To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks o...To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre-trained deep convolution neural network,the true positives are segmented,and crack properties are extracted using two different methods.The first method is primarily based on active contour models and level-set segmentation and the second method consists of the domain adaptation of a mathematical morphology-based method known as FIL-FINDER.A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method.An advanced convolution neural network-based multi-output regression model has been proposed which was trained with the prepared database and validated with the held-out dataset for the prediction of crack-length,crack-width,and width-uncertainty directly from input image patches.The pro-posed model has been tested on crack patches collected from different locations.Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it.Additionally,an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the pre-diction results.Finally,the best performing model HHc-X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.展开更多
Biological data in fishery ecology have complex structures and are highly heterogeneous.Catch per unit effort(CPUE)estimated from fishery-dependent data are often used to characterize abundance indices(AI)of fish spec...Biological data in fishery ecology have complex structures and are highly heterogeneous.Catch per unit effort(CPUE)estimated from fishery-dependent data are often used to characterize abundance indices(AI)of fish species,which is critical in fish stock assessment.However,additional considerations need to be undertaken to ensure robust estimation because of the latently complicated structures in fishery-dependent data.Here,we elaborated the process of constructing multi-output artificial neural network models to standardize CPUE for heterogeneous fishing operations and applied it to the skipjack tuna(Katsuwonus pelamis)in the western and central Pacific Ocean(WCPO).Seasonal,spatial,and environmental factors were input variables,and the CPUE of four types of skipjack tuna fisheries were set as output variables.The optimal structure for multi-output neural network was evaluated by systematic comparison in 100 runs hold-out cross-validation.The results showed that the final multi-output neural network model with high accuracy can predict the spatial and temporal trends of skipjack tuna abundance.展开更多
文摘To cater the need for real-time crack monitoring of infrastructural facilities,a CNN-regression model is proposed to directly estimate the crack properties from patches.RGB crack images and their corresponding masks obtained from a public dataset are cropped into patches of 256 square pixels that are classified with a pre-trained deep convolution neural network,the true positives are segmented,and crack properties are extracted using two different methods.The first method is primarily based on active contour models and level-set segmentation and the second method consists of the domain adaptation of a mathematical morphology-based method known as FIL-FINDER.A statistical test has been performed for the comparison of the stated methods and a database prepared with the more suitable method.An advanced convolution neural network-based multi-output regression model has been proposed which was trained with the prepared database and validated with the held-out dataset for the prediction of crack-length,crack-width,and width-uncertainty directly from input image patches.The pro-posed model has been tested on crack patches collected from different locations.Huber loss has been used to ensure the robustness of the proposed model selected from a set of 288 different variations of it.Additionally,an ablation study has been conducted on the top 3 models that demonstrated the influence of each network component on the pre-diction results.Finally,the best performing model HHc-X among the top 3 has been proposed that predicted crack properties which are in close agreement to the ground truths in the test data.
基金supported by the National Key R&D Program of China(No.2023YFD2401303).
文摘Biological data in fishery ecology have complex structures and are highly heterogeneous.Catch per unit effort(CPUE)estimated from fishery-dependent data are often used to characterize abundance indices(AI)of fish species,which is critical in fish stock assessment.However,additional considerations need to be undertaken to ensure robust estimation because of the latently complicated structures in fishery-dependent data.Here,we elaborated the process of constructing multi-output artificial neural network models to standardize CPUE for heterogeneous fishing operations and applied it to the skipjack tuna(Katsuwonus pelamis)in the western and central Pacific Ocean(WCPO).Seasonal,spatial,and environmental factors were input variables,and the CPUE of four types of skipjack tuna fisheries were set as output variables.The optimal structure for multi-output neural network was evaluated by systematic comparison in 100 runs hold-out cross-validation.The results showed that the final multi-output neural network model with high accuracy can predict the spatial and temporal trends of skipjack tuna abundance.
基金国家自然科学基金重大项目(the Grand National Natural Science Foundation of China under Grant No.90407008)国家自然科学基金重点项目(the Key National Natural Science Foundation of China Under Grant No.60633060)安徽省自然科学基金(the Natural Science Foundation of Anhui Province of China under Grant No.050420103)
