检索结果-内蒙古大学图书馆

A literature study and performance gaps on Centralized server-based load balancing and routing strategies under cloud-IoT-WSN

引用

Australian Journal of Electrical and Electronics engineering 2024年第2期21卷 138-160页

作者： GSR, Yogaraja M N, Thippeswamy K, Venkatesh Information Science and Engineering S J C Institute of Technology Chickaballapura Karnataka India Ramaiah Institute of Technology Karnataka Bangalore India Computer Science & Engineering Nitte Meenakshi Institute of Technology Karnataka Bangalore India

Wireless Sensor Network (WSN) infrastructure has to be balanced for maintaining the Quality of Service (QoS) in the network. However, load balancing technology is complex for meeting the requirements of high flexibility and adaptability due to the conventional WSN architecture. The major complication for developing distributed techniques for these models is load balancing that is the major aim of this study. These distributed methodologies use routing decisions that must be efficient without the need for more information about the system, where one of the efficient techniques is probabilistic routing. This paper plans to conduct a critical literature review on a diverse centralised server for controlling the load balancing in the cloud and routing strategies in WSN as well as linked with an IoT systems. This study reviews a set of contributions regarding load balancing in the cloud and routing strategies in WSN with clear algorithmic analysis. The simulation tools and recorded performance measures are also analysed and sorted out. Finally, the existing research gaps and the future directions are expedited that to be adaptable to attain better protocol performance with a centralised server in balancing node traffic, load balancing in the cloud and improving the throughput of the entire network. ©, Engineers Australia.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Novel Music Recommendation System Using Filtering Techniques

引用

Informatica (Slovenia) 2024年第4期48卷 595-610页

作者： Vashishtha, Srishti Varshney, Deepika Sarin, Eva Kaur, Simran Computer Science and Engineering Dept. Bharati Vidyapeeth’s College of Engineering GGSIPU New Delhi India Computer Science and Engineering Dept. Jaypee Institute of Information Technology Noida India

With the growth of the World Wide Web, a large amount of music data is available on the Internet. A large number of people listen to music online rather than downloading and listening offline. But only some sites provide personalized and accurately recommended songs while they listen to an auto-playing playlist. Hence the need for recommendation systems arises. Two approaches can be applied to the recommendation system: content based filtering and collaborative filtering. While in content-based filtering approach, analysis on the songs’ content which has been preferred by the user in history is done and the songs with relative similarity are recommended. While latter suggests songs that certain users of similar listening pattern have preferred. But collaborative filtering-based recommendation systems not only requires time to attain stability but also might recommend unsuitable music because it is not personalized to each user’s preference. Also, the latter requires the songs to be listened by a few users already to recommend it any other user. Hence for overall analysis, answers to few questions need to be implemented in recommendation systems: the very first one is how the properties should be analyzed, next one is how the analysis should be done and last is how the songs related to the user’s preference should be chosen. So, for suggesting the better system which solves these three questions as well as provides better and personalized recommendations, In this paper we build a collaborative filtering as well as content based filtering recommendation system, where various factors determine the essence of the songs, i.e. liveliness, keys used, loudness, pitch, valence, etc., are analyzed for comparison. From the experimental analysis in has been identified that content-based filtering technique performed best on KNN machine learning classifier with accuracy of 85%. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Prediction of strength properties of concrete under the influence of recycled aggregate using machine learning models

引用

Interactions 2024年第1期245卷 1-21页

作者： Ashwathi, R. Soundariya, R.S. Tharsanee, R.M. Yuvaraj, S. Ramya, R. Department of Civil Engineering Bannari Amman Institute of Technology Erode India Department of Computer Technology Bannari Amman Institute of Technology Erode India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Civil Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Information Technology Dr NGP Institute of Technology Coimbatore India

The upsurge in urbanization is depleting natural resources due to the wide usage of aggregates in construction, posing a menace to further progress. If the contemporary state persists, it becomes a threat for further progress. As an initiative to preserve the natural resources, recycled aggregate is employed as a partial additive of fine aggregate, this practice endorses sustainability but demands a cautious investigation of its effect on concrete strength. Predicting the strength characteristics of concrete becomes crucial in this situation. Machine Learning (ML) algorithms estimate these properties, enabling engineers to evaluate and enhance the concrete mix with recycled materials, confirming durability and performance without solely depending on outdated testing methods The proposed work attempts how ML algorithms have been utilized to forecast the strength properties of concrete. Input samples were collected from the experimental setup for three grades of concrete (M15, M20, M25) with four various proportions (5%, 10%, 15% and 20%) at 7, 14, 21 and 28 ages of curing excluding the conventional mix. The ML models are developed by training the collected laboratory samples with respect to four parameters– cement, fine aggregate (FA), coarse aggregate (CA) and recycled aggregate (RA). The trained models predict the three properties of concrete– compressive strength, split tensile strength and flexural strength. The test outcomes are further validated using statistical measures such as correlation coefficient– R2, Mean Square Error (MSE) and Mean Absolute Error (MAE) to assess the performance of the model. The performance evaluation of the proposed approach shows that The Support Vector Regressor outperforms the other ML models, achieving an R² value of about 90% and showing a reduced error rate in terms of MSE and MAE. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Tensile testing

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning, Ensemble Learning and Deep Learning Classifiers for Parkinson’s Disease Detection

引用

SN computer science 2024年第1期5卷 1-14页

作者： Goyal, Palak Rani, Rinkle Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India

A progressive neurodegenerative ailment called Parkinson's disease (PD) is marked by the death of dopamine-producing cells in the substantia nigra area of the brain. The exact etiology of PD remains elusive, but it is believed to involve the presence of Lewy bodies, abnormal protein aggregates, in affected brain regions, leading to the mobile symptoms of PD. Hence, as the management of PD continues to evolve, there is a growing demand for the establishment of a descriptive system that enables the early detection of PD. In this study, we conducted an extensive analysis using machine learning, ensemble learning, and deep learning models with different hyperparameters to develop accurate classification models for PD prediction. To enhance classifier performance and address overfitting, we employed principal component analysis (PCA) for feature selection along with various preprocessing techniques. The dataset used consisted of voice samples, comprising 188 PD patients and 64 normal individuals. Our results demonstrated that the Random Forest (RF) model with accuracy of 82.37% outperformed the other base classifiers Among the ensemble classifiers, the LGBM model exhibited the highest accuracy of 85.90% when compared to both base and ensemble classifiers. Notably, the deep learning model has 91.33% training accuracy and 85.02% testing accuracy, suggesting that deep learning models perform comparably equivalent on small datasets compared to machine learning classifiers. Overall, our findings underscore the effectiveness of machine learning, ensemble techniques and deep learning models in accurately predicting PD. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep learning Hyperparameters LGBM Machine learning Parkinson’s disease Random forest

来源：评论

学校读者我要写书评

暂无评论

A Software Defect Prediction Method Using a Multivariate Heterogeneous Hybrid Deep Learning Algorithm

引用

computers, Materials & Continua 2025年第2期82卷 3251-3279页

作者： Qi Fei Haojun Hu Guisheng Yin Zhian Sun College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Information Technology Research Department Jiangsu Automation Research InstituteLianyungang222062China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China

Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.

关键词： Software defect prediction multiple heterogeneous data graph convolutional network models based on adjacency and spatial topologies CNN-BiLSTM TabNet

来源：评论

学校读者我要写书评

暂无评论

A Novel Enhanced Approach for Security and Privacy Preserving in IoT Devices with Federal Learning Technique

引用

SN computer science 2024年第6期5卷 750页

作者： Moeed, Syed Abdul Karnati, Ramesh Ashmitha, G. Mohammad, Gouse Baig Mohanty, Sachi Nandan Department of Computer Science and Engineering Kakatiya Institute of Technology and Science Department of Computer Science and Engineering Vardhaman College of Engineering School of Computer Science & amp Engineering (SCOPE) VIT-AP University

The Internet of Things (IoT) has revolutionized our lives, but it has also introduced significant security and privacy challenges. The vast amount of data collected by these devices, often containing sensitive information, makes them prime targets for cyberattacks. Traditional security methods struggle to keep pace with the evolving threat landscape of the interconnected IoT world. In response, this paper explores the transformative potential of federated learning (FL) in safeguarding both the privacy and security of IoT devices. FL keeps data on individual devices, only sharing updated models, not raw data, thus protecting user privacy and eliminating the need for a central data storage server, which reduces the risk of data breaches and security vulnerabilities. The effectiveness of the proposed model is evaluated using established open-source datasets like NSL-KDD and UNSW NB15, ensuring real-world applicability. Analysis of the dataset's features enabled the development of a model utilizing federated learning. Notably, the proposed model achieved superior performance with FL in detecting attacks on IoT networks. Furthermore, this research investigates the transformative potential of FL to address the inherent security and privacy challenges plaguing traditional, centralized data collection methods in the ever-expanding realm of IoT devices. FL empowers collaborative learning on distributed datasets, allowing devices to collectively improve security without compromising user privacy. The findings of this study demonstrate the promise of FL as a secure and privacy-preserving solution for the future of IoT. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cyberattacks Federal learning Internet of Things Machine learning Security and privacy

来源：评论

学校读者我要写书评

暂无评论

Integration of cloud-based scheme with industrial wireless sensor network for data publishing in privacy of point source

引用

International Journal of Cloud Computing 2024年第2期13卷 124-138页

作者： Ravindhar, N.V. Sasikumar, S. Bharathiraja, N. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu India Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Wireless sensor networks (WSNs) are normally conveyed in arbitrary regions with no security. The source area uncovers significant data about targets. In this paper, a plan dependent on the cloud utilising data publishing in privacy of point source is proposed to resolve the issue of source area security. Then, at that point, a cloud-moulded phony area of interest is made to add counterfeit parcels into the WSN to confound the enemy and give a far-reaching protection area. Every important parcel is steered through a way that is very hard for the area of interest finding enemy to discover straightforwardly. Recreation results represent that the plan can forestall antagonistic catch and keep a significant degree of security insurance simultaneously. The energy utilisation in this plan applies restricted impact on the organisation lifetime contrasted and a cloud-based plan and an all-course irregular steering calculation conspire. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Natural Language Processing Algorithms for Sentiment Analysis

引用

SN computer science 2024年第6期5卷 724页

作者： Silviya, S. H. Annie Faith, S. Julia Seetha, R. Hemalatha, M. Department of Computer Science and Engineering Rajalakshmi Institute of Technology (RIT) Department of Information Technology S.A.Engineering College Department of Information Technology Vellore Institute of Technology Department of Computer Science and Engineering RMD Engineering College

Sentiment analysis can be used to identify if a text’s sentiment is neutral, positive, or negative. One type of natural language processing is sentiment analysis. An interdisciplinary field encompassing linguistics, computer science, and artificial intelligence called “natural language processing” studies how computers and human language interact, with a focus on how to teach computers to process and analyze vast volumes of natural language data. Sentiment analysis, sometimes referred to as opinion mining or emotion artificial intelligence, is the methodical identification, extraction, quantification, and study of affective states and subjective data using natural language processing, text analysis, computational linguistics, and biometrics. Sentiment analysis is frequently used in online and social media platforms, voice of the customer materials (such as reviews and survey replies), and healthcare materials for marketing, customer service, and clinical medicine purposes. This paper discusses different sentiment analysis methods and selects the best approach for a certain task. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Biometrics Computational linguistics Natural language processing Sentiment analysis Text analysis

来源：评论

学校读者我要写书评

暂无评论

An efficient botnet detection approach based on feature learning and classification

引用

Journal of Control and Decision 2023年第1期10卷 40-53页

作者： B.Padmavathi B.Muthukumar Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennaiIndia Computer Science and Engineering Easwari Engineering CollegeChennaiIndia DMI College of Engineering ChennaiIndia

Bot detection is considered a crucial security issue that is extensively analysed in various existingapproaches. Machine Learning is an efficient way of botnet attack detection. Bot detectionis the major issue faced by the existing system. This research concentrates on adopting a graphbasedfeature learning process to reduce feature dimensionality. The incoming samples arecorrectly classified and optimised using an Adaboost classifier with an improved grey wolfoptimiser (g-AGWO). The proposed IGWO optimisation approach is adopted to fulfil the multiconstraintissues related to bot detection and provide better local and global solutions (to satisfyexploration and exploitation). The extensive results show that the proposed g-AGWO model outperformsexisting approaches to reduce feature dimensionality, under-fitting/over-fitting andexecution time. The error rate prediction shows the feasibility of the given model to work over thechallenging environment. This model also works efficiently towards the unseen data to achievebetter generalization.

关键词： Botnet machine learning AdaBoost grey wolf optimisation exploration exploitation

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Toward Efficient and Accurate Recommendation Using Improved Alternating Least Squares in Social Media

引用

Journal of The Institution of Engineers (India): Series B 2024年第3期105卷 657-675页

作者： Dhawan, Sanjeev Singh, Kulvinder Batra, Amit Choi, Anthony Choi, Ethan Department of Computer Science and Engineering University Institute of Engineering and Technology Kurukshetra University Haryana India Department of Electrical and Computer Engineering Mercer University MaconGA United States

The increasing number of electronic transactions on the Internet has given rise to the design of recommendation systems. The main objective of these systems is to give recommendations to the users about the items (i.e., movies, music, books, etc.) they are likely to purchase in near future. These recommendations are on the foundation of the response provided by the other individuals about these products in the terms of ratings, which are in the form of a five-star rating system. Plenty of algorithms have been proposed in the past for building recommender systems. The most popular of these algorithms comprise content-centered and collaborative filtering recommendation methodologies. Recently, matrix factorization has appeared as a technique in recommender systems. Several algorithms centered on matrix factorization have been suggested in the recent past. In this paper, an improved alternating least squares algorithm has been proposed for building more efficient and accurate recommender systems which improves the performance of matrix factorization. The performance of the model has been evaluated using metrics like root-mean-square-error and execution time. However, in general, the time complexity of both algorithms is O(n^3), where n is the number of users or items. This is because both IALS and ALS involve iteratively solving a system of linear equations, and the time complexity of solving a system of linear equations is O(n^3). However, IALS can achieve significant performance improvements over ALS, particularly for large datasets, due to its incorporation of stochastic gradient descent and parallelization techniques. © The Institution of Engineers (India) 2024.

关键词： Recommender systems

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：