Detection of Suspicious Activity using Mobile Sensor Data and Modified Sub-space K-NN for Criminal Investigations

Abstract

With the bulk availability of mobile sensors, the data collected from them mustn’t be wasted. Nowadays the creation of black-box software that collects this data is not a very difficult task. It is possible to detect suspicious unlawful events using this black-box data. In this paper, we present a novel way of doing forensic investigation using a modified sub-space K-NN (MSK) algorithm. The MSK algorithm is capable of detecting suspicious activities from mobile sensor data. Using this technique, we could detect any normal activity versus suspicious activity with 99.7 % accuracy. This study lays the foundation for future explorations, envisioning potential applications in diverse fields, including zoology. By adapting and expanding the proposed methodology, researchers in zoology could harness mobile sensor data to study animal behavior, offering an innovative approach to understanding and monitoring wildlife activities. Such interdisciplinary bridges highlight the versatility of technological advancements, where tools developed for criminal investigations may find unexpected yet valuable applications in the study of zoological phenomena