Open AccessLEVERAGING THE INTERNET OF THINGS BASED ON THE ANALYTICAL STUDY OF THE SKELETON JOINT POSITION IN RECOGNISING THE QUALITY OF HUMAN ACTIVITY
Author(s) -
Nipun Arora
Publication year - 2020
Publication title -
international journal of research in science and technology(online)/international journal of research in science and technology
Language(s) - English
Resource type - Journals
eISSN - 2454-180X
pISSN - 2249-0604
DOI - 10.37648/ijrst.v10i03.003
Subject(s) - classifier (uml) , artificial intelligence , computer science , support vector machine , pattern recognition (psychology) , euclidean distance , margin classifier
To give consequently dissecting and identifying human exercises to offer better help in the medical services area, securityreason and so on Strategy: We have utilized UTKinect-Action 3D dataset containing the Position of 20 body joint caughtby Kinect sensor. We chose two arrangement of joints J1 and J2; after that, we have shaped a few principles for movementgrouping then we have applied SVM classifier, KNN classifier utilizing Euclidean distance and KNN classifier usingMinkowski distance for action order. At the point when we have been used joint set J1 we got 97.8% exactness with SVMclassifier, 98.8% precision with KNN classifier utilizing Euclidean distance, and 98.9% exactness with KNN classifierutilizing Minkowski distance and for joint set J2 we got 97.7% exactness with SVM classifier, 98.6% exactness with KNNclassifier using Euclidean distance, and 98.7% exactness with KNN classifier utilizing Minkowski distance. We havearranged four exercises hand waving, standing, sitting and picking. In future, more exercises can likewise be rememberedfor this examination. IoT alongside this action acknowledgement strategy can be utilized to lessen overheads