MSC Projects 2013-14
Control-Based Projects
[HKL01] Fuzzy-model-based control of virtual ball-and-plate system
The aim of this project is to control the ball-and-plate system using fuzzy-model-based control method. A fuzzy model will be developed to facilitate the design of the fuzzy controller. Stability analysis will then be carried out. By solving numerically the solution to the stability conditions, a fuzzy controller can be obtained. To verify the analysis result, the control system will be implemented using a Lego Mindstorm NXT kit and a smart phone/tablet. The Lego Mindstorm NXT kit will be used to implement the control platform. The smart phone/tablet will be used to implement the virtual ball-and-pate system, which is mounted on the Lego Mindstorm platform. The smart phone/tablet will show a ball on the screen. The information of the ball, e.g., position, velocity, etc, will be fed back to the Lego Mindstorm platform. By adjusting the angle of the platform (which controls the angle of the smart phone/tablet), the ball position is driven to the origin. Student taking this project is required to be hardworking and self-motivated. Good Matlab and smart phone programming skills are essential to this project.
Another option: Instead of virtual ball-and-pate system, a physical system can be implemented using Lego Mindstorm NXT kit or Arduino microcontroller. An image processing technique will be developed to locate the ball position in the beam or an inferred sensor is used instead. Various controllers will be employed to stabilize the ball position or drive the ball to keep track of a pre-defined trajectory. Good programming and hardware-building skills are essential to the project.
[HKL02] Fuzzy control of virtual inverted pendulum system
Please refer to the description of [HKL01]. Instead of ball-and-plate system, an inverted pendulum system or a system of your choice is considered.
[HKL03] Fuzzy control of vehicle active suspension systems
The aim of the project is to design a fuzzy controller to control the vehicle active suspension system, subject to the performance constraints and user preferences. This project can be broken down into the following tasks. 1) Fuzzy model will be constructed describing the system dynamics for analysis and design. 2) Stability analysis and control synthesis will be investigated based on the Lyapunov stability theory. A set of linear matrix inequalities (LMIs) will be derived to determine the system stability and feedback gains of the fuzzy controller. 3) Computer simulations will be done to verify the analysis result and control performance will be compared with other control schemes. 4) A Graphic User Interface (GUI) will be implemented based on Matlab which involves an animated inverted pendulum. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill and mathematical background are essential to this project.
[HKL04] Position and tracking control of wheeled mobile robots
The aim of this project is to design a fuzzy controller for wheeled mobile robot for position and tracking control. For position control, the wheeled mobile robot is driven to reach a target position. For tracking control, the wheeled mobile robot is driven to move along a pre-defined trajectory. This project can be broken down into the following tasks. 1) The dynamic model of the wheeled mobile robot is developed. Based on the model, various types of controllers, such as fuzzy controller, PID controller, linear state-feedback controller, will be employed to perform the control. 2) The system performance will be investigated and optimised by genetic algorithm (GA) or particle swarm optimization (PSO). 3) A path planning algorithm will be developed to find the shortest path to reach the target with the ability of obstacle avoidance. 4) A Matlab software with Graphic User Interface (GUI) will be implemented to facilitate computer simulations and control synthesis with animated output. 5) The system will be implemented physically using a Lego Mindstorm NXT kit. Hardware results will be recorded and compared. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill and mathematical background are essential to this project.
[HKL04] Regulation of DC-DC switching converters using computational intelligence techniques
This project aims at regulating the output voltage of the DC-DC switching converter subject to changing input voltage and/or output load using fuzzy control approach. A fuzzy controller incorporating expert knowledge is employed to realise the output regulation. Expert knowledge extracted from the characteristic of DC-DC switching converter is expressed by linguistic rules in IF-THEN format. By properly designing the membership functions of the fuzzy controller using computational intelligence technique (Genetic algorithm (GA)/Particle Swarm Optimisation (PSO)), a well-performed fuzzy controller can be realised. Various types of DC-DC switching controller and fuzzy controllers will be studied and investigated. MATLAB and fuzzy logic toolbox will be employed for implementation of the algorithms and carrying out simulations. A Graphic User Interface (GUI) will be implemented. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL06] Control of backward movement of articulated vehicle based on fuzzy-model-based control approach
A fuzzy controller is designed to control the backward movement of an articulated vehicle using fuzzy-model-based control approach. The system dynamics of the articulated vehicle is described by a T-S fuzzy model. Based on the T-S fuzzy model, a stable fuzzy controller is designed using Lyapunov approach. Stability conditions in terms of linear matrix inequalities (LMIs) are obtained to guarantee the system stability and synthesise the controller. The solution to the LMI conditions will be solved numerically using convex programming techniques such as MATLAB LMI tool box. This project can be broken down into the following tasks. 1) A fuzzy model will be developed to describe the system dynamics of the articulated vehicle. A fuzzy controller will then be proposed to control the system. 2) System stability will be investigated based on the Lyapunov stability theory. A set of linear matrix inequalities (LMIs) will be obtained to guarantee the system stability and feedback gains of controller. 3) Computer simulations will be done to verify the analysis result. 4) The system will be implemented physically using the Lego Mindstorm NXT kit. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill and mathematical background are essential to this project.
Computational Intelligence-Based Projects
[HKL07] Mind recogniser and its Applications.
The aim of this project is develop a recogniser which is able to recognise someone’s mind. A headset (Emotiv EEG Headset) will be employed to capture your mind. Brain signals will be recorded and features will be extracted for recognition purposes. Neural networks or other classifier will be developed to classify the intentions of the user where the recognised command will used for an application for demonstration purposes. A suggested application is the control of virtual mobile robot on the screen. The robot will react according to the user’s intentions in his/her mind. Student taking this project is expected to explore how the EEG headset works and data collection. Also, good Matlab programming skill is essential to this project.
[HKL08] Classification of Epilepsy using Computational Intelligence Techniques
This project aims at classifying the epilepsy status of patients. Real clinical data will be used for this project. Given EEG epochs obtained from patients, classifiers are designed to recognise three status, namely seizure-free, pre-seizure and seizure. Features will be extracted from the raw data which will be used as the input of classifiers. Different computational intelligence techniques including neural networks, support vector machines, fuzzy logic systems, self-organisation map and traditional classifiers including k-NN and naive Bayes will be employed for classifying the epilepsy status and compare their performance. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL09] Ship Traffic Prediction using Computational Intelligence Techniques
This project aims at designing a ship traffic predictor using computational intelligence techniques, for example, neural networks, fuzzy logic systems, support vector regressors. Real ship traffic data will be used for this project. For comparison purposes, traditional predictors such as linear/nonlinear regressors will be employed. The proposed traffic ship predictor demonstrates a potential solving the sea traffic problem. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL10] Classification of EMG signals using Neural Networks
This project aims at classification of EMG signals using neural networks. EMG data of different movement actions will be collected by the student taking this project. Various feature points will be extracted for the purposes of classification. Various neural-network-based classifiers will be proposed and implemented using Matlab. Recognition performance will be investigated and compared with existing methods. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL11] Voice commanded calculator
This project will implement a calculator, which performs calculation according to voice commands. Speech recognition will be done by the following steps: 1) Student taking this project will collect speech data of himself/herself as the command input of calculator. 2) Feature extraction will be done for all collected speech data. 3) Neural networks or support vector machines will be employed to implement the speech classifier. The voice commanded calculator will be implemented using Matlab. Recognition performance will be investigated and compared with existing methods. Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL12] Recognition of handwritten characters using neural networks
The aim of this project is to recognise handwritten characters using neural-network-based techniques. A number of neural networks will be investigated and employed to implement the recognisers. An algorithm for pattern recognition will be developed to capture the feature points from the images of the characters. Various recognisers constructed by neural networks will be proposed to perform recognition using the captured feature points. Learning and optimisation algorithms will be employed to train the neural networks. The proposed approaches will be compared with the traditional ones in terms of recognition accuracy. Matlab will be used to implement the proposed algorithms and a graphic user interface (GUI). Student taking this project is required to be hardworking and self-motivated. Good Matlab programming skill is essential to this project.
[HKL13] Graffiti interpretation using support vector machines
The aim of this project is recognise graffiti using support vector machines. Different types of support vector machines, i.e., support vector classifiers and support vector regressors will be employed to construct the graffiti interpreters. Based on optimisation theory, with the sample points of the graffiti, the optimal parameters of the support vector machines will be determined. The graffiti interpreters will be implemented by Matlab and the performances will be investigated through computer simulation. Good Matlab programming skill is essential to this project. Student taking this project is required to be hardworking and self-motivated.