检索结果-内蒙古大学图书馆

Coupling input feature construction methods and machine learning algorithms for hourly secondary supply temperature prediction

引用

ENERGY 2023年第1期278卷

作者： Ling, Jihong Zhang, Bingyang Dai, Na Xing, Jincheng Tianjin Univ Sch Environm Sci & Engn Tianjin Peoples R China Tianjin Univ Sch Environm Sci & Engn Tianjin Key Lab Indoor Air Environm Qual Control Tianjin 300350 Peoples R China Tianjin Univ Tianjin Key Lab Built Environm & Energy Applicat Tianjin 300350 Peoples R China

Accurate supply temperature prediction plays a vital role in achieving meticulous management of heating sta-tion. However, there are relatively few studies on ultra-short-term supply temperature prediction at present. This paper comprehensively applied 4 feature selection methods and 3 prediction algorithms to estimate hourly secondary supply temperature. Taking a floor radiant heating system as the case, the correlation analysis (CA) based on the back propagation neural network (BPNN) model and the support vector regression (SVR) model shows that outdoor temperature, supply and return temperatures are the main input feature categories. This paper novelty proposed the categorical principal component analysis (CPCA) method, compared with the traditional principal component analysis (PCA), this method can reduce the root mean square error (RMSE) of BPNN model and SVR model by an average of 18.6% and 19.7%, respectively. The comparison of 4 historical input lengths for the long and short-term memory (LSTM) model shows that historical 12 h can fully consider the influence of building thermal inertia and heating system thermal delay for floor radiant. Further comprehensive comparison shows that the BPNN model based on correlation analysis has the best performance.

关键词： Secondary supply temperature prediction Input feature construction prediction algorithms Categorical principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Congestion Control prediction Model for 5G Environment Based on Supervised and Unsupervised Machine Learning Approach

引用

IEEE ACCESS 2024年 12卷 91127-91139页

作者： Alshawki, Mohammed B. Najm, Ihab Ahmed Hamoud, Alaa Khalaf Univ Kufa Dept Comp Sci Najaf 54003 Iraq Eotvos Lorand Univ Dept Comp Algebra H-1053 Budapest Hungary Univ Tikrit Dept Math Tikrit 43000 Iraq Univ Basrah Dept Cybersecur Basrah 61004 Iraq

With the emergence of 5G technology, congestion control has become a vital challenge to be addressed in order to have efficient communication. There are several congestion control models that have been proposed to control and predict the possible congestion in 5G technology. However, finding the optimal congestion control model is an important yet challenging task. In this paper, we examine the supervised and unsupervised machine learning approaches to the task of predicting the possible node that causes congestion in the 5G environment. Due to the huge variance in the domains of the data set columns, measuring the prediction's consistency was not an easy task. During our study, we tested twenty-six supervised and seven clustering algorithms. Finally, and based on the performance criteria, we have identified the best five algorithms out of the studied algorithms.

关键词： 5G mobile communication Machine learning algorithms prediction algorithms Classification algorithms Clustering algorithms Random forests Predictive models Unsupervised learning Supervised learning Machine learning congestion control 5G supervised ML unsupervised ML

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning for Detection and prediction of Chronic Diseases

引用

IEEE ACCESS 2024年 12卷 177674-177691页

作者： Yanes, Nacim Jamel, Leila Alabdullah, Bayan Ezz, Mohamed Mohamed Mostafa, Ayman Shabana, Hossameldeen Manouba Univ RIADI Lab Manouba 2010 Tunisia Gabes Univ Higher Inst Management Gabes Gabes 6033 Tunisia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia Jouf Univ Coll Comp & Informat Sci Sakaka 72388 Saudi Arabia Shaqra Univ Coll Med Shaqra 11961 Saudi Arabia

Heart attacks are a leading cause of mortality worldwide, necessitating the development of accurate predictive models to enhance early detection and intervention strategies. This study addresses the significant problem of class imbalance in medical datasets, specifically focusing on heart attack prediction using the Behavioral Risk Factor Surveillance System (BRFSS) dataset. To tackle this challenge, advanced machine learning (ML) methods are proposed to involve a refined dataset of 399,875 instances, with 47 significant features maintained through rigorous data cleaning and preparation. Balanced accuracy and macro-recall were chosen as primary metrics to ensure fair performance evaluation across classes in the imbalanced dataset. Our proposed system entails a detailed evaluation of various algorithms known for their effectiveness in managing class imbalance. The LGBM Classifier, XGB Classifier, and Logistic Regression (LR) are optimized using recursive feature elimination and hyperparameter tuning with Optuna. The results of this study are encapsulated in an ensemble model that significantly enhances predictive accuracy. The final model achieved 80.75% balanced accuracy and 79.97% recall for critical heart attack cases (class 1), along with an AUC score of 88.9%, indicating superior class distinction capability. Additionally, the application of SHAP (SHapley Additive exPlanations) analysis provided valuable insights into the contribution of each feature to heart attack likelihood, thus improving model transparency. This study's successful integration of complex ML techniques with interpretability analyses like SHAP marks a substantial advance in early detection and intervention strategies in healthcare. It demonstrates the potential of sophisticated ML approaches for early heart attack detection and prevention, highlighting their value in improving outcomes for patients with chronic diseases. These findings suggest promising pathways for employing advanced analytic

关键词： Predictive models Accuracy Cardiac arrest Diseases Heart Medical services Data models prediction algorithms Classification algorithms Tuning Heart attack prediction ensemble model chronic diseases class imbalance ML classifiers model transparency

来源：评论

学校读者我要写书评

暂无评论

Piecewise Congruence Regressed Indexive Extreme Learning Classifier for Software Fault prediction

引用

IEEE ACCESS 2024年 12卷 119958-119972页

作者： Sivavelu, Sureka Palanisamy, Venkatesh Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore 632014 India

Software fault prediction is a significant task in software development to discover faults early. It is the process of developing models that can be used by the software practitioners in the early phases of software development life cycle for detecting faulty constructs such as modules or classes. Therefore, early fault prediction is a critical and challenging task faced by the Project managers. Several kinds of approaches were utilized to predict software faults. In this work we propose a Piecewise Congruence Regressed Indexive Extreme Learning Classifier (PRILEC) to predict the software faults accurately. The process consists of two stages namely feature selection or software metric selection and classification. In feature selection process, congruence correlative piecewise regression method is utilized to extract the most relevant features from the given input dataset. In the next phase, statistical indexive levenberg extreme learning classifier is utilized to classify the fault prediction with better accuracy. The testing and training data analysis in extreme learning classifiers is evaluated using Camargo's statistical index. Hardlimit activation function is utilized to identify the faulty or non-faulty software code. The least square problem can be minimized using Levenberg-Marquardt algorithm and this algorithm can obtain the better classification results. The performance of the proposed approach is evaluated using software fault prediction data analysis dataset. The evaluation metrics such as precision, recall, F-measure, and specificity were used to assess the performance of the proposed algorithm. It was observed that compared with the state-of-the-art traditional methods (Linear regression), proposed technique increases data accuracy of software fault prediction. The system reduces the fault detection time by 4%, 2%, 2%, 2%, 29% and 21% respectively.

关键词： Feature extraction Accuracy Software algorithms Predictive models prediction algorithms Testing Fault diagnosis Extreme learning machines Software fault prediction congruence coefficient piecewise regression statistical indexive Levenberg extreme learning classifier Camargo's statistical index Hardlimit activation function

来源：评论

学校读者我要写书评

暂无评论

prediction of Chemical Compounds Biodegradability: Molecular Fingerprint-Based Machine Learning Models

引用

IEEE ACCESS 2024年 12卷 135577-135588页

作者： Elsayad, Alaa M. Zeghid, Medien Ahmed, Hassan Yousif Elsayad, Khaled A. Prince Sattam Bin Abdulaziz Univ Coll Engn Wadi Alddawasir Dept Elect Engn Wadi Alddawasir 11991 Saudi Arabia Univ Monastir Fac Sci Elect & Microelect Lab Monastir 5000 Tunisia Cairo Univ Cairo Univ Hosp Pharm Dept Cairo 11662 Egypt

This work evaluates the performance of four machine learning models (MLMs): support vector machine (SVM), K-nearest neighbor (KNN), discriminant analysis (DA), and logistic regression (LR) in predicting the biodegradability of chemicals, a critical factor for assessing environmental risks. For this purpose, the RDKit library was initially employed to extract nine fingerprints from a dataset consisting of 1717 chemical compounds. Subsequently, the Information Gain (IG) feature ranking algorithm was used to identify the top 100 predictive features for each fingerprint. The MLM Hyperparameters were optimized, and informative features were selected using a multi-objective genetic algorithm (MOGA), which identified dominant pairs (MLM/fingerprint) maximizing F1-score while minimizing number of features. MACCS, Layered, and Avalon molecular fingerprints associated with the different MLM showed superior performance, with KNN/MACCS achieving a cross-validated F1-score of 87.63% using only 13 features. Afterwards, the final classification models were constructed using the solution with the highest cross-validated F1-score complement for each combination of MLM/fingerprint. These models were then evaluated on both the training and test datasets. In the training subset, the MACCS fingerprint consistently outperformed others, achieving cross-validated AUC scores above 90% for all models (SVM: 91%, KNN: 90.4%, DA: 90.9%, LR: 91.32%). The SVM/MACCS pair demonstrated the highest accuracy (94.17%), specificity (95.84%), and F1-score (93.14%). In the test subset, the SVM/Layered pair exhibited the highest accuracy (84.01%) and specificity (88.09%). The DA/Avalon combination achieved the highest sensitivity (84.40%), while the SVM/Avalon pair reached the highest F1-score (82.58%). These results underscore the effectiveness of MACCS fingerprints for biodegradation classification across various models. Additionally, Permutation Feature Importance (PFI) and Shapley Additive Explanations

关键词： Biological system modeling Predictive models Fingerprint recognition Chemicals Support vector machines Feature extraction prediction algorithms Biodegradable materials Classification algorithms Risk management Genetic algorithms Biodegradability prediction classification models environmental risk assessment molecular fingerprints genetic algorithm feature ranking RDKit library sustainable chemical design permutation feature importance Shapley additive explanations

来源：评论

学校读者我要写书评

暂无评论

A Fusion Intelligent Degradation Interval prediction Method Based on Hybrid Health Indicator for Proton Exchange Membrane Fuel Cells

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第4期10卷 9839-9851页

作者： Li, Haolong Liu, Li Zhang, Liyan Xie, Liang Chen, Qihong Wuhan Univ Technol Sch Automat Wuhan 430070 Peoples R China Wuhan Univ Technol Sch Sci Wuhan 430070 Peoples R China

The degradation state is a critical specification reflecting the health of proton exchange membrane fuel cells (PEMFCs). Uncertainty factors associated with PEMFC make traditional data-driven method difficult to accurately predict the decay behavior of fuel cells. To address the problem, a fusion interval prediction method based on hybrid health indicators (HIs) and quantile regression (QR)-bidirectional gated recurrent unit (BiGRU) is proposed to quantify the uncertainty of PEMFC decay. First, a hybrid HI is developed to characterize the decay behavior of PEMFCs under static and dynamic operating conditions. Second, a QR-BiGRU interval prediction model is proposed to forecast the fluctuation range of PEMFC degradation through constructing intervals of different quantities. Third, the sparrow search algorithm is utilized to search for the optimal hyperparameters of the QR-BiGRU and to reduce interval prediction model complexity. Finally, the upper and lower bounds of the prediction intervals are obtained by linearly weighting the combination of the predicted values of different QRs to realize the multistep interval prediction of PEMFC decay. The performance of the fusion interval prediction method for quantifying decay uncertainty is verified based on real PEMFC durability experimental data. The prediction error of the fusion interval prediction method static and dynamic operating conditions is only 0.13% and 0.18%. Compared with three popular prediction methods, the fusion interval prediction method can accurately quantify the uncertainty of degradation, which is important for the energy management of PEMFC.

关键词： Predictive models Degradation Uncertainty Fuel cells prediction algorithms Load modeling Transportation Bidirectional gated recurrent unit (BiGRU) fusion interval prediction hybrid health indicator (HI) proton exchange membrane fuel cells (PEMFCs) sparrow search algorithm (SSA)

来源：评论

学校读者我要写书评

暂无评论

Road Traffic Accident Risk prediction and Key Factor Identification Framework Based on Explainable Deep Learning

引用

IEEE ACCESS 2024年 12卷 120597-120611页

作者： Pei, Yulong Wen, Yuhang Pan, Sheng Northeast Forestry Univ Sch Civil Engn & Transportat Harbin 150040 Peoples R China

The prediction and identification of key factors in road traffic accidents are crucial for accident prevention, yet previous studies have often examined these aspects separately. To comprehensively assess the risk level of road traffic accidents and their key determinants, this paper proposes a comprehensive forecasting and analysis framework that offers a novel perspective for identifying key risk factors from a modeling standpoint compared to existing methods. The CNN-BiLSTM-Attention model was developed for predicting the risk value of road accidents, and DeepSHAP was employed to interpret the model and extract the key factors contributing to traffic accidents. This deep learning framework combines convolutional neural networks (CNN) and Bi-directional long short-term memory (BiLSTM), while incorporating a spatial-temporal local attention mechanism to enhance its capability in capturing spatiotemporal features. Through analysis and experimentation on real-world datasets, our model demonstrates superior accuracy in predicting traffic accident risk compared to the benchmark model, achieving a Mean Absolute Error (MAE) of 0.2475 on the UK dataset and 0.2683 on the US dataset. The results obtained from DeepSHAP were found to be more rational and informative in identifying key factors of different severity levels using four methods. To verify the rationality and stability of obtaining these key factors, the first 15 factors were reintegrated into the prediction model, resulting in almost unchanged accuracy and reduced model iteration time. By improving the influential factors, road traffic accidents can be effectively mitigated.

关键词： Accidents Predictive models Analytical models Data models Machine learning prediction algorithms Deep learning Traffic control Explainable AI Traffic accidents risk prediction explainability deep learning

来源：评论

学校读者我要写书评

暂无评论

Water Level prediction of Firewater System Based on Improved Hybrid LSTM Algorithm

引用

IEEE ACCESS 2024年 12卷 130305-130316页

作者： Li, Wenlei Gao, Tianyi Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 210016 Peoples R China Avic Jincheng Nanjing Engn Inst Aircraft Syst Nanjing 211106 Peoples R China

Aiming at the incomplete data and difficult prediction in the prediction of firewater system water level, a data filling method is proposed based on the reinforcement learning approach and a deep learning (DL) prediction method is studied based on the long-term short-term memory (LSTM) model in this paper. Firstly, a reinforcement learning-based K-nearest neighbor (KNN) algorithm is designed for the data incompleteness that occurs in the firewater level. The parameters of the KNN algorithm are optimized through the reinforcement learning to enhance the accuracy of data filling. Secondly, to compensate for the shortcomings of the traditional firewater pool level prediction methods, a DL prediction method based on the LSTM network approach is proposed by using the complete data. Through the LSTM three gate functions, the previous information is rounded to avoid causing gradient explosion, rounding the method is more stable and accurate. Finally, the simulation results show that the proposed method in this paper can effectively predict incomplete water level information.

关键词： prediction algorithms Nearest neighbor methods Long short term memory Predictive models Accuracy Reinforcement learning Data models Deep learning Firewater system LSTM deep learning K-nearest neighbors reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Synchronous Bi-Directional Framework With Temporally Dependent Interaction Modeling for Pedestrian Trajectory prediction

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第1期11卷 793-806页

作者： Li, Yuanman Xie, Ce Liang, Rongqin Du, Jie Zhou, Jiantao Li, Xia Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Sch Biomed Engn Natl Reg Key Technol Engn Lab Med Ultrasound Guangdong Key Lab Biomed Measurements & Ultrasound Shenzhen 518060 Peoples R China Univ Macau Fac Sci & Technol Dept Comp & Informat Sci Macau 999078 Peoples R China

As an essential part of motion behavior modeling, pedestrian trajectory forecasting with social interactions has become an increasingly important problem in many applications, such as visual navigation and intelligent video surveillance. Most existing methods adopt autoregressive frameworks to forecast the future trajectory, where the trajectory is iteratively generated based on the preceding outputs. Such a process suffers from large accumulated errors over long-term forecasting. To address this issue, in this work, we propose a synchronous bi-directional framework for pedestrian trajectory prediction, where the predicting procedures for two opposite directions are forced to be synchronous through a shared motion characteristic. Unlike previous works, the mutual constraints inherent to our framework from the synchronous opposite predictions can significantly prevent error accumulation. In addition, we devise a temporally dependent interaction model to learn the complex social interactions among pedestrians from correlated historical trajectories. By resorting to a temporally dependent attention scheme and a progressive temporal fusion method, our interaction model can effectively reveal the interacting influence among pedestrians across temporal domains, and also capture the long-term dependencies of the historical trajectory. Experiments conducted on the ETH-UCY benchmark and the Stanford Drone dataset show that our method achieves much better results than existing algorithms. Particularly, our scheme exhibits superior performance in long-term pedestrian trajectory prediction.

关键词： Trajectory Pedestrians Predictive models Behavioral sciences Bidirectional control prediction algorithms Task analysis Motion behavior modeling social interactions social behaviors deep networks trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

Potential microRNA-Disease Association prediction Using Node2vec and Singular Value Decomposition

引用

IEEE ACCESS 2024年 12卷 110563-110574页

作者： Liu, Yunxia Lin, Jiazhen Liang, Pin Tian, Yayu He, Xuan Northeastern Univ Coll Med & Biol Informat Engn Shenyang 110819 Peoples R China

Many biological studies show that microRNAs (miRNAs) play an indispensable role in the regulation of various biological processes. MiRNAs are significant biomakers in disease diagnosis, aiding in the understanding of pathogenesis and facilitating the identification, diagnosis, and treatment of various diseases. However, the exact mechanism by which miRNAs influence the development of these diseases remains incompletely understood. Thus, it is crucial to develop a computational method to identify unknown miRNA-disease associations. In this study, we designed a computational framework based on singular value decomposition (SVD) and node2vec to predict unknown miRNA-disease associations (SNMDA). We use SVD technique to extract the linear features of miRNAs and diseases. The node2vec method is applied to learn the non-linear embeddings of miRNAs and diseases. We combine the linear feature and non-linear feature to get a new feature vector and feed it into the Gradient Boosting (GB) classifier for binary classification prediction. According to the experimental findings, SNMDA demonstrated an average area under the curve (AUC) of 0.9608 during five-fold cross-validation. Compared with the other Cutting-edge methods, SNMDA achieved the highest AUC value. Furthermore, the case studies on gastric cancer, malignant esophageal lesions, and lung tumors validate the effectiveness of SNMDA. The comprehensive experimental results demonstrate that SNMDA is effective in identifying unknown miRNA-disease associations.

关键词： Diseases Predictive models Semantics Feature extraction Databases Computational modeling prediction algorithms Node2vec singular value decomposition miRNA-disease association prediction linear feature non-linear feature

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：