Quasi Opportunistic Supercomputing for Geospatial Socially Networked Mobile Devices

Abstract: Machine to Machine based communication and coordination in cyber physical systems for manufacturing application is a daunting problem. Here, the difficulty is in developing a multi task learning algorithm for finding collaborative key points within high dimensional decision space. In order to overcome such a problem a gradient based method is required to enable distributed control and collaborative decision making. This paper presents membrane computing based gradient method for online multitask learning and controlling the distributed coordination to achieve stochastic planning to formulate optimize semantic network to derive a local optimal policy. Experimental verification is achieved through implementation of several concurrent functioning of mobile robotic platforms.

Abstract: Abstract The ability to analyse the traffic and urban mobility pattern with the help of video analytics, which occur in massive volumes of surveillance video will lead us to provide a knowledge based for the urban planners and policy makers to come up with better construction planning. This will soothe the needs of urban commuters and thereby saving unnecessary spillage of money on the construction projects. In this research project, we present an artificial intelligence framework for transport video analytic; which autonomously models behavioural patterns of commuters and flow of traffic, wherein it taxonomically classifies essential patterns based on geometrical feature points of interest to facilitate reality mining. This behavioural pattern of commuter and traffic flow can later be queried and fetched through the newly mathematically programmed ontological data warehousing module, where such reality mined contextual data could be used for sharing essential data.

Abstract: The objective of this study is to develop the design of a generic infrastructure for on-demand applications for intelligent transport systems (ITS) in an urban area. The main idea of the study is to allow seamless service composition and consumption, but also to allow rapid deployment of new services through the pooling of different devices and access networks that may be owned and operated by different actors such as telecom operators, transportation service operators, governmental organizations, etc. This research serves the solution for the problem of interoperability between different devices, on the fly device reconfiguration and service discovery.

Abstract: Networked Virtual Environments (NEV) are sets of disjointed virtual worlds which are topographically set apart from the users yet connected through the communication network to give them the illusion of being in the same virtual location. NVEs are increasingly receiving consideration from business and research point of view. Contrasted with various sorts of possible applications, NVEs require a high responsiveness to ensure continuous streaming of live data for full immersion. It is as yet difficult to develop such applications since it require to create virtual reality framework over distributed databases; as every user needs locally adequate data flow to concurrently construct a scene as with other users and able to accommodate multi-user interactions in the virtual environment. Such information requires simultaneous computation and communication of streaming data. In this study we built up a prototype of a NVE in view of the blend of Minority Game (MG) and Online Induction Algorithm (OIA) with lossless transfer functions.

Abstract: Plasticity of the neurons and the synchronization features are essential to bring out the intelligence in a biological specimen. Thus, in this study we model the synchronistic behavior of neuronal firing to avail control system of cyber physical system. Also, a brief review of neuronal oscillations is also discussed