Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground st...Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.展开更多
Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are iden...Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are identified.Challenges in analysing small datasets are discussed,and solution is proposed to handle small datasets with multiple variables.Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity.The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability.Metallurgical-property relationships between chemistry,sample size,and hardness are predicted via two optimized machine learning algorithms:neural networks(NNs)and extreme gradient boosting(XGboost).A comparison is drawn between all algorithms,evaluating their performance based on small data sets.The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.展开更多
Efficient and accurate segmentation of complex microstructures is a critical challenge in establishing process-structure-property(PSP) linkages of materials. Deep learning(DL)-based instance segmentation algorithms sh...Efficient and accurate segmentation of complex microstructures is a critical challenge in establishing process-structure-property(PSP) linkages of materials. Deep learning(DL)-based instance segmentation algorithms show potential in achieving this goal.However, to ensure prediction reliability, the current algorithms usually have complex structures and demand vast training data.To overcome the model complexity and its dependence on the amount of data, we developed an ingenious DL framework based on a simple method called dual-layer semantics. In the framework, a data standardization module was designed to remove extraneous microstructural noise and accentuate desired structural characteristics, while a post-processing module was employed to further improve segmentation accuracy. The framework was successfully applied in a small dataset of bimodal Ti-6Al-4V microstructures with only 112 samples. Compared with the ground truth, it realizes an 86.81% accuracy IoU for the globular αphase and a 94.70% average size distribution similarity for the colony structures. More importantly, only 36 s was taken to handle a 1024 × 1024 micrograph, which is much faster than the treatment of experienced experts(usually 900 s). The framework proved reliable, interpretable, and scalable, enabling its utilization in complex microstructures to deepen the understanding of PSP linkages.展开更多
在施工项目领域,有效风险预测对于施工项目的顺利完成至关重要。针对传统风险预测模型难以实现非线性条件下的风险预测问题,提出了一种基于土拨鼠优化算法支持向量回归机(Prairie Dog Optimization Algorithm Optimizes Support Vector ...在施工项目领域,有效风险预测对于施工项目的顺利完成至关重要。针对传统风险预测模型难以实现非线性条件下的风险预测问题,提出了一种基于土拨鼠优化算法支持向量回归机(Prairie Dog Optimization Algorithm Optimizes Support Vector Regression Machine,PDO-SVR)的施工项目风险预测模型。该模型利用SVR强大的非线性预测能力,对施工项目的风险进行预测,针对人工选择SVR参数存在不合理的问题,利用PDO对SVR参数进行优化。实验结果表明,PDO-SVR模型具有更低的预测误差和良好的预测效果。展开更多
Fruit processing devices,that automatically detect the freshness and ripening stages of fruits are very important in precision agriculture.Recently,based on deep learning,many attempts have been made in computer image...Fruit processing devices,that automatically detect the freshness and ripening stages of fruits are very important in precision agriculture.Recently,based on deep learning,many attempts have been made in computer image processing,to monitor the ripening stage of fruits.However,it is timeconsuming to acquire images of the various ripening stages to be used for training,and it is difficult to measure the ripening stages of fruits accurately with a small number of images.In this paper,we propose a prediction system that can automatically determine the ripening stage of fruit by a combination of deep neural networks(DNNs)and machine learning(ML)that focus on optimizing them in combination on several image datasets.First,we used eight DNN algorithms to extract the color feature vectors most suitable for classifying them from the observed images representing each ripening stage.Second,we applied seven ML methods to determine the ripening stage of fruits based on the extracted color features.Third,we propose an automatic prediction system that can accurately determine the ripeness in images of various fruits such as strawberries and tomatoes by a combination of the DNN and ML methods.Additionally,we used the transfer learning method to train the proposed system on few image datasets to increase the training speed.Fourth,we experimented to find out which of the various combinations of DNN and ML methods demonstrated excellent classification performance.From the experimental results,a combination of DNNs and multilayer perceptron,or a combination of DNNs and support vector machine or kernel support vector machine generally exhibited excellent classification performance.Conversely,the combination of various DNNs and statistical classification models shows that the overall classification rate is low.Second,in the case of using tomato images,it was found that the classification rate for the combination of various DNNs and ML methods was generally similar to the results obtained for strawberry images.展开更多
基金funded by the University Transportation Center for Underground Transportation Infrastructure(UTC-UTI)at the Colorado School of Mines under Grant No.69A3551747118 from the US Department of Transportation(DOT).
文摘Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.
文摘Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are identified.Challenges in analysing small datasets are discussed,and solution is proposed to handle small datasets with multiple variables.Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity.The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability.Metallurgical-property relationships between chemistry,sample size,and hardness are predicted via two optimized machine learning algorithms:neural networks(NNs)and extreme gradient boosting(XGboost).A comparison is drawn between all algorithms,evaluating their performance based on small data sets.The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.
基金supported by the National Key R&D Program of China(Grant No.2023YFB4606502)the National Natural Science Foundation of China(Grant Nos.51871183 and 51874245)+1 种基金the Research Fund of the State Key Laboratory of Solidification Processing(NPU), China(Grant No.2020-TS-06)Sponsored by the Practice and Innovation Funds for Graduate Students of Northwestern Polytechnical University。
文摘Efficient and accurate segmentation of complex microstructures is a critical challenge in establishing process-structure-property(PSP) linkages of materials. Deep learning(DL)-based instance segmentation algorithms show potential in achieving this goal.However, to ensure prediction reliability, the current algorithms usually have complex structures and demand vast training data.To overcome the model complexity and its dependence on the amount of data, we developed an ingenious DL framework based on a simple method called dual-layer semantics. In the framework, a data standardization module was designed to remove extraneous microstructural noise and accentuate desired structural characteristics, while a post-processing module was employed to further improve segmentation accuracy. The framework was successfully applied in a small dataset of bimodal Ti-6Al-4V microstructures with only 112 samples. Compared with the ground truth, it realizes an 86.81% accuracy IoU for the globular αphase and a 94.70% average size distribution similarity for the colony structures. More importantly, only 36 s was taken to handle a 1024 × 1024 micrograph, which is much faster than the treatment of experienced experts(usually 900 s). The framework proved reliable, interpretable, and scalable, enabling its utilization in complex microstructures to deepen the understanding of PSP linkages.
文摘在施工项目领域,有效风险预测对于施工项目的顺利完成至关重要。针对传统风险预测模型难以实现非线性条件下的风险预测问题,提出了一种基于土拨鼠优化算法支持向量回归机(Prairie Dog Optimization Algorithm Optimizes Support Vector Regression Machine,PDO-SVR)的施工项目风险预测模型。该模型利用SVR强大的非线性预测能力,对施工项目的风险进行预测,针对人工选择SVR参数存在不合理的问题,利用PDO对SVR参数进行优化。实验结果表明,PDO-SVR模型具有更低的预测误差和良好的预测效果。
基金This work was supported by Korea Institute of Planning and Evaluation for Technology in Food,Agriculture,Forestry(IPET)through Smart Plant Farming Industry Technology Development Program,funded by Ministry of Agriculture,Food and Rural Affairs(MAFRA)(421017-04)the National Research Foundation of Korea(Project No.2020R1F1A1067066)(NRF-2019K2A9A1A06100184).
文摘Fruit processing devices,that automatically detect the freshness and ripening stages of fruits are very important in precision agriculture.Recently,based on deep learning,many attempts have been made in computer image processing,to monitor the ripening stage of fruits.However,it is timeconsuming to acquire images of the various ripening stages to be used for training,and it is difficult to measure the ripening stages of fruits accurately with a small number of images.In this paper,we propose a prediction system that can automatically determine the ripening stage of fruit by a combination of deep neural networks(DNNs)and machine learning(ML)that focus on optimizing them in combination on several image datasets.First,we used eight DNN algorithms to extract the color feature vectors most suitable for classifying them from the observed images representing each ripening stage.Second,we applied seven ML methods to determine the ripening stage of fruits based on the extracted color features.Third,we propose an automatic prediction system that can accurately determine the ripeness in images of various fruits such as strawberries and tomatoes by a combination of the DNN and ML methods.Additionally,we used the transfer learning method to train the proposed system on few image datasets to increase the training speed.Fourth,we experimented to find out which of the various combinations of DNN and ML methods demonstrated excellent classification performance.From the experimental results,a combination of DNNs and multilayer perceptron,or a combination of DNNs and support vector machine or kernel support vector machine generally exhibited excellent classification performance.Conversely,the combination of various DNNs and statistical classification models shows that the overall classification rate is low.Second,in the case of using tomato images,it was found that the classification rate for the combination of various DNNs and ML methods was generally similar to the results obtained for strawberry images.
