1 / 1

An Investigation into Fuzzy Logic for use in Inhabited Intelligent Environments

An Investigation into Fuzzy Logic for use in Inhabited Intelligent Environments. Aims To investigate the use of fuzzy logic in Intelligent Inhabited Environments. Specifically how ANIFIS is used in Smart Homes. The goal is to test previous cutting edge work using a rich set of inputs. ANFIS

ajay
Download Presentation

An Investigation into Fuzzy Logic for use in Inhabited Intelligent Environments

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. An Investigation into Fuzzy Logic for use in Inhabited Intelligent Environments Aims To investigate the use of fuzzy logic in Intelligent Inhabited Environments. Specifically how ANIFIS is used in Smart Homes. The goal is to test previous cutting edge work using a rich set of inputs. ANFIS ANFIS is simply a FIS, built inside an adaptive fuzzy neural network. This means that it can optimise the parameters of the FIS by applying a learning algorithm. In terms of smart homes, ANFIS can be given a set of data and learn a set of fuzzy rules that fit the data. This leaves us with a Fuzzy Logic Controller for the smart home. Background One of the key ideas in the development of Intelligent Buildings (IBs) in Ubiquitous Environments is that of using fuzzy logic to model in a more realistic fashion. The idea is that if we don’t use fuzzy logic we naturally impose some sort of threshold on a system. Key to the vision of Intelligent Environments is that of fuzziness, for example, setting a temperature, describing the weather, or recognizing speech. If a user in their house wants the temperature in the morning to be warm we need fuzzy rules to interpret what this actually means in terms of setting the actual temperature they desire. We have seen many applications marketed that use fuzzy logic effectively, such as everyday washing machines and even some heating systems. The next stage is to use fuzzy logic I learning algorithms to create constantly learning IBs, a prim example of this being the iDorm/iDorm2 projects. Benefits of fuzzy logic 2: More realistic modelling Results so far In researching the iDorm projects I intended to re-create some of their previous work that used ANFIS. However, despite various claims from the producers of the iDorm projects, the test data has never been released. This has meant that I have not been able to test their work, and validate it. This means that despite the work claiming to be cutting edge it has not been possible, nor will ever be possible, to verify this claim. Currently I am looking for various input data for an ANFIS model of a select part of the iDorm project, to test the suitability of ANFIS in finding fuzzy rules within a rich set of input data. Benefits of fuzzy logic 1: Relevance of modelling real world scenarios. Fuzzy Inference Systems (FIS) Fuzzy Inference Systems (FIS) are based on the concepts of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. The benefits of using FIS is that they are interpretable as they make use of linguistic labels. This project is being undertaken by Andrew Miller, third year CS student, as part of Co620 Research Project. Project manager Ian Marshall. Contact: ajm27@kent.ac.uk

More Related