We propose an online sliding window based selforganisingfuzzy neural network (SOFNN) as the corecomponent of a cognitive reasoning system for a smart homeenvironment. The network has the ability to configure itsneuronal structure through adding and pruning of neuronswhile exploring the relationships between the inputs and thedesired reasoning outputs, thus enabling continuous learningand reasoning to provide meaningful cognitive understandingof the environment. Initially, the network is trained withenvironmentally realistic synthesised data thus demonstratingits adaptation capabilities. The network is then validated usingunseen data. In the simulation, we have studied the networkstructures and responses for three different scenarios with andwithout online sliding window based approaches and theresults obtained show the effectiveness of the proposed method.
|Title of host publication||Unknown Host Publication|
|Publisher||International Academy, Research, and Industry Association|
|Number of pages||6|
|Publication status||Published - 28 May 2013|
|Event||COGNITIVE 2013 : The Fifth International Conference on Advanced Cognitive Technologies and Applications - Valencia, Spain|
Duration: 28 May 2013 → …
|Conference||COGNITIVE 2013 : The Fifth International Conference on Advanced Cognitive Technologies and Applications|
|Period||28/05/13 → …|
Leng, G., Ray, A., McGinnity, TM., Coleman, SA., & Maguire, LP. (2013). Online Sliding Window Based Self-Organising Fuzzy Neural Network for Cognitive Reasoning. In Unknown Host Publication (pp. 114-119). International Academy, Research, and Industry Association.