Novel Framework for Multi-Scale Occupancy Sensing for Distributed Monitoring in Internet-of-Things

Occupancy sensing is one of the integral parts of modern evolving security surveillance and monitoring systems used over different types of infrastructure. With multiple forms of occupancy sensors, the prime idea of occupancy sensing is to identify the presence or absence of occupants in a precisely monitored area, followed by transmitting the sensing information for storage or prompting a set of commands from the connected control units. A review of existing schemes exhibits the presence of the adoption of multiple methodologies over different variants of use cases; however, they are quite case-specific, use expensive deployment processes, and perform highly sophisticated operations. Currently, no studies specifically reported using multi-scale occupancy sensing suitable for large and distributed Internet-of-Things (IoT) environments. Therefore, the proposed study introduces a mechanism of novel multi-scale occupancy sensing considering a smart university campus use case. However, it can be implemented over different infrastructures connected to an IoT environment. The proposed scheme is implemented considering varied forms of cost-effective sensors, handheld devices and access points for determining the state of occupancy in a large number of rooms on campus. The sensed data from distributed connected campuses are aggregated over a cloud server subjected to suitable preprocessing to increase the data quality suitable for reliable prediction. Multiple potential learning-based schemes are integrated with a proposed model to explore the best-fit model. This assessment scenario is not reported in the existing scheme to classify states of occupancy. The study outcome shows Convolution Neural Network and Long Short-Term Memory to accomplish higher accuracy than other learning approaches.