The theoretically elegant yet broadly functional capability of graphical models shows intriguing potential to span in a uniform manner perception, cognition and action; and thus to ultimately yield simpler yet more powerful integrated architectures for intelligent robots and other comparable systems. This position paper explores this potential, with initial support from an effort underway to de...

A Curious Place is modelled on the concept of an intelligent room, with an added capacity for behaving in a curious manner. Intelligent rooms are responsive physical spaces in which human activities are monitored and responses generated which facilitate or augment these activities. Recent trends in intelligent agent research towards intrinsically motivated learning agents allow physical places ...

The ever-growing demand and heterogeneity of Cloud Computing is garnering popularity with scientific communities to utilize the services of Cloud for executing large scale scientific applications in the form of set of tasks known as Workflows. As scientific workflows stipulate a process or computation to be executed in the form of data flow and task dependencies that allow users to simply artic...

This paper presents a comparative study of different neural network models for forecasting the weather of Vancouver, British Columbia, Canada. For developing the models, we used one year’s data comprising of daily maximum and minimum temperature, and wind-speed. We used Multi-Layered Perceptron (MLP) and an Elman Recurrent Neural Network (ERNN), which were trained using the one-step-secant and ...

This paper discusses an evaluation methodology that can be used to assess the performance of intelligent techniques at detecting, as well as predicting, unauthorised activities in networks. The effectiveness and the performance of any developed intrusion detection model will be determined by means of evaluation and validation. The evaluation and the learning prediction performance for this task...

In this paper, we demonstrate the usage of connectionist networks for intelligent prediction of power factor and efficient utilization of power. We propose two neuro-fuzzy networks and artificial neural networks using various learning techniques. The proposed connectionist networks are trained with the plant load current and a highly fluctuated voltage for online prediction of power factor. For...

The importance of research for rapid and automated model construction of decision support systems is prominent and recognized. In the literature, research on model construction methods has been conducted using either component-based approaches or artificial intelligent approaches; however, these methods are usually incapable of handling dynamic constrains under different situations. To obtain s...

Application of fuzzy automaton in Intelligent Space gives a simple way for quick adaptive personalisation. The concept of ‘Intelligent Space’ was originally introduced in 1996 by the Hashimoto Laboratory at the University of Tokyo, as a mixed human-robot assisted environment, where the robots are controlled by the the distributed intelligent devices of the ‘Intelligent Space’ called Ubiquitous ...

This work analyzes many different models and algorithms in the literature for the optimization of routes and frequencies of buses, necessary in the framework of the support tools development to take decisions for the collective urban public transportation systems design. The problem is NP-hard, for which diverse heuristic procedures to resolve it have been proposed in the literature. The method...