检索结果-内蒙古大学图书馆

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Abdullah Al-Sakib Zishad Hossain Limon Anamul Sakib Md Nuruzzaman Pranto Md Ariful Islam Shayma Sultana Md. Redwan Ahmed Shafiur Rahman Dept. of Information Technology Westcliff University CA USA Dept. of Computer Science Westcliff University CA USA Dept. of Business Administration International American University CA USA Dept. of Management Information System International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

Phishing attacks are a major cybersecurity threat that resulted in over 1.2 million incidents in the first half of 2020. These attacks caused substantial financial losses and posed risks to individuals and organizations. Being able to identify fraudulent websites is crucial in order to effectively address these potential risks. This study introduces a novel method for detecting phishing URLs by using word and character embeddings to capture complex URL patterns. We used a dataset of 80,000 URLs, including 50,000 legitimate ones and 30,000 phishing instances, and applied thorough preprocessing techniques. We utilized word embeddings in FastText to handle unseen words, with the added advantage of n-gram representations. Additionally, we captured character-level features through dense character embeddings. We trained several machine learning and deep learning models, and one model, the Convolutional Bidirectional LSTM (CBiLSTM), stood out with an accuracy of 99.01% and an F1-score of 99.08%. Furthermore, we made a thorough comparison with the most advanced techniques available, and our findings demonstrated clear superiority over previous research. This study presents an effective approach for classifying phishing URLs, providing a valuable tool to combat fraud and protect against identity theft, thereby helping to minimize the financial and emotional harm experienced by victims.

关键词： Deep learning Uniform resource locators Training Adaptation models Phishing Prevention and mitigation Encoding Tokenization Real-time systems Robots

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in STAR-RIS-Aided SWIPT with RSMA via Meta-Learning

arXiv

引用

arXiv 2024年

作者： Amiri, Mojtaba Vaezpour, Elaheh Javadi, Sepideh Mili, Mohammad Robat Yanikomeroglu, Halim Bennis, Mehdi School of Electrical and Computer Engineering University of Tehran Tehran Iran Dept. of Communication ICT Research Institute Tehran Iran Tehran Iran Dept. of Systems and Computer Engineering Carleton University OttawaON Canada Centre for Wireless Communications University of Oulu Oulu Finland

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) is a cutting-edge concept for the sixth-generation (6G) wireless networks. In this paper, we propose a novel system that incorporates STAR-RIS with simultaneous wireless information and power transfer (SWIPT) using rate splitting multiple access (RSMA). The proposed system facilitates communication from a multi-antenna base station (BS) to single-antenna users in a downlink transmission. The BS concurrently sends energy and information signals to multiple energy harvesting receivers (EHRs) and information data receivers (IDRs) with the support of a deployed STAR-RIS. Furthermore, an optimization is introduced to strike a balance between users’ sum rate and the total harvested energy. To achieve this, an optimization problem is formulated to optimize the energy/information beamforming vectors at the BS, the phase shifts at the STAR-RIS, and the common message rate. Subsequently, we employ a meta deep deterministic policy gradient (Meta-DDPG) approach to solve the complex problem. Simulation results validate that the proposed algorithm significantly enhances both data rate and harvested energy in comparison to conventional DDPG. © 2024, CC BY.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Reversible Neural Network

SSRN

引用

SSRN 2023年

作者： Barman, Asit Dutta, Paramartha Dept. of Computer Science & Engineering and Information Technology Siliguri Institute of Technology Darjeeling734009 India Dept. of Computer & System Sciences Visva-Bharati University Santiniketan731235 India

When identifying facial expressions using a set of salient features, reversible neural network plays a crucial role. In order to create a prominent feature set, these salient features are extracted from a face image utilizing distance and shape signatures, corresponding stability indices, and statistical measurements. The collected feature set is fed into the Reversible Neural Network (RNN), which maps it to various emotions. To carry out our experiment and verify the efficacy of facial expression recognition, the suggested network was applied to the MMI, CK+, and JAFFE data sets. © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Inverter-embedded DFIG Rotor Winding Insulation Testing for Wind Energy Applications

Inverter-embedded DFIG Rotor Winding Insulation Testing for ...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Cheol-Hui Park Adrian Jose Salcedo Bolanos Namhyuk Byun Sang Bin Lee Marcos Orviz Zapico David Diaz Reigosa Fernando Briz Del Blanco Mohamed Osama Dept. of Electrical Engineering Korea University Seoul Korea Dept. of Electrical Computer & System Engineering University of Oviedo Gijon Spain General Electric Company Munich Germany

Failure in the rotor winding insulation of doubly-fed induction generators (DFIG) used in wind turbines is common due to the harsh environment and operating stresses. However, rotor insulation testing is difficult and costly due to limited accessibility of wind generators installed inside the nacelle at remote locations. Therefore, remote and automated insulation testing can help reduce the maintenance cost and improve the reliability of DFIGs. In this paper, a new approach for testing the condition of rotor winding insulation for DFIGs is proposed. The main idea is to use the rotor-side inverter to perform off-line insulation testing whenever the wind generator is stopped. New test methods for partial discharge (PD), capacitance (C), and dissipation factor (DF) testing based on impulse and common mode voltage injection are proposed. Testing on a 6.3 kW wound rotor induction machine under emulated insulation defects is performed to verify that the proposed method can provide automated inverter-embedded testing for assessing the integrity of the DFIG rotor insulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Malware Detection and Classification for Internet of Things Using Self-Attention Based Long Short-Term Memory 3

Malware Detection and Classification for Internet of Things ...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Sudhakar, K. Husain, Saif O. Babu, D. Raja Kumar, M. Ashok Dineshkumar, R. Nitte Meenakshi Institute Of Technology Dept. Of Ai & Ds Bengaluru India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Sr University Department Of Electrical And Electronics Engineering Warangal India Skyline University Nigeria Department Of Computer Science Software Engineering And Cyber Security Kano State Nigeria Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Saveetha University Department Of Electronics And Communication Engineering Chennai India

ISBN: (纸本)9798350318609

The Internet of Things (IoT) connects numerous intelligent devices providing security features that interact with default settings accessed through applications. Additionally, Deep Learning (DL)-based mechanisms was involved for malware detection to identify and mitigate attacks. The Adaptive Synthetic Sampling (ADASYN) technique addresses class imbalances, especially when splitter class instances are distributed data in complex patterns. The proposed Self-Attention based Long Short-Term Memory (LSTM) classification method facilitates the handling of long-range dependencies in transferred data sequences offering high flexibility and adaptability to varying input lengths. For feature selection Particle Swarm Optimization (PSO) is utilized iteratively optimizes a solution in a high-dimensional space although it may have a low convergence rate due to its iterative process. The obtained results demonstrate the proposed Self-Attention based LSTM model achieves better accuracy reaching 98.05% on the NSL-KDD dataset and 99.01 % on the UNSW-NB15 dataset. These results ensure accurate classification compared to other existing methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Speaker Identification Using MFCC Feature Extraction : A Comparative Study Using GMM, CNN, RNN, KNN and Random Forest Classifier

Speaker Identification Using MFCC Feature Extraction : A Com...

引用

Trends in Electrical, Electronics, computer engineering Conference (TEECCON)

作者： Dhanvanth Reddy Yerramreddy Jayasurya Marasani Ponnuru Sathwik Venkata Gowtham Samudrala Yashwanth Poorna S S Anuraj K Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Dept. of Electronics and Communication Engineering Amrita Vishwa Vidyapeetham Amritapuri India

Speech recognition plays a major role in technology that enables computers and devices to understand and interpret human speech, while speaker identification is a specialized application within speech recognition that focuses on recognizing and distinguishing individual speakers based on their unique vocal characteristics. By utilizing techniques such as feature extraction, pattern recognition and machine learning algorithms speaker identification systems can match an input speech sample to a known set of speaker profiles and determine the most likely speaker’s identity. This process involves comparing the extracted features of the input speech with the features stored in a database or model. In this project we are performing a comparative study which mainly focuses on extracting features through MFCC feature extraction for all models in common and then the implementation of identifying speakers using Gaussian Mixture Model, CNN, LSTM in case of RNN, k-Nearest Neighbour and a Random Forest Classifier.A comparative study on various types of models helps us to pave way on analyzing these to implement one of the best among these in day to day life. Among all the models, GMM performed very well with an accuracy of 98.68% followed by LSTM with an accuracy of 95.77%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Accurate Prediction of Progression in Parkinson’s Disease

A Hybrid Model for Accurate Prediction of Progression in Par...

引用

Computing, Power and communication Technologies (IC2PCT), IEEE International Conference on

作者： S Anirudh Manushri Tummala Sri Sai Suhas Sanisetty K Dinesh Kumar Nidal Nasser Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Dept. of Electronics and Communication Engineering Amrita School of Engineering Bengaluru Amrita Vishwa Vidyapeetham India College of Engineering Al Faisal University Saudi Arabia

Evaluating the extent of motor impairment is an important aspect in Parkinson’s disease, where the Unified Parkinson’s Disease Rating Scale (UPDRS) plays a crucial role. The UPDRS assessment is traditional, time-consuming and labor intensive. This paper presents a stacked regression model using Light gradient-boosting machine (LightGBM) and CatBoost to automate and enhance UPDRS score predictions. It is an important advancement in managing Parkinson’s disease that provides more efficient and individualized care for patients through ensemble learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey on LED lamps for residential applications: Characterization of performance 23

Survey on LED lamps for residential applications: Characteri...

引用

23rd International Scientific Conference on Electric Power engineering, EPE 2023

作者： Hudač, Tomáš Drapela, Jiri Kukačka, Leoš Meyer, Jan Stiegler, Robert Brno University of Technology Faculty of Elect. Eng. and Communication Dept. of Electrical Power Engineering Brno Czech Republic Institute of Mechatronics and Computer Engineering Technical University of Liberec Liberec Czech Republic Institute of Electrical Power Systems and High Voltage Engineering Technische Universität Dresden Dresden Germany

ISBN: (纸本)9798350335934

Aim of the paper is to conduct a survey of the present market, focusing on the best-selling retrofit LED lamps and to analyze experimentally their fundamental EMC performance for subsequent classification of the LED drivers. Two stage experimental characterization testing approach is adopted. First, input current and output luminous flux in steady-state under nominal supply conditions is acquired. Next, transfer of input supply voltage interharmonics to output visible flicker components in terms of gain factor curves is obtained. Based on the achieved and discussed testing results, classification of the LED lamps is developed. © 2023 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Securing Mobile Robotic Networks Against Replacement Attack

引用

IEEE Transactions on Automatic Control 2025年

作者： Li, Yushan He, Jianping Chen, Cailian Guan, Xinping Cai, Lin Shanghai Jiao Tong University Dept. of Automation China Ministry of Education of China The Key Laboratory of System Control and Information Processing China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Victoria Dept. of Electrical and Computer Engineering BC Canada

The security of mobile robotic networks (MRNs) has been an active research topic in recent years. This paper aims to secure the ubiquitous formation control of MRNs against the replacement attack, where an external robot can replace a formation robot by compromising the communication and physically interfering with the victim simultaneously. To counter this advanced attack, the novel idea of this work is to leverage the physical proximity of the formation shape and the interaction topology among robots for defense design. First, from the physical proximity perspective, we propose the convex neighbor polygon (CNP) to capture the geometric characteristic of the formation robots, and design a CNP-based security mechanism for the robots during the replacement attack. Then, from the interaction perspective, we introduce the indirect controllability to characterize the possibility that the attacker leverages the interaction between robots to deactivate the CNP mechanism, and establish the conditions regarding the topology structure and the attack input to counter the replacement. Finally, based on the obtained conditions, we demonstrate how to design the initiatory topology among the formation robots to enhance the defense performance. Comparative simulations verify the effectiveness of the proposed method. © 1963-2012 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Using AI and Natural Language Processing to Enhance Consumer Banking Decision-Making

Using AI and Natural Language Processing to Enhance Consumer...

引用

2024 International Conference on E-Mobility, Power Control and Smart systems, ICEMPS 2024

作者： Temara, Sheetal Samanthapudi, Sagar Varma Rohella, Piyush Gupta, Ketan Ashokkumar, S.R. University of The Cumberlands Dept of Computer & Information Sciences WilliamsburgKY United States The Polis Center Indiana University Purdue University Indianapolis Applied Data Science IndianapolisIN United States Payments & Commerce GoDaddy EdmondsWA United States University of The Cumberlands Dept. of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Centre For Blockchain and Cyber Security Department of Computer and Communication Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350394399

This technical summary outlines the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) to beautify patron banking decision-making. AI-based banking systems can autonomously identify patterns in consumer information and generate insights from a number of sources, including but not restricted to purchaser 360 profiles, 1/3-party statistics, and transactional statistics. With the assistance of AI and NLP, this gadget can answer customer questions relating to their banking wishes and offer personalized recommendations. AI-based monetary decision-making systems also permit banks to offer computerized customer service with information on clients' needs, respond speedily to purchaser requests, and offer quick acclaim for loans and other banking merchandise. Moreover, AI and NLP enhance patron engagement via chatbot-like solutions and purchaser sentiment analysis. The extraordinary AI and NLP-based services being presented by using banks are mentioned in this technical abstract. In conclusion, AI and NLP technology are giving banks the capacity to meet the desires of their customers and improve typical purchaser pleasure. © 2024 IEEE.

关键词： Artificial intelligence

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：