检索结果-内蒙古大学图书馆

Machine Learning-Based Autonomous Optimization of Unattended Wireless Sensor Networks Through Multi-Cause Reinforcement Learning

引用

SN computer science 2025年第2期6卷 1-11页

作者： Chaudhary, Jitendra Kumar Dudeja, Deepak Verma, Neeraj Kumar Saini, Arun Kumar Kapila, Dhiraj Mohapatra, Smaranika School of Computing Graphic Era Hill University Bhimtal Campus Uttrakhand Bhimtal India Department of Computer Science and Engineering M.M. Engineering College Maharishi Markandeshwar (Deemed to Be University) Mullana Haryana Ambala India Department of Data Science and Engineering Manipal University Jaipur Jaipur India Department of IcfaiTech The ICFAI University Jaipur India Department of Computer Science & Engineering Lovely Professional University Punjab Phagwara India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India

Self-configuration refers to a node's ability to dynamically adjust resource allocation based on changing network conditions, either autonomously or with minimal human input. Alongside this, self-optimization is aimed at maintaining optimal network performance despite fluctuating conditions. Protocols like MRL-SCSO, designed for Unattended Wireless Sensor Networks (UWSNs), ensure robust coverage, connectivity, and energy efficiency under varying loads. MRL-SCSO employs learning-based mechanisms, such as Reinforcing Multiple Agents, incorporating features like boundary construction, state scheduling, topology control, and data dissemination to enhance network management. When compared to the Collect Tree Protocol (CTP), MRL-SCSO exhibits faster packet transmission due to backbone nodes and traffic load prediction, reducing delays by 2–5 ms, which is a significant improvement over existing algorithms. Additionally, MRL-SCSO delivers a better packet delivery ratio, dropping only by 5–12% with shorter data transmission intervals, while CTP experiences a 20–40% drop when all nodes are active. Furthermore, MRL-SCSO improves throughput by 20–30 kb/s compared to CTP, demonstrating its superior ability to optimize network performance without sacrificing reliability. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： CTP MRL-SCSO PDR Reliability UWSN

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction with Convolutional Neural Networks and Hyperparameter Tuning 8th

Cardiovascular Disease Prediction with Convolutional Neural ...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Hossain, Mohammad Alamgir Metwally, Abdelnasser Abdelwakil Khan, Asif Ali Amin, Sherif Tawfik Hamdan, Alfadil Ahmed Limkar, Suresh Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer and Network Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Artificial Intelligence & Data Science AISSMS Institute of Information Technology Maharashtra Pune India

ISBN: (纸本)9789819765805

CVD continues to pose a substantial global health burden, demanding the need for the creation of precise predictive models that can aid in the timely identification and evaluation of risks. This research paper aims to provide a thorough examination of the prediction of CVD by utilizing CNN in aggregation with hyperparameter tuning techniques. This paper examines the effectiveness of three widely recognized CNN architectures, namely ResNet, VGGNet, and Xception CVD. The Tree-structured Parzen Estimator (TPE) is utilized as a method for tuning hyperparameters in order to optimize the CNN models. The study commences with a comprehensive examination of the dataset, encompassing a wide array of cardiovascular CT image data. The chosen CNN architectures serve as the fundamental framework for our predictive models. The selection of these architectures is based on their established track record in effectively addressing image analysis tasks and their capacity to accurately capture complex patterns and features present in medical images. The models undergo training using a dataset in order to acquire knowledge about distinctive features that are linked to various cardiovascular conditions. The experimental findings presented in the study indicate that the utilization of the Xception architecture, in aggregation with TPE for hyperparameter optimization, yields the most favorable predictive accuracy. Specifically, the achieved accuracy rate of 98.26% is notably remarkable. This result highlights the significance of not only choosing advanced CNN architectures but also optimizing their hyperparameters to fully exploit their potential in predicting cardiovascular disease. This establishes it as a promising tool for the early diagnosis and risk assessment of CVD. This study establishes a fundamental basis for future investigations in the advancement of precise and dependable predictive models applicable to various medical imaging contexts. © The Author(s), under exclusive license

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Virtual Twin Modelling for Strengthening IoT software Security Protocols 1

AI-Enhanced Virtual Twin Modelling for Strengthening IoT Sof...

引用

1st International Conference on software, Systems and Information Technology, SSITCON 2024

作者： Kumara, Bharath Barmola, Pareshwar Prasad Arora, Renuka Parikh, Swapnil M Maranan, Ramya Ramaiah University of Applied Science Department of Electronics and Communication Engineering Bengaluru India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Jagannath University Department of Computer Science and Engineering Haryana India Parul Institute of Engineering and Technology Parul University Faculty of Computer Science and Engineering Vadodara India Simats Saveetha School of Engineering Department of Research and Innovation Chennai India

ISBN: (纸本)9798350352931

To fortify security mechanisms in software systems for the Internet of Things (IoT), this article presents a framework for AI-Enhanced Virtual Twin Modelling. In order to track and examine the actions of IoT devices in real-time, the suggested method makes use of virtual twin technology that is combined with machine learning techniques. Automated response generation, continuous threat assessment, and anomaly detection are made possible by creating a digital clone of the actual IoT network using the virtual twin paradigm. By combining deep learning models like CNNs and LSTMs, it becomes easier to forecast possible security risks in network traffic data by seeing intricate spatial and temporal patterns. When tested in a virtual Internet of Things (IoT) setting, the suggested framework outperforms conventional rule-based approaches by a wide margin, reducing reaction time by 35% while achieving an accuracy of 9 6. 2 %in threat identification. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Recommendation System for Riyadh Restaurants: Integrating Content-Based and Context-Aware Techniques 4

A Novel Hybrid Recommendation System for Riyadh Restaurants:...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Rohilla, Vinita Kaur, Mandeep Chakraborty, Sudeshna Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India Maharaja Surajmal Institute of Technology Department of Computer Science and Engineering New Delhi India Galgotia University Department of Computer Science and Technology Greater Noida India

ISBN: (纸本)9798350364729

Recommendation systems are often used to deliver consumers a customised set of services. Their main purpose is to provide recommendations or concepts (such as restaurants, tourist attractions, medicines, movies, etc.) that effectively address consumer issues and may be used across several sectors. In today's environment, when there are so many eating alternatives, selecting the ideal restaurant to meet our interests may be difficult. Saudi Arabia's tourist industry has lately emerged as an important economic engine. It is becoming more difficult for customers to choose among the vast array of restaurants available in Riyadh due to the industry's fast expansion in recent years. This research presents a comprehensive recommendation system for Riyadh restaurants that integrates content-based filtering and context-aware location analysis to provide personalised suggestions. Utilising a dataset from Kaggle with information on 20,000 restaurants, the system employs a hybrid approach combining TF-IDF and cosine similarity for content-based filtering with geographic distance calculations for location-based recommendations. The hybrid model balances content relevance with geographic proximity, enhancing user satisfaction by delivering accurate and contextually relevant restaurant recommendations. The outcomes demonstrate an effectiveness of a hybrid method, outperforming individual techniques by generating more relevant and practical recommendations. The uniqueness of this study resides in the use of hybrid filtering, which has not before been used in comparable investigations. A more detailed and easily digestible list of suggested models is what this study report is aiming to provide. According to the findings and conclusion, the proposed strategy is effective in recommending restaurants in Riyadh. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Integrating Blockchain in Cloud Computing for Enhanced Data Management and Security 11

Integrating Blockchain in Cloud Computing for Enhanced Data ...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Choubey, Abha Choubey, Siddhartha Jaiswal, Dipti Jaiswal, Manuraj Shri Shankaracharya Technical Campus Department of Computer Science and Engineering Chhattisgarh Durg India Noida International University Department of Computer Science and Engineering Uttarpradesh Greater Noida India Galgotias University Department of Computer Science and Engineering Uttarpradesh Greater Noida India

ISBN: (纸本)9798350350357

This article details a decentralized cloud data management and protection scheme. The Decentralized Data Storage Algorithm, Smart Contracts for Access Control Algorithm, Consensus Mechanisms for Data Validation Algorithm, Blockchain-based Encryption Algorithm, and Tokenization of Data Algorithm solve important data storage, access control, validation, encryption, and tokenization problems. Each piece of software is carefully designed to add features to the system. The Decentralized Data Storage Algorithm secures data via blockchain and agreement processes. The Smart Contracts for Access Control Algorithm dynamically limits access based on user passwords and policy outcomes. Autonomous systems need the Consensus Mechanisms for Data Validation Algorithm to maintain trust and freedom. The blockchain-based encryption algorithm secures data via blockchain keys and encryption. Finally, the tokenization of data algorithms emphasizes data security and transport. Ablation research emphasizes each mathematical component and how they work together to improve the framework. Performance tables and graphs show that the recommended method improves cloud computing data management and security. This method addresses the developing issues of cloud data management in a thorough and adaptable manner, making it valuable to the area. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Scheme for Image-Text Comments based on Multimodal Deep Learning and Spatiotemporal Attention 6

Sentiment Analysis Scheme for Image-Text Comments based on M...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Fanchang TangYaLing Yadav, Amit Sah, Abhishek Pratap Khan, Asif Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (纸本)9798331522667

A sentiment analysis scheme for image and text comments based on multimodal deep learning and spatiotemporal attention is proposed to address the issues of incomplete spatiotemporal considerations, incomplete implementation details, and cutting-edge theoretical algorithms in graphic and textual sentiment analysis schemes. The proposed model has clear layering including data preprocessing layer, modal encoding layer, modal fusion layer, sentiment classification layer, loss function and optimizer, evaluation and feedback. The implementation details of each layer are introduced. The entire scheme model incorporates Multimodal Fusion Neural Network (MFNN) deep learning and spatiotemporal attention mechanism, which makes the scheme perform well in terms of security, robustness and performance, making up for the shortcomings of existing research schemes. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Advanced agricultural supply chain management: integrating blockchain and young’s double-slit experiment for enhanced security

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1329-1337页

作者： Santhanam, Esakki Muthu kamatchi, Kartheeban Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Srivilliputtur India

In the agricultural supply and food, chain Ensuring product safety is important which includes monitoring the effective logistics management and advancements of agricultural products. An effective model that guarantees sufficient safety of the product is required because many issues have been raised regarding contamination risks and food safety. Thus, an efficacious model is introduced in this article referred to as Blockchain Based-Crossover Young’s double-slit (BC-CYD) algorithm, which enables securing agriculture-based data in supply chain management. The developed approach successfully executes the transactions in the traceability and tracking of products with high-level security for the agricultural supply chain. The developed method utilizes an authentication process in provenance tracking and product information storage. The developed BC-CYD method improves safety and efficiency by obtaining higher security, reliability, and integrity. Here, product transactions are stored in the blockchain ledger, thereby, the developed model offers high-level traceability and transparency in a capable manner in the supply chain management. The effectiveness of the proposed BC-CYD method is assayed, where evaluation parameters quantify the efficiency of the developed BC-CYD method. Based on the performance rates of Precision, ROC, accuracy, and Processing time, the developed BC-CYD method’s effectiveness is ascertained as higher. The suggested BC-CYD method yields a greater precision of 97.4% and its accuracy is 98.8% with lower processing time and training time. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Agriculture Authentication Blockchain technology Supply chain management Young’s double-slit experiment optimizer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ANN

Enhancing Energy Efficiency in WSNs with Hybrid LEACH-D and ...

引用

2024 Multimedia University engineering Conference, MECON 2024

作者： Qamar, Muhammad Salman Haq, Ihsan Ul Munir, Muhammad Fahad Roslee, Mardeni Bin Awan, Adnan Anwar Waseem, Athar International Islamic University Department of Electrical and Computer Engineering Islamabad Pakistan Multimedia University Centre for Wireless Technology Faculty of Engineering Cyberjaya63100 Malaysia School of Engineering California Polytechnic State University Department of Computer Science and Software Engineering San Luis ObispoCA United States

ISBN: (纸本)9798331530747

This paper explores strategies to improve the energy efficiency and operational longevity of Wireless Sensor Networks (WSNs) through the optimization of clustering techniques and energy efficient routing protocols. The proposed methodology is precisely crafted to optimize energy consumption (EC) while preserving the overall effectiveness of WSNs. LEACH (Low Energy Adaptive Cluster Hierarchy) is a cluster-based protocol where non-cluster head nodes deactivate their RF until their allocated time slots. Nevertheless, a drawback of traditional LEACH is its random rotation of local Cluster Heads (CH), leading to unequal cluster distribution. To overcome this issue, we proposed a novel hybrid technique called LEACH-D protocol and Artificial Neural Network (ANN). The LEACH-D algorithm enhances the duration of transmission tasks while ensuring uniform battery energy consumption. On the other hand, the ANN plays a pivotal role in coordinating optimal routing decisions and CH placement, refining data aggregation and transmission mechanisms to restrain idle listening. The findings indicate that the suggested approach manifests as substantial reductions in energy consumption and prolonged network lifespan of WSN. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Recent advances in tip-enhanced Raman spectroscopy probe designs

引用

Nano Research 2023年第4期16卷 5555-5571页

作者： Da Xu Boqun Liang Yaodong Xu Ming Liu Department of Electrical and Computer Engineering University of California-RiversideRiversideCalifornia 92521USA Materials Science and Engineering program University of California-RiversideRiversideCalifornia 92521USA

Tip-enhanced Raman spectroscopy(TERS)imaging is a super-resolution imaging technique that features the merits of both surface-enhanced Raman spectroscopy(SERS)and scanning probe microscopy(SPM),such as the high chemical sensitivity from the former and the nanoscale spatial resolution from the *** advantages make TERS an essential nanospectroscopic characterization technique for chemical analysis,materials science,bio-sensing,*** probes,the most critical factor determining the TERS imaging quality,are expected to provide a highly confined electromagnetic hotspot with a minimized scattering background for the generation of Raman signals with high spatial *** two decades of development,numerous probe design concepts have been proposed and *** review provides a comprehensive overview of the state-of-the-art TERS probe designs,from the working mechanism to the practical *** start with reviewing the recent development of TERS configurations and the corresponding working mechanisms,including the SPM platforms,optical excitation/collection techniques,and probe preparation *** then review the emerging novel TERS probe designs,including the remote-excitation probes,the waveguide-based nanofocusing probes,the metal-coated nanofocusing probes,the nanowire-assisted selective-coupling probes,and the tapered metal-insulator-metal *** discussion focuses on a few critical aspects,including the surface-plasmon-polariton(SPP)hotspot excitation technique,conversion efficiency,working frequency,and *** the end,we review the latest TERS applications and give a perspective on the future of TERS.

关键词： tip-enhanced Raman spectroscopy plasmonics scanning probe microscopy nanoscale imaging nanophotonics nanofocusing

来源：评论

学校读者我要写书评

暂无评论

Pilot-based channel estimation in spatial modulated OFDM systems for mobile wireless applications

引用

International Journal of Wireless and Mobile Computing 2023年第2期24卷 181-194页

作者： Soman, Anetha Mary Nakkeeran, R. John, Shinu Mathew Department of Electronics Engineering School of Engineering and Technology Pondicherry Central University Pondicherry India Department of Computer Science Engineering St. Thomas College of Engineering and Technology Mattannur Kerala Kannur India

Spatial modulation Orthogonal Frequency Division Multiplexing (SM OFDM) is a newly developed transmission technique that has been proposed as an alternative for multiple input multiple output (MIMO)-OFDM transmission. Channel estimation is important for coherent data detection in practical scenarios. This paper investigates estimate power, Mean Square Error (MSE) and Bit Error Rate (BER) parameter metrics with channel estimation algorithm for Additive White Gaussian Noise (AWGN) and Rayleigh fading channel on three test environments proposed by International Telecommunication Union (ITU) specified standard model. Simulation output shows that for an AWGN channel, an improvement of approximately 1 dB and 0.3 dB power is obtained with Minimum Mean Square Error (MMSE) estimate and Least Square (LS)-linear/Spline using DFT. Additionally, for various interpolations employed, MSE decreases as Signal to Noise Ratio (SNR) rises, and performance improvement in BER when compared to traditional LS/MMSE estimators also occurs. For Rayleigh fading channel also there arises an enhanced performance in the parameter metrics with MMSE-DFT compared to conventional estimators. In summary, simulation output shows that incorporating DFT algorithm can provide better estimate power, BER and MSE by eliminating the effect of noise externally the extreme channel delay length. © 2023 Inderscience Enterprises Ltd.

关键词： Interpolation

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

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

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：