检索结果-内蒙古大学图书馆

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Yuemei Sun School of Finance and Economics Guangdong University of Science and Technology Dongguan Guangdong China

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Economic globalization has driven the rapid development of the digital economy, with cross-border e-commerce rising alongside it. In this context, the accurate prediction of user behavior is crucial for shaping future marketing strategies and optimizing the allocation of social resources. To address this, this paper proposes a user behavior prediction model based on deep learning algorithms. The model integrates the strengths of three fundamental models: Logistic Regression, Support Vector Machine (SVM), and Random Forest, enhancing the overall performance. In cases where the feature matrix is extremely sparse, the model efficiently predicts user behavior by utilizing second-order feature interactions. Experimental results indicate that the importance of the predictive factors for user behavior is as follows: Product Functionality (D) > Influencer Recommendations (B) > User Inertia (E) > Product Quality (C) > Brand Image (A). Additionally, the model's normalized Gini coefficient reaches a maximum value of 0.77, with a prediction accuracy of 0.95 and a recall rate of 0.94 in both iterations, demonstrating excellent predictive performance. Overall, the deep learning algorithm-based prediction model outperforms all other comparison models in terms of accuracy, recall, stability, and generalization capability, making it the most effective model among those tested.

关键词： Deep learning Support vector machines Accuracy Predictive models prediction algorithms Stability analysis Product design Circuit stability Quality assessment Random forests

来源：评论

学校读者我要写书评

暂无评论

Regressive Multi-Scale BiGRU Model for Work Function prediction of MXene Materials With Oppositional Learning-Based Optimization

引用

IEEE ACCESS 2024年 12卷 105550-105565页

作者： Jameer Basha, S. K. Ajith Jubilson, E. VIT AP Univ Sch Comp Sci Engn Guntur 522237 Andhra Pradesh India

MXenes are two-dimensional transition metal carbides and nitrides with variable compositions and complex chemical properties. MXenes are used in various applications such as electronics, energy storage, and catalysis due to their highly tunable electrical, optical, and physical characteristics and composition adaptability. The applicability of MXenes for these applications can be determined by its work function, which is a crucial fundamental characteristic. Many researchers have recently concentrated on machine learning models to predict the work function, but these models still need improvement. So, this research proposes a deep learning (DL) based accurate 2D MXenes work function prediction model called a Regressive Multi-scale Dynamic Adaptive Convolutional BiGRU Weighting (RMDAC-BiGRUW) ensemble model. To improve the effectiveness, the pre-processing stage is included for normalizing and standardizing the input data. Furthermore, the oppositional gazelle transition algorithm (OGTA) technique is employed for deep feature selection. Finally, the proposed DL-based ensemble model, composed of several layers, is utilized for work function prediction. The proposed model is accessed with various existing models in the performance evaluation scenario, including decision tree, Random Forest (RF), K-Nearest Neighbors (KNN), and Convolutional Neural network (CNN). Furthermore, different kinds of analysis are performed in terms of mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2). Finally, the experimental outcomes demonstrate that the proposed model is perfectly suitable for precise MXenes work function prediction as the model selection criterion values are better compared to the existing models. In addition, the proposed work function prediction model obtained 0.1875 as MSE, 0.7662 as R2, and 0.1875 as MAE.

关键词： Predictive models Computational modeling Adaptation models Accuracy prediction algorithms Feature extraction Deep learning MXenes work function deep learning RMDAC BiGRUW oppositional gazelle transition algorithm prediction ensemble model deep feature selection MSE R-2 MAE

来源：评论

学校读者我要写书评

暂无评论

An Improved Data Fusion Algorithm Based on Cluster Head Election and Grey prediction

引用

IEEE ACCESS 2024年 12卷 22746-22758页

作者： Wang, Jun Wang, Ning Sun, Bingnan Cao, Kerang Jung, Hoekyung El-Meligy, Mohammed A. Sharaf, Mohamed Shenyang Univ Chem Technol Coll Comp Sci & Technol Shenyang 110142 Peoples R China Key Lab Intelligent Technol Chem Proc Ind Liaoning Coll Engn Dept Comp Engn Shenyang 110142 Peoples R China Paichai Univ Comp Engn Dept Daejeon 35345 South Korea King Saud Univ Coll Engn Ind Engn Dept Riyadh 11421 Saudi Arabia

In traditional Wireless Sensor Network routing protocols, data collected through timed interval sensing tends to have high temporal redundancy, which leads to unnecessary energy drain. To alleviate this problem and enable sensor networks to save energy to some extent, a practical solution is to utilize prediction-based data fusion methods. To this end, this paper first proposes a Low Energy Adaptive Clustering Hierarchy-Energy-Kopt-N algorithm, an optimization algorithm explicitly designed to address the cluster-head election phase of the Low Energy Adaptive Clustering Hierarchy protocol. Then, a data collection model using data prediction techniques - the Grey Data prediction Model is formatted. Combining these improvements, a new data fusion algorithm that relies on data prediction, Grey-Clusters-Leach (GCL), is proposed. Simulation experiments demonstrate that the network energy drain of the GCL algorithm is reduced by 18%, 35%, 21.5% and 20%, and the network operation critical period life is extended by 3%, 35%, 22%, and 5% compared to the EQDC LEACH, LEACH-E, and SEP algorithms, respectively. GCL can effectively manage the size and number of clusters and reduce the number of packet transmissions by 20%.

关键词： prediction algorithms Data models Adaptation models Wireless sensor networks Clustering algorithms Predictive models Integrated circuit modeling Wireless sensor network cluster head election grey model data fusion

来源：评论

学校读者我要写书评

暂无评论

Improved Marine Predators Algorithm Optimized BiGRU for Strip Exit Thickness prediction

引用

IEEE ACCESS 2024年 12卷 56719-56729页

作者： Luo, Hao Chen, Jiaxuan Sun, Zhan Zhang, Ying Zhang, Li Liaoning Univ Coll Informat Shenyang 110036 Peoples R China

The strip exit thickness is an important indicator for measuring the production quality of steel rolling products. Controlling its accuracy is crucial in producing high-quality rolling products in the steel industry. This study proposed an improved marine predators algorithm (IMPA) optimized bidirectional gated recurrent unit (BiGRU) for predicting the strip exit thickness. Firstly, an adaptive weight factor was introduced into the marine predators algorithm (MPA) to overcome the drawbacks of slow early convergence speed and limited search range of the algorithm, addressing the issue of local optimization. Secondly, an average fitness strategy was developed to enhance the quality of the algorithm population, improve optimization accuracy, and strengthen algorithm stability. In addition, IMPA was used to optimize parameters, reducing the impact of hyper-parameters such as the number of hidden layer neurons, learning rate, and batch size on the prediction accuracy of BiGRU, thereby establishing IMPA-BiGRU model. The experiments were conducted on an actual rolling process dataset. The experimental results showed that IMPA outperformed traditional MPA, particle swarm optimization (PSO), grey wolf optimization (GWO), whale optimization algorithm (WOA), and recent variants of MPA. The IMPA-BiGRU also demonstrated excellent prediction capabilities for strip exit thickness, meeting the practical production requirements for high-quality rolling products.

关键词： prediction algorithms Statistics Social factors Predictive models Optimization Vectors Parameter estimation Feature detection Marine animals Heuristic algorithms Whale optimization algorithms BiGRU parameter optimization feature selection marine predators algorithm heuristic algorithm strip thickness

来源：评论

学校读者我要写书评

暂无评论

Maximum Latency prediction Based on Random Forests and Gradient Boosting Machine for AVB Traffic in TSN

引用

IEEE COMMUNICATIONS LETTERS 2025年第2期29卷 264-268页

作者： Zhang, Xiaodi Li, Dong Piao, Jinnan Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China Chinese Acad Sci Key Lab Networked Control Syst Shenyang 110016 Peoples R China Univ Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110016 Peoples R China

In this letter, we propose a latency prediction method based on random forests (RFs) and gradient boosting machine (GBM) to estimate the maximum latency of audio-video bridging (AVB) traffic in time-sensitive networks. We use a dataset collected from actual networks as the input features for the RFs. Then, we use the prediction results of the RFs as input features for the GBM to complete the model training. The experimental results show that the proposed method, compared to network calculus, performs better in terms of deviations as well as error metrics when the link utilization is 25%.

关键词： Radio frequency Predictive models prediction algorithms Accuracy Training Boosting Real-time systems Calculus Topology Network topology TSN maximum latency prediction random forests gradient boosting machine network calculus

来源：评论

学校读者我要写书评

暂无评论

An extensible simulation framework for evaluating centralized traffic prediction algorithms

An extensible simulation framework for evaluating centralize...

引用

International Conference on Connected Vehicles and Expo (ICCVE)

作者： Michael Wisely Ali Hurson Sahra Sedigh Sarvestani Department of Computer Science Missouri S&T Rolla Missouri Department of Electrical and Computer Engineering Missouri S&T Rolla Missouri

Due to the increasing popularity of smartphones and in-dash navigation equipment, traffic data gathered by mobile devices has grown in popularity as a basis for predicting traffic conditions. Mobile devices submit location information to a central server, where future traffic conditions are computed. Because this type of system would be expensive to test with real drivers, algorithms for road traffic prediction are often evaluated according to the outcomes of simulations. These simulations frequently use the same types of vehicle data to model the flow of traffic. Based on the observation that these algorithm simulators share common functionality, we have developed a framework to facilitate the rapid development of simulators for traffic prediction. Using our framework, developers can quickly implement traffic prediction simulators with included data processing and visualization features. To date, we have utilized the framework in creating two separate simulators for influence-aware predictive density queries and naive density queries, respectively.

关键词： Vehicles prediction algorithms Roads Servers Generators Data models Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fruit Yield prediction: Evaluating Multiobject Tracking algorithms for Calamansi Fruit Detection Using Yolov8m

Optimizing Fruit Yield Prediction: Evaluating Multiobject Tr...

引用

International Conference on Computer and Automation Engineering, ICCAE

作者： Regine A. Ponce-Machete Arnel Fajardo Technological Institute of the Philippines Manila Philippines Mindoro State University Calapan City Campus Oriental Mindoro Philippines Isabela State University Cauayan Campus Isabela Philippines

ISBN: (数字)9798331533816

ISBN: (纸本)9798331533823

Accurate fruit yield prediction is necessary for enhancing agricultural methods and providing quality output. This work analyzes the efficacy of multi-object tracking (MOT) algorithms in detecting calamansi fruits from drone-captured video footage, using the YOLOv8m object detection model. Data were gathered from a commercial calamansi farm in Naujan, Philippines, and prepared for model training. Three MOT algorithms-SORT, DeepSORT, and ByteTrack-were evaluated using performance metrics such as Multiple Object Tracking Accuracy (MOTA), Higher Order Tracking Accuracy (HOTA), and ID F1 Score (IDF1). ByteTrack achieved exceptional performance with MOTA, HOTA, and IDF1 ratings of 59.67 %, $\mathbf{6 5. 4 2 \%}$ , and $\mathbf{7 3. 7 2 \%}$ respectively. The integration of YOLOv8m for detection with ByteTrack for tracking significantly reduced double-counting while ensuring good computational efficiency. The results underscore ByteTrack's capability in real-time fruit monitoring and its significance for improving yield estimate and agricultural production.

关键词： Training Productivity Accuracy Object detection prediction algorithms Real-time systems Computational efficiency Yield estimation Object tracking Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Machine Learning algorithms for Early prediction of Alzheimer's Disease

A Comparative Study of Machine Learning Algorithms for Early...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： A. Akilandeswari Saveetha School of Engineering Simats University

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Alzheimer's disease (AD) is one of the most common neurodegenerative disorders, leading to progressive impairment of cognitive function. There is an immediate need to diagnose AD early to intervene in a timely fashion that could slow up disease progression. Traditional diagnosis methods are often expensive and take a very long time, motivating the pursuit of ML as an alternative diagnosis approach. In terms of algorithms, the effectiveness of five types was compared: Random Forest, Gradient Boosting, Logistic Regression, Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN) in predicting Alzheimer's disease. Different metrics such as accuracy, precision, recall, and F1-score were utilized using a patient dataset. Results show that Gradient Boosting achieved the highest accuracy at 95.81%, followed by Random Forest at 92.79%. The ensemble methods were seen to perform pretty well since they had the ability to manage complex patterns and noisy data. On the contrary, the performance was relatively less precise for k-NN (72.55%) due to the very high dimensionality of the dataset itself. The findings emphasize the requirement of the suitable machine learning approach that would be used for better predictive accuracy, particularly the earlier detection of AD.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Boosting prediction algorithms Ensemble learning Reliability Alzheimer's disease Random forests

来源：评论

学校读者我要写书评

暂无评论

SM-FPLF: Link-State prediction for Software-Defined DCN Power Optimization

引用

IEEE ACCESS 2024年 12卷 79496-79518页

作者： Nsaif, Mohammed Kovasznai, Gergely Malik, Ali de Frein, Ruairi Univ Debrecen Fac Informat Dept Informat Technol H-4032 Debrecen Hungary Univ Kufa Dept Comp Sci Kufa 540011 Iraq Eszterhazy Karoly Catholic Univ Dept Computat Sci H-3300 Eger Hungary Technol Univ Dublin Sch Elect & Elect Engn Dublin D07 EWV4 Ireland

Efficient monitoring systems that optimize resource allocation, reduce energy usage through machine learning and flow aggregation routing techniques, are needed due to the escalating power consumption of data center networks, which, as has been recently reported, account for up to eight percent of global energy consumption, posing environmental operational concerns. We propose a software-defined data-center monitoring algorithm that reduces power consumption by: 1) using a GPU implementation of a Stacked Long Short-Term Memory Recurrent Neural Network (RNN) model for link utilization prediction, thus reducing monitoring overhead;and 2) utilizing a flow aggregation routing algorithm with feedback from online, OpenFlow-powered monitoring and machine learning modules. This combined approach results in a new algorithm called SMart-Fill Prefer Path First (SM-FPLF). In the context of SM-FPLF, the objective of this paper is to compare the: 1) training and validation loss curves for various models;2) to evaluate the prediction accuracy of learning approaches for a range of prediction horizons;3) to assess the time-cost and accuracy for different models, with a specific focus on the GuSLSTM and GuGRU models;4) to analyze OpenFlow traffic with and without using the preferred prediction algorithm, the GuSLSTM model, assessing the accumulated power consumption per OpenFlow channel in the data-centre when SM-FPLF is applied. Our findings indicate that the GuSLSTM outperforms rival algorithms in terms of link utilization prediction accuracy over varying input sequence lengths. This accuracy is achieved whilst satisfying the SDN domain-specific requirement of a small computation time in a real-time implementation. Embedding a GuSLSTM in the SM-FPLF algorithm offers a power saving of 372 watts per OpenFlow channel, which is achieved in part due to a 13.7% CPU usage reduction in controllers and switches. These findings provide a valuable perspective into the performance and suitabil

关键词： Monitoring Power demand Optimization Topology prediction algorithms Routing Predictive models Data center networks software-defined networks power consumption machine learning OpenFlow monitoring prediction overhead

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning algorithms for Disease prediction Using Medical Datasets

Comparative Analysis of Machine Learning Algorithms for Dise...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： C. Roopa R.S. Latha M. Dhavamani G. Bommisrilekkhaa P. Angel Shalini R. Dhanyajothi Department of Computer Science and Engineering Kongu Engineering College Erode Tamilnadu Department of Artificial Intelligence Kongu Engineering College Erode Tamilnadu Department of Mathematics Kongu Engineering College Erode Tamilnadu

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Application of machine learning in the analysis of medical data can be said to be one of the current transformations happening within the healthcare fraternity. This paper highlights several ways in which various machine learning techniques can be used for gaining valuable insight into disparate types of medical data, such as patient records or genetic information, toward further clinical decision-making with a view to better prediction of diseases or strategies related to personalized medicine. The study critically evaluated various algorithms by considering their performances, suitability with regard to certain medical datasets they would be set upon to analyze, and to interpret the performance, particularly within the supervised learning frameworks. It talks about methodologies through which feature selection can take place to make sure that there is effective model development. Consequential applications in early disease detection as well as the optimization of their treatments are further emphasized, representing great potential for massive improvements in their recovery outcomes. The results highlight how far reaching data-driven approaches can affect the future of healthcare. It is envisioned that, with the use of such methods, the paper foresees a paradigm shift in disease diagnosis and treatment for personalized medical care and improved health outcomes.

关键词： Machine learning algorithms Precision medicine Supervised learning Machine learning Predictive models Feature extraction prediction algorithms Medical diagnostic imaging Optimization Diseases

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：