GPSPiChain-Blockchain and AI based self-contained anomaly detection family security system in smart home
Raza, A and Hardy, L and Roehrer, E and Yeom, S and Kang, BH, GPSPiChain-Blockchain and AI based self-contained anomaly detection family security system in smart home, Journal of Systems Science and Systems Engineering pp. 1-17. ISSN 1861-9576 (2021) [Refereed Article]
With advancements in technology, personal computing devices are better adapted for and further integrated into peopleís lives and homes. The integration of technology into society also results in an increasing desire to control who and what has access to sensitive information, especially for vulnerable people including children and the elderly. With blockchain rise as a technology that can revolutionize the world, it is now possible to have an immutable audit trail of locational data over time. By controlling the process through inexpensive equipment in the home, it is possible to control whom has access to such personal data. This paper presents a block-chain based family security system for outdoor tracking and in-house monitoring of usersí activities via sensors to detect anomalies in usersí daily activities with the integration of Artificial Intelligence (AI). For outdoor tracking the locations of the consenting family membersí smart phones are logged and stored in a private blockchain which can be accessed through a node installed in the family home on a computer. The data for the whereabouts and daily activities of family members stays securely within the family unit and does not go to any third-party organizations. A Self-Organizing Maps (SUM) based smart contract is used for anomaly detection in usersí daily activities in a smart home, which notifies emergency contact or other family members in case of anomaly detection. The approach described in this paper contributes to the development of in-house data processing for outdoor tracking, and daily activities monitoring and prediction without any third-party hardware or software. The system is implemented at a small scale with one miner, two user nodes and several device nodes, as a proof of concept; the technical feasibility is discussed along with the limitations of the system. Further research will cover the integration of the system into a smart-home environment with additional sensors and multiple users, and ethical implementations of tracking, especially of vulnerable people, via the immutability of blockchain.
blockchain, security, global positioning system (GPS), self-organizing maps (SOM), smart home