Support Vector Regression (SVR) has already been proved to be one of the mostreferred and used machine learning technique in various fields. In this study, wehave addressed a predictive-cum-prescriptive analysis for f...Support Vector Regression (SVR) has already been proved to be one of the mostreferred and used machine learning technique in various fields. In this study, wehave addressed a predictive-cum-prescriptive analysis for finalizing fundallocations by the Government at center to the schemes under Central Plan andto the schemes under States and Union Territories Plan, with a goal to maximizeGross Value Added (GVA) at factor cost. Here, we have proposed a hybridmachine learning model comprising of OFS (Orthogonal Forward Selection),TLBO (Teaching Learning Based Optimization) and SVR for the prediction ofGVA at factor cost. In this model, referred as OFS–TLBO–SVR hybrid model,SVR is at the core of prediction mechanism, OFS is for identifying the relevantfeatures, and TLBO is to support in optimizing the free parameters of SVR andagain TLBO is used for optimizing the governable attributes of data.展开更多
Fiber Bragg grating (FBG) based sensors offer important advantages over traditional instrumentation with regards to real-time structural health monitoring (SHM) of composite materials and structures in recent years. F...Fiber Bragg grating (FBG) based sensors offer important advantages over traditional instrumentation with regards to real-time structural health monitoring (SHM) of composite materials and structures in recent years. FBG sensors, integrated into existing structures or embedded into new ones, have played a major role in assessing the safety and integrity of engineering structures. In this paper, a review on the latest research of the FBG-based SHM technique for composite field is presented. Firstly, the FBG sensing principle is briefly discussed and FBG and several other optical fiber sensors (OFSs) for SHM are performance-compared. Then, several examples of the use of FBG sensors in composite SHM are illustrated, including those from the field of cure monitoring, civil engineering, aviation, aerospace, marine and offshore platform. Finally, some existing problems are pointed out and some proposals for further researches are provided.展开更多
文摘Support Vector Regression (SVR) has already been proved to be one of the mostreferred and used machine learning technique in various fields. In this study, wehave addressed a predictive-cum-prescriptive analysis for finalizing fundallocations by the Government at center to the schemes under Central Plan andto the schemes under States and Union Territories Plan, with a goal to maximizeGross Value Added (GVA) at factor cost. Here, we have proposed a hybridmachine learning model comprising of OFS (Orthogonal Forward Selection),TLBO (Teaching Learning Based Optimization) and SVR for the prediction ofGVA at factor cost. In this model, referred as OFS–TLBO–SVR hybrid model,SVR is at the core of prediction mechanism, OFS is for identifying the relevantfeatures, and TLBO is to support in optimizing the free parameters of SVR andagain TLBO is used for optimizing the governable attributes of data.
基金the National High Technology Research and Development Program (863) of China(No. 2011AA7052011)the National Natural Science Foundation of China (No. 51205253)
文摘Fiber Bragg grating (FBG) based sensors offer important advantages over traditional instrumentation with regards to real-time structural health monitoring (SHM) of composite materials and structures in recent years. FBG sensors, integrated into existing structures or embedded into new ones, have played a major role in assessing the safety and integrity of engineering structures. In this paper, a review on the latest research of the FBG-based SHM technique for composite field is presented. Firstly, the FBG sensing principle is briefly discussed and FBG and several other optical fiber sensors (OFSs) for SHM are performance-compared. Then, several examples of the use of FBG sensors in composite SHM are illustrated, including those from the field of cure monitoring, civil engineering, aviation, aerospace, marine and offshore platform. Finally, some existing problems are pointed out and some proposals for further researches are provided.
