检索结果-内蒙古大学图书馆

A Computational Intelligence Framework Integrating Data Augmentation and Meta-Heuristic Optimization algorithms for Enhanced Hybrid Nanofluid Density prediction Through Machine and Deep Learning Paradigms

引用

IEEE ACCESS 2025年 13卷 35750-35779页

作者： Mathur, Priya Shaikh, Hammad Sheth, Farhan Kumar, Dheeraj Gupta, Amit Kumar Poornima Inst Engn & Technol Jaipur 302022 Rajasthan India Manipal Univ Jaipur Dept Comp Sci & Engn Jaipur 303007 Rajasthan India

This research presents a robust and comprehensive framework for predicting the density of hybrid nanofluids using state-of-the-art machine learning and deep learning techniques. Addressing the limitations of conventional empirical approaches, the study used a curated dataset of 436 samples from the peer-reviewed literature, which includes nine input parameters such as the nanoparticle, base fluid, temperature (degrees C), volume concentration ( phi ), base fluid density ( rho bf ), density of primary and secondary nanoparticles ( rho(np1) and rho(np2) ), and volume mixture ratios of primary and secondary nanoparticles. Data preprocessing involved outlier removal via the Interquartile Range (IQR) method, followed by augmentation using either autoencoder-based or Gaussian noise injection, which preserved statistical integrity and enhanced dataset diversity. The research analyzed fourteen predictive models, employing advanced hyperparameter optimization methods facilitated by Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). In particular, autoencoder-based augmentation combined with hyperparameter optimization consistently improved predictive accuracy across all models. For machine learning models, Gradient Boosting achieved the most remarkable performance, with R-2 scores of 0.99999 and minimal MSE values of 0.00091. Among deep learning models, Recurrent Neural Networks (RNN) stacked with Linear Regression achieved superior performance with an R-2 of 0.9999, MSE of 0.0014, and MAE of 0.012. The findings underscore the synergy of advanced data augmentation, meta-heuristic optimization, and modern predictive algorithms in modelling hybrid nanofluid density with unprecedented precision. This framework offers a scalable and reliable tool for advancing nanofluid-based applications in thermal engineering and related domains.

关键词： Autoencoders Nanoparticles Predictive models Machine learning Fluids prediction algorithms Gaussian noise Deep learning Data models Data augmentation Density prediction hybrid nanofluids machine learning deep learning data augmentation meta-heuristic optimization optimization algorithms thermal engineering

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Preventing Bias in Text-based Personal Trait prediction algorithms

Analyzing and Preventing Bias in Text-based Personal Trait P...

引用

International Conference on Tools with Artificial Intelligence

作者： Isil Doga Yakut Kilic Shimei Pan University of Maryland Baltimore County

ISBN: (纸本)9781509044603

Personality prediction based on textual data is one topic gaining attention recently for its potential in large-scale personalized applications such as social media-based marketing and political campaigning. However, when applying this technology in real-world applications, users often encounter situations in which the personality traits derived from different sources (e.g., social media posts versus emails) are inconsistent. Varying results for the same individual renders the tool ineffective and hard to trust. This paper demonstrates the impact of domain bias in automated text-based personality prediction, and proposes a novel method to correct domain bias. The proposed approach is generic since it requires neither retraining the system using examples from an application domain, nor any knowledge of the original training data used by a personal trait analysis tool. We conduct comprehensive experiments to evaluate the effectiveness of the method, and the findings indicate a significant improvement of prediction accuracy (e.g., a 20-30% relative error reduction) with the proposed method.

关键词： personality trait prediction algorithms electronic mail Bias Bias Bias Statistical Biases bias(electronics) Personality Domain train data Campaigning

来源：评论

学校读者我要写书评

暂无评论

Feeder-link outage prediction algorithms for SDN-based high-throughput satellite systems

Feeder-link outage prediction algorithms for SDN-based high-...

引用

IEEE International Conference on Communications (ICC)

作者： Maurizio Mongelli Tomaso De Cola Marco Cello Mario Marchese Franco Davoli National Research Council Genoa Italy German Aerospace Center (DLR) Germany Nokia Bell Labs Dublin Ireland University of Genoa Genoa Italy

The design of High Throughput Satellite (HTS) systems builds on the concept of Smart Gateway Diversity (SGD) to exploit the spatial diversity of gateways in case of feeder link outage, occurring because of atmospheric impairments introduced in Extremely High Frequency (EHF) frequency bands. The gateway handover procedure requires precise prediction algorithms and coordination among different network elements. This paper presents novel outage prediction algorithms based on machine learning concepts, integrated in the framework of SDN architectures, to efficiently orchestrate the gateway handover operations. Simulation campaigns prove the validity of the proposed concept and shed light on the potentials of the SDN architecture in future HTS systems.

关键词： Logic gates Satellites Handover Signal to noise ratio prediction algorithms Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning algorithms for 5G Coverage prediction: Identification of Dominant Feature Parameters and prediction Accuracy

引用

IEEE ACCESS 2024年 12卷 18939-18956页

作者： Yuliana, Hajiar Iskandar Hendrawan Inst Teknol Bandung Sch Elect Engn & Informat Bandung 40132 Indonesia

5G technology is a key factor in delivering faster and more reliable wireless connectivity. One crucial aspect in 5G network planning is coverage prediction, which enables network providers to optimize infrastructure deployment and deliver high-quality services to customers. This study conducts a comprehensive analysis of machine learning algorithms for 5G coverage prediction, focusing on dominant feature parameters and accuracy. Notably, the Random Forest algorithm demonstrates superior performance with an RMSE of 1.14 dB, MAE of 0.12, and R2 of 0.97. The CNN model, the standout among deep learning algorithms, achieves an RMSE of 0.289, MAE of 0.289, and R2 of 0.78, showcasing high accuracy in 5G coverage prediction. Random Forest models exhibit near-perfect metrics with 98.4% accuracy, precision, recall, and F1-score. Although CNN outperforms other deep learning models, it slightly trails Random Forest in performance. The research highlights that the final Random Forest and CNN models outperform other models and surpass those developed in previous studies. Notably, 2D Distance Tx Rx emerges as the most dominant feature parameter across all algorithms, significantly influencing 5G coverage prediction. The inclusion of horizontal and vertical distances further improves prediction results, surpassing previous studies. The study underscores the relevance of machine learning and deep learning algorithms in predicting 5G coverage and recommends their use in network development and optimization. In conclusion, while the Random Forest algorithm stands out as the optimal choice for 5G coverage prediction, deep learning algorithms, particularly CNN, offer viable alternatives, especially for spatial data derived from satellite images. These accurate predictions facilitate efficient resource allocation by network providers, ensuring high-quality services in the rapidly evolving landscape of 5G technology. A profound understanding of coverage prediction remains pivotal for suc

关键词： Machine learning algorithms prediction algorithms 5G mobile communication Deep learning Machine learning Predictive models Classification algorithms Performance evaluation 5G coverage prediction classifier algorithm deep learning performance evaluation feature importance

来源：评论

学校读者我要写书评

暂无评论

Hybridizing Artificial Neural Networks Through Feature Selection Based Supervised Weight Initialization and Traditional Machine Learning algorithms for Improved Colon Cancer prediction

引用

IEEE ACCESS 2024年 12卷 97099-97114页

作者： Sajjad Ahmed Nadeem, Malik Hammad Waseem, Muhammad Aziz, Wajid Habib, Usman Masood, Anum Attique Khan, Muhammad Univ Azad Jammu & Kashmir Dept Comp Sci & Informat Technol Muzaffarabad 13100 Pakistan Univ Azad Jammu & Kashmir Dept Comp Sci Neelum Campus Athmuqam 13230 Pakistan Natl Univ Comp & Emerging Sci FAST Sch Comp Software Engn Dept Islamabad 44000 Pakistan Norwegian Univ Sci & Technol Dept Phys N-7491 Trondheim Norway Lebanese American Univ Dept Comp Sci & Math Beirut 11022801 Lebanon

Computer-aided decision support systems (DSSs) are becoming popular in a variety of professions. Notably, medical DSSs assist healthcare professionals (decision makers) choose the optimal course of action (decisions) while treating patients. Such systems help decision-makers in situations when there is uncertainty in manual decisions due to lack of information or expertise. Choosing a suitable learning algorithm in a DSS is essential and affects its performance. Among machine learning (ML) algorithms, artificial neural networks (ANNs) are considered the most suitable framework for many classification tasks. In healthcare, an ML-based prediction system/DSS employs data (genetic profile or clinical characteristics) and learning algorithms to forecast target values, which may give promising results. However, improving prediction accuracy is a crucial step in making informed decisions. One can apply various preprocessing methods (cross validation, feature selection, bagging, boosting, etc.) to achieve this. For complex classification tasks like cancer, decision-makers can utilize the hybridization of classifiers to increase prediction accuracy. The presented study investigates the possibilities of improvements in the design of hybridized systems for DSSs to assist healthcare professionals in robust decision-making before, during, and after cancer diagnosis. Since the network weights and the activation functions are the two crucial elements in the learning process of an ANN, this study is organized to investigates the improvement in the hybrid system by selecting suitable features from gene expression microarray data and using these features to compute the more realistic initial weights instead of using random guesses as initial weights for ANN. The use of the proposed framework gives promising results (upto 6.67% gain in accuracy when compared to previous study (Table-5) while 10.43% increase in accuracy when compared to conventional ML classifiers (Table-4).

关键词： Accuracy Feature extraction Classification algorithms Task analysis Classification tree analysis prediction algorithms Machine learning Artificial neural networks Computer aided diagnosis Cancer classification feature selection genetic profile machine learning hybrid classifiers artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Temperature prediction for Electric Vehicles Using Machine Learning algorithms

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第6期60卷 9251-9259页

作者： Kishore, Shradha Bharti, Sonam Kumari Anand, Priyadarshi Srivastav, Dishant Sonali, Shubham Birla Inst Technol Dept Elect & Elect Engn Patna Off Campus Patna 800014 India

The development of precise, efficient, and cost-effective temperature prediction algorithms to maintain the ambient charging and operational environment of electric vehicles (EVs) has gained significance in recent times. Machine learning algorithms are widely used for prediction and decision-making processes due to the growing presence of optimized statistical models based on training datasets, that are far superior to conventional computational statistical methods. In this work, a temperature dataset has been generated in real-time from an IoT and temperature sensor-based hardware, clipped-on the casing of a vehicle, pre-possessed and fitted into optimized models so that future values of temperature can be accurately predicted using different supervised regression machine learning algorithms. The predicted temperatures have been compared with the actual recorded temperatures and a statistical error analysis has been done to compare the results based on the Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R-Square (R-2) and adjusted R-2 Score. The advantage of this methodology is that it is independent of system parameters, and that any future values of critically high temperature may be predicted before they occur, so that drivers can be alerted and take corrective measures before actual damage takes place. This methodology may be applied to prevent incidents of fire in EV batteries, energy wastage due to high temperatures during charging or normal running, and to enhance passenger comfort.

关键词： Temperature sensors Temperature measurement Machine learning algorithms Predictive models Monitoring Batteries prediction algorithms Regression machine learning temperature prediction random forest r-square

来源：评论

学校读者我要写书评

暂无评论

Object Tracking With Movement prediction algorithms

Object Tracking With Movement Prediction Algorithms

引用

IEEE International Conference on Industrial and Information Systems

作者： Akhilesh Raj Abishalini Sivaraman Chandreyee Bhowmick Nishchal K. Verma Dept. of Electrical Engg. IIT Kanpur Kanpur India - 208016 Dept. of Electrical Engg. Texas A&M University College Station United States

The task of tracking an object becomes tedious when the object moves through a dynamic background and the camera also has a random motion. This type of problem has three main aspects - object detection, prediction of object motion and compensation of the camera motion. In this paper, we have developed three algorithms using three different object detection algorithms, namely background subtraction, template matching and Speeded Up Robust Features (SURF). Unscented Kalman Filter (UKF) algorithm has been devised for the motion prediction of the moving object as well as to compensate for the camera movement. The proposed algorithms have been validated through extensive simulations performed on several video datasets and an analytical study has also been presented. Through the simulation results, performance of the proposed algorithms are compared.

关键词： Cameras prediction algorithms Tracking Heuristic algorithms Object detection Kalman filters Feature extraction prediction algorithms Object detection Cameras Kalman filters Heuristic algorithms Feature extraction tracking objects tracking algorithms Object motion

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic algorithms for Solar Radiation prediction: A Systematic Analysis

引用

IEEE ACCESS 2024年 12卷 100134-100151页

作者： Perez-Rodriguez, Sergio A. Alvarez-Alvarado, Jose M. Romero-Gonzalez, Julio-Alejandro Aviles, Marcos Mendoza-Rojas, America Eileen Fuentes-Silva, Carlos Rodriguez-Resendiz, Juvenal Univ Autonoma Queretaro Fac Informat Queretaro 76230 Mexico Univ Autonoma Queretaro Fac Ingn Queretaro 76010 Mexico Univ Politecn Queretaro Queretaro 76240 Mexico

In the contemporary world, where the escalating demand for energy and the imperative for sustainable sources, notably solar energy, have taken precedence, the investigation into solar radiation (SR) has become indispensable. Characterized by its intermittency and volatility, SR may experience considerable fluctuations, exerting a significant influence on energy supply security. Consequently, the precise prediction of SR has become imperative, particularly in the context of the potential proliferation of photovoltaic panels and the need for optimized energy management. Several works in the existing literature review the state of the art in SR prediction, focusing on trends identified using machine learning (ML) or deep learning (DL) techniques. However, there is a gap in the literature regarding the integration of optimization algorithms with ML and DL techniques for SR prediction. This systematic review addresses this gap by studying prediction models for SR that leverage metaheuristic optimization algorithms alongside artificial intelligence (AI) techniques, aiming primarily for maximum prediction accuracy. Metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) have featured in 29% and 12.1% of the analyzed articles, respectively, while intelligent approaches like Convolutional Neural Networks (CNN), Extreme Learning Machine (ELM), and Multilayer Perceptron (MLP) have emerged as the predominant choices, collectively accounting for 43.9% of the studies. Analysis has encompassed studies examining SR across hourly, daily, and monthly intervals, with daily intervals representing 48.7% of the focus. Noteworthy variables including temperature, humidity, wind speed, and atmospheric pressure have surfaced, capturing proportions of 90%, 68.2%, 56%, and 41.4%, respectively, within the reviewed literature.

关键词： Predictive models prediction algorithms Optimization Biological system modeling Metaheuristics Computational modeling Accuracy Forecasting Solar radiation metaheuristics optimization solar radiation time-series

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning algorithms for CKD Risk prediction

引用

IEEE ACCESS 2024年 12卷 171205-171220页

作者： Yang, Weilin Ahmed, Nasim Barczak, Andre L. C. Univ Sydney Sch Comp Sci Sydney NSW 2006 Australia Bond Univ Ctr Data Analyt Gold Coast Qld 4226 Australia

Chronic Kidney Disease (CKD) remains a significant global health challenge, with increasing prevalence and a substantial impact on patient quality of life. Early and accurate prediction of CKD risk is crucial for timely intervention and management. This study presents a comprehensive comparative analysis of both machine learning and deep learning algorithms applied to predict CKD risk. The research involved the application of eight traditional machine learning algorithms: Naive Bayes, K-nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, AdaBoost, and XGBoost, each implemented on a CKD dataset retrieved from the UCI data repository. Furthermore, three neural network-based algorithms, Artificial Neural Network (ANN), Simple Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) were used to compare to the traditional algorithms. This comparative study not only assessed each algorithm's performance in terms of accuracy, precision, recall, and F1 score but also examined their computational efficiency and applicability in real-world clinical settings. All eleven algorithms were trained with three versions of the dataset. The first version kept the original unbalance between classes and used KNN imputation to fill up missing values (unbalanced). The second dataset used SMOTENC to create new samples to balance the dataset (balanced). The third dataset used feature selection to choose 14 features from the original 24. The results showed that there is almost no performance difference among the classifiers produced with the balanced, unbalanced and feature selection datasets. This means that the best algorithms for this task are the ones with short training and testing runtime, namely RF, SVM, AdaBoost and XGBoost. The experiments also showed that the neural network-based algorithms had no performance advantage and were slower to train due to the small size of samples available in the original dataset.

关键词： Chronic kidney disease Predictive models Accuracy Random forests Machine learning algorithms Machine learning prediction algorithms Nearest neighbor methods Support vector machines Classification algorithms machine learning deep learning risk prediction healthcare analytics

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Hybrid Feature Selection: Integrating ACO algorithms With a Statistical Ensemble Technique for EV Demand prediction

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2025年第3期61卷 5091-5102页

作者： Marzbani, Fatemeh Osman, Ahmed H. Hassan, Mohamed S. Amer Univ Sharjah Dept Ind Engn Sharjah U Arab Emirates Amer Univ Sharjah Dept Elect Engn Sharjah U Arab Emirates

This paper presents a novel hybrid algorithm combining Ant Colony Optimization (ACO) and multi-model ensemble feature selection techniques to enhance the accuracy of Support Vector Regression (SVR) models for predicting Electric Vehicle Charging Demand (EVCD). Addressing the challenge of highly nonlinear data in EVCD time series, our approach integrates the exploratory strengths of ACO with the robustness of four statistical feature selection algorithms in a two-phased process. Initially, ACO identifies a preliminary subset of relevant features, which is then refined through a multi-model ensemble process to select the most relevant features via a vote of majority strategy. This process involves a thorough examination of a broad solution space to uncover promising feature subsets, acting as an effective method for dimensionality reduction and leading to a streamlined set of features for further analysis. Applied to a real-case study, the effectiveness of our framework was compared with that of basic multi-model, hybrid GA, and PSO multi-model techniques. The results underscore the superior efficiency of the proposed method.

关键词： Feature extraction prediction algorithms Electricity Accuracy Predictive models Electric vehicle charging Support vector machines Power grids Metaheuristics Long short term memory Electric vehicles feature selection metaheuristic algorithms support vector regression time series analysis

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：