检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Mwaura, Jedidah Araki, Shunsuke Kakizaki, Ken'Ichi Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering FuKuoka Japan Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Fukuoka Japan

ISBN: (纸本)9798350324136

In recent years, there has been a proliferation of Internet of Things (IoT) devices, and so has been the attacks on them. In this paper we will propose a methodology to detect Distributed Denial of Service (DDoS) attacks on IoT devices using Machine Learning for Microcontrollers. We will discuss a model which we made for Arduino Nano 33 BLE Sense using Machine Learning for Microcontrollers. Additionally, we will discuss results of our proposal in detecting DDoS attacks on IoT devices. Lastly, we will describe the feasibility of our model on IoT devices. © 2024 IEEE.

关键词： DDoS IoT Machine Learning TinyML

来源：评论

学校读者我要写书评

暂无评论

Highly Compact Wideband High-Gain Four-Element MIMO Antenna for 5G New Radio IoT

引用

IEEE Internet of Things Journal 2025年第12期12卷 22350-22365页

作者： Khan, Shahid Khan, Owais Shah, Syed Ahson Ali Nasir, Jamal Malik, Bilal Tariq Khan, Salahuddin Koziel, Slawomir COMSATS University Islamabad Department of Electrical and Computer Engineering Islamabad45550 Pakistan Gwangju Institute of Science and Technology Department of Electrical Engineering and Computer Science Gwangju61005 Korea Republic of King Saud University College of Engineering Riyadh11421 Saudi Arabia Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk80-233 Poland Reykjavik University Department of Engineering Engineering Optimization and Modeling Center Reykjavik101 Iceland

Wideband millimeter-wave (mm-wave) coverage is essential for the high-speed, low-latency communication required in next-generation 5G New radio (NR) Internet of Things (IoT) systems. This study develops a T-shaped four-element, highly compact wideband multiple-input multiple-output (MIMO) antenna covering the mm-wave n260 (37 40 GHz) and n259 (42 43.5 GHz) bands for 5G NR IoT applications. The antenna is designed on a 0.76 mm-thick Rogers RO4350B substrate with overall dimensions of 28 28 mm2 (3.3 3.3 ?2). For design simplicity, a T-shaped patch backed by a full-ground plane is devised to serve as the radiator of a single-element antenna with the dimensions of (Ls Ws) mm2, optimized through a systematic three-step design process for improved performance. Moreover, the design has evolved into a 4 4 orthogonal MIMO configuration, achieving improved gain, polarization diversity, and higher data rates, with each element exhibiting wideband characteristics across 11.5 GHz (36.5 48 GHz) with high gains of 9.8 dBi and 6.6 dBi at n260 and n259 5G mm-wave bands, respectively. Additionally, arc-shaped complementary split-ring resonators (CSRR) are integrated into the ground plane to significantly enhance the gain while effectively reducing mutual coupling, remarkably achieving a maximum gain of 9.8 dBi. Furthermore, the MIMO antenna exhibits an envelope correlation coefficient of less than 0.10 between any two MIMO elements encountering the required condition of © 2025 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled Semantic Web 2

AI-Enabled Semantic Web

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Saeed, Abdullah Dhanda, Namrata Rao, Ansh Samuel Verma, Rajat Amity University Uttar Pradesh Department of Computer Science and Engineering Lucknow India Pranveer Singh Institute of Technology Department of Computer Science and Engineering Kanpur India

ISBN: (纸本)9798350371055

The paper presents a comprehensive study on the development of an AI-enabled Semantic Search application using a Full Stack approach. The project integrates cutting-edge technologies, such as ***, Langchain, Pinecone, and ChatGPT, to create a robust and efficient information retrieval system. The methodology begins by setting up the essential imports and utility functions for Langchain and Pinecone. Diverse data types are then loaded seamlessly using specialized loaders. The project's core involves the creation of a Pinecone index and successfully uploading documents, which establishesa powerful and accessible database. The application's user interface can be enriched with advanced UI features. These features enhance the aesthetic appeal and interactivity of the platform, facilitating user navigation and query formulation. The implemented technique discusses the challenges of developing an AI-enabled Semantic Search application, such as the need to deal with large volumes of data and the complexity of natural language processing, and suggests solutions to these challenges, such as using distributed computing and machine learning techniques. The culmination of these efforts is a comprehensive Semantic Search application that leverages the capabilities of AI and modern web technologies to deliver an immersive, efficient, and personalized information retrieval experience. This research contributes to the advancement of full-stack development practices and demonstrates the potential of integrating AI technologies to enhance user interactions with data-rich platforms. © 2024 IEEE.

关键词： LangChain LLMs Semantic Search Text Embedding Web

来源：评论

学校读者我要写书评

暂无评论

An Efficient Convolutional Neural Network Hardware IP for Epilepsy Detection 17

An Efficient Convolutional Neural Network Hardware IP for Ep...

引用

17th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2024

作者： Gong, Yi Zhang, Yuejun Tu, Jiangtao Zou, Rongxin Wen, Liang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China

ISBN: (纸本)9798350361834

Epilepsy is a common neurological disease which is sudden and unpredictable. In response to the current problems of low efficiency and high false detection rate in epilepsy detection, this paper proposes an efficient convolutional neural network (CNN) hardware intellectual property (IP) design scheme for epilepsy detection. According to the epilepsy pathology, the oversampling technique is used to solve the sample imbalance. Filters out the noise by using band-pass filters, and improves the model by using Z-score normalization. Then, the structure of convolutional neural network is optimized to build an end-to-end network model and train the corresponding weights as well as biases. A single convolutional kernel is used to lighten the network model and reduce the parameters. The 22-channel EEG data are processed in a parallelized manner to fully extract the correlation between the channels. The 3-layer convolutional and max pooling module is designed by combining with pipelining technique. Validated on the CHB-MIT dataset, the epilepsy detection accuracy is reached 97.45%. Under TSMC 65 nm process, the IP core area is measured as 1.625 mm 2 , power consumption is measured as 4.225 mW, single detection delay is 0.01935 ms, and single detection energy consumption is 0.237 μJ/class. © 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

Multiple Relays Assisted MEC System for Dynamic Offloading and Resource Scheduling with Energy Harvesting 18th

Multiple Relays Assisted MEC System for Dynamic Offloading ...

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Wang, Jiming Qu, Long Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Ningbo China

ISBN: (纸本)9789819998951

Mobile Edge Computing (MEC) has become an indispensable way to reduce the execution delay of devices. However, for some devices located far away from the MEC server, the transmission delay of communication with MEC is still large. In this case, we consider using multiple relay devices to assist Internet of Things (IoT) devices to communicate with MEC servers. To enhance the energy efficiency of the system, we introduce Energy Harvesting (EH) devices to provide energy for the IoT devices. Our objective is to maximize the utilization of EH devices while minimizing the overall delay in task offloading for the IoT devices. We tackle the problem by formulating it as a Markov Decision Problem (MDP). However, due to the significant expansion of the state space, traditional methods such as relative value iteration and linear iterative reconstruction are ineffective in solving this problem. Hence, we propose an approach called Multi-Relay Assisted Dynamic Computation Offloading (MRADCO) algorithm, which leverages the Lyapunov optimization technique. It is important to note that our proposed algorithm makes decisions solely based on the current state, without requiring the distribution information of the wireless channel and EH process. This characteristic enhances the algorithm’s practicality and reduces complexity in real-world implementations. Through rigorous theoretical derivation and comprehensive simulation experiments, we demonstrate that our algorithm is asymptotically optimal. And compared with the benchmark algorithm LODCO, our algorithm reduces the time by 50%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

VOICE METRICS FOR DISCOURSE QUALITY ANALYSIS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2023年第3期85卷 3-12页

作者： Jinga, Nicolae Moldoveanu, Florica Moldoveanu, Alin Morar, Anca Mocanu, Irina Butean, Alexandru Faculty of Automatic Control and Computer Science University POLITEHNICA of Bucharest Romania Faculty Engineering "Lucian Blaga" University of Sibiu Romania

In this paper, we introduce new discourse quality metrics and an evaluation method, and furthermore, we provide a pilot implementation and evaluate it in a specific use case – that of public speaking. Voice analysis and discourse quality metrics are important topics as they can solve various problems of modern-day life. In public speaking trainings, it is important to be able to analyze voice and discourse, to offer the speaker valuable feedback and information on how to improve when speaking in public. We identified several papers that study this issue, in which rhythm, tone, fluency and clarity, as well as biological signals, are analyzed, to detect emotions or anxiety. We defined a set of voice quality metrics that can be implemented based on any speech recognition system. Our pilot implementation showcases the difference of using various Speech-to-Text (STT) APIs over the proposed metrics and how these affect the discourse evaluation process. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

BERT-Based Model for Reading Comprehension Question Answering 11

BERT-Based Model for Reading Comprehension Question Answerin...

引用

11th IEEE International Conference on Intelligent Computing and Information Systems, ICICIS 2023

作者： Mosaed, Abdelrahman A. Hindy, Hanan Aref, Mostafa Faculty of Computer and Information Sciences Computer Science Department Cairo Egypt

ISBN: (纸本)9798350322101

Question Answering (QA) has been an open research topic in the past years due to its significance in different domains. Moreover, it has different challenges to be solved to reach a stage where models can mimic human reasoning and answer various questions and tasks efficiently. This paper proposes an implementation of a pre-trained BERT model that aims to answer reading comprehension questions. The proposed model can be applied to different downstream tasks that are either single sentence, such as sentiment analysis tasks, or pair of sentences, such as question-answering tasks with a given context. The existence of different input embedding representations and output representations supported the model to integrate together to overcome such any downstream task. The proposed model is a BERTBASE with a total of 110M pre-trained parameters. The model has been fine-tuned and evaluated using the SQuAD 2.0 dataset. The model results reached an Exact Match score of 61.12 and 72.5 F1 score. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Sentimental Analysis of Amazon Reviews

Machine Learning Model for Sentimental Analysis of Amazon Re...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Umamageswari, A. Pratishwaran, R.J. Poojitha Reddy, M. Yuvan Sankar Raj, R. SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering With Specialization in Big Data Analytics Ramapuram Chennai India

ISBN: (纸本)9798331522988

The goal of this project is to draw a deeper understanding of the subjective nature behind online product reviews, largely by examining a large dataset received from Amazon that contains numerous star ratings and comments. Since there is such a massive amount of data on the Amazon platform, it was perfect for the analysis. Our methodology is platform-agnostic and can be easily extended to other comparable datasets from other web platforms with comparable guarantees in achieving wide applicability. Our primary motivation is improving the dependability of online shopping. Since product reviews are currently widely used by many consumers as guides in making decisions to buy products, such reviews ought to be fair representations of the actual dependability and quality of the products. The goal of our effort is to identify patterns in the language and ratings of such reviews that would directly reflect the real customer sentiment and also the reliability of the product. Our approach has yielded already a rate of about 92%, which shows it has the potential greatly to raise the legitimacy of online reviews. We'd like to make our customers feel more confident and better equipped with information to make better and safer purchases on a website like Amazon and others. In the final analysis, we strive to make online shopping for our customers worldwide safer and more trustworthy. © 2024 IEEE.

关键词： Data reliability

来源：评论

学校读者我要写书评

暂无评论

An Improvement of a Heuristic Algorithm for 3D Bin-Packing Problem 28

An Improvement of a Heuristic Algorithm for 3D Bin-Packing P...

引用

28th International computer science and engineering Conference, ICSEC 2024

作者： Krisadee, Sarun Jindaluang, Wattana Chiang Mai University Faculty of Science Department of Computer Science Chiang Mai50200 Thailand

ISBN: (纸本)9798350366860

We are given the large 3-dimensional rectangular items, which we refer to as the bins, in the 3D bin-packing problem. They have specific weight, length, height, and depth measurements. Additionally, we have various small, rectangular, 3-dimensional items that we call boxes. These boxes also have specific weights, lengths, heights, and depths. The goal of this problem is to pack all the small boxes into the bins so that their combined weight does not exceed the weight limit of each bin. Additionally, we aim to use as few bins as possible. In this paper, we refine the computational processes to enhance an algorithm by Youssef Harrath [1]. Experimental results indicate that as the number of boxes increases, our improvements can reduce the number of bins used, decrease running time, increase efficiency, and reduce memory usage. That is, the number of bins used, processing time, and memory use were all decreased to 38.68%, 58.42%, and 63.33%, respectively. In the meantime, bin space utilization efficiency scaled to 35.38%. © 2024 IEEE.

关键词： Bins

来源：评论

学校读者我要写书评

暂无评论

Beyond Cloud: Serverless Functions in the Compute Continuum

引用

SN computer science 2025年第3期6卷 1-19页

作者： Calavaro, Cecilia Cardellini, Valeria Lo Presti, Francesco Russo Russo, Gabriele Department of Civil Engineering and Computer Science Engineering Tor Vergata University of Rome Rome 00133 Italy

Serverless computing and, in particular, the Function-as-a-Service (FaaS) paradigm are increasingly popular, promising seamless scalability, simplified operations and flexible pricing. As more and more applications aim to benefit from near-user computation, there is increasing interest in deploying and running FaaS systems in the emerging edge-to-cloud compute continuum of computational resources. However, this new environment forces FaaS systems, originally developed with cloud in mind, to deal with limited resource availability, high hardware heterogeneity, and geographical distributions. In this paper, we discuss the key challenges for deployment and execution of serverless functions in the compute continuum, reviewing recent research contributions on the topic. We also discuss the key issues that remain unsolved and highlight a research opportunities to make FaaS adoption easier and more efficient far from cloud data centers. © The Author(s) 2025.

关键词： Cloud computing Edge computing Function-as-a-service Serverless computing

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：