Programs
- M. Tech. in Automotive Engineering -
- Fellowship In Interventional Pulmonology and Pulmonary Critical care - Fellowship
Publication Type : Conference Paper
Thematic Areas : Wireless Network and Application
Publisher : 2017 International Conference on Computation of Power, Energy Information and Commuincation (ICCPEIC).
Source : 2017 International Conference on Computation of Power, Energy Information and Commuincation (ICCPEIC), 2017
Keywords : Artificial neural networks, back propagation algorithm, building management systems, Buildings, buildings (structures), Classification algorithms, data analysis, Data collection, energy conservation, Energy management, Energy management systems, energy savings, energy usage, Home automation, industrial buildings, learning (artificial intelligence), logistic regression, Machine learning, Machine learning algorithms, neural nets, personalized behavior analysis, real-time data analysis, Sensors, Smart building, smart building solutions, smart personalized learning system, Switches, wearable device system, wireless communication
Campus : Amritapuri
School : School of Engineering
Center : Amrita Center for Wireless Networks and Applications (AmritaWNA)
Department : Wireless Networks and Applications (AWNA)
Year : 2017
Abstract : Integration of energy management systems into existing buildings brings in several challenges and financial constraints. Some of the challenges in the existing smart building solutions are that they require large-scale deployment of sensors, high rate of data collection, real-time data analysis in short span of time, and lack of knowledge about the energy usage with respect to the behavior of individuals and groups. This work proposes an affordable wearable device system as an alternative for large-scale deployment of sensors in industrial buildings. For effective energy management in the buildings, a personalized behavior analysis has been done in machine learning and neural networks algorithm and integrated with the proposed system. The complete system is implemented and tested extensively. The results show that the proposed system could provide 85% user comfort and 23% energy savings.
Cite this Research Publication : S. R. George, Arya Devi R. D., and Dr. Maneesha V. Ramesh, “Smart Personalized Learning System for Energy Management in Buildings”, in 2017 International Conference on Computation of Power, Energy Information and Commuincation (ICCPEIC), 2017