检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Chandra, Sucheta Das, Priyanka Mandal, Ankita Chakroborty, Sriparno Chowdhury, Ishika Ghosh, Kathamrita University of Engineering & Management Institute of Engineering & Management Dept. of Computer Application and Science Kolkata India

ISBN: (纸本)9798331523893

Phishing attacks remain a critical threat to cybersecurity, leveraging deception to steal sensitive information from individuals and organizations. Traditional detection methods often fail to keep up with evolving phishing tactics, highlighting the need for advanced solutions. This paper investigates the use of the Random Forest algorithm, a powerful machine learning technique, to enhance phishing detection systems. By leveraging the ensemble learning approach of Random Forest, we improve accuracy and efficiency in classifying phishing attempts, while reducing false positives. The methodology includes data preprocessing, feature extraction, and model implementation, showcasing its effectiveness in real-time detection. The study also emphasizes the importance of continuous learning, allowing the model to adapt to new phishing strategies, thereby offering a robust defense against emerging threats. This research contributes to advancing cybersecurity by providing a dynamic, scalable approach to phishing detection. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

LightNN: An Optimized Deep Learning Framework for Enhanced Fruit Classification

LightNN: An Optimized Deep Learning Framework for Enhanced F...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Afroj, Maharin Jahan, Israt Islam, Md Polash Saifur Rahman, Md. Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Stockholm University Dept. of Computer and Systems Sciences Stockholm Sweden

ISBN: (纸本)9798331529765

The crucial field of fruit classification in computer vision and deep learning brings about breakthroughs that have broad applications in the retail and agricultural industries. By automating the identification and sorting of various fruit types, these technologies enhance efficiency, accuracy, and scalability, benefiting processes from farm production to market distribution. The integration of sophisticated algorithms and neural networks not only improves the speed and reliability of fruit classification but also offers the potential for real-time quality control and inventory management, revolutionizing traditional methods and paving the way for more innovative, data-driven approaches in these sectors. This study introduces LightNN, a novel and effective paradigm with a lightweight architecture that tackles the complex problems related to computational efficiency. Combining a small classifier with a simplified feature extractor, LightNN achieves the ideal balance between simplicity and accuracy. The feature extractor is capable of extracting hierarchical features from RGB images by using convolutional layers with ReLU activations and max-pooling procedures. The flattened output is then processed by the classifier, which consists of fully connected layers with ReLU activations and dropout regularisation. Remarkably, LightNN, with just 298,835 parameters, manages to get a respectable 96.37% test accuracy in fruit categorization tasks. The results highlight LightNN's promise as an effective and efficient fruit classifying method, particularly in situations with constrained computational resources. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Energy Recovery and Power Management in EVs Using Supercapacitors and Regenerative Braking 2

Energy Recovery and Power Management in EVs Using Supercapac...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Shib, Sowrov Komar Dipto, Durjoy Roy Rahman, Md Tanvir Islam, Md Ashikul Islam, Md Mahafuzul Shufian, Abu American International University-Bangladesh Dept. of Electrical and Electronics Engineering Dhaka Bangladesh Dhaka Bangladesh Lamar University Dept. of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798331506995

Regenerative braking (RB) is crucial in enhancing the efficiency and sustainability of electric vehicles (EVs) by converting kinetic energy into usable electric energy during braking. However, current systems face challenges in maximizing energy recovery and managing power effectively. This research presents an optimized regenerative braking system that combines the benefits of supercapacitors and Brushless DC (BLDC) motors to improve energy recovery efficiency. The study introduces advanced control algorithms for BLDC motors to ensure precise and reliable operation across various driving conditions. Furthermore, refined power management strategies are developed to optimize energy storage between supercapacitors and batteries, enhancing overall system efficiency. The proposed model employs modern control techniques and power management solutions, allowing for real-time energy optimization during braking. With an overall energy recovery efficiency of 92.5%, the system shows significant promise in minimizing energy losses and supporting the sustainability goals of electric vehicles. © 2025 IEEE.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Protecting Battery Health During Charge and Discharge for Electric Vehicles

Protecting Battery Health During Charge and Discharge for El...

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Anonto, Hasanur Zaman Hossain Emon, Md Mukter Nandi, Anup Islam, Sashyni Hossain, Md Ismail Shufian, Abu American International University-Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh Dhaka Bangladesh Lamar University Dept. of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798331541125

Lithium-ion (Li-ion) batteries are pivotal to electric vehicles performance, efficiency, and sustainability (EVs), offering high energy density, lightweight design, and the ability to endure hundreds of charge-discharge cycles. However, they are susceptible to suboptimal operating conditions, including overcharging, under-discharging, and exposure to extreme temperatures. These can significantly degrade battery capacity, shorten lifespan, and pose safety hazards such as thermal runaway. This paper investigates advanced battery management systems (BMS) and protection mechanisms to mitigate these risks. Through optimized charge/discharge strategies, real-time monitoring, and precise temperature regulation within safe operating limits (15°C to 45°C), the proposed methods demonstrate the potential to reduce battery degradation by up to 30% and extend overall battery life by 20%. Additionally, integrating solid-state battery technology is explored as a promising solution to enhance battery safety, energy density, and reliability. These advancements improve the long-term performance of EV batteries and contribute to the broader goal of making electric transportation systems safer, more sustainable, and more efficient for future mobility. © 2025 IEEE.

关键词： Solid-State Batteries

来源：评论

学校读者我要写书评

暂无评论

Optimizing Photovoltaic System Efficiency: A Comparative Study of RNN-based Controller and Incremental Conductance in MPPT 52

Optimizing Photovoltaic System Efficiency: A Comparative Stu...

引用

52nd IEEE Photovoltaic Specialist Conference, PVSC 2024

作者： Soyoye, Babatunde D. Bhattacharya, Indranil Vinolisha, Mary Banik, Trapa Tennessee Tech University Electrical and Computer Engineering dept. CookevilleTN38505 United States Tennessee Tech University Antony Dhason Electrical and Computer Engineering dept. CookevilleTN38505 United States

ISBN: (纸本)9781665464260

In this study, a Recurrent Neural Network (RNN)- based PV controller is thoroughly examined and compared with conventional Incremental Conductance techniques for Maximum Power Point Tracking (MPPT). The study emphasizes the improved responsiveness and efficiency of the RNN controller and focuses on the dynamic adaptation of PV systems to changing environmental conditions. In this study, the better performance of the RNN controller in monitoring the maximum power point, its fast convergence time, and its stability under various environmental conditions are demonstrated by comprehensive simulations and comparative studies. According to the results, using cutting-edge machine learning methods, such as RNNs, may greatly increase PV systems' operational effectiveness, highlighting their potential to optimize renewable energy systems. This study offers insights that advance the realm of renewable energy technologies. © 2024 IEEE.

关键词： DC-DC Boost converter Incremental conductance Machine learning Maximum Power Point Tracking (MPPT) Photovoltaic systems Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Robust Line-Convex Polygon Intersection Computation in E2 using Projective Space Representation

引用

Machine Graphics and Vision 2023年第3-4期32卷 3-16页

作者： Skala, Vaclav Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

This paper describes modified robust algorithms for a line clipping by a convex polygon in E2 and a convex polyhedron in E3. The proposed algorithm is based on the Cyrus-Beck algorithm and uses homogeneous coordinates to increase the robustness of computation. The algorithm enables computation fully in the projective space using the homogeneous coordinates and the line can be given in the projective space, in general. If the result can remain in projective space, no division operation is needed. It supports the use of vector-vector operations, SSE/AVX instructions, and GPU. © 2023 Institute of Information Technology, Warsaw university of Life sciences - SGGW. All rights reserved.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

A systematic review of decentralized finance protocols

引用

International Journal of Intelligent Networks 2023年第1期4卷 171-181页

作者： Shah, Kaushal Lathiya, Dhruvil Lukhi, Naimish Parmar, Keyur Sanghvi, Harshal Dept. of Computer Science and Engineering Pandit Deendayal Energy University Gujarat Gandhinagar382007 India Dept. of Computer Science and Engineering Sardar Vallabhbhai National Institute of Technology Gujarat Surat395007 India Dept. of CEECS Florida Atlantic University Boca Raton United States

Decentralized finance (DeFi) has revolutionized the financial industry in recent years. Industries such as banking, insurance, and investment are experiencing a significant shift due to the growth of DeFi. The decentralized finance market is expanding exponentially, emphasizing the potential of digital currencies and decentralized platforms in providing an alternative to the traditional finance paradigm. It eliminates the need for costly intermediaries, reduces transaction fees, and increases accessibility to financial services for everyone, regardless of their geographic location or economic status. With the enormous increase in cryptocurrency investment, individuals and institutions have started to use DeFi. In this context, understanding the architecture and working mechanisms of different DeFi protocols becomes crucial in creating new and innovative products. This review paper explores various DeFi protocols, including derivatives, decentralized exchanges (DEX), lending and borrowing, asset management, and stablecoins. It analyses their internal structure and composability, providing insights into how these protocols can be combined to create new and innovative DeFi products and explore the potential of DeFi in providing an alternative to the traditional finance paradigm. © 2023 The Authors

关键词： Asset management

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Power Gating for Enhanced Energy Efficiency in Superscalar Processors 31

AI-Driven Power Gating for Enhanced Energy Efficiency in Sup...

引用

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Kalra, Naman Tudu, Jaynarayan T. Dept. of Electrical Engineering Indian Institute of Technology Tirupati India Dept. of Computer Science Engineering Indian Institute of Technology Tirupati India

ISBN: (纸本)9798331509118

Amid the rising demand for efficient processors, the challenge has always been to reduce power consumption without compromising performance. FinFET technology has significantly reduced leakage power issues, but dynamic power consumption at lower nodes has reemerged as a concern. Methodologies such as power/clock gating, DVFS, and voltage biasing have been proposed in the past. However, next-generation complex SoC designs at © 2024 IEEE

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Optimizing EV Charging Infrastructure through Behavioral Analysis, Smart Charging, and V2G Integration

Optimizing EV Charging Infrastructure through Behavioral Ana...

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Hossain, Md Ismail Anonto, Hasanur Zaman Hossain Emon, Md Mukter Nandi, Anup Shahriyar, Azad Shufian, Abu American International University-Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh Dhaka Bangladesh Lamar University Dept. of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798331541125

The rapid adoption of electric vehicles (EVs) underscores the pressing need for optimized charging infrastructure to meet growing demands. This study investigates the integration of behavioral analysis, innovative charging strategies, and vehicle-to-grid (V2G) technology to improve EV infrastructure efficiency and grid stability. This research identifies key factors that influence charging demand and usage by examining user-specific charging patterns, including differences between private and fleet users. Smart charging and dynamic pricing models are explored to alleviate peak load stress, while V2G solutions enhance energy distribution during demand fluctuations. The findings emphasize the significance of flexible infrastructure planning, which includes Level 1, Level 2, and DC fast chargers strategically deployed to cater to diverse EV user needs. This approach offers a pathway to a sustainable, scalable charging ecosystem, promoting both user convenience and grid resilience. © 2025 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

Enhancing Question-Answering with Knowledge Graph Retrieval and Generation using LLMs

Enhancing Question-Answering with Knowledge Graph Retrieval ...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Gijre, Supraj Agrawal, Rishi Laddha, Priyash Keswani, Gunjan Shri Ramdeobaba College of Engineering and Management Dept. Computer Science and Engineering Nagpur India School of Computer Science and Engineering Ramdeobaba University Nagpur India

ISBN: (纸本)9798331517953

This paper describes a novel technique to improving Large Language Models (LLMs) for document analysis that employs knowledge graphs and retrieval-augmented generation (RAG). We are working on constructing a chatbot system that can handle and analyze large documents from a variety of fields. Our approach addresses basic LLM issues including context maintenance and hallucination avoidance. The system combines document chunking, vector embedding, and similarity search with graph-based knowledge representation. Users can upload large papers and answer questions accurately. We show that integrating standard information retrieval approaches with graph-based storage and LLM capabilities improves context awareness and response accuracy across a wide range of document genres. This strategy is especially promising for complicated publications such as financial reports. © 2024 IEEE.

关键词： Knowledge graph

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：