Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the sett...Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the settlement caused by tunneling.However,well-performing ML models are usually less interpretable.Irrelevant input features decrease the performance and interpretability of an ML model.Nonetheless,feature selection,a critical step in the ML pipeline,is usually ignored in most studies that focused on predicting tunneling-induced settlement.This study applies four techniques,i.e.Pearson correlation method,sequential forward selection(SFS),sequential backward selection(SBS)and Boruta algorithm,to investigate the effect of feature selection on the model’s performance when predicting the tunneling-induced maximum surface settlement(S_(max)).The data set used in this study was compiled from two metro tunnel projects excavated in Hangzhou,China using earth pressure balance(EPB)shields and consists of 14 input features and a single output(i.e.S_(max)).The ML model that is trained on features selected from the Boruta algorithm demonstrates the best performance in both the training and testing phases.The relevant features chosen from the Boruta algorithm further indicate that tunneling-induced settlement is affected by parameters related to tunnel geometry,geological conditions and shield operation.The recently proposed Shapley additive explanations(SHAP)method explores how the input features contribute to the output of a complex ML model.It is observed that the larger settlements are induced during shield tunneling in silty clay.Moreover,the SHAP analysis reveals that the low magnitudes of face pressure at the top of the shield increase the model’s output。展开更多
Objective： To explore the core acupoints and combination rules of auricular acupoint therapy for simple obesity, and to further analyze the characteristics of the prescription of auricular acupoint therapy for simple...Objective： To explore the core acupoints and combination rules of auricular acupoint therapy for simple obesity, and to further analyze the characteristics of the prescription of auricular acupoint therapy for simple obesity.Methods： Relevant clinical study literature in recent 30 years in PubMed, China Biology Medicine disc（CBM）, China National Knowledge Infrastructure（CNKI）, Wan Fang Database. VIP Database and TCM Online Database was retrieved, and eligible articles were selected in order to build a prescription database of auricular acupoint therapy for simple obesity. On the basis of complex network techniques, the core acupoints and combination rules of auricular acupoint therapy for simple obesity were analyzed, and the characteristics of auricular acupoint therapy for simple obesity were analyzed comprehensively.Results： There were 46 network nodes of auricular acupoint. The top 16 core acupoints for auricular acupoint therapy for simple obesity included Nèifēnmì（内分泌CO18）, Pí（脾CO13）, Wèi（胃CO4）, Sānjiāo（三焦CO17）, Jīdiǎn（饥点）.Shénmén（神门TF4）. Dàcháng（大肠CO7）. Pízhìxià（皮质下AT4）. Fèi（肺CO14）. Shèn（肾CO10）. Jiāogǎn（交感AH6 a）, Kǒu（口CO1）,Gān（肝CO12）. Xiǎocháng（小肠CO6） and Nǎo（脑）. The combination of auricular acupoints was mainly based on the main indications of acupoints. The analysis of auricular acupoints combination indicated that the combination of CO4 with CO18 was applied most frequently, which was followed by the combinations of CO13 with CO18 and CO13 with C04. According to the analysis of auricular acupoint stimulation methods, ear point taping and pressing with Wángbùliúxíng（王不留行,Semen Vaccariae） seeds was used frequently, which was followed by magnetic beads taping and pressing and pyonex therapy. Auricular acupoint therapy combined with acupuncture for simple obesity was used most commonly, which was followed by auricular acupoint therapy combined with catgut embedment in acupoint and simple auricular acupoint therapy.Conclusion： In this study, the core acupoints and combinations of auricular acupoint therapy for simple obesity were explored effectively, and the pressing materials and major combined intervention methods were summarized and analyzed, thus providing references and treatment thoughts in terms of the point and prescription selection of auricular acupoint therapy for simple obesity.展开更多
基金support provided by The Science and Technology Development Fund,Macao SAR,China(File Nos.0057/2020/AGJ and SKL-IOTSC-2021-2023)Science and Technology Program of Guangdong Province,China(Grant No.2021A0505080009).
文摘Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the settlement caused by tunneling.However,well-performing ML models are usually less interpretable.Irrelevant input features decrease the performance and interpretability of an ML model.Nonetheless,feature selection,a critical step in the ML pipeline,is usually ignored in most studies that focused on predicting tunneling-induced settlement.This study applies four techniques,i.e.Pearson correlation method,sequential forward selection(SFS),sequential backward selection(SBS)and Boruta algorithm,to investigate the effect of feature selection on the model’s performance when predicting the tunneling-induced maximum surface settlement(S_(max)).The data set used in this study was compiled from two metro tunnel projects excavated in Hangzhou,China using earth pressure balance(EPB)shields and consists of 14 input features and a single output(i.e.S_(max)).The ML model that is trained on features selected from the Boruta algorithm demonstrates the best performance in both the training and testing phases.The relevant features chosen from the Boruta algorithm further indicate that tunneling-induced settlement is affected by parameters related to tunnel geometry,geological conditions and shield operation.The recently proposed Shapley additive explanations(SHAP)method explores how the input features contribute to the output of a complex ML model.It is observed that the larger settlements are induced during shield tunneling in silty clay.Moreover,the SHAP analysis reveals that the low magnitudes of face pressure at the top of the shield increase the model’s output。
基金Supported by special program of scientific research in Traditional Chinese Medicine in 2015(201507003)National Natural Science Foundation of China(81674081)~~
文摘Objective： To explore the core acupoints and combination rules of auricular acupoint therapy for simple obesity, and to further analyze the characteristics of the prescription of auricular acupoint therapy for simple obesity.Methods： Relevant clinical study literature in recent 30 years in PubMed, China Biology Medicine disc（CBM）, China National Knowledge Infrastructure（CNKI）, Wan Fang Database. VIP Database and TCM Online Database was retrieved, and eligible articles were selected in order to build a prescription database of auricular acupoint therapy for simple obesity. On the basis of complex network techniques, the core acupoints and combination rules of auricular acupoint therapy for simple obesity were analyzed, and the characteristics of auricular acupoint therapy for simple obesity were analyzed comprehensively.Results： There were 46 network nodes of auricular acupoint. The top 16 core acupoints for auricular acupoint therapy for simple obesity included Nèifēnmì（内分泌CO18）, Pí（脾CO13）, Wèi（胃CO4）, Sānjiāo（三焦CO17）, Jīdiǎn（饥点）.Shénmén（神门TF4）. Dàcháng（大肠CO7）. Pízhìxià（皮质下AT4）. Fèi（肺CO14）. Shèn（肾CO10）. Jiāogǎn（交感AH6 a）, Kǒu（口CO1）,Gān（肝CO12）. Xiǎocháng（小肠CO6） and Nǎo（脑）. The combination of auricular acupoints was mainly based on the main indications of acupoints. The analysis of auricular acupoints combination indicated that the combination of CO4 with CO18 was applied most frequently, which was followed by the combinations of CO13 with CO18 and CO13 with C04. According to the analysis of auricular acupoint stimulation methods, ear point taping and pressing with Wángbùliúxíng（王不留行,Semen Vaccariae） seeds was used frequently, which was followed by magnetic beads taping and pressing and pyonex therapy. Auricular acupoint therapy combined with acupuncture for simple obesity was used most commonly, which was followed by auricular acupoint therapy combined with catgut embedment in acupoint and simple auricular acupoint therapy.Conclusion： In this study, the core acupoints and combinations of auricular acupoint therapy for simple obesity were explored effectively, and the pressing materials and major combined intervention methods were summarized and analyzed, thus providing references and treatment thoughts in terms of the point and prescription selection of auricular acupoint therapy for simple obesity.
