2016/06/10 by Dana Hughes, Hughes, Dana, Nikolaus Correll +1 · 3 citations
Engineering · Environmental Science · #Advanced Chemical Sensor Technologies #Advanced Sensor and Energy Harvesting Materials #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO) #Smart Materials for Construction
paper · pdf · doi:10.48550/arxiv.1606.03508
openalex publication_date 2016/06/10 · openalex created_date 2022/09/30 · openalex updated_date 2026/07/28
This paper reviews machine learning applications and approaches to detection,\nclassification and control of intelligent materials and structures with\nembedded distributed computation elements. The purpose of this survey is to\nidentify desired tasks to be performed in each type of material or structure\n(e.g., damage detection in composites), identify and compare common approaches\nto learning such tasks, and investigate models and training paradigms used.\nMachine learning approaches and common temporal features used in the domains of\nstructural health monitoring, morphable aircraft, wearable computing and\nrobotic skins are explored. As the ultimate goal of this research is to\nincorporate the approaches described in this survey into a robotic material\nparadigm, the potential for adapting the computational models used in these\napplications, and corresponding training algorithms, to an amorphous network of\ncomputing nodes is considered. Distributed versions of support vector machines,\ngraphical models and mixture models developed in the field of wireless sensor\nnetworks are reviewed. Potential areas of investigation, including possible\narchitectures for incorporating machine learning into robotic nodes, training\napproaches, and the possibility of using deep learning approaches for automatic\nfeature extraction, are discussed.\n