检索结果-内蒙古大学图书馆

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Cherukuri, Bangar Raju Arulkumar, V. Germantown MD United States School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

ISBN: (纸本)9798350383522

The optimization of data structures and trade-offs is a complex problem. This is simplified and provides solutions through the aid of artificial intelligence. There are various synchronization problems occur due to the concurrent access to the data structures. This affects the overall performance of the system. To overcome various challenges, deep learning with optimization algorithms is implemented. This helps to achieve the potential areas for optimization in multithread software by evaluating the historical patterns and performance information. Trade-offs are defined as the choices that are initiated in the optimization process for data structures in concurrency. Deep learning helps to analyze the impacts of these trade-offs by developing training models on the historical data. A large amount of data is retrieved through the deep learning techniques. This includes extracting image data for CNN and time series data for RNN and LSTM. The reduction of using data compression techniques helps in obtaining optimal performance parameters. The various forms of threats are neglected through data loading and preprocessing stages. The concurrency is essential due to the usage of multiple threats working on the neural networks. This is further accessed through synchronizing access to shared data structures. They must be properly done because excess synchronization leads to the origin of bottlenecks. A balance between data structure optimization and concurrency control must be maintained properly. Excessive concurrency control may reduce the performance. The execution speed of the CNN is enhanced through the aid of hardware accelerators. Thus the fine-tuning of trade-offs and creation of software are done through training and testing to obtain increased use of multi-core processors. © 2024 IEEE.

关键词： Artificial intelligence Concurrency Data structures Deep learning Multi-core processors Multithread software Trade-offs

来源：评论

学校读者我要写书评

暂无评论

Monolithic Fabrication of On-Paper Self-Charging Power Systems Through Direct Ink Writing 60

Monolithic Fabrication of On-Paper Self-Charging Power Syste...

引用

60th Annual Microelectronics and Packaging Conference and Exhibition, NordPac 2024

作者： Su, Yingchun Fu, Yujie Chen, Shiqian Li, Zheng Xue, Han Li, Jiantong School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Electrum 229 Kista16440 Sweden

ISBN: (纸本)9789189896925

The rapid development of emerging electronics requires power sources with the advantages of lightweight, high efficiency, and portability. Considering the use of critical raw materials (such as Li, Co, etc.) and the increasing global concern of battery waste, self-charging power systems (SCPSs) integrating energy harvesting, power management, and energy storage devices have been envisioned as promising solutions to replace traditional batteries to avoid the use of toxic materials and the need of frequent recharging/replacement. Up to date, the reported SCPSs still hold the problem of large form factor, unscalable fabrication, noble materials, and material complexity. In our work, a highly stable and eco-friendly organic conductive ink based on poly(3,4-ethylenedioxythiophene): poly(styrenesulfonate) (PEDOT:PSS) has been developed for monolithic fabrication on-paper SCPSs almost fully through a simple direct ink writing (DIW) process. The ink possesses multiple functions and enables to directly print almost all the key components in the SCPSs, including electrodes for triboelectric nanogenerators (TENGs, mechanical energy harvesters), electrodes for micro-supercapacitors (MSCs, energy storage devices), and interconnects, on the same paper substrate in a monolithic manner without the need for "post-integration". The monolithic printing process exhibits excellent upscaling capability for manufacturing. In particular, the direct patterning merit of the DIW process offers great flexibility in optimizing the system performance through adjusting the cell number, electrode dimension, and thickness of the MSC arrays. By adjusting the cell numbers, the MSC arrays attain high-rate capability up to 50 V/s to match the pulsing electricity produced from the TENGs. For small-size printed SCPSs (~ 2 cm × 3 cm ×1 mm), after continuous press and release of the TENGs for ~79000 cycles, the 3-cell series-connected MSC array can be charged to 1.6 V while 6-cell array to 3.0 V. For a lar

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

SvaVoting: A Novel Secret Sharing-Based Verifiable and Anonymous E-Voting Scheme in Blockchain Systems 29

SvaVoting: A Novel Secret Sharing-Based Verifiable and Anony...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zhang, Jingyu Wu, Chenghao Yang, Jin Luo, Lailong Changsha University of Science and Technology School of Computer and Communication Engineering Changsha China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering Changsha China

ISBN: (纸本)9798350330717

E-Voting systems play a vital role in various communities, aiming to enhance the efficiency, transparency, and citizen engagement in elections. However, as technology advances, ensuring the security and reliability of e-voting systems becomes profound. While researchers have explored the integration of blockchain technology to improve e-voting systems, there still are technical challenges, particularly regarding voters' privacy, ballots' confidentiality, and system performance. To address these challenges, we propose SvaVoting, an innovative blockchain-based e-voting scheme. SvaVoting utilizes the Borda counting method and the identity-based ring signature based on symmetric primitives to anonymously verify the validity of the voter's identity and ballot format. In addition, we introduce secret sharing and a Cloud Service Provider (CSP) to conduct the final counting while preserving the privacy of the ballots. All users in the system can verify the results of CSP calculations, thereby meeting security goals such as correctness, unforgeability, anonymity and verifiability. The identity-based ring signature in our scheme provides 128-bit security, and even it can work in a quantum computing environment. Experimental results demonstrate that our solution significantly enhances the security and performance of e-voting systems, offering a practical path forward for future e-voting systems. © 2023 IEEE.

关键词： cloud service provider e-voting identity-based ring signatures post-quantum cryptography secret sharing

来源：评论

学校读者我要写书评

暂无评论

Healthcare Fraud Detection Using an Integrated ML Approach with SMOTE

引用

Procedia computer Science 2025年 258卷 800-810页

作者： Dipti Dash Mukesh Kumar Shaswati Patra Ajay Kumar Ankit Ganguly School of Computer Engineering Kalinga Institute of Industrial Technology-751024 Computer Science and Engineering Government Engineering College Kaimur School of Mechanical Engineering Kalinga Institute of Industrial Technology-751024

Healthcare fraud is a growing problem with significant financial ramifications for healthcare systems worldwide, demanding effective detection measures to preserve resources and assure the delivery of excellent treatment. This paper presents a novel approach to fraud detection that integrates Random Forest and K-Nearest Neighbors (KNN) algorithms with the Synthetic Minority Over-sampling Technique (SMOTE) to effectively address the challenges of identifying fraudulent healthcare claims. Our research tackles the common issue of class imbalance in training datasets, where legitimate transactions vastly outnumber fraudulent ones. By generating synthetic samples of fraudulent claims, SMOTE enhances the model’s learning capabilities, leading to improved detection accuracy. Our approach consisted of thorough data preparation, the creation of an integrated model, and a rigorous assessment using several performance measures including accuracy, precision, recall, and F1-score. The model exhibits exceptional performance in detecting fraud, achieving remarkable scores in accuracy 97.96%, precision 94.96%, F1-score 97.41%, and AUC 96.44%. This research ofers a promising solution to healthcare fraud by leveraging sophisticated methodologies, empowering healthcare providers and insurers to better safeguard their resources.

关键词： Machine Learning Synthetic Minority Over-sampling Technique (SMOTE) Class Imbalance Data Preprocessing Confusion Matrix

来源：评论

学校读者我要写书评

暂无评论

FLBC-DSS: Federated Learning-Enabled Blockchain-Based Data Sharing Scheme for IIoT 11

FLBC-DSS: Federated Learning-Enabled Blockchain-Based Data S...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Yao, Yan Li, Guangshun Zhang, Huihui Feng, Shanshan Yan, Biwei Cao, Jian School of Computer Science Qufu Normal University Rizhao China Rizhao-Qufu Normal University Joint Technology Transfer Center Rizhao China School of Computer Engineering Weifang University Weifang China Qilu University of Technology Shandong Academy of Sciences Jinan China School of Information Science and Engineering Shandong Normal University Jinan China School of Computer Scienceand Technology Shandong University Qingdao China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798331531904

This paper introduces the Federated Learning-Empowered Blockchain-based Data Sharing Scheme (FLBC-DSS), a novel framework designed to enhance data security and efficiency in Industrial Internet of Things (IIoT) environments. By integrating federated learning with blockchain technology, FLBC-DSS addresses the critical challenges of data privacy and unauthorized access, promoting secure, decentralized data sharing across various industrial sectors. Utilizing zk-SNARKs, the scheme provides a mechanism for anonymous data verification without compromising data integrity. Performance evaluations conducted using Hyperledger Fabric and SecureBoost demonstrate significant improvements in prediction accuracy and computational efficiency compared to traditional approaches. The implementation of non-cooperative game theory further illustrates the economic benefits of FLBC-DSS, highlighting its potential to increase profitability through strategic data sharing. The results affirm the effectiveness of FLBC-DSS in leveraging advanced cryptographic and machine learning techniques to foster a secure, transparent, and efficient digital ecosystem for IIoT. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Harvest Harmony by Leveraging Machine Learning for Optimal Crop Yield Recommendations 3

Harvest Harmony by Leveraging Machine Learning for Optimal C...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Sahu, Premananda Bharany, Salil Kaushik, Keshav Kaur, Upinder Kumar, Anand Choudhury, Amitava Lovely Professional University School of CSE Punjab Jalandhar India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India Amity School of Engineering and Technology Amity University Punjab Mohali India Lovely Professional University Department of Computer Science and Engineering Punjab Phagwara144411 India School of Technology Department of Computer Science and Engineering Pandit Deendayal Energy University Gandhinagar India

ISBN: (纸本)9798350354171

In the past few years, advancement and upgradation in terms of technology has been a massive aspect including the field of data science and machine learning. Taking any one instance out of that aspect is 'CropYieldML systems'. The abstract behind this system is such that it makes up the utilization of complex algorithms to analyze extensive datasets containing information properties of the soil, climatic conditions, and historical crop yields. Based on the data, it's a great assistance for the farmers to make certain decisions on which crop has to be grown upon the desired sort of soil. The focus of this project certainly lies in developing deeply the potential of machine learning techniques in recommending suitable crops based on a variety of environmental and soil parameters. Modeling and Thorough analysis make the project seek to enhance agricultural productivity, profitability, and sustainability. This project can reduce the costs of the inputs and environmental impact by helping the farmers with selective recommendations to optimize their yield by analyzing weather patterns, past crop performances, and soil composition. The data-driven insights can also help the farmers selective decisions for better crops which in the future lead to the sustainability of agriculture. The outcomes of this project are expected to have significant implications for agricultural practices. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

computer-aided hierarchical interactive gesture modeling under virtual reality environment

引用

computer-Aided Design and Applications 2022年 19卷 43-53页

作者： Zhu, Lihua Lu, Na School of Computer Science and Information Engineering Anyang Institute of Technology Henan Anyang455000 China

The first mock exam is based on the interaction gesture in virtual reality. There are many different types of interaction gestures. In this paper, a dynamic visual gesture interaction method suitable for desktop VR is designed with the help of computational assistant tools and gesture recognition method. Through the interactive experimental analysis of the visualization system, the designed dynamic gesture interaction method works well in the immersive visualization system, provides users with a high sense of immersion and helps users understand the data more effectively. In addition, aiming at the shortcomings of leap motion gesture tracking in desktop VR, we use computer vision technology and deep learning gesture recognition method to propose a strategy. By calculating the self-occlusion degree of hand images captured by deep camera, we recognize simple gestures with low self-occlusion degree by fast model-based method, the complex gesture image uses the trained convolution neural network for joint point recognition, which not only ensures the recognition accuracy, but also improves the problem of low frame number when the deep learning method is applied to VR. Finally, the superiority and reliability of computer-aided hierarchical interactive gesture modeling for virtual reality are verified by experiments. © 2022 CAD Solutions, LLC,.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A High-Performance Data Verification Mechanism in Blockchain-Based IoT Systems 21

A High-Performance Data Verification Mechanism in Blockchain...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Jingyu Zhou, Pian Sun, Yongtao Luo, Lailong Changsha University of Science and Technology School of Computer and Communication Engineering Changsha China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering Changsha China

ISBN: (纸本)9798350329223

With the rapid development of the distributed network and communication, the Internet of Things (IoT) systems have been applied to all walks of life. Blockchain technology is one of the most popular research fields recently, which can provide a reliable storage solution and solve information security issues for IoT systems. Transaction information is the most critical fundamental data in the blockchain systems, which needs to be verified to avoid being tempered with by malicious nodes in the process of transmission. With the exponential growth of the number of IoT devices, the limitations of the current storage structure put too much pressure on the system nodes. How to improve verification efficiency has become a key challenge. To alleviate this problem, this paper proposes a novel high-performance verification mechanism for data security protection in blockchain-based IoT systems. We design a new storage structure based on Huffman trunk tree (HTT), and conduct the quantitative analysis of transaction weights. Transactions are stored in full-featured devices in the form of Huffman Merkle tree (HMT), and only the content of HTT is saved in lightweight devices. Finally, the performance superiority of our mechanism is proved through theoretical analysis and experimental evaluation. In blockchain-based IoT systems, our mechanism significantly reduces the data transmission cost and computation overhead, effectively improving the efficiency of data verification. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Microgrid digital twins: concepts and their controlling through multi-agent systems

引用

International Journal of High Performance Systems Architecture 2023年第4期11卷 225-236页

作者： Negi, Gaurav Singh Mishra, Anupama Gupta, Mukul Kumar Saxena, Nitin Kumar Saini, DilipKumar Jang Bahadur Joshi, Kapil Electrical and Electronics Engineering Uttaranchal Institute of Technology Uttaranchal University Dehradun248007 India Department of Computer Science and Engineering Himalayan School of Science and Technology Swami Rama Himalayan University Uttarakhand Dehradun248140 India School of Engineering University of Petroleum and Energy Studies Dehradun248006 India Department of Electronics & Instrumentation Engineering MJP Rohilkhand University UP Bareilly243006 India Electrical and Electronics Engineering KIET Group of Institutions Ghaziabad201206 India Electrical and Computer Engineering University of Denver Denver80210 United States Department of Computer Science and Engineering School of Engineering and Technology Pimpri Chinchwad University Pune411044 India Department of CSE Uttaranchal Institute of Technology Uttaranchal University Dehradun248007 India

Real-time grid analysis is made possible by the electric digital twin grid, which combines history and present data to convey system status and project future circumstances. Cooperative smart agents that can solve problems bigger than one agent's scope make up a multi-agent system (MAS). A micro-grid digital twin (MGDT) uses real-time data interchange and high-fidelity models to simulate a microgrid’s operation. Hybrid energy storage systems are managed by agents who maximise renewable resources and minimise expenses. Microgrids combine sensing, control, and intelligence technology in utility networks. Plant management, communication protocols, and power system operations are all made easier with MAS-based control. For dependable microgrid operation, dispersed energy resources are coordinated by MAS. In order to handle complexity and improve resilience and control of the energy system, this study investigates the application of MAS in microgrid control. Energy management and agent communication in microgrids are the main topics of MAS research. Integrating microgrid digital twins with MAS holds promise for advancing energy systems. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Based on A Multi-Scale Weighted Kernel Network

引用

Chinese Journal of Electronics 2022年第5期31卷 832-843页

作者： SUN Le XU Bin LU Zhenyu School of Computer Science Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing University of Information Science and Technology

Recently, many deep learning models have shown excellent performance in hyperspectral image(HSI) classification. Among them, networks with multiple convolution kernels of different sizes have been proved to achieve richer receptive fields and extract more representative features than those with a single convolution kernel. However, in most networks, different-sized convolution kernels are usually used directly on multibranch structures, and the image features extracted from them are fused directly and simply. In this paper, to fully and adaptively explore the multiscale information in both spectral and spatial domains of HSI, a novel multi-scale weighted kernel network(MSWKNet) based on an adaptive receptive field is proposed. First, the original HSI cubic patches are transformed to the input features by combining the principal component analysis and one-dimensional spectral convolution. Then, a three-branch network with different convolution kernels is designed to convolve the input features, and adaptively adjust the size of the receptive field through the attention mechanism of each branch. Finally, the features extracted from each branch are fused together for the task of *** on three well-known hyperspectral data sets show that MSWKNet outperforms many deep learning networks in HSI classification.

关键词： multibranch structures image features convolution kernels multiple convolution kernels adaptive receptive field image classification feature extraction HSI classification single convolution kernel convolutional neural nets hyperspectral image classification representative features hyperspectral imaging geophysical image processing deep learning (artificial intelligence) multiscale weighted kernel network deep learning networks hyperspectral data sets three-branch network HSI cubic patches principal component analysis 1D spectral convolution different-sized convolution kernels

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：