Leveraging Data Analytics and IoT for Women’s Safety: An Overview

As the availability of data sources continues to grow exponentially, the introduction of innovative sensor technologies, data, information/communication networks in a targeted manner forms the core of the optimization of the security chain. Observation, analysis, decision making and action form the pillars when it comes to talking about the security domain and the availability as well as the quality of data/information in order to improve the knowledge-position of key personnel associated with citizen safety are of utmost importance in this case. According to a survey by WHO, crimes against women are at an all-time high, with 35% women globally experiencing some form of abuse and physical violence. This percentage, as shocking as it may seem, will only become higher if unreported cases get reported. The application of data analytics in conjunction with ICT (with special reference to IoT) in all their aspects are the key innovation arenas within the ambit of safety and security for women domain, as they can be leveraged to discover, gather and predict safety/security related trends within a targeted society. The need of the hour, hence, is to integrate the two and create novel concepts for processing the gathered data. Conjunction of Analytics and IoT: One of the key ways that IoT and Analytics in conjunction can leverage ICT on national and state level is via a National Vehicle Security and Tracking System and City Command and Control Center namely. With a coverage ratio of over a million, the aim of aiding women in distress, keeping in mind minimum response time, can be done through the tracking and geo-fencing of all public transport, with visual/text signals denoting violations. CCTV cameras and Panic buttons that can alert the police can communicate through an Intelligent Transport M2M platform, that can display incident location, as well as the shortest route to reach the location. Additionally, the usage of data analytics and data mining techniques can aid in the identification of undesired, irregular behaviour, which can be used to predict future criminal incidents or hostile conducts, in preparation of which security personnel can be extra vigilant for such scenarios. Reported events of misconduct can help in red-flagging particular parts of the city, which can have additional security deployed, as well as have other proactive measures taken to ensure women’s safety. In fact, the data gathered via CCTV cameras, sensors etc. can become the foundation for the prevention of prohibited behaviour or for the intervention at an early stage which can prevent an escalation. The development of a form of pattern recognition specifically in human behaviour means moving towards real-time multisensory information, along with assisted information that can be gathered from open sources or even third-party information systems/databases. Conclusion: With analytics working in successful conjunction with M2M technology, it is possible to envisage a world where connected devices can ride over secure-end to end solutions. They can help safety/health professionals access as well as analyze gathered data in real time and increase their response efficiency accordingly, ensuring the safety of individuals. Security personnel can respond to citizen panic calls in a timely manner and the framework can also enable remote monitoring of the incident by officials, with the data being used as verifiable cause and evidence against any individual accused of instigating an incident. With a collective responsibility to create an ecosystem that can ensure the safety, security and dignity of women, technological interventions today have begun to address the need for both incidence prevention and post-incidence assistance. With considerable work to still be done, there is hope that the critical issue of women’s safety will soon find effective smart solutions, creating a safer environment for women worldwide.

Author: Rajiv Diwan, Practice Head – Advanced Analytics

Rajiv Diwan heads the Advanced Analytics Practice at ITL and is responsible for both – customer acquisition and defining solution offerings of the Practice. He has setup the CoE on Machine Learning from scratch at ITL and has been instrumental in penetrating into new verticals for ITL; including BFSI. Rajiv is engineering graduate from BIT, Bangalore with specialization in Computer Science; having over 18 years of experience in Analytics, Data warehousing, BI and Large Program Management.

Post a Comment