Multi-Objective Evolutionary Algorithm Based Approach for Solving Rfid Reader Placement Problem Using Weight-Vector Approach with Opposition-Based Learning Method
Spurti Sachin Shinde1, K. Devika2, S. Thangavelu3, G. Jeyakumar4
1Spurti Sachin Shinde, Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, (Tamil Nadu), India.
2K. Devika, Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, (Tamil Nadu), India.
3S. Thangavelu, Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, (Tamil Nadu), India.
4G. Jeyakumar, Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, (Tamil Nadu), India.
Manuscript received on 24 January 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 January 2019 | PP: 177-184 | Volume-7 Issue-6, March 2019 | Retrieval Number: E1994017519©BEIESP
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: For smart building applications, identifying and tracking the objects and people in and around a building is an inevitable problem. There exist many approaches for solving this problem. Nowadays, the RFID network based approaches have become most popular for its speed and accuracy. However, placing the RFID readers at optimal places in a building to cover all the areas in order to identify and track the objects and people is a cumbersome task. This paper proposes a model in which the RFID reader placement problem is formulated as a multi-objective optimization problem and also proposes an algorithmic framework to solve the same. The proposed algorithmic frame work consists of a multi-objective Differential Evolution algorithm which adds weights to each of the objective and also follows the opposition-based learning approach for initializing the populations. The results obtained in solving the RFID reader placement problem with proposed algorithmic framework is studied and reported in details for individual objectives, combined objectives with different schemes and for two different population initialization techniques.
Keywords: Multi-Objective Optimization, Evolutionary Algorithms, RFID Reader Placement, Opposition-Based Learning, Weight-Vector approaches.
Scope of the Article: Deep Learning