Going through these types of challenges is very severe for the widespread adoption and successful deployment of automated traffic signal systems powered by IoT and machine learning. Continuous research and development efforts are essential to refine algorithms, improve data integration capabilities, and validate system performance in diverse real-world conditions. By overcoming these hurdles, cities can unlock the full potential of automated traffic signal systems to create more efficient, sustainable, and liveable urban environments. © ASCE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Exploring CNN-Based algorithms for Human Action Recognition in Videos 14th

Exploring CNN-Based Algorithms for Human Action Recognition ...

引用

14th EAI international conference on Broadband Communications, Networks, and systems, BROADNETS 2024

作者： Begum, Shaik Salma Sathvik, Jami Anjana Adi Ahmed, Mohammed Ezaz Satya, Dantu Vyshnavi Javvadi, Tulasi Kuma, Majji Naveen Sai Kumar, Kommoju V. V. S. M. Manoj S R Gudlavalleru Engineering College Gudlavalleru Gudlavalleru India

ISBN: (纸本)9783031811708

This study presents a comparative analysis of three convolutional neural network (CNN)-based methodologies, namely the Two-Stream CNN, CNN + LSTM, and 3D CNN, for human action recognition in video sequences. The main goal of this research is to analyze and understand human behaviors in video content. And subsequently, generate associated tags, all while surmounting the intricate spatial and temporal intricacies inherent in this task. The experimental evaluation employs the HMDB-51 dataset, and the findings reveal that all three proposed algorithms effectively discern human actions within the video domain, albeit with distinct performance variations. Furthermore, the paper offers in-depth elucidations and comprehensive analyses of each of these methods, thereby imparting valuable insights and directions for prospective research endeavors in the realm of human action recognition. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Soft Computing Paradigms for Load Balancing in Cloud Computing 3rd

Soft Computing Paradigms for Load Balancing in Cloud Computi...

引用

3rd international conference on Computational Electronics for Wireless Communications, ICCWC 2023

作者： Ghafir, Shabina Alam, M. Afshar Alankar, Bhavya Department of Computer Science and Engineering School of Engineering Sciences and Technology Jamia Hamdard New Delhi India

ISBN: (纸本)9789819719457

This paper provides a comprehensive comparison of load-balancing algorithms employed in cloud computing, spanning from the earliest to the most recent developments. Emphasizing the significance of load balancing for system performance, resource optimization, and equitable allocation among users, the paper offers insights into various techniques, their effectiveness across workloads, and associated limitations. With an overview of each algorithm, this study caters to practitioners and researchers in the dynamic field of cloud computing, aiming to contribute valuable perspectives for enhanced system efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advanced AI Surveillance for Human Trafficking and Accident Prevention 14th

Advanced AI Surveillance for Human Trafficking and Accident ...

引用

14th EAI international conference on Broadband Communications, Networks, and systems, BROADNETS 2024

作者： Makka, Shanthi Sowmya, A. Vishwanath, Sanagala Snigdha, Kattekola Charan, Vankadaru Vardhaman College of Engineering Kacharam Shamshabad Telangana Hyderabad501218 India

ISBN: (纸本)9783031811708

The population has grown, there have been significant urban developments, and there have also been upsetting social situations. Today, technology is improving human life. The use of AI-detector surveillance systems to identify people trafficking, accidents, and emergency situations and notify neighboring police stations, hospitals, and concerned departments is explored in this research article. Since there is a communication gap in the majority of these situations, particularly at night, fatalities and unsolved cases are the result. This technology functions as a communication channel, sending information about these incidents to the control center, prevent this gap in communication. The Artificial Intelligence Surveillance System promises to accelerate emergency response times by utilizing sophisticated computer vision algorithms and clever communication protocols. This paper offers a thorough methodology, explains the findings, and emphasizes the system's ramifications. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Convolutional neural networks

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：