检索结果-内蒙古大学图书馆

Asia-Pacific Conference on Communications

作者： Md. Arquam Utkarsh Tiwari Suchi Kumari Dept. Computer Science and Engineering IIIT Sonepat Haryana India Dept. Computer Science and Engineering Shiv Nadar Institute of Eminence Delhi-NCR India

ISBN: (数字)9798331517816

ISBN: (纸本)9798331517823

The movement changes the underlying spatial representation of the participated mobile objects or nodes. In real-world scenarios, such mobile nodes can be part of any biological network, transportation network, social network, human interaction, etc. The change in the geometry leads to the change in various desirable properties of real-world networks, especially in human interaction networks. In real life, human movement is concerned with a better lifestyle where they form their new connections due to the geographical changes. Therefore, in this paper, we design a model for geometric networks with mobile nodes (GNMN) and conduct a comprehensive statistical analysis of their properties. We analyze the effect of node mobility by evaluating key network metrics such as connectivity, node degree distribution, second-hop neighbors, and centrality measures. Through extensive simulations, we observe significant variations in the behavior of geometric networks with mobile nodes.

关键词： Measurement Geometry Analytical models Statistical analysis Social networking (online) Asia Transportation Biology Mobile nodes

来源：评论

学校读者我要写书评

暂无评论

CNN Autoencoder Resizer: A Power-Efficient LoS/NLoS Detector in MIMO-enabled UAV Networks

CNN Autoencoder Resizer: A Power-Efficient LoS/NLoS Detector...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Azim Akhtarshenas Navid Ayoobi David Lopez-Perez Ramin Toosi Matin Amoozadeh dept. of Telecommunication Engineering Universitat Politècnica de València Valencia Spain dept. of Computer Science University of Houston Houston USA dept. of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

Optimizing the design, performance, and resource efficiency of wireless networks (WNs) necessitates the ability to discern Line of Sight (LoS) and Non-Line of Sight (NLoS) scenarios across diverse applications and environments. Unmanned Aerial Vehicles (UAVs) exhibit significant potential in this regard due to their rapid mobility, aerial capabilities, and payload characteristics. Particularly, UAVs can serve as vital nonterrestrial base stations (NTBS) in the event of terrestrial base station (TBS) failures or downtime. In this paper, we propose CNN autoencoder resizer (CAR) as a framework that improves the accuracy of LoS/NLoS detection without demanding extra power consumption. Our proposed method increases the mean accuracy of detecting LoS/NLoS signals from 66% to 86%, while maintaining consistent power consumption levels. In addition, the resolution provided by CAR shows that it can be employed as a preprocessing tool in other methods to enhance the quality of signals.

关键词： Base stations Power demand Accuracy Wireless networks Autoencoders Autonomous aerial vehicles Automobiles Signal resolution Payloads Land mobile radio

来源：评论

学校读者我要写书评

暂无评论

Drishyam: An Image is Worth a Data Prefetcher 23

Drishyam: An Image is Worth a Data Prefetcher

引用

Proceedings of the 32nd International Conference on Parallel Architectures and Compilation Techniques

作者： Shubdeep Mohapatra Biswabandan Panda Dept. of Computer Science and Engineering BITS Pilani Goa India Dept. name of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9798350342543

Hardware prefetching is a latency-hiding technique that hides the costly off-chip DRAM accesses. Although hardware prefetching is an extensively researched topic with many state-of-the-art data prefetchers pushing the performance limits, prefetching for irregular applications with hard-to-predict access patterns is still a challenging problem to solve. The usage of neural networks for hardware prefetching is a promising direction, especially for predicting irregular memory access patterns. This paper presents Drishyam, a novel hardware prefetcher based on computer vision algorithms that use images to learn memory access patterns and predict future memory accesses with high accuracy and coverage. For hardware prefetching, an image is a graphical representation of memory accesses observed over time. For a sequence of memory addresses, Drishyam creates images that predict the future addresses by predicting the future OS page and a cache line offset within the OS page. Drishyam outperforms Voyager, the state-of-the-art machine learning (ML) based prefetcher, for a set of irregular benchmarks by an average of 4.7% with an average prefetch accuracy and prefetch coverage of 89.5% and 66.6%, respectively. In terms of training time, Drishyam outperforms Voyager by 225.5%.

关键词： Cache

来源：评论

学校读者我要写书评

暂无评论

An Information-Theoretic Framework for Unifying Active Learning Problems 35

An Information-Theoretic Framework for Unifying Active Learn...

引用

35th AAAI Conference on Artificial Intelligence, AAAI 2021

作者： Nguyen, Quoc Phong Hsiang Low, Bryan Kian Jaillet, Patrick Dept. of Computer Science National University of Singapore Singapore Singapore Dept. of Electrical Engineering and Computer Science MIT United States

ISBN: (纸本)9781713835974

This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant. We first introduce a novel active learning criterion that subsumes an existing LSE algorithm and achieves state-of-the-art performance in LSE problems with a continuous input domain. Then, by exploiting the relationship between LSE and BO, we design a competitive information-theoretic acquisition function for BO that has interesting connections to upper confidence bound and max-value entropy search (MES). The latter connection reveals a drawback of MES which has important implications on not only MES but also on other MES-based acquisition functions. Finally, our unifying information-theoretic framework can be applied to solve a generalized problem of LSE and BO involving multiple level sets in a data-efficient manner. We empirically evaluate the performance of our proposed algorithms using synthetic benchmark functions, a real-world dataset, and in hyperparameter tuning of machine learning models. © 2021, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

On Managing Test-Time, Power, and Layer Assignment in 3D SoCs with Built-In-Self-Repair Modules

On Managing Test-Time, Power, and Layer Assignment in 3D SoC...

引用

International Conference on VLSI Design

作者： Sabyasachee Banerjee Subhashis Majumder Bhargab B. Bhattacharya Dept. of Computer Science and Engineering Heritage Institute of Technology Kolkata India Dept. of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India

Although built-in self-repair (BISR) techniques have been widely used to improve memory yield, their applications to the testing of 3D systems-on-chip (SoC) remained primarily unexplored. In this manuscript, we present a multi-stage approach to implement BISR in 3D SoCs with an aim to (i) reduce test time by proposing a test scheduling technique satisfying given power constraints, (ii) reduce the number of BISR modules, and (iii) to place BISR circuitry in suitable layers for facilitating thermal dissipation. Experimental results on several SoC benchmarks show that our approach reduces both test time as well as the cost of BISR architecture in most cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Demystifying PDFs: Emerging AI for text generation and operation on PDF

Demystifying PDFs: Emerging AI for text generation and opera...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Ashish Sharma Mannu Baveja Suhaj Kanikicherla Devansh Kaushik Yashuman Sharma Jessica Jessica Dept of Electrical Engineering Chandigarh University Mohali India Dept. of Computer Science Chandigarh University Mohali India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

AI is considered as most disruptive language and revolutionized various sectors with its ability analyze data with its large language model. incapability of other AI to read PDF and accept prompt and do text generation using their large language models .The work is based on proposing a new technique to integrate it into current AI. It will eliminate the need manual work of copy pasting Portable Document Format data to AI for prompt . In this can rely on Technologies Like Optical character recognition for reading images to text but challenging part is Portable Document Format to image and then image to text. this work is advancement of Optical character recognition which can eliminate the drawback of already existing technology.

关键词： Integrated optics Technological innovation Analytical models Large language models Optical character recognition Manuals Portable document format Optical imaging

来源：评论

学校读者我要写书评

暂无评论

A Neural Network-based System Identification Model to Predict Output Current and Voltage of Solar Photovoltaic Panels

A Neural Network-based System Identification Model to Predic...

引用

2023 International Conference on science, engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Adetiba, Emmanuel Oluleye, Olumide O. Ifijeh, Ayodele H. Oguntosin, Victoria Olaniyan, Olatayo M. Akinola, Olubunmi Adewale Afolabi, Gbenga Odetola, Jacob O. Abayomi, Abdultaofeek Covenant University Dept. of Electrical & Information Engineering Ogun State Ota Nigeria Federal University Dept. of Computer Engineering Ekiti Ekiti State Oye Nigeria Mangosuthu University of Technology Dept. of Information and Communication Technology Durban South Africa

ISBN: (纸本)9798350324785

Solar irradiance is the energy per unit area received by the Sun as electromagnetic radiation. It is one of the most important renewable energy sources. Photovoltaic or other solar technologies are used to generate power more accurately than direct sun irradiation. Solar irradiance research and measurement have a variety of critical applications, including forecasting power generation from solar power plants, climate modeling, and weather forecasting. This paper presents a neural network-based system identification model developed using measured parameters from solar panels with various wattage specifications, namely, 10W, 20W, 40W, and 100W. The parameters that were measured to train the ANN model for the prediction of the output current and voltage include the angle of panel orientation, panel temperature, ambient temperature, irradiance, and wattage. Several training experiments were conducted and the best ANN model produced at 500 epochs gave an accuracy of 99.81% and a loss of 0.1940. The model was deployed into an intelligent Web App that was also developed in this study. This app could be a potential tool for renewable energy engineers and researchers. © 2023 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Automated Bengali Sign Language Character Classification with Deep Learning Techniques

Automated Bengali Sign Language Character Classification wit...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Tahmina Akter Tanjim Mahmud Tikle Barua Sultana Rokeya Naher Mohammad Shahadat Hossain Karl Andersson Dept. of Computer Science and Engineering Port City International University Chittagong Bangladesh Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Dept. of Computer Science and Engineering University of Information Technology and Sciences Dhaka Bangladesh Dept. of Computer Science and Engineering University of Chittagong Chittagong Bangladesh Cybersecurity Laboratory Luleå University of Technology Luleå Sweden

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Recognition of Bengali sign language characters is crucial for facilitating communication for the deaf and hard-of-hearing population in Bengali-speaking regions, which encompass approximately 430 million people worldwide. Despite the significant number of individuals requiring this support, research on Bengali sign language character recognition remains underdeveloped. This article presents a novel approach to categorize Bengali sign language characters using the Ishara-Lipi dataset, based on convolutional neural networks (CNNs) and pretrained models. We evaluated our approach using metrics such as accuracy, precision, recall, F1-score, and confusion matrices. Our findings indicate that the CNN model achieved the highest performance with an accuracy of 98%, followed by VGG19 with $\mathbf{94\%}$ and ResNet variants achieving around $\mathbf{88\%}$. The proposed model demonstrates robust and efficient classification capabilities, significantly bridging the gap in existing literature. This study holds substantial promise for enhancing assistive technology, thereby improving social inclusion and quality of life for Bengalispeaking deaf and hard-of-hearing individuals.

关键词： Measurement Deep learning Sign language Accuracy Assistive technologies Convolutional neural networks Character recognition

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Federated Bayesian Optimization with Distributed Exploration 35

Differentially Private Federated Bayesian Optimization with ...

引用

35th Conference on Neural Information Processing Systems, NeurIPS 2021

作者： Dai, Zhongxiang Hsiang Low, Bryan Kian Jaillet, Patrick Dept. of Computer Science National University of Singapore Singapore Singapore Dept. of Electrical Engineering and Computer Science MIT United States

ISBN: (纸本)9781713845393

Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm, which has promising applications such as federated hyperparameter tuning. However, FTS is not equipped with a rigorous privacy guarantee which is an important consideration in FL. Recent works have incorporated differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. Following this general DP framework, our work here integrates DP into FTS to preserve user-level privacy. We also leverage the ability of this general DP framework to handle different parameter vectors, as well as the technique of local modeling for BO, to further improve the utility of our algorithm through distributed exploration (DE). The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off. We also use real-world experiments to show that DP-FTS-DE achieves high utility (competitive performance) with a strong privacy guarantee (small privacy loss) and induces a trade-off between privacy and utility. © 2021 Neural information processing systems foundation. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of the Properties of Geometric Network with Node Mobility

arXiv

引用

arXiv 2024年

作者： Arquam, Md. Tiwari, Utkarsh Kumari, Suchi Dept. Computer Science and Engineering IIIT Haryana Sonipat India Dept. Computer Science and Engineering Shiv Nadar Institute of Eminence Delhi-NCR India

The movement changes the underlying spatial representation of the participated mobile objects or nodes. In real world scenario, such mobile nodes can be part of any biological network, transportation network, social network, human interaction, etc. The change in the geometry leads to the change in various desirable properties of real-world networks especially in human interaction networks. In real life, human movement is concerned for better lifestyle where they form their new connections due to the geographical changes. Therefore, in this paper, we design a model for geometric networks with mobile nodes (GNMN) and conduct a comprehensive statistical analysis of their properties. We analyze the effect of node mobility by evaluating key network metrics such as connectivity, node degree distribution, second hop neighbors, and centrality measures. Through extensive simulations, we observe significant variations in the behavior of geometric networks with mobile nodes. © 2024, CC BY.

关键词： Complex 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：