Fuzzy Logic Optimized Controller $($FLC$)$ for an Intelligent Assistive Care Environment

Design and Implement an FLC for controlling the environmental parameters of an intelligent flat

for disabled residence, where the system needs to automate the regulation of environmental

conditions and user preferences or the operation of assistive equipment, ramps, auto adjusting

furniture, kitchen worktops, HAVC, lighting or water temperature control. The environment could

be based on a room of choice in a small flat. A more ambitious project might consider the

aspects of the whole flat, but this is left to your choice.

The environmental parameters to be controlled could be ambient temperature, thermal

conformity and lighting using actuators such as cooling fans, heaters$/$boilers$,$ blinds and dimmer

switches. You might also consider other parameters such as TV or music volume control, and

power down options for electronic devices and heating. Environmental parameters could be

controlled based on monitoring sensors such as temperature, humidity, weather conditions,

light levels, time of day, level of activity $/$ motion of the user as well as mood and qualitative

indicators such as user preferences

FLC Design

The FLC should be based on determining the inputs and outputs of the system, depending

on what control behavior$($s$)$ you decide the FLC should implement.

Note that, depending on the control behaviors you wish to implement, you can select to use

a subset of the input sensors for example, so first think about the behavior$($s$)$ the FLC should

control.

Design choices should be made to consider the type and number of fuzzy sets for the inputs

and$/$or outputs of the FLC$.$

A set of suitable control rules should be defined, which can be experimented with to achieve

a good control performance of the chosen behavior$($s$).$

The FLC should therefore implement the followings:

$$ Consideration of which Fuzzy Inference model to use: Mamdani or Sugeno $($TSK$)$ fuzzy

models.

$$ Mapping the crisp input and output data into the designed fuzzy sets.

$$ Map input fuzzy sets into output fuzzy sets $($for Mamdani model$)$ based on a set of

designed rules that capture the desired control behavior of the system.

$$ Employ appropriate inference operation $($rule implication$)$ that handles the way in

which rules are activated and combined together $($composition and aggregation$).$

The outputs of the fuzzy inference engine will define a modified output fuzzy set $($for

Mamdani model$)$ that specifies a probability distribution of the control actions in relation

to activated rules.

$$ Use an appropriate defuzzifier to convert the modified fuzzy outputs into non fuzzy

$($crisp$)$ control values that can then be used to set the actuation outputs.

Part $1$ Design and Implementation of the FLC $(30$ Marks$)$

Design and implement a demonstrable FLC$,$ which can be a simulated system programmed

in Matlab, FuzzyLite or Juzzy, see links below:

Matlab Fuzzy Logic Toolbox $($http:$//$uk$.$mathworks.com$/$videos$/$getting$-$started$-$with$-$fuzzylogic toolbox$-$part$-1-68764.$html$,$

http:$//$www$-$rohan.sdsu.edu$/$doc$/$matlab$/$toolbox$/$fuzzy$/$fuzzyt$10.$html$)$

Fuzzylite $($http:$//$www$.$fuzzylite.com$)$

Juzzy $($http:$//$juzzy$.$wagnerweb.net$)$

Provide suitable evidence of your implementation in the form of diagrams and screenshots

of the different components. $(16$ marks$)$

Discuss and justify your design decisions for the choice of fuzzy sets $-$ membership functions,

fuzzy rules, FLC inference mechanism selected, and defuzzification method that was chosen.

Back up your explanations with evidence in the form of appropriate diagrams and

screenshots. $(7$ marks$)$

Perform analysis of the output behavior of the controller showing the rules activation,

controller output and control surface plots, demonstrating how the controller achieves the

specified behaviors in relation to an operational scenario. $(7$ marks$)$

Part $2$ Optimize the FLC developed for Part $1$

$(10$ Marks$)$

Consider the Fuzzy Logic Controller $($FLC$)$ for controlling the smart home you have designed

for the above Part $1.$ The purpose of this part is to optimize the fuzzy controller you have

previously developed. A data set of n input$-$output examples, $($xi$,$yi$),$ i $=1,2...,$ n$,$ is available

to evaluate the performance of your controller.

Keeping the same structure of the FLC as you have used in Part $1,$ design a genetic algorithm

to adjust the membership functions of the input and output variables of the FLC to optimize

the performance of your FLC$.$ Give details of the genetic algorithm you have used, i$.$e$.,$

problem encoding, genetic operators, fitness function. Some of you may have designed the

FLC as a Mamdani model, while others may have used Sugeno models. Clarify what is the

length of the chromosomes used in your solution. In case you have used a Mamdani model

to implement

your FLC$,$ describe how the genetic algorithm solution would change if you were to use a Sugeno

m