AOCM-OAC: Architecture of Optimal Computational Model for Occupant Action Classification using Machine Learning
Preethi K. Mane1, K. Narasimha Rao2
1Preethi K.Mane*, Associate Prof, Department of Electronics & Instrumentation Engineering, BMS College of Engineering, Bangalore, India, Country.
2K. Narasimha Rao, Professor, Department of Electronics & Instrumentation Engineering, BMS College of Engineering, Bangalore.
Manuscript received on November 13, 2019. | Revised Manuscript received on 24 November, 2019. | Manuscript published on December 10, 2019. | PP: 566-571 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6524129219/2019©BEIESP | DOI: 10.35940/ijitee.B6524.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Occupancy sensing is one of predominant technology used in various control and context aware systems. The efficiency of such systems is highly corelated with the level of accuracy of the classification model of activity or stage detection of the subject or an occupant. The classification approaches based on computer need to evolve optimally for balancing the computational and time complexity with the classication accuracy using occupancy data acquired from Doppler radar. The proposed study presents a simplified framework that emphasizes on feature extraction technique as a medium to obtain more precision in the process of monitoring occupancy. The proposed logic has been implemented using analytical methodology convention and the extracted feature has been subjected to different forms of frequently used machine learning process with respect to processing time inclusive of training and testing period, efficiency, and accuracy of the proposed system.
Keywords: Occupancy Sensing, Doppler Radar, Optimization, Machine Learning, Surveillance, Motion Sensing.
Scope of the Article: Machine Learning