CRAM: A Conditioned Reflex Action Inspired Adaptive Model for Context Addition in Wireless Sensor Networks

Abstract

In Wireless Sensor Networks (WSNs), Context Awareness is typically realized through Context Aware Systems (CASs). Although almost each CAS follows sense-decide-adapt cycle, the notion of context is hardwired into the applications; that is, when an event is triggered, the sense-decide-actuate cycle runs and performs required actuation. In situations, for instance, whenever the same event is triggered, the cycle produces the same actuation through mechanical use of the same resources, posing the same processing and time. In this paper, we propose CRAM, a context added system in which actuations once performed by the system help it to internally evolve by serving as new contexts. As the system is exposed to more situations overtime, its context repository is enriched through such retrospective contexts, gradually letting it perform internal actuation through improved introspective contexts. This internal actuation leads the system towards the evolution of intelligent processing by reducing the independent function of decision in sense-decide-actuate cycle and merging it with new context. Finally, the system reaches a juncture where recurrence of each event proves to be a stimulus for the system to respond impulsively, through priming memory of introspective contexts, to achieve an imitation of learned reflex action resulting into reduced time and energy expenditure.

A conditioned reflex action embedded associative context learning‐based energy efficient paradigm in smart city milieu

“…Underlying framework of CRIEEM is based on CRAM [6] that is developed through tenon‐mortise cross‐layered modular architecture. Proposed CRIEEM potentially improves the processing layer through altering the certain algorithmic aspects that leads the system towards enhanced energy efficiency however, physical layer does not pose any change.…”

“…Subsequent to image change detection module there exists silhouette subtraction module that subtracts the silhouette of the detected MO from the image (single frame) yielded by GMM. This module further optimises the processing through Don't Care operation [6]. Table 2 demonstrates the silhouette extraction under different instantaneous image quality levels.…”

“…A conceptualised model based on relation Energy = Power × Time can be utilised to calculate the energy extent of a system at each specific node. $$${E}_{T}=[(GMM\times IQ)+(SS\times DC)+SC+C]\times T$$$ where, E T = Total Energy Consumption at a specific node GMM = Gaussian Mixture Model IQ = Image Quality SS = Silhouette Subtraction DC = Don't Care operation [6] SX = Silhouettes Compared at specific node T = Time taken by processing at specific node C = Sensing Constant (Sonar + Image Sensor) W = Watt …”

“…The authors in refs. [6,31] presented an event-based CAS for MO detection, classification, tracking and identification implemented through camera based networks and distributed image analyses. In addition to that, as argued by ref.…”

“…Those applications of VSNs require capabilities, such as smart use of on‐board resources, autonomous decision making in distributed manner, multi‐camera synchronisation, and optimal transmission of data [5]. Such intelligent resource utilisation in VSNs is attainable through visual context awareness [6]. Context awareness is the ability of a computer system, artefact, or service to be aware of real‐time characteristics of its environment and respond intelligently and proactively against a requisite situation through utilising a sense‐decide‐actuate cycle and adopt cycle [7].…”