检索结果-内蒙古大学图书馆

Falcon Optimization Algorithm-Based Energy Efficient Communication Protocol for Cluster-Based Vehicular Networks

computers, Materials & Continua 2024年第3期78卷 4243-4262页

作者： Youseef Alotaibi B.Rajasekar R.Jayalakshmi Surendran Rajendran Department of Software Engineering College of ComputingUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Electronics and Communication Engineering Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Science and Engineering Panimalar Engineering CollegeChennai600123India Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical ScienceChennai602105India

Rapid development in Information Technology(IT)has allowed several novel application regions like large outdoor vehicular networks for Vehicle-to-Vehicle(V2V)*** networks give a safe and more effective driving experience by presenting time-sensitive and location-aware *** communication occurs directly between V2V and Base Station(BS)units such as the Road Side Unit(RSU),named as a Vehicle to Infrastructure(V2I).However,the frequent topology alterations in VANETs generate several problems with data transmission as the vehicle velocity differs with ***,the scheme of an effectual routing protocol for reliable and stable communications is *** research demonstrates that clustering is an intelligent method for effectual routing in a mobile ***,this article presents a Falcon Optimization Algorithm-based Energy Efficient Communication Protocol for Cluster-based Routing(FOA-EECPCR)technique in *** FOA-EECPCR technique intends to group the vehicles and determine the shortest route in the *** accomplish this,the FOA-EECPCR technique initially clusters the vehicles using FOA with fitness functions comprising energy,distance,and trust *** the routing process,the Sparrow Search Algorithm(SSA)is derived with a fitness function that encompasses two variables,namely,energy and distance.A series of experiments have been conducted to exhibit the enhanced performance of the FOA-EECPCR *** experimental outcomes demonstrate the enhanced performance of the FOA-EECPCR approach over other current methods.

关键词： Vehicular networks communication protocol clustering falcon optimization algorithm routing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Hybrid Recommendation System for Safe Approach to Curated Cosmetics 3

Deep Learning-based Hybrid Recommendation System for Safe Ap...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Rohitha Chowdary, G. Tharun, J. Sivaiah, G. Raveena, S. Surendran, R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Insititute of Medical and Technical Science Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

In the rapidly evolving cosmetics market, it is imperative to prioritize customer safety while offering personalized recommendations. This study introduces a hybrid recommendation system for cosmetics, using deep learning to combine the advantages of collaborative filtering with content-based filtering. The system assesses user preferences, skin types, and ingredient sensitivities, recommending solutions that are both effective and safe. The system proposes an integration of user-based and item-based collaborative filtering methodologies with deep neural networks to effectively elucidate intricate links among individuals, items, and their characteristics. This hybrid technique facilitates the system's ability to propose goods that provide both aesthetic appeal and skin safety, therefore fostering a healthier and more confident lifestyle. The system has an impressive accuracy of 92.5% in recommending suitable cosmetic products for individual clients. This enhanced accuracy reduces the likelihood of negative reactions and elevates customer satisfaction via personalized suggestions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble of Deep Learning with Crested Porcupine Optimizer Based Autism Spectrum Disorder Detection Using Facial Images

引用

computers, Materials & Continua 2025年第5期83卷 2793-2807页

作者： Jagadesh Balasubramani Surendran Rajendran Mohammad Zakariah Abeer Alnuaim Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105Tamil NaduIndia Department of Computer Science and Engineering College of Applied Studies and Community ServiceKing Saud UniversityP.O.Box 22459Riyadh11495Saudi Arabia

Autism spectrum disorder(ASD)is a multifaceted neurological developmental condition that manifests in several *** all autistic children remain undiagnosed before the age of *** problems affecting face features are often associated with fundamental brain *** facial evolution of newborns with ASD is quite different from that of typically developing *** recognition is very significant to aid families and parents in superstition and *** facial features from typically developing children is an evident manner to detect children analyzed with ***,artificial intelligence(AI)significantly contributes to the emerging computer-aided diagnosis(CAD)of autism and to the evolving interactivemethods that aid in the treatment and reintegration of autistic *** study introduces an Ensemble of deep learning models based on the autism spectrum disorder detection in facial images(EDLM-ASDDFI)*** overarching goal of the EDLM-ASDDFI model is to recognize the difference between facial images of individuals with ASD and normal *** the EDLM-ASDDFI method,the primary level of data pre-processing is involved by Gabor filtering(GF).Besides,the EDLM-ASDDFI technique applies the MobileNetV2 model to learn complex features from the pre-processed *** the ASD detection process,the EDLM-ASDDFI method uses ensemble techniques for classification procedure that encompasses long short-term memory(LSTM),deep belief network(DBN),and hybrid kernel extreme learning machine(HKELM).Finally,the hyperparameter selection of the three deep learning(DL)models can be implemented by the design of the crested porcupine optimizer(CPO)*** extensive experiment was conducted to emphasize the improved ASD detection performance of the EDLM-ASDDFI *** simulation outcomes indicated that the EDLM-ASDDFI technique highlighted betterment over other existing models in terms of numerous performance measures.

关键词： Autism spectrum disorder ensemble learning crested porcupine optimizer facial images computeraided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving cross-domain recommendation using hybrid federated transfer learning

引用

Multimedia Tools and Applications 2025年第18期84卷 19343-19377页

作者： Goyal, Samta Jain Goyal, Rajeev Singh, Vinay Kumar Arunachalam, Rajesh Tripathi, Kuldeep Narayan Computer Science and Engineering ASET Amity University Madhya Pradesh Madhya Pradesh Gwalior India Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Thandalam Chennai India Madhya Pradesh Gwalior India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India

Cross-domain recommender systems, which serve as a panacea to data sparsity and cold-start problems, are increasingly vital for providing personalized content across diverse application domains like medicine, e-commerce, etc. This is accomplished by leveraging adequate ratings ad user profiles in one domain to ensure precise recommendations in another domain. However, the domains with good ratings are unwilling to share user ratings with third-party recommender systems/domains due to privacy-concern. It demands the need for privacy mechanism to transfer knowledge between domains securely. So, this research introduces the CrossRec-Hybrid Federated Transfer Learning (CrossRec-HFTL) framework to address cold start and privacy problems in a cross-domain recommendation system, which combines adversarial domain adaptation and federated learning to leverage user and item interactions from a labeled source domain to generate recommendations in an unlabeled target domain. CrossRec-HFTL uses a model architecture called CrossRec-CDAN, which consists of multiple generators and discriminators for domain adaptation. The generators produce user, item, and interaction embeddings, while the discriminators distinguish between source and target domain samples. Federated learning enables collaborative model training across multiple clients while maintaining data locality, further bolstered by encryption techniques for privacy preservation. The framework was evaluated on the Amazon dataset across three domain pairs: Home and kitchen to Office Products (HK → OP), CDs and vinyl to Digital Music (CDs → DM) and Digital Music to Music Instruments (DM → MI). The simulation findings reveal that CrossRec-HFTL outperforms baseline and modern recommendation models in terms of recommendation accuracy, achieving a very less RMSE of 0.82 and MAE of 0.58. This shows the robust performance of CrossRec-HFTL in cold-start scenarios and enhanced privacy preservation. © The Author(s), under exclusive lice

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Fuzzy Marine White Shark Optimization Based Efficient Routing and Enhancing Network Lifetime in MANET

引用

WIRELESS PERSONAL COMMUNICATIONS 2023年第4期132卷 2363-2385页

作者： Devi, K. Lalitha Bhat, C. Rohith Devi, K. Lalitha KSR College of Engineering Tiruchengode Namakkal India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

A mobile ad hoc network (MANET) is an independent wireless temporary network established by employing a set of mobile nodes (i.e. laptops, smartphones, iPods, etc.) appropriate for the environment in which the network infrastructures are not fixed. The most common problems faced by MANET are energy efficiency, high energy consumption, low network lifetime as well as high traffic overhead which create an impact on overall network topology. Hence, it is necessary to provide an energy-effective CH election to take steps against such issues. Therefore, this paper proposes a novel model to enhance the network lifetime and energy efficiency by performing a routing strategy in MANET. In this paper, an optimal CH is selected by proposing a novel Fuzzy Marine White Shark optimization (FMWSO) algorithm which is obtained by integrating fuzzy operation with two optimization algorithms namely the marine predator algorithm and white shark optimizer. The proposed approach comprises three diverse stages namely Generation of data, Cluster Generation and CH selection. A novel FMWSO algorithm is proposed in such a way to determine the CH selection in MANET thereby enhancing the network topology, network lifetime and minimizing the overhead rate, and energy consumption. Finally, the performance of the proposed FMWSO approach is compared with various other existing techniques to determine the effectiveness of the system. The proposed FMWSO approach consumes minimum energy of 0.62 mJ which is lower than other approaches.

关键词： MANET Cluster head Fuzzy Marine White Shark Cluster generation Network lifetime Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Predicting Stock Prices with K-Nearest Neighbors using Moving Average Techniques 1

Predicting Stock Prices with K-Nearest Neighbors using Movin...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Kajendran, K. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

This research analyzes the effectiveness of the K-Nearest Neighbors algorithm combined with moving average techniques, Five-day and Ten-day Exponential Moving Averages, specifically EMA-5 and EMA-10, to predict stock prices. The study will focus on the adjusted closing price to deal with the autocorrelation issue that is common in time series data. The performance of the models was evaluated based on four key metrics: mean absolute error, mean squared error, root mean square error, coefficient of determination, overfitting risk test and generalization capability test. It was shown from the results that KNN models integrated with EMA-5 and EMA-10 offered high accuracy, one of which, with an R2 coefficient indicating the capacity to capture stock price trends with an accuracy of up to 99%. The research pointed out how short-term EMAs, combined with machine-learning algorithms, can substantially improve stock price prediction accuracy. It gives useful insights into stock price behaviour, therefore providing a decisive precedent for future works in creating a viable method for selecting trading strategies using machine-learning tools and moving averages. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Leveraging Random Forests for Stock Market Bubble Identification: A Comparative Analysis 1

Leveraging Random Forests for Stock Market Bubble Identifica...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

This research attempts to identify stock market bubbles using technical indicators combined with machine-learning processes. If not detected early on, stock bubbles arising from overvaluation and speculation can incur huge losses. The study used Technical Indicators such as the Relative Strength Index(RSI), Moving Average Convergence Divergence(MACD), Bollinger Bands, and Volume Indicators to catch the market trends. These features were analyzed using Support Vector Machine, Logistic Regression, and Random Forest models with a 99.84% test accuracy and AUC equal to 1.0 obtained with Random Forest, which proved to be, in this research, the most reliable for bubble detection. The study compares, in detail, the results, including Confusion Matrices and Receiver Operating Characteristic curves, validating the findings. The approach here would be a robust and data-driven framework for investors and analysts to recognize bubbles, facilitating better decision-making by risk minimization. The results also contribute to further developments in the role of machine learning in equity markets. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Supply Chain Efficiency with IoT and Data Analytics

Enhancing Supply Chain Efficiency with IoT and Data Analytic...

引用

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Jayalakshmi, D. Vimal, V.R. Loganayagi, S. Narayanan, Lakshmi Kanthan Hemavathi, R. Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Thandalam Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Simats Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350388602

This study aims at exploring the use of internet of things technology and data analytics in the field of supply chain management. Using a range of software tools, including Apache Kafka, Apache NiFi, Python libraries such as Pandas, and Scikit-learn, the study accumulated, assimilated, and quantified data from IoT sensors, supply chain systems, and qualitative interviews. The primary data sources are primary supply chain data history and IoT sensor data while secondary data includes academic and industrial journals, and reports. This paper presents a number of basic quantitative measures showing the general performance indicators: the average percentage of order fulfilment as 92.5% and the inventory turnover ratio equalling 6.2. When using linear regression, random forest, and LSTM neural network, the models reveal the mean absolute errors of demand forecasting between 80 and 120 units. The results suggest that IoT and data analysis offer significant opportunities to create value through the integration of SC, cost cutting, and higher customer satisfaction. It has now become essential for organizations to effectively apply data trends to enable competitive gains within the complex business setting to foster operational efficacy and stability. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Improving the Accuracy by Comparing with CatBoost Classifier Algorithm over Multilayer Perceptron Classifier Algorithm for Predicting the Air Pollution 15

Improving the Accuracy by Comparing with CatBoost Classifier...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Naidu, Y. Pavan Kumar Amanullah, M. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical andTechnical Sciences Saveetha Univerity Tamilnadu India

ISBN: (纸本)9798350370249

Aim: This effort aims to determine the type of air pollution quality. Through a comparison study of the cat-boost Classifier procedure and the MLP classifier method, it has been found which algorithm is the most accurate in forecasting air pollution. Materials and methods: The Kaggle website is used to obtain the dataset required for finding the air pollution quality type. The algorithms for the Novel Cat boost algorithm and Multilayer perceptron are tested when the dataset is imported and data mining can be done. The G power test with α=0.05 and power= 0.85 was employed in this study. For two algorithms, there are two groups. Each group sample size iteration 10. Results: Accuracy for the supplied inputs is acquired as the results. The results are obtained using the IBM SPSS software. According to findings, A statistically significant distinction exists between the Novel Cat Boost Classifier Procedure, which has an accuracy of 83.11%, and the MLP Classifier Algorithm, which has a 77.76% accuracy. The Statistically Novel Gradient Boosting Classifier Algorithm was significant with p = 0.002 (p ©2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Texture- and Symptom-Based Coffee Leaf Disease Classification Using CNN and ResNet algorithms 4

Texture- and Symptom-Based Coffee Leaf Disease Classificatio...

引用

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

作者： Surendran, R. Sree, C. Pranitha Sumathy, K. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institution of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350364729

This work aims to improve plant disease prediction through the implementation of an intriguing and revolutionary model that combines refined algorithms for machine learning with predictive analytics strategies. The goal is to strengthen utilities' resilience by providing precise and trustworthy forecasts of the potential classification of diseases. This study aims to push the limits of present prediction skills, analyze cutting-edge technology, and test unique features to improve the accuracy and timeliness of plant pathogen prophecies significantly. The ultimate goal in a rapidly evolving technological environment is to contribute to the development of proactive and effective mitigation techniques that reduce the impact of electrical glitches on equipment, infrastructure, and system-wide consistency. Materials required: The core database for the present investigation was obtained from the reputable data-gathering and analytics website Kaggle. The dataset includes a wide range of line voltages and currents for various failure scenarios. In Group 1, the convolutional neural network approach was applied. The statistical power of the 48 sample sizes utilized in the study was 0.8, the alpha value was 0.05, and the beta value was 0.2. ResNet is used by Group 2. Clinical is the method used to compute these figures. To run the accurate prediction software, Google Colab is employed. It analyzes data and displays accuracy as a percentage and in a graphical format for simple interpretation. Result: The convolutional neural network technique yielded an accuracy of 78.65% percent for Group 1, while the ResNet strategy yielded an accuracy of 70.61% for Group 2. SPSS data analysis program is employed for data set statistical analysis and correctness. A two-tailed test is used to appraise to what extent there is a statistically significant discrepancy in accuracy between both sets of data. Conclusion: Convolutional neural networks are more accurate than ResNet algorithms. © 2024 I

关键词： Convolutional neural 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：