Bridging the gap: An integrated approach to motif discovery and discord detection in time-series data

Anomaly detection in time-series data is a critical task with implications for healthcare, law enforcement, and smart policing, yet it presents considerable challenges. Traditional methods often require extensive computational resources and exhibit limited success in discerning various anomaly types, hindering their practical deployment. To address these shortcomings, we propose the Motif Discovery with Discord Removal (MDR) algorithm, which markedly enhances computational efficiency and the accuracy of anomaly detection. The MDR algorithm adopts an integrated approach, combining motif analysis with discord removal, to furnish both a computationally frugal and robust anomaly identification system. To overcome scalability constraints, we introduce a variant of MDR utilizing Particle Swarm Optimization for parallel processing, thereby leveraging distributed computing to efficiently handle voluminous datasets. Our empirical assessments show that the MDR and its parallel adaptation surpass existing methods, supporting agile and precise real-time anomaly detection. Of particular interest to law enforcement, the enhancements in temporal crime data analysis offered by our methods can significantly advance predictive policing capabilities and the discernment of criminal patterns, leading to more proactive and intelligent law enforcement practices.