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

Leveraging Machine and Deep Learning algorithms for hERG Blocker prediction

引用

IEEE Access 2025年 13卷 81018-81028页

作者： Mohammad, Syed Chandrasekar, Vaisali Aboumarzouk, Omar Vikram Singh, Ajay Prasad Dakua, Sarada Hamad Medical Corporation Department of Surgery Doha Qatar Qatar University College of Medicine Doha Qatar Qatar University College of Health Sciences Doha Qatar Berlin10589 Germany

The human ether-a-go-go-related (hERG) gene is crucial in enabling the regulation of repolarisation process in the heart. Some chemicals act as hERG blockers, resulting in prolonged QT intervals. Predicting the binding capability of molecules with hERG channels is expected to reduce the burden of cardiotoxicity testing in drug evaluation. The application of machine learning (ML) and deep learning (DL) models in the field of toxicity has gained burgeoning interest. The current study utilises state-of-the-art ML and DL models for predicting the hERG-blocking ability of chemical compounds using a dataset of 8337 molecules. It is noted that spatial relationships within molecules are crucial in predicting hERG blockers. While the threshold for blockers is defined as ≤ 10 µM and for non-blockers, it is 10>μM, our analysis indicates that a threshold of 60- 80 µM provides a more accurate cut-off for non-blockers. This adjustment highlights the importance of concentration levels in reflecting the variability specific to individual interaction sites. The algorithm results show that the internal validation performance of RF, XGBoost, and MLP is strong, with AUC scores of 0.90, 0.90, and 0.87, respectively. In summary, the current study provides a machine learning framework for computation cardiotoxicity assessment by analysis of the hERG blocker concentration cut-offs using different fingerprints at multiple thresholds. © 2013 IEEE.

关键词： Fingerprint recognition Feature extraction Predictive models prediction algorithms Compounds Classification algorithms Chemicals Training Principal component analysis Drugs

来源：评论

学校读者我要写书评

暂无评论

A Feature-Aware Approach to Acupoint Compatibility prediction Using Residual Graph Attention Networks and Matrix Factorization

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第5期29卷 3750-3761页

作者： Li, Ruiling Pan, Ying Wu, Song Ma, Li Peng, Limei Hubei Univ Chinese Med Sch Informat Engn Wuhan 430065 Peoples R China Hubei Univ Chinese Med Sch Acupuncture Moxibust & Orthoped Wuhan 430065 Peoples R China Kyungpook Natl Univ Sch Comp Sci & Engn Daegu 41566 South Korea

Compatibility among acupoints is a fundamental principle in acupuncture treatment within traditional Chinese medicine, playing a vital role in enhancing the effectiveness and scope of therapeutic interventions. With the increasing availability of acupuncture-related data, link prediction offers a data-driven approach that facilitates the evidence-based exploration and validation of acupoint compatibilities. However, existing link prediction methods often focus on mapping acupoints and their compatibility relationships into lower-dimensional spaces. These approaches can overlook essential acupoint features and make the predictions susceptible to noise interference. To address these challenges, we propose a novel acupoint compatibility prediction model based on a Feature-Aware Residual Graph Attention Network and Matrix Factorization (FRGATMF). Our model introduces a feature-aware connectivity fusion strategy that integrates acupoint attributes with structural information to enrich acupoint representations. Following this, a deep non-negative matrix factorization approach is employed to construct a denoised feature matrix. This matrix is processed through a residual graph attention network to derive comprehensive and effective node embeddings, which are crucial for accurate link prediction. Experimental results on the acupuncture dataset, along with three public datasets, demonstrate that FRGATMF significantly outperforms seven existing comparison models across various evaluation metrics. Additionally, link prediction can identify previously unconsidered or undocumented acupoint combinations that may offer better therapeutic results, thus expanding the range of treatment options and highlighting its potential in improving the prediction of acupoint compatibility relationships.

关键词： Predictive models Acupuncture Noise Drugs Autoencoders Adaptation models Semantics prediction algorithms Diseases Biological system modeling Acupoint compatibility deep non-negative matrix factorization residual graph attention network link prediction

来源：评论

学校读者我要写书评

暂无评论

Application of Bidirectional Gated Recurrent Unit and Stacked Gated Recurrent Unit algorithms for Stock Price prediction

Application of Bidirectional Gated Recurrent Unit and Stacke...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Nasya Amirah Melyani Mustakim Angraini M. Afdal Department of Information Systems Faculty of Science and Technology Sultan Syarif Kasim State Islamic University of Riau Pekanbaru Indonesia Department of Information System Faculty of Science and Technology State Islamic University of Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Stocks are financial instruments that provide ownership rights and profits to their holders in public companies, which attract investors because of the potential for high returns despite the risks. Because stock price volatility is difficult to predict, accurate analysis techniques are needed to help investors make the right decisions, especially in the banking sector such as Bank Rakyat Indonesia. This study predicts the stock price of Bank Rakyat Indonesia (BBRI) using deep learning techniques, namely Bidirectional Gated Recurrent Unit (Bi-GRU) and Stacked Gated Recurrent Unit (Stacked GRU), which are chosen because of their ability to capture complex time series data patterns. BBRI stock data from 2018 to 2024 and from 2023 to 2024 were collected, processed, and divided into training and testing data with a ratio of 80:20. The Bi-GRU and Stacked GRU algorithms were optimized with Nadam, Adamax, AdamW, and SGDM, and evaluated using MSE, RMSE, and MAPE. As a result, 7-year data outperform 2-year data with the best algorithm Bi-GRU with Nadam optimization, batch size 8, and learning rate 0.001 giving the best performance with MSE 7283.1848, RMSE 85.3416, MAE 65.0879, and MAPE 1.2421%. The best prediction shows a decrease in BBRI stock prices in November 2024 which indicates a decrease towards the end of the year, thus providing valuable information for companies and investors in anticipating market behavior and making the right investment decisions.

关键词： Training Accuracy Time series analysis Companies Banking prediction algorithms Reliability Optimization Investment Testing

来源：评论

学校读者我要写书评

暂无评论

Review on Traffic prediction Framework Using Machine and Deep Learning algorithms

Review on Traffic Prediction Framework Using Machine and Dee...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： R. Anto Pravin Nancy Noella R S Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Management of road traffic and congestion is a critical feature of urban planning and infrastructure development. Traffic congestion has recently become a major problem on a global scale due to the rapid increase in industrialization and the number of vehicles on the road. Efficient traffic management not only enhances the flow of vehicles but also contributes to reducing fuel consumption, minimizing air pollution, and improving road safety. Traditional traffic management methods, which primarily rely on static models and historical data, have proven to be insufficient in handling the complexities of modern transportation systems. Therefore, there is a growing need for advanced techniques that can predict traffic patterns and optimize traffic flow in real time. Techniques of machine learning and deep learning have become increasingly effective in recent years for addressing the difficulties in controlling traffic and predictions. By influencing the vast amount of data generated from traffic sensors, GPS devices, and other sources, machine learning and deep learning algorithms can analyze, learn, and predict traffic conditions more accurately than traditional methods. These techniques are particularly effective in handling the dynamic and nonlinear nature of traffic flow, making them ideal for real-time applications in traffic control, congestion prediction, and incident management.

关键词： Deep learning Machine learning algorithms Heuristic algorithms Transportation Traffic control prediction algorithms Real-time systems Vehicle dynamics Traffic congestion Optimization

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Regression algorithms in Lung Cancer prediction

A Comparative Analysis of Regression Algorithms in Lung Canc...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Prakash Kumar Jha Avni Garg Ramachandran T Pavan Chaudhary Jitha Janardhanan Prabhjot Kaur Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India Department of Mechanical Engineering School of Engineering and Technology JAIN (Deemed to be University) Bangalore Karnataka Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Applications (DCA) Presidency College Bengaluru India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Results of All Cancers The mortality of lung cancer is highest among both international and domestic patients. Hence, early detection and accurate prediction are essential for treatment-affecting diagnoses to improve patient outcomes. Throughout the evolution of machine learning technologies, numerous regression algorithms have been introduced to predict lung cancer using clinical data or imaging datasets. In this work, we perform a comparison analysis among linear regression, logistic regression, and all commonly used decision-tree-based methods, including Decision Trees (CART), Random Forests, and Support Vector Machines for predicting lung cancer diagnosis and prognosis. We use patient data from two hospitals, including age, smoking information, lung function tests, and imaging results, to perform the analysis. Our results suggest that random forest and support vector machines generally offer the best accuracy, sensitivity, and specificity in diagnosis and prognosis prediction. Decision tree algorithms also do but depend heavily on the feature set chosen. In addition, we show improved performance in predicting placebo response by combining different data sources. Our study demonstrates that selecting regression algorithms are critical in lung cancer prediction and that combining multiple data types can improve accuracy. Realizing this potential requires accurate prediction algorithms, which are not currently available; such information can lead to better-developed forecast models and improved lung cancer patients' diagnoses and outcomes.

关键词： Support vector machines Logistic regression Accuracy Linear regression Lung cancer Imaging prediction algorithms Decision trees Prognostics and health management Random forests

来源：评论

学校读者我要写书评

暂无评论

User Behavior prediction Model Based on Deep Learning algorithms in the Digital Economy Environment

User Behavior Prediction Model Based on Deep Learning Algori...

引用

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

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

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

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：