检索结果-南通市图书馆

Novel rockburst prediction criterion with enhanced explainability employing CatBoost and nature-inspired metaheuristic technique

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Underground Space 2024年第6期19卷 101-118页

作者： Yingui Qiu Jian Zhou School of Resources and Safety Engineering Central South UniversityChangsha 410083China

Rockburst is a major challenge to hard rock engineering at great *** and timely assessment of rockburst risk can avoid unnecessary casualties and property *** the existence of various methods for rockburst assessment,there remains an urgent need for a comprehensive and reliable criterion that is easy to both apply and *** a new rockburst criterion based on simple parameters can potentially fill this *** its advantages,this criterion can facilitate a more effective and efficient prediction of rockburst potential,thereby contributing significantly to enhancing safety *** this paper,combined with the internal and external factors of rockburst,four control variables(i.e.,integrity index,stress index,brittleness index,and elastic energy index)were selected to be incorporated into a comprehensive rockburstability index(RBSI).Based on 116 sets of rockburst cases,the rockburst potential was accurately quantified and predicted using the categorical boosting(CatBoost)model and the nature-inspired metaheuristic African vultures optimization algorithm(AVOA).In its performance validation,the criterion achieved the highest accuracy of 90.48%,verifying the reliability and effectiveness of the proposed RBSI ***,an interpretive method was applied to analyze the variable influence on the criterion,facilitating the explanation of predictions and the analysis of the formula’s robustness under different *** general,compared with existing criterion methods involving relevant indicators,the newly proposed RBSI criterion enhances the accuracy of rockburst potential prediction,and it can effectively and swiftly evaluate the preliminary risk of ***,a graphical user interface was developed to provide a clear visualization of the assessment of rockburst potential.

关键词： Rockburst criterion CatBoost Metaheuristic optimization model interpretation Graphical user interface

Data-driven glass-forming ability criterion for bulk amorphous metals with data augmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2022年第26期121卷 99-104页

作者： Jie Xiong Tong-Yi Zhang School of Materials Science and Engineering Harbin Institute of TechnologyShenzhen 518000China Hong Kong University of Science and Technology(Guangzhou) Guangzhou 511400China Material Genome Institute Shanghai UniversityShanghai 200444China

A data augmentation technique is employed in the current work on a training dataset of 610 bulk metallic glasses(BMGs),which are randomly selected from 762 collected *** ensemble machine learning(ML)model is developed on augmented training dataset and tested by the rest 152 *** result shows that ML model has the ability to predict the maximal diameter Dmaxof BMGs more accurate than all reported ML *** addition,the novel ML model gives the glass forming ability(GFA)rules:average atomic radius ranging from 140 pm to 165 pm,the value of TT/(T-T)(T-T)being higher than 2.5,the entropy of mixing being higher than 10 J/K/mol,and the enthalpy of mixing ranging from-32 k J/mol to-26 k J/*** model is interpretative,thereby deepening the understanding of GFA.

关键词： Materials informatics Glass-forming ability Data augmentation model interpretation Meta-ensemble model

End-to-end data-driven modeling framework for automated and trustworthy short-term building energy load forecasting

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2024年第8期17卷 1419-1437页

作者： Chaobo Zhang Jie Lu Jiahua Huang Yang Zhao Department of the Built Environment Eindhoven University of TechnologyEindhovenThe Netherlands Energy Efficient Cities Initiative Department of EngineeringUniversity of CambridgeCambridgeUK Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Institute of Green Building and Engineering Design Zhejiang Province Institute of Architectural Design and Research Co.Ltd.HangzhouChina Key Laboratory of Clean Energy and Carbon Neutrality of Zhejiang Province Jiaxing Research InstituteZhejiang UniversityJiaxingChina

Conventional automated machine learning(AutoML)technologies fall short in preprocessing low-quality raw data and adapting to varying indoor and outdoor environments,leading to accuracy reduction in forecasting short-term building energy ***,their predictions are not transparent because of their black box ***,the building field currently lacks an AutoML framework capable of data quality enhancement,environment self-adaptation,and model *** address this research gap,an improved AutoML-based end-to-end data-driven modeling framework is *** optimization is applied by this framework to find an optimal data preprocessing process for quality improvement of raw *** bridges the gap where conventional AutoML technologies cannot automatically handle missing data and outliers.A sliding window-based model retraining strategy is utilized to achieve environment self-adaptation,contributing to the accuracy enhancement of AutoML ***,a local interpretable model-agnostic explanations-based approach is developed to interpret predictions made by the improved *** overcomes the poor interpretability of conventional AutoML *** performance of the improved framework in forecasting one-hour ahead cooling loads is evaluated using two-year operational data from a real *** is discovered that the accuracy of the improved framework increases by 4.24%–8.79%compared with four conventional frameworks for buildings with not only high-quality but also low-quality operational ***,it is demonstrated that the developed model interpretation approach can effectively explain the predictions of the improved *** improved framework offers a novel perspective on creating accurate and reliable AutoML frameworks tailored to building energy load prediction tasks and other similar tasks.

关键词： building energy load forecasting end-to-end data-driven modeling automated machine learning Bayesian optimization model retraining model interpretation

Data Information integrated Neural Network (DINN) algorithm for modelling and interpretation performance analysis for energy systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2024年第2期16卷 306-315页

作者： Waqar Muhammad Ashraf Vivek Dua The Sargent Centre for Process Systems Engineering Department of Chemical EngineeringUniversity College LondonTorrington PlaceLondon WC1E 7JEUK

Developing a well-predictive machine learning model that also offers improved interpretability is a key challenge to widen the application of artificial intelligence in various application domains. In this work, we present a Data Information integrated Neural Network (DINN) algorithm that incorporates the correlation information present in the dataset for the model development. The predictive performance of DINN is also compared with a standard artificial neural network (ANN) model. The DINN algorithm is applied on two case studies of energy systems namely energy efficiency cooling (ENC) & energy efficiency heating (ENH) of the buildings, and power generation from a 365 MW capacity industrial gas turbine. For ENC, DINN presents lower mean RMSE for testing datasets (RMSE_test = 1.23 %) in comparison with the ANN model (RMSE_test = 1.41 %). Similarly, DINN models have presented better predictive performance to model the output variables of the two case studies. The input perturbation analysis following the Gaussian distribution for noise generation reveals the order of significance of the variables, as made by DINN, can be better explained by the domain knowledge of the power generation operation of the gas turbine. This research work demonstrates the potential advantage to integrate the information present in the data for the well-predictive model development complemented with improved interpretation performance thereby opening avenues for industry-wide inclusion and other potential applications of machine learning.

关键词： Explainable AI model interpretation Scientific machine learning Artificial neural network Loss function

Trusted Encrypted Traffic Intrusion Detection Method Based on Federated Learning and Autoencoder

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第8期21卷 211-235页

作者： Wang Zixuan Miao Cheng Xu Yuhua Li Zeyi Sun Zhixin Wang Pan School of Modern Posts Nanjing University of Posts&TelecommunicationsNanjing 210003China School of Computer Science Nanjing University of Posts&TelecommunicationsNanjing 210003China

With the rapid development of the Internet,network security and data privacy are increasingly *** classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detection accuracy,but collecting samples for centralized training brings the huge risk of data privacy ***,the training of supervised deep learning models requires a large number of labeled samples,which is usually ***“black-box”problem also makes the DL models of NIDS *** this paper,we propose a trusted Federated Learning(FL)Traffic IDS method called FL-TIDS to address the above-mentioned *** FL-TIDS,we design an unsupervised intrusion detection model based on autoencoders that alleviates the reliance on marked *** the same time,we use FL for model training to protect data *** addition,we design an improved SHAP interpretable method based on chi-square test to perform interpretable analysis of the trained *** conducted several experiments to evaluate the proposed *** first determine experimentally the structure and the number of neurons of the unsupervised AE ***,we evaluated the proposed method using the UNSW-NB15 and CICIDS2017 *** exper-imental results show that the unsupervised AE model has better performance than the other 7 intrusion detection models in terms of precision,recall and ***,federated learning is used to train the intrusion detection *** experimental results indicate that the model is more accurate than the local learning ***,we use an improved SHAP explainability method based on Chi-square test to analyze the *** analysis results show that the identification characteristics of the model are consistent with the attack characteristics,and the model is reliable.

关键词： autoencoder federated learning intrusion detection model interpretation unsupervised learning

An ensemble machine learning model to uncover potential sites of hazardous waste illegal dumping based on limited supervision experience

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Fundamental Research 2024年第4期4卷 972-978页

作者： Jinghua Geng Yimeng Ding Wenjun Xie Wen Fang Miaomiao Liu Zongwei Ma Jianxun Yang Jun Bi State Key Laboratory of Pollution Control and Resource Reuse School of the EnvironmentNanjing UniversityNanjing 210023 China

With the soaring generation of hazardous waste(HW)during industrialization and urbanization,HW illegal dumping continues to be an intractable global *** in developing regions with lax regulations,it has become a major source of soil and groundwater *** dominant challenge for HW illegal dumping supervision is the invisibility of dumping sites,which makes HW illegal dumping difficult to be found,thereby causing a long-term adverse impact on the *** to utilize the limited historic supervision records to screen the potential dumping sites in the whole region is a key challenge to be *** this study,a novel machine learning model based on the positive-unlabeled(PU)learning algorithm was proposed to resolve this problem through the ensemble method which could iteratively mine the features of limited historic *** of the random forest-based PU model showed that the predicted top 30%of high-risk areas could cover 68.1%of newly reported cases in the studied region,indicating the reliability of the model *** novel framework will also be promising in other environmental management scenarios to deal with numerous unknown samples based on limited prior experience.

关键词： Hazardous waste Illegal dumping site Positive-unlabeled machine learning Probability prediction model interpretation