ICT3903 – Final Year Project in Computer Engineering Proposals 2015 / 2016 ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 1 Image Processing Techniques for Lung Lesion / Nodule Detection in Chest CT Scans Supervisor(s): Prof. Ing. Carl James Debono, carl.debono@um.edu.mt Co-supervisor (if any): Dr Paul Bezzina, paul.bezzina@um.edu.mt Dr Francis Zarb, francis.zarb@um.edu.mt Problem Background Medical image analysis provides a tool for diagnostics of organs inside and outside of the body. Image processing allows for the isolation of the organ of interest from the rest of the body parts in the image and then search for any abnormalities. The aim of this project is to detect lesions / nodules in lungs. • Project Objective(s): • • Project Resources • • • • Industrial Partners involved: No Apply image processing techniques on CT scans to detect the lung structure and the presence of any lesions / nodules Develop a curve fitting algorithm to enclose the lesions / nodules detected Evaluate the accuracy of the method through expert analysis of results Budget: €__0___ CT scans will be available from Malta’s General Hospital OpenCV or Maltab Publications Expected Project Deliverables: • • • Software developed Experimental results Analysis and comparison of results Student background / interest: • • Programming Image processing Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. ■ The project has ethical issues; please specify. Project will analyse patient medical data ■ The project involves human subjects; please specify. The CT scans will come from patients at Malta’s General Hospital ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 2 Wireless Transmission of Ultrasound Video using HEVC Supervisor(s): Prof. Ing. Carl James Debono, carl.debono@um.edu.mt Co-supervisor (if any): None Problem Background Transmission of medical video is more stringent than other content because the received video must be of high quality to allow medical practitioners to perform diagnostics. More robust video coding techniques can be applied to protect regions of medical interests better than other areas. Furthermore, HEVC provides higher compression ratios and thus the performance under error conditions needs to be investigated. • • • Project Objective(s): Project Resources • • • Industrial Partners involved: No Implement region of interest coding for medical video Evaluate the performance under different packet error rates Suggest methods to improve the quality of experience Budget: €__0___ Visual Studio .NET, Matlab Publications Expected Project Deliverables: • • • Software developed Experimental results Analysis and comparison of results Student background / interest: • • Programming Multimedia Communications Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 3 A Study on Compression of Light-Field Imaging Supervisor(s): Prof. Ing. Carl James Debono, carl.debono@um.edu.mt Co-supervisor (if any): None Problem Background The JPEG committee has launched a new activity called JPEG PLENO. The target of this activity is to eventually provide a standard framework that allows the representation and exchange of new image modalities. One of these new modalities is light-field imaging. This study will review available techniques, benchmark them, and propose possible solutions. • • • Project Objective(s): Project Resources • • • Industrial Partners involved: No Review the literature Benchmark the techniques used and implement one solution Propose possible solutions for new frameworks Budget: €__0___ Matlab, OpenCV Publications Expected Project Deliverables: • • • Review of available techniques Software and results of one technique Proposal for future work Student background / interest: • • • Programming Multimedia Communications Image processing and coding Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 4 Video Broadcasting in Vehicular Networks Supervisor(s): Prof. Ing. Carl James Debono, carl.debono@um.edu.mt Co-supervisor (if any): None Problem Background New vehicles are equipped with on-board computers and can also have wireless access. The IEEE 802.11p standard defines the lower network layers for vehicle communications. Visual communications can provide important information for the driver while it can be of entertainment to passenger in the vehicle. However, video data generates huge amounts of data that needs adequate routing to meet playback deadlines. Multihop and cluster-based methods will be studied as possible routing solutions. • • Project Objective(s): • Project Resources • • • Industrial Partners involved: No Develop a model of the network Design and implement the multi-hop and cluster-based routing algorithms Analyze the performance Budget: €__0___ SUMO and (OMNET++ or NS-3) Publications Expected Project Deliverables: • • • Software developed Experimental results Analysis and comparison of results Student background / interest: • • Programming Telecommunication networks Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 5 Home Monitoring System Supervisor(s): Prof. Ing. Edward Gatt edward.gatt@um.edu.mt; Co-supervisor (if any): None Problem Background The popularity of home automation has been increasing greatly in recent years due to much higher affordability and simplicity through smartphone and tablet connectivity. The concept of the "Internet of Things" has tied in closely with the popularization of home automation. A home automation system integrates electrical devices in a house with each other. The techniques employed in home automation include those in building automation as well as the control of domestic activities. Devices may be connected through a home network to allow control by a personal computer, and may allow remote access from the internet. Through the integration of information technologies with the home environment, systems and appliances can communicate in an integrated manner which results in convenience, energy efficiency, and safety benefits Project Objective(s): The project aims at producing an FPGA module which can allow monitoring of different environmental properties. Project Resources • Budget: € 400 Industrial Partners involved: Expected Project Deliverables: FPGA interfacing to sensors Student background / interest: VHDL/Electronics Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 6 Body Monitoring System Supervisor(s): Prof. Ing. Edward Gatt edward.gatt@um.edu.mt; Co-supervisor (if any): None Problem Background Recent technological advances in sensors, low-power microelectronics and miniaturization, and wireless networking enabled the design and proliferation of wireless sensor networks capable of autonomously monitoring and controlling environments. One of the most promising applications of sensor networks is for human health monitoring. A number of tiny sensors, strategically placed on the human body, create a body area network that can monitor various vital signs, providing real-time feedback to the user and medical personnel. Project Objective(s): The project aims at producing an FPGA module which can allow monitoring of different human vital signals. Project Resources • Budget: € 600 Industrial Partners involved: Expected Project Deliverables: FPGA interfacing to sensors Student background / interest: VHDL/Electronics Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. ■ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 7 Design of an Intelligent Multimeter Supervisor(s): Prof. Ing. Edward Gatt edward.gatt@um.edu.mt; Co-supervisor (if any): None Problem Background A multimeter is used to make various electrical measurements, such as AC and DC voltage, AC and DC current, and resistance. It is called a multimeter because it combines the functions of a voltmeter, ammeter, and ohmmeter. Multimeters may also have other functions, such as diode and continuity tests. T Project Objective(s): The project aims at producing an FPGA module which can allow monitoring of different electrical signals with automatic scaling and ranging facilities. Project Resources • Budget: € 400 Industrial Partners involved: Expected Project Deliverables: FPGA interfacing to sensors Student background / interest: VHDL/Electronics Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 8 Learning Parameters of COSFIRE Object Recognition Model Supervisor(s): Dr George Azzopardi george.azzopardi@um.edu.mt; Co-supervisor (if any): None Problem Background COSFIRE filters are highly effective to detect and recognize objects in complex scenes. A COSFIRE filter is trainable in that it is configured to detect an object that a user specifies in a training phase. In its current form, a COSFIRE filter is configured by analyzing the geometrical properties of a single training example. While this is very useful in applications where we only have one training example, it lacks the ability to generalize when multiple training examples are available. Project Objective(s): In this project we will aim to configure COSFIRE filters by learning the parameters from multiple training examples. We will explore machinelearning techniques such as maximization expectation to determine the involved parameters. As to the evaluation, we will use an object detection benchmark data set (e.g. car side view detection: http://tinyurl.com/jvpmy48), to compare the enhanced COSFIRE filters that uses multiple examples for configuration with the basic COSFIRE filters that use only one training example. There is a high potential that this project will lead to a publication. Downloads: • Research paper on COSFIRE filters: http://tinyurl.com/mdb6gmk • Matlab code of the current COSFIRE filters: http://tinyurl.com/n3t5r7g. Project Resources • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: • • • • Literature survey Develop a learning algorithm to determine the parameters of COSFIRE filters for the modeling of objects Evaluation on benchmark data sets; e.g. side-view car detection Thesis Student background / interest: Interest in machine learning and/or vision systems Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 9 Smart Phone App for Interactive Line Drawing of Natural Images Supervisor(s): Dr. George Azzopardi george.azzopardi@um.edu.mt; Co-supervisor (if any): None Problem Background The idea is to allow a user converting images taken by a smart phone into line drawings. Project Objective(s): The aim of this project is to improve the efficiency of the existing stateof-the-art CORF algorithm and to implement it as a smartphone app. Just like the image enhancements functionalities on smartphones we will add a new app to extract the contours of a given picture. The extraction of contours may also be performed in an interactive way. For instance, the user may be allowed to extract the contours only of selected objects, such as faces. Also the user will be able to add, remove and modify strokes created by the algorithm. The student will then evaluate the implemented app by comparing its improved efficiency with other state of the art contour extraction algorithms and by analyzing a user satisfaction questionnaire. Downloads: • Matlab code of the contour detection algorithm: http://tinyurl.com/kkkplnd • Research paper of the CORF algorithm: http://tinyurl.com/pexz4xh Project Resources • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: • • • • Literature survey Implementation of an efficient version of the CORF contour detection algorithm as a smart phone app. Evaluation on benchmark data sets and user satisfaction survey Thesis Student background / interest: Interest in vision systems and smart phone applications Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 10 Aggression Detection in Urban Areas Based on Audio Analysis Supervisor(s): Dr George Azzopardi george.azzopardi@um.edu.mt; Co-supervisor (if any): None Problem Background Aggression detection in urban environments is an important application as it increases the piece of mind of residents. Surveillance cameras are used to record the visual and audio information of particular place. This topic has attracted the interest of a large research community Project Objective(s): The aim of this project to detect and recognize audio signals, which are associated with aggression. In particular we will investigate three types of audio signals, namely gunshots, screams, and breaking of glass. We will use a benchmark data set of audio signals created by the University of Salerno with whom I have close collaboration. For the detection of the mentioned three patterns we will compare at least two techniques: dynamic time warping and COSFIRE filters. This work has a high potential of a publication. Project Resources • Industrial Partners involved: University of Salerno Expected Project Deliverables: Budget: €__0___ • • • • Literature survey Implementation of the detection of screams, gunshots and breaking of glass patterns in audio signals Comparison of the dynamic time warping method with COSFIRE filters Thesis Student background / interest: Interest in audio analysis is required Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 11 Image Classification using Bag of Visual Words and Novel COSFIRE Descriptors Supervisor(s): Dr George Azzopardi george.azzopardi@um.edu.mt; Co-supervisor (if any): None Problem Background Image classification is used in several computer vision applications, ranging from scene categorization, movie shot detection, object recognition, music categorization in genres based on their spectrogram, among others. The bag of visual words (BOVW) approach has gained particular popularity in computer vision especially in image classification tasks. The main idea is to describe an image as a histogram of keypoint descriptors. A keypoint descriptor is a set of numerical values that describes the (geometrical) properties around a point. The SIFT, SURF, and LBP are among the mostly used descriptors in BOVW. Project Objective(s): In this project the student will evaluate a new type of keypoint operators called COSFIRE (Combination of Shifted Filter Responses). COSFIRE filters are trainable and they have been found highly effective in various applications, including traffic sign detection and recognition in complex scenes, detection of vascular bifurcations in retinal images and handwritten digit recognition. The student will extend the COSFIRE filters by generating descriptors and use them within the BOVW model. The student will use an image classification benchmark data set (such as scene categorization, CALTECH data sets, see: http://tinyurl.com/kava77p) to compare the performance of BOVW using the new COSFIRE descriptors with the traditional BOVW that uses SIFT keypoint detectors. There is a high potential that this project will lead to a publication. Downloads: • Research paper on COSFIRE filters: http://tinyurl.com/mdb6gmk • Matlab code of the current COSFIRE filters: http://tinyurl.com/n3t5r7g Project Resources Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: • • • • • Literature survey Develop COSFIRE based descriptor Implementation of bag of words using COSFIRE descriptors Evaluation on a benchmark data set of image classification Thesis Student background / interest: Interest in vision systems Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 12 Delineation of Vessels in Retinal Fundus Images Supervisor(s): Dr George Azzopardi george.azzopardi@um.edu.mt; Co-supervisor (if any): None Problem Background Retinal images provide a unique opportunity to investigate the health status of a person in a non-invasive way. Besides eye-related diseases (e.g. diabetic retinopathy, and age-macular diseases), from such images medical experts can identify signs of other pathologies such as atherosclerosis and hypertension. The delineation of vessels in retinal images is a crucial step in medical differential analysis. The ability of delineating the vessel tree from the rest of the image can help medical experts to perform better diagnosis. This is not a new problem in the literature and several attempts have been made. Recently, a vessel delineation algorithm, called B-COSFIRE, has been proposed for the delineation of vessels in retinal images (Azzopardi et al. 2015). While it is highly effective to detect medium size vessels, it suffers from insufficient ability to detect thin vessels. Project Objective(s): In this project we will use insight from the inhibition mechanism that was proposed in a contour detection operator (Azzopardi and Petkov 2014), which achieves high robustness to low signal-to-noise ratio. We expect that by adding a similar inhibition mechanism to the B-COSFIRE algorithm, we will be able to improve the performance especially on detecting thin vessels. There is high potential that this project will lead to a publication. Downloads: • Matlab code of the B-COSFIRE algorithm: http://tinyurl.com/pfxcxl5 • Matlab code of the contour detection algorithm: http://tinyurl.com/kkkplnd • Research paper of the B-COSFIRE algorithm: http://tinyurl.com/l43z7oy Project Resources • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: • • • • • Literature survey Develop an inhibition mechanism to B-COSFIRE filters Implementation of retinal segmentation using the developed BCOSFIRE filters with inhibition Evaluation on benchmark data sets of retinal images Thesis Student background / interest: Interest in vision systems and/or medical image analysis Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 13 □ The project involves human subjects; please specify. Design of a Multistage Noise Shaping (MASH) Converter using the 0.18 µm CMOS Process Supervisor(s): Prof. Ivan Grech ivan.grech@um.edu.mt; Co-supervisor (if any): None Problem Background ADCs are an important element for most systems in order to interface the analogue sensors to the digital processing section. Noise-shaping converters are widely used since they rely on low-precision components and can still achieve high resolution. The multistage approach achieves st nd high order noise filtering using only 1 and 2 order closed loop modulators, eliminating problems with stability. Project Objective(s): The scope of this project is to design a 1-1-1 or a 2-1 noise shaping converter using the 0.18 µm AMS CMOS process. Project Resources • Cadence with AMS 0.18µm hit kit (available). Industrial Partners involved: • None Expected Project Deliverables: • • Literature review on MASH conveters Design of ADC building blocks and simulation results Student background / Interest: Ethical and Data Protection Issues • Analogue circuit design Please tick if any of the following apply □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 14 Design of MEMS-Based Resonators Supervisor(s): Prof. Ivan Grech ivan.grech@um.edu.mt Co-supervisor (if any): None Problem Background MEMS resonators offer high quality (narrow band) response and also compatibility with CMOS processes. Furthermore, by appropriate choice of the resonant modes and electrode placement, it is possible to achieve balanced/unbalanced port termination, which greatly opens the application field of such resonators. Project Objective(s): • • • • • Choice of appropriate drive/sense transduction mechanism (piezo / electrostatic) Design of basic resonator structures (1 or 2 port) including Q-factor characterization Analysis of unbalanced/balanced port topologies Analysis of resonators for impedance transformation Analysis of the possibility of fine tuning using appropriate DC bias Project Resources • Coventor or ANSYS FEM software (available) Industrial Partners involved: • None Expected Project Deliverables: • • • • • • Literature review on MEMS resonators Design and simulation of simple 1 or 2 –port resonators Design and simulation of balanced/unbalanced port resonators Design and simulation of resonators intended for impedance transformation Analysis of the possibility of fine tuning via DC bias Student background / Interest: • • Analogue circuit design MEMS design Ethical and Data Protection Issues Please tick if any of the following apply □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 15 Auditory Processing Modelling using FPGAs (continuation) Supervisor(s): Prof. Ivan Grech ivan.grech@um.edu.mt; Co-supervisor (if any): None Problem Background The inner ear structure, referred to as the cochlea performs important spectral analysis of the incoming audio signal whose output is further processed by the auditory pathway and the brain in order to performs tasks such as speech recognition and sound localization. Traditionally, silicon models of the cochlea were designed using analogue hardware. However, today’s FPGAs can compete in speed with analogue systems, with the added advantage of higher precision and flexibility, making FPGA implementation of cochlea models an attractive solution. A digital model of the inner ear has already been developed in a previous FYPs. The scope of this project is to add further processing capability as well as post auditory signal processing for pitch and localization cues extraction. Project Objective(s): The objective of this project is to model auditory processing which takes place in the auditory nerve using FPGA hardware. Such processing includes, auto-correlation, cross correlation and peak detection in order to extract pitch information and localization cues Automatic gain control in the inner ear will also be modeled. The digital system should extract monaural and binaural cues which can be used for sound source localisation. Project Resources • • • • Xilinx ISE Foundation Series MATLAB ModelSim FPGA Evaluation board Industrial Partners involved: • None Expected Project Deliverables: • • Student background / interest: Ethical and Data Protection Issues • • • Literature review of cochlea and post-cochlea processing with emphasis on digital implementations Design of the HDL code for the cochlea and auditory pathway modeling Simulation Results. VHDL/ FPGA programming Familiarity with Xilinx ISE Foundation Series / Modelsim Please tick if any of the following apply □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 16 Implementation of a Customisable Decimation Filter for SigmaDelta Converters using VHDL Supervisor(s): Prof. Ivan Grech ivan.grech@um.edu.mt ; Co-supervisor (if any): None Problem Background Sigma-delta ADCs are used in applications requiring high resolution and relatively low sampling rates. The analogue front-end of sigma-delta ADCs (called a sigma-delta modulator), produces a 1-bit, high oversampled bit stream that needs to be processed into a low frequency high resolution output. In this process, there is a compromise between output data rate and resolution. Project Objective(s): The objective of this project is to design customisable VHDL code which will implement the decimation filter. The decimation rate (and output resolution) should be user-programmable. The code should also be easily adaptable to different converter topologies. Test sequences for the designed VHDL code can be generated using a Simulink Model for the sigma-delta modulator front-end. Project Resources • • • • Xilinx ISE Foundation Series MATLAB ModelSim FPGA Evaluation board Industrial Partners involved: • None Expected Project Deliverables: • • • • • • Literature review on decimation filters for sigma-delta modulators Design of the HDL code for the decimation filer Simulation Results. Integration with simulink model for sigma-delta modulator VHDL/ FPGA programming Familiarity with Xilinx ISE Foundation Series / Modelsim Student background / interest: Ethical and Data Protection Issues Please tick if any of the following apply □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 17 A LLVM Bitcode Interpreter for Microcontrollers Supervisor(s): Dr Joshua Ellul joshua.ellul@um.edu.mt; Co-supervisor (if any): None Problem Background Over the past decade LLVM [3] has been gaining more traction and adoption by both academia and the industry alike. LLVM provides a compiler infrastruc- ture and intermediate representation (IR) that allows different source languages (e.g. C and Java) to be compiled for different architectures. LLVM uses its IR as the target of the first ’Frontend’ compilation pass. A final ’Backend’ compilation pass is performed on IR to produce the native code for the target architecture (e.g. x86, ARM, etc). IR is often smaller than native code. In resource constrained microcontrollers having tens of kilobytes of program space and around ten kilobytes of memory, space is of prime importance. In this project we will investigate techniques to interpret LLVM IR code on resource constrained 16-bit microcontrollers in an efficient manner. We will aim to specifically implement an interpreter for Atmel AVR 8-Bit microcontrollers, how- ever will also focus on facilitating other resource constrained microcontrollers. In doing so we will investigate intermediate representation design [1], garbage collection and memory management [2] techniques. References: [1] Faisal Aslam, Luminous Fennell, Christian Schindelhauer, Peter Thiemann, Gidon Ernst, Elmar Haussmann, Stefan Ru ̈hrup, and Zastash A Uzmi. Op- timized java binary and virtual machine for tiny motes. In Distributed Com- puting in Sensor Systems, pages 15–30. Springer, 2010. [2] Niels Brouwers, Koen Langendoen, and Peter Corke. Darjeeling, a feature- rich vm for the resource poor. In Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems, pages 169–182. ACM, 2009. [3] Chris Lattner and Vikram Adve. Llvm: A compilation framework for lifelong program analysis & transformation. In Code Generation and Optimization, 2004. CGO 2004. International Symposium on, pages 75– 86. IEEE, 2004. Project Objective(s): Implement an LLVM Bitcode Interpreter for Atmel AVR microcontrollers Project Resources • Budget: €__0___ N/A resources in hand Industrial Partners involved: N/A Expected Project Deliverables: Interpreter for LLVM Bitcode for Atmel AVR microcontrollers Student background / interest: C, Assembly Ethical and Data Please tick if any of the following apply. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 18 Protection Issues □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 19 Multi-core Thread Scheduling Supervisor(s): Dr Kevin Vella kevin.vella@um.edu.mt; Co-supervisor (if any): Mr Keith Bugeja, Mr Sandro Spina Problem Background This project concerns the efficient scheduling light-weight threads on contemporary multi-core processors. The principal aim is to minimise overheads and maximise the utilisation of computational resources. A number of alternative designs for thread schedulers will be proposed and implemented, and their relative merits and shortcomings compared and contrasted through empirical measurement. Issues to be considered include the impact of alternative scheduling queue arrangements, contention on shared scheduler data structures, effective utilisation of the cache hierarchy, automatic thread migration across cores and integration with the operating system. • • Project Objective(s): • • • Project Resources • • Industrial Partners involved: N/A Implement a uniprocessor thread scheduler Implement a multiprocessor thread scheduler with per-core run queues Implement a multiprocessor thread scheduler with a shared run queue Investigate, propose and implement alternative run queue arrangements for the multiprocessor thread scheduler Measure and contrast the relative performance of the above design alternatives across a variety of work-loads Budget: €__0___ A multi-core PC Expected Project Deliverables: • • • Literature review on thread scheduling Working implementations of various thread schedulers Empirical results that characterise the relative performance of the alternative designs, and a thorough analysis Student background / interest: • • • • Concurrent programming Operating systems and systems programming (preferably Linux) Contemporary computer architecture C and assembly language Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 20 EEG Analysis and Epileptic Seizure Detection Supervisor(s): Dr Lalit Garg lalit.garg@um.edu.mt; Co-supervisor (if any): None Problem Background Epilepsy is a serious neurological disease that has an adverse socioeconomic impact on a substantial segment of the world population. A number of studies have been carried out in the past to explore the feasibility of a practical real-time seizure detector for effective management and mitigation of this disease [1]. With this goal in sight we have already developed/ proposed some novel methods using machine learning techniques such as singular vector machine (SVM) and extreme learning machine (ELM) [2-3] for seizure detection using an exhaustive scalp EEG data collected from pediatric patients. [2]. In this final year project (FYP), we will extend our work to develop novel machine learning approaches for seizure detection. Empirical datasets would be used to assess these novel approaches against existing approaches. 1. Ali H. Shoeb, John V. Guttag: Application of Machine Learning To Epileptic Seizure Detection. ICML 2010: 975-982. 2. Huang, G. B., Wang, D. H., & Lan, Y. (2011). Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics, 2(2), 107-122. 3. Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1), 489-501. 4. Agrawal A, Garg L, Dauwels J (2013) Application of empirical mode decomposition algorithm for epileptic seizure detection from scalp EEG, The 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’13) Osaka, Japan, 3-7 July 2013. Project Objective(s): 1. Review of literature on EEG analysis methods, epileptic seizure and methods for epileptic seizure detection. 2. Understand popular approaches for EEG analysis and epileptic seizure detection. 3. Understanding of advanced signal processing and machine learning methods for EEG analysis and epileptic seizure detection. 4. Problem analysis and design. 5. Acquiring exhaustive scalp EEG data of seizure patients. 6. Rigorous testing and comparison of existing epileptic seizure detection methods. 7. Developing novel approaches for epileptic seizure detection by analyzing EEG data. 8. Implementing these techniques using real datasets using Matlab/ C/ C++. 9. Evaluating these approaches using real datasets. 10. Report writing Project Resources • Budget: €__0___ A computing device (PC or Laptop), Internet Access, Matlab, C/C++, UM Library access, Access to high quality literature resources. Industrial Partners None ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 21 involved: Expected Project Deliverables: • • • • • Literature review on EEG analysis methods, epileptic seizure and methods for epileptic seizure detection. A fully properly tested working prototype implementation of approaches for epileptic seizure detection by analyzing EEG data. Critical evaluation of these approaches Results, analysis and conclusion The project Report Student background / interest: Knowledge of basic signal processing methods, Good programming skills in a language of your choice. strong analytical and problem solving skills and fast learning abilities, reliable, responsible, hardworking, enthusiasm and determination to learn and acquire new skills. Ethical and Data Protection Issues Please tick if any of the following apply. ■ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 22 Hospital Admission Pattern Analysis, Bed Resource Requirements Forecasting, Allocation and Management Supervisor(s): Dr Lalit Garg lalit.garg@um.edu.mt; Co-supervisor (if any): None Problem Background Healthcare resource planners need to develop policies that ensure optimal allocation of scarce healthcare resources. This goal can be achieved by analysing admission patterns to forecast daily resource requirements to ensure optimum allocation and management of available resources. If resources are limited, admission should be scheduled according to the resource availability. Such resource availability or demand can change with time. We here model admissions and patient flow through the care system as a discrete time Markov chain. In order to have a more realistic representation, a non-homogeneous model is developed which incorporates time-dependent covariates, namely a patient’s present age and the present calendar year. However, more sophisticated models are required to better manage changes in admission patterns and resource requirements. As our previous work, we have already developed many such sophisticated models for better modelling admission patterns and resource requirements [1-4]. In this final year project (FYP), we will extend our work to develop novel approaches to effectively solve the problem using AI/ML based methods. 1. Garg L, McClean SI, Meenan BJ, Millard PH (2010). A nonhomogeneous discrete time Markov model for admission scheduling and resource planning in a care system. Health Care Management Science. 13(2):155–169. 2. Garg L, McClean SI, Meenan BJ, Millard PH (2009). Nonhomogeneous Markov Models for Sequential Pattern Mining of Healthcare Data. IMA journal Management Mathematics. 20(4): 327344. 3. Garg L, McClean SI, Meenan BJ, Barton M, Fullerton K (2012). Intelligent patient management and resource planning for complex, heterogeneous and stochastic healthcare systems. In press. IEEE Transactions on Systems, Man, and Cybernetics--Part A: Systems and Humans. 4. Garg L, McClean SI, Meenan BJ, Barton M, Fullerton K (2013). An Extended Mixture Distribution Survival Tree for Patient Pathway Prognostication. Communications in Statistics: Theory and Methodology. 42(16):2912-2934. Project Objective(s): 1. Review of literature on hospital admission pattern analysis, bed resource requirements forecasting, allocation and management and hospital waiting lists. 2. Understand approaches for forecasting and scheduling. 3. Understanding of advanced AI and machine learning methods, including phase type survival tree analysis, survival analysis, Markov process model, Bayesian Analysis. 4. Problem analysis and design. 5. Pattern analysis and mining of hospital admission data. 6. Developing novel models for characterizing hospital admissions and its interrelationship with bed resource requirements, ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 23 enhancing/ improving on the existing models. 7. Implementing these models characterizing hospital admissions and its interrelationship with bed resource requirements using Matlab/ C/C++. 8. Evaluating the model using a real database from a hospital. 9. Report writing Project Resources • Budget: €__0___ A computing device (PC or Laptop), Internet Access, Matlab, C/C++, UM Library access, Access to high quality literature resources. Industrial Partners involved: Expected Project Deliverables: • • • • • Literature review on hospital bed occupancy and requirements forecasting A fully properly tested working implementation of characterizing hospital admissions and its interrelationship with bed resource requirements. Critical evaluation of the model Results, analysis and conclusion A Report Student background / interest: Knowledge of basic probabilistic methods, Good programming skills in a language of your choice. strong analytical and problem solving skills and fast learning abilities, reliable, responsible, hardworking, enthusiasm and determination to learn and acquire new skills. Ethical and Data Protection Issues Please tick if any of the following apply. ■ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 24 Machine Learning Methods for Handling Missing Data in Medical Questionnaires Supervisor(s): Dr Lalit Garg lalit.garg@um.edu.mt; Co-supervisor (if any): None Problem Background The proposed project is a part of a University funded project. Self-report questionnaires are used as an extremely valuable instrument to assess the quality of life of a patient, its relationship with socioeconomic and environmental factors, disease risk/ progress, treatment and disease burden, treatment response and quality of care. However, a common problem with such questionnaires is missing data. Despite enormous care and effort to prevent it, some level of missing data is common and unavoidable. Such missing data can have a detrimental impact on statistical analyses based on the questionnaire responses. A variety of methods have been suggested for missing data imputation. Nevertheless, more research is desperately needed to assess and improve the reliability of data imputation. We have already developed/ proposed some novel methods to handle missing data [1-4]. In this final year project (FYP), we will extend our work to develop novel machine learning procedures enforcing collaborative filtering to complete missing data in medical questionnaires. Empirical datasets would be used to assess these novel methods against existing methods. 1. Garg L, Dauwels J, Earnest A, Pang L (2013) Tensor based methods for handling missing data in quality-of-life questionnaires. IEEE Journal of Biomedical and Health Informatics. In press. doi: 10.1109/JBHI.2013.2288803. 2. Asif MT, Srinivasan K, Garg L, Dauwels J, Jaillet P (2013) Lowdimensional Models for Missing Data Imputation in Road Networks, ICASSP 2013, May 26 - 31, 2013. 3. Dauwels J, Garg L, Earnest A, Pang LK (2012). Tensor Factorizations for Missing Data Imputation in Medical Questionnaires, The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, Japan, March 25 - 30, 2012. 4. Dauwels J, Garg L, Earnest A, Pang LK (2011). Handling Missing Data in Medical Questionnaires Using Tensor Decompositions. The Eighth International Conference on Information, Communications, and Signal Processing (ICICS 2011). Singapore 13-16 December, 2011. Project Objective(s): 1. Review of literature on missing data imputation, types of missingness in data, missing data in medical questionnaires and novel machine learning methods for collaborative filtering. 2. Understand approaches for missing data imputation. 3. Understanding of advanced probabilistic, mathematical and machine learning methods, including Singular vector decomposition, extreme learning machine, tensor decomposition methods. 4. Problem analysis and design. 5. Acquiring real data and simulating data with different proportions, patterns and types of missingness. 6. Rigorous testing and comparison of existing missing data techniques for application to medical questionnaires 7. Developing novel missing data techniques, specifically designed ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 25 for repeated medical questionnaires. 8. Implementing these techniques using real and simulated datasets using Matlab/ R/ C/ C++. 9. Evaluating these techniques using real and simulated datasets. 10. Report writing Project Resources • Budget: €__0___ A computing device (PC or Laptop), Internet Access, Matlab, C/C++, UM Library access, Access to high quality literature resources. Industrial Partners involved: Expected Project Deliverables: • • • • • Literature review on missing data handling in survey questionnaires and missing data imputation techniques. A fully properly tested working implementation of tools for missing data handling in medical questionnaires. Critical evaluation of the model Results, analysis and conclusion The project Report Student background / interest: Knowledge of basic AI methods, Good programming skills in a language of your choice. Strong analytical and problem solving skills and fast learning abilities, reliable, responsible, hardworking, enthusiasm and determination to learn and acquire new skills. Ethical and Data Protection Issues Please tick if any of the following apply. ■ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 26 Design and Implementation of RF Microstrip Filters Supervisor(s): Dr Ing. Owen Casha owen.casha@um.edu.mt; Co-supervisor (if any): None Project Background: Radio frequency (RF) filters represent a class of electronic filters, designed to operate on signals in the megahertz to gigahertz frequency ranges. Filter designs beyond 1 GHz are difficult to realize with discrete components because the wavelength becomes comparable with the physical filter element dimensions, resulting in various losses that severely degrade the circuit performance. Thus, to arrive at practical filters, the lumped component filters must be converted into distributed element realizations. Such filters are commonly used as building blocks for duplexers and diplexers to combine or separate multiple frequency bands. Project Objective(s): The aim of this project is to design, simulate and implement various RF microstrip filters such as Stepped-Impedance L-C Ladder Type Lowpass Filters, Quasilumped Highpass Filters, Stub Bandpass Filters and Optimum Bandstop Filters. Project Resources • • • • QUCS - Quite Universal Circuit Simulator SonnetLite - Electromagnetic Simulator Vector Network Analyzer (VNA) MATLAB Industrial Partners involved: • None Expected Project Deliverables: • • • • Literature review Modeling and simulation of RF microstrip filters Implementation of the filter prototypes on a PCB Testing and Characterization Student background / Interest: Ethical and Data Protection Issues • Radio and Microwave Theory Please tick if any of the following apply □ The project has data protection issues: N/A. □ The project has ethical issues: N/A. □ The project involves human subjects: N/A. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 27 IoT in 4G and Beyond Supervisor(s): Dr. Ing. Saviour Zammit, savior.zammit@um.edu.mt; Co-supervisor (if any): None Problem Background The Internet of Things promises to change current business processes by connecting all “things” to the Internet. The Internet-connected fridge is a good example, which can inform its owner when supplies run low or how efficient it is running, but can also inform the white goods supplier about the mechanical and electrical health of the fridge itself, to enable preventive and corrective maintenance. However, the sheer number of devices to be connected, security issues, M2M communications and low power applications need careful design and implementation in 4G and beyond. This project investigates these aspects. Project Objective(s): • • To perform a literature review on the subject. To propose and model schemes supporting IoT implementation in 4G and 5G mobile systems. Project Resources • • • • Budget: None Required Indicate source of funds: None Required Literature: UoM Subscription Software: Matlab Industrial Partners involved: • None Expected Project Deliverables: • • • Literature Review, Physical and Link layer models, Protocol Analysis. A study of secure M2M communications in 4G and 5G Documentation - Dissertation (including documented simulation models and results) Student background / interest: • • Interest in Matlab programming and signal processing Interest in data communications protocols IP Issues □ The project has patent possibilities; please specify. Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. 1 1 If you tick the box then please consult the UREC webpage http://www.um.edu.mt/urec/gpropform for guidelines to prepare the necessary documents to accompany your proposal that will be forwarded to FREC to be approved by UREC. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 28 Portable Device for Detecting Electric Fields in Water Supervisor(s): Dr. Ing. Saviour Zammit, savior.zammit@um.edu.mt; Co-supervisor (if any): Dr. Chris Cooke, Coovers Infosec Ltd. (UK) Problem Background Swimming pool installations usually employ electric pumps, water treatment and underwater lighting. In event of fault conditions or poor engineering practice, electrical hazards can arise. The problem is the detection of water-borne electric fields, for the purposes of safety testing and certification of swimming pools. Hazardous electric fields will be simulated and there will be no actual exposure to hazardous voltages. Project Objective(s): • Project Resources • • Industrial Partners involved: • Expected Project Deliverables: • HARDWARE - Demonstrator or pre-production prototype (analogue test harness + microcontroller) • SOFTWARE - Compiled microcode (plus annotated source code) • DOCUMENTATION - Dissertation (including appended test results & software documentation) Student background / interest: • • • To develop a hand portable, battery-operated module, based on a programmable micro-controller and discrete interface components, to detect differential alternating electrical potentials and output to a normalised scale on an LED display with audio alarm. • Selection of the optimum microcontroller will be an essential preobjective. It is highly desirable to mature the design sufficiently to be able to build a PCB-based demonstrator / pre-production prototype. Successful project outcome would be the microcontroller properly performing against the target functional requirements. • The project scope includes the design of analogue components, however this is limited to those necessary for interfacing with and programming the microcontroller, and for testing purposes. Budget: €500 Indicate source of funds: Coovers Infosec Ltd is able to reimburse the cost of components purchased. Coovers Infosec Ltd. requires to own the IP in return for its financial and technical support. • Equipment/Software/Literature Coovers Infosec Ltd. The company will provide a detailed target technical specification which is available on request. Guidance on preparation of an analogue test harness can also be provided (this is to simulate hazardous electric fields without any exposure to hazardous voltages.) IP Issues Interest in Microprogramming Interest in Microcontrollers and DSP Interest in analogue electronics □ The project has patent possibilities; please specify. Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. 2 2 If you tick the box then please consult the UREC webpage http://www.um.edu.mt/urec/gpropform for guidelines to prepare the necessary documents to accompany your proposal that will be forwarded to FREC to be approved by UREC. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 29 □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. Smart Metering Supervisor(s): Dr. Ing. Saviour Zammit, savior.zammit@um.edu.mt; Co-supervisor (if any): None Problem Background The remote reading of utility meters can be of significant benefit to utility companies and their customers. Collecting the remote meter data in a reliable, timely and cost-effective manner depends on the optimization of the data communications protocols in use between the smart meters and the utility’s data collection points. This final year projects sets to analyze the data communications protocols in use so as to improve the timely and reliable collection of data. Project Objective(s): • • • • • To perform a literature review on the subject. To develop a model of the data communications channel between a smart meter and the data collection point. To develop a model of the data communications protocol on top of the data communications channel. To predict the behavior of data communications between the smart meter and the data collection points based on these two models. To study improvements in the data protocols to increase the throughput and reliability of the data exchanges between the smart meters and the data collection points. Project Resources • • • • Budget: None Required Indicate source of funds: None Required Literature: UoM Subscription Software: Matlab Industrial Partners involved: • Maltese utility company Expected Project Deliverables: • • • Literature Review, Physical and Link layer models, Protocol Analysis. A study of performance enhancement techniques. DOCUMENTATION - Dissertation (including documented simulation models and results) Student background / interest: • • Interest in Matlab programming and signal processing Interest in data communications protocols IP Issues □ The project has patent possibilities; please specify. Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. 3 3 If you tick the box then please consult the UREC webpage http://www.um.edu.mt/urec/gpropform for guidelines to prepare the necessary documents to accompany your proposal that will be forwarded to FREC to be approved by UREC. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 30 Configurable Soft Microprocessor on FPGA Supervisor(s): Dr Ing. Trevor Spiteri, trevor.spiteri@um.edu.mt Co-supervisor (if any): None Problem Background Soft microprocessors can be implemented completely using logic synthesis. Such soft cores can be implemented on FPGAs. In this project, a simple microprocessor with a number of configurable features be designed. For example, the word size and the address bus width can be configurable. Also, some features and their corresponding instructions can be enabled or disabled. For example, a multiplier with a multiplication instruction can be implemented and enabled or disabled during configuration. As a starting point, a VHDL implementation of a very basic microprocessor with a minimalist instruction set is provided. Project Objective(s): The aim is to start with a simple microprocessor with a minimalist instruction set, and then add some more specialized instructions, or change the basic features such as word size and address bus width. These features will be configurable, and a GUI application is to be designed to configure the microprocessor before synthesis. Project Resources • • • Industrial Partners involved: None Budget: €__0___ FPGA development board (available in labs) Xilinx ISE WebPACK design software Expected Project Deliverables: • • • • VHDL code GUI application to configure the microprocessor Testing Performance analysis Student background / interest: • • Hardware design using VHDL Simple GUI programming (Java, C#, Visual Basic, or any other language is suitable) Microprocessors • Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 31 Fast Block-Matching Motion Estimation Search on FPGA Supervisor(s): Dr Ing. Trevor Spiteri, trevor.spiteri@um.edu.mt Co-supervisor (if any): None Problem Background Most of the processing time in video compression algorithms is taken by the motion estimation search, making the motion estimation search a suitable target for optimization and acceleration. A macroblock is a block of pixels. A motion estimation search for a macroblock involves searching for a similar macroblock in a reference video frame. The displacement of this matching macroblock in the reference frame from the original macroblock is called a motion vector, as it represents the motion of the block from one frame to another. Unlike exhaustive searches, where all the possible macroblocks in a particular window are compared to the macroblock, fast searches involve matching only macroblocks at specific relative locations, and iterating a few times. This greatly reduces the amount of matches to compute. Project Objective(s): The aim is to develop a fast block-matching motion estimation search on FPGA that can be used to accelerate a video coding application. If there is enough time, different block-matching techniques can be developed and compared. Project Resources • • • • Industrial Partners involved: None Budget: €__0___ FPGA development board (available in labs) Xilinx ISE WebPACK design software Test video sequences Expected Project Deliverables: • • • • VHDL code Simulation results Testing Performance analysis Student background / interest: • • Image processing Hardware design using VHDL Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 32 Text Detection and Localisation in Video Supervisor(s): Prof Ing Victor Buttigieg victor.buttigieg@um.edu.mt; Co-supervisor (if any): None Problem Background Indexing video using semantic information is in general not an easy task. However, one way how this can be facilitated is by making use of any text embedded in the video. For example news video sources normally caption each news item using a corresponding headline. This can be used to segment the news video into different stories and the headline text to give an indication of what the news story is about. Project Objective(s): To detect artificial text in video and to localise its position. An OCR engine is then used to recognise this text. The extracted text is then used to suitably index the video. Project Resources • • • • Industrial Partners involved: None Expected Project Deliverables: Software (and relative documentation) implementing text detection and localisation algorithms. Student background / interest: Signal/Image processing, Programming in C# (very similar to Java/C++) Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. Budget: €0 1 PC running Microsoft Windows Microsoft Visual Studio (freely available to ICT students) Video Indexer Platform (Locally developed software that facilitates the processing of videos – freely available) ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 33 Efficient Implementation of Sequence Matching Supervisor(s): Prof Ing Victor Buttigieg victor.buttigieg@um.edu.mt; Co-supervisor (if any): None Problem Background There are several application areas (e.g. bioinformatics, error-correcting codes, information retrieval) where we need to compare two long sequences and to measure their similarity. Sequences may differ in symbol substitutions, insertion of extra symbols, deletion of symbols, or possibly transposition of adjacent symbols. Project Objective(s): The project’s objectives are to research algorithms to compare long sequences and to implement in software one (or more) such algorithm in an efficient way. Parallel implementations may also be investigated (using CUDA or other parallel architectures). Project Resources • • Industrial Partners involved: None Expected Project Deliverables: Implemented algorithm that measures the similarity between sequences. Student background / interest: Programming. Optimised algorithm implementation. Parallel processing. Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. Budget: €0 Software and hardware readily available ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 34 Digital Fountain Codes Supervisor(s): Prof Ing Victor Buttigieg vitor.buttigieg@um.edu.mt; Co-supervisor (if any): None Problem Background Digital Fountain Codes are a very efficient class of erasure-correcting codes. Erasures occur when data is lost over a channel, but it is known to be lost. For example a packet of data is lost over a network. The biggest advantage of Fountain Codes is that they are rate-less, and extra redundant bits are only transmitted only if required. Project Objective(s): The objective of this project is to familiarise oneself with these codes, implementing a coder and a decoder for a simple Fountain code and to analyse its performance over typical network scenarios. Project Resources • • Industrial Partners involved: None Expected Project Deliverables: Implemented codec in software and analysis simulation results. Student background / interest: Programming. Computer networks Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. Budget: €0 Software and hardware readily available ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 35 Sound Localisation Supervisor(s): Prof Ing Victor Buttigieg victor.buttigieg@um.edu.mt; Co-supervisor (if any): None Problem Background In several application areas it is required to automatically determine the location of a sound source. One possible application is to separate the sound from two different speakers located in different locations in a room. Project Objective(s): The objective of this project is to research different techniques that can be used to localise sound and to implement a simple, effective and cost efficient solution. Project Resources • • Industrial Partners involved: None Expected Project Deliverables: A system (using a computer) that is able to determine the location of the sound. Student background / interest: Signal Processing, programming Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. Budget: €0 A number of microphones may need to be purchased dependent on the technique adopted ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 36 Implementation and Comparison of Data Embedding Algorithms Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): None Problem Background Spatial-domain information hiding in images consists in the modification of pixel data in order to represent some message sequence. The resistance of each embedding method to lossy image compression schemes (such as JPEG) and the detectability of the embedding have a direct impact on the usability of these schemes. This project is researchoriented, and has potential for publication. Project Objective(s): Investigate the relationship between the parameters for the hidden information (such as message length, embedding strength, etc.) and the resistance to image compression and detectability Project Resources • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues • • • Interest in information hiding. Some knowledge of digital imaging fundamentals. Aptitude and willingness to program (the project is likely to use a selection of languages, including C++ and Python). Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 37 Algorithm Implementation on Highly Parallel Architectures Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): Problem Background CUDA is an interface for general-purpose programming on Graphical Processing Units (GPUs) from NVIDIA. The architecture of GPUs emphasises massive parallelism of arithmetic units at the expense of control units and memory caching. This allows a very high speed-up for classes of computationally-intensive data-parallel problems, often found in scientific computing. This is an implementation project, with a significant research orientation. Project Objective(s): Implement a compute-intensive algorithm on GPUs; suitable algorithms to be discussed with supervisor Project Resources • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues • Interest in parallel computing. Aptitude and willingness to program (the project requires the use of C++ and NVIDIA CUDA; prior OO development experience in another language is suitable). • Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 38 High Density 2D Barcodes - Research Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): Problem Background A number of standards for 2D barcodes exist, which allow the encoding of more data (in the same physical space) than conventional 1D barcodes. Various companies, including Microsoft and HP, have shown interest in techniques that increase the encoding density – that is, the amount of data that can be encoded per unit area. Other researchers have also used techniques from watermarking and steganography to create barcodes that do not look random. This project is research-oriented, and has potential for publication. Project Objective(s): Investigate existing standards and proposed techniques, comparing their embedding density and decoding reliability. It is expected that some of these techniques will need to be implemented and tested. Project Resources • Budget: €__0___ • Interest in information hiding. • Some knowledge of digital imaging fundamentals. • Aptitude and willingness to program (the project is likely to use a selection of languages, including C++ and Python). Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 39 High Density 2D Barcodes - Implementation Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): Problem Background A number of standards for 2D barcodes exist, which allow the encoding of more data (in the same physical space) than conventional 1D barcodes. Various companies, including Microsoft and HP, have shown interest in techniques that increase the encoding density – that is, the amount of data that can be encoded per unit area. Other researchers have also used techniques from watermarking and steganography to create barcodes that do not look random. This project is implementationoriented. Project Objective(s): Investigate and compare existing standards and proposed techniques. Implement a reader for a specific system on an embedded or portable device (such as a mobile phone). Project Resources • Budget: €__0___ • Interest in information hiding. • Some knowledge of digital imaging fundamentals. • Aptitude and willingness to program. • Knowledge of Java and Android development would be helpful. Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 40 Information Hiding using Imperceptible Yellow Printer Dots Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): None Problem Background Since the introduction of high quality colour laser printers, the US Government has required colour laser printouts to imperceptibly embed document tracking information. This has been achieved by creating an imperceptible grid of tiny yellow dots across the page. Yellow dots are used to take advantage of a weakness in the human visual system that makes seeing yellow on white difficult. If the dots need to be extracted, a blue light can be shone on page, resulting in the dots becoming visible, and thus enabling manual detection. Our previous work has demonstrated that the same technique can be used to embed arbitrary data, which can then be automatically extracted after printing and scanning. This project is challenging, heavily research based and would aim to produce a publication. Project Objective(s): This project will look to continue our previous work in this area. There are two possible streams that could be looked at. \begin{enumerate} Project Resources • Optimising the placement of the yellow dots in order to both reduce errors and increase capacity. This may also involve looking at whether it is possible to interleave our dots with those printed by the laser printer itself – currently we print our documents on ink jet printers that do not print their own yellow dots. This is a more practical based approach and will involve conducting extensive testing and require good programming skills to implement any changes. • A more theoretical approach would look at optimising the error correction code currently used. We initially used a naive error correction code as proof of concept, however, there is substantial scope for optimisation. This would involve both conducting tests to evaluate the characteristics of the channel (printing and scanning documents to determine error rates) as well as constructing a more optimised error correction code. • Budget: €__0___ Industrial Partners involved: Expected Project Deliverables: Student background / interest: • • Interest in information hiding Willingness to program – the current implementation is in Java, so good Java skills are essential • For stream 2 a background in mathematics or error coding is desirable ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 41 Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 42 Updates to Distributed Simulator for Communications Systems Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): None Problem Background SimCommSys is a multi-platform distributed Monte Carlo simulator for communication systems. The error control coding component implements various kinds of binary and non-binary codes, including turbo, LDPC, repeat-accumulate, and Reed-Solomon. This code base has been in continuous development since 1997, and currently weighs in at over 45 700 physical lines of code, written by Dr Briffa and collaborators. The distributed computing component of this code uses a client/server architecture built on TCP/IP to facilitate running simulations on grid resources; this also works well on local clusters. Project Objective(s): This project will look to extend the existing code base, continuing our previous work in this area. Various extensions could be looked at, including: Project Resources • Writing a cross-platform GUI for the simulator (i.e. writing software to create and edit simulation files in a user-friendly way). • Writing a back-end / middle-ware for matching resources with simulations. • Adding a result validation component to confirm simulation reproducibility and facilitate the use of public computing. • Budget: €__0___ • Interest in low-level computing issues and parallel computing. • Aptitude and willingness to program (the project requires the use of C++; prior OO development experience in another language is suitable). Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 43 Image Forensics Supervisor(s): Dr Johann A. Briffa johann.briffa@um.edu.mt; Co-supervisor (if any): None Problem Background This topic involves participation in the supervisor's ongoing work in multimedia security. The topic of image forensics deals with issues related to the authentication of digital images, or the identification of their provenance. Usually these topics are of interest to cases in the courts of law, where such images are used as evidence. Project Objective(s): Depends on identified problems within the supervisor's ongoing work, as agreed with the student. Project Resources • Budget: €__0___ • Interest in image forensics / multimedia security. • Some knowledge of digital imaging fundamentals. • Aptitude and willingness to program (the project is likely to use a selection of languages, including C++ and Python). Industrial Partners involved: Expected Project Deliverables: Student background / interest: Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 44 A Finger Detection System for a Projected Phone Keypad Supervisor(s): Dr. Ing. Nicholas J. Sammut nicholas.sammut@um.edu.mt; Co-supervisor (if any): None Problem Background A Finger Detection System for a Projected Phone Keypad Research is underway to have nano video projectors replace touch screens and hence increase the portability of mobile phones, tablets, laptops and wearable devices. To complete the human interface, a robust finger detection system is required to allow the user to control the device, select buttons and move cursors on the projected image. If these issues are overcome, the user would be able to use a projected image in the same way as a touchpad. Apart from the challenges of detecting the finger itself such systems have other practical considerations stemming from shadows and the lack of an actuator to indicate selection. Project Objective(s): This project involves the setting up of the necessary hardware to detect a finger on a projected phone keypad, distinguish it from its shadow and finding a practical method of distinguishing user selection from user browsing. This very interesting practical project may have commercial value and may be patentable. Project Resources Budget: €750 + license fees (Video projector, video camera, tilt sensor, actuator, Matlab or LabVIEW Vision toolbox license) Industrial Partners involved: None Expected Project Deliverables: Hardware and software system to select phone buttons of a projected mobile phone keypad. Student background / interest: Computer Engineering Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 45 An Automatic Projection Correction System for Corner Surfaces Supervisor(s): Dr. Ing. Nicholas J. Sammut nicholas.sammut@um.edu.mt; Co-supervisor (if any): None Problem Background An Automatic Projection Correction System for Corner Surfaces Video projected images are skewed when projected onto wall or ceiling corners or round surfaces. This creates challenges for video immersion applications and projections of advertisements on corner surfaces or round surfaces due to misalignments between the projector and the screen. Project Objective(s): This project involves the setting up of the necessary hardware to detect and measure the image skew as well as the programming of the calibration system, the image reconstruction, the image rendering and the overall correction of the skew effects on the uneven surfaces. This very interesting practical project may have commercial value and may be patentable. Project Resources Budget: €750 + license fees (Video projector, video camera, tilt sensor, Matlab or LabVIEW Vision toolbox license) Industrial Partners involved: None Expected Project Deliverables: Hardware and software system to correct the skewed images of projectors on corners and/or round surfaces. Student background / interest: Computer Engineering Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 46 Automatic Automotive Mirror Correction System Supervisor(s): Dr. Ing. Nicholas J. Sammut nicholas.sammut@um.edu.mt; Co-supervisor (if any): None Problem Background Automatic Automotive Mirror Correction System The wrong adjustment of vehicle side and room mirrors results in blind spots that are the cause of several road accidents. Drivers often forget to adjust the mirrors correctly especially when they change their position in the car or when they use a different vehicle. Project Objective(s): This project involves the setting up of the necessary hardware and software to automatically find the optimum mirror angle for vehicles. The system includes a camera system to detect the position of the driver a software system to perform the image processing and the control system to control the mirror angle. Project Resources Budget: €1000 + license fees (2 automatic side mirrors with controllers, video camera, proximity sensor, Matlab or LabVIEW Vision toolbox license) Industrial Partners involved: None Expected Project Deliverables: Hardware and software system to correct the projector mirror angles Student background / interest: Computer Engineering Ethical and Data Protection Issues Please tick if any of the following apply. □ The project has data protection issues; please specify. □ The project has ethical issues; please specify. □ The project involves human subjects; please specify. ICT3903 – Final Year Project in Computer Engineering B.Sc. (Hons.) in Computer Engineering Faculty of ICT, Final Year Project Proposal 47