Modelling dynamic scenarios using fuzzy cognitive map

Recurrent neural models such as fuzzy cognitive maps are well established in decision modeling through progressive variations of system’s concept. However, existing activation functions have shortcomings such as lack of sensitivity to initial concepts’ weight that is due to exaggerated focus on training of network’s casual links. Therefore, in most cases decision outputs converge toward lower and higher extremes and do not represent gray scales. Another disadvantage is that, current models require sufficient time delay for convergence towards results. This makes FCM unable to handle transient changes in input. A new technique has been examined in this paper using a real-life example to improve FCM activation in terms of fast response to dynamic stimuli. A simple expert model of hexapod locomotion is developed without focus on weight training. The system’s response to stimuli is evaluated through a complete six-phase stride to validate the effectiveness of the developed activation function.

PDF 57666.pdf Restricted to Repository staff only Download (685kB)

Actions (login required)

View Item