MSC Projects 2017-18
Please email me at This email address is being protected from spambots. You need JavaScript enabled to view it. if you are interested in any of these topics and would like to have a discussion.
Keywords: Computer Programming, Fuzzy Control, Control Theory, Linear/Nonlinear Control, Computational Intelligence, Convolution Neural Network, Fuzzy Logic, Neural Network, Machine Learning, Pattern Recognition, Population-Based Search Algorithms (Genetic Algorithm, Particle Swarm Optimisation, Q-learning, Support Vector Machine, etc.)
Requirements: Hardworking, self-motivated, creative, good programming skills, willing to learn.
Digital libraries for more reference papers: IEEE Xplore, Science Direct
Control Type Projects
[HKL01] Position and Tracking Control of Wheeled Mobile Robots using Fuzzy Logic Controller
References: Matlab Fuzzy Logic Toolbox, A Short Fuzzy Logic Tutorial, Type-2 Fuzzy Stes and Systems, General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial, Tutorial on Type-2 Fuzzy Sets and Systems, PID Controller, Fuzzy PID Controller, Linear State-feedback Controller
Open Source toobox: An Open Source Matlab/Simulink Toolbox for Interval Type-2 Fuzzy Logic Systems, toolbox downloaded here
Papers: Fuzzy model reference control of wheeled mobile robots; A practical fuzzy logic controller for the path tracking of wheeled mobile robots; Remote Control of a Mobile Robot for Indoor Patrol; Fuzzy Logic Tracking Control for Unicycle 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.
[HKL02] Fuzzy Control of Vehicle Active Suspension Systems
References: Matlab LMI toolbox, Active Suspension, Automotive Suspension Systems, Automotive Suspension Systems, Modelling simulation and control of an active suspension systemodelling simulation and control of an active suspension system
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.
[HKL03] Regulation of DC-DC Power Converters using Neural and Neural-Fuzzy Networks
References: Matlab Neural Network Document, Matlab Neuro-Fuzzy Network, A Short Fuzzy Logic Tutorial, Type-2 Fuzzy Stes and Systems, General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial, Tutorial on Type-2 Fuzzy Sets and Systems, PID Controller, Fuzzy PID Controller, Linear State-feedback Controller, Neuro-Fuzzy Network, Neuro-Fuzzy Systems, Neuro-Fuzzy Systems: A Survey, DC-DC Converters, DC-DC Converter Tutorial, DC-DC Converter, Basic DC-DC Converter Theory
This project is to design a control strategy for the regulation of DC-DC power converters, which can maintain the output voltage to constant subject to input disturbance and/or load variation. Matlab (or Pspice) are used to implement the converter's models (for example, buck, boost, buck-boost DC-DC converters) and controllers (for example, neural-network-based, neuro-fuzzy, fuzzy logic, interval-type-2 fuzzy logic, PID, fuzzy PID, state-feedback controllers). Simulations are to be done for verification of the design. Graphic User Interface (GUI) is to be built for visualisation of the design process and simulations.
Computational Intelligence Type Projects
[HKL04] Object Recognition using Convolution Neural Networks
References: What is deep learning?, Object recognition example, Convolution Neural Networks, Deep Learning Basics and Examples, CNN1, CNN2
This project is to build a classifier/recognizer using machine learning techniques such as convolution neural networks and training algorthms. The classifier/recognizer can be applied to some real-life applications, say, for recognition of objects from static images or videos. This project involves the design of classifiers and their implementation. A graphical user interface is to be built for the demonstration of results. Comparison will be done to demonstrate that the proposed clssifiers are more efficient than some existing ones.
Below are some examples from Youtube:
[HKL05] Electronic Arts
This project uses computational intelligence and machine learning techniques. such as genetic algorithm, particle swarm optimisation, to teach a machine which can create arts, say, evolve images, mimic drawings, etc.
References: Automatic and Interactive Evolution of Vector Graphics Images with Genetic Algorithms, Evolving Line Drawings.
Some examples from Youtube are shown below:
[HKL06] Auto-Driving using Computational Intelligence Techniques
This project is to create artificial creatures living in a simulated environment. Artificial creatures will evolve to adopt the environment for survival using computational intelligence techniques, for example, genetic algorithm/particle swarm optimisation, fuzzy logic and neural networks. Variable computational techniques will be employed, modified and tested under different scenarios for comparison of performance.
References: Q-learning 1, Q-learning 2, Q-learning 3, Q-learning + NN 1, Q-learning + NN 2, Q-learning + NN 3, Q-learning + NN 4, What is deep learning?, Object recognition example, Convolution Neural Networks, Deep Learning Basics and Examples, CNN1, CNN2
Demos: demon 1
Some examples from Youtube are shown below:
[HKL07] Classification of Epilepsy using Computational Intelligence Techniques
The project aim is to classify 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.
References: Autoencoder, Ensemble Classification, Classification Ensembles, Support Vector Machines, Neural Networks, Fuzzy Logic, A Short Fuzzy Logic Tutorial, Type-2 Fuzzy Stes and Systems, General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial, Tutorial on Type-2 Fuzzy Sets and Systems, What is deep learning?, Object recognition example, Convolution Neural Networks, Deep Learning Basics and Examples, CNN1, CNN2
Papers: Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications; Classification of epilepsy using computational intelligence techniques; Classification of epilepsy seizure phase using interval type-2 fuzzy support vector machines; A study of neural-network-based classifiers for material classification; Feature reduction and selection for EMG signal classification
[HKL08] Classification of EMG Signals using Neural Networks
This project aims at classification of EMG signals using neural networks. 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.
References: Autoencoder, Ensemble Classification, Classification Ensembles, Support Vector Machines, Neural Networks, Fuzzy Logic, A Short Fuzzy Logic Tutorial, Type-2 Fuzzy Stes and Systems, General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial, Tutorial on Type-2 Fuzzy Sets and Systems, What is deep learning?, Object recognition example, Convolution Neural Networks, Deep Learning Basics and Examples, CNN1, CNN2
Papers: Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications; Classification of epilepsy using computational intelligence techniques; Classification of epilepsy seizure phase using interval type-2 fuzzy support vector machines; A study of neural-network-based classifiers for material classification; Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals; Feature reduction and selection for EMG signal classification
Dataset used in the paper "Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals" is available here.