top of page


  • Use of Machine Learning in Twitter Feed Sentiment Analysis (2018-2019): (Source of funding: Teesside University Computing School Research Fund, UK)
    This project aims to develop an application for sentiment analysis through Twitter feeds. There are different events happening and there are many tweets about any event. But many events have an important outcome like in the case of an election, mass protest, football match or a movie. In this research, we will analyse the twitter feeds surrounding an event or person or company using machine learning and try to do sentiment analysis and/or behaviour prediction based on our analysis, along with other inputs surrounding that event. Status: Ongoing.


  • Automatically Detect Eye Diseases through Retinal Image processing and Machine Learning (2017-2108): (Source of funding: Teesside University Grand Challenge Research Fund, UK)
    This project aims to automatically detect eye diseases early from retinal images through image processing and machine learning. This work will use public datasets like DRIVE, STARE, and HRF. There is clearly a need to address and diagnose eye diseases early and efficiently which is the rationale behind this project. An estimated 19 million children under age 15, are visually impaired. Of these 12 million children are visually impaired due to refractive errors, a condition that could be easily diagnosed and corrected. Status: Ongoing.

  • Smart City Sensing (2017-2108): (Source of funding: Teesside University Grand Challenge Research Fund, UK)
    This project demonstrated the capabilities of real-time online environmental data acquisition and analytics for the provision of smart city services. The review and application of identified suitable data ontologies for urban sensor data transfer were conducted to enable best-practice ways for near-real-time online upload of urban sensory data and subsequent provision of smart city services. The application of such ontologies was pursued using real-time open source online sensor data storage and visualisation platforms, e.g. world air quality index project ( Testing of the sensor data collection and visualisation were conducted using desktop and mobile access devices. Status: Completed.


  • North East Innovation Observatory Project (2017-2018): (Source of funding: North East LEP through Durham University, UK)
    This project was Durham University-led that aimed to measure the level of business innovation in the industries across North East, collaborating with three other universities (Northumbria, Sunderland and Teesside). The project was led by Professor Kiran Jude Fernandes of Durham University who had won a seed grant through North East Local Enterprise Partnership (NE-LEP). Most of these universities hosted the research progress meetings for discussions and debate. A report on the study done was being submitted to LEP in May 2018, with analysis and graphs generated through web visualization tools. Status: Completed. The draft report (Developing an Innovation System):
    The report (pdf)

  • Tackling Twitter Spam Drift through Semi-Supervised Learning Approach (2016-2017): (Masters Student Research Project, Teesside University, UK)
    In this project, a semi-supervised learning approach (SSLA) has been proposed to tackle Twitter Spam drift. In order to protect the users, Twitter and the research community have been developing different spam detection systems by applying different machine-learning techniques. However, a recent study showed that the current machine learning-based detection systems are not able to detect spam accurately because spam tweet characteristics vary over time. This issue is called 'Twitter Spam Drift'. Our new approach uses the unlabeled data to learn the structure of the domain. Different experiments were performed on datasets to test and evaluate the proposed approach and the results show that the proposed SSLA can reduce the effect of Twitter Spam Drift and outperform the existing techniques. Status: Completed.

  • Automatic Analysis and Scoring of Corporate Sustainability Reports - A Machine Intelligence Approach (2012-2014): (Source of funding: Swinburne University of Technology Studentship Grant, Malaysia)
    This project developed a software tool to automate the analysis of corporate sustainability reports. As more and more corporations and business entities have been publishing corporate sustainability reports, the current manual process of analyzing the reports is becoming obsolete and tedious. We argued that, given sufficient quality training using a custom corpus, corporate sustainability reports can be analyzed in mass numbers using a supervised learning based text mining software. We improved the accuracy of our classifier as well as the feature selector in order to gain better performance and more stability. Additionally, the achieved results of executing the developed software on one hundred reports were discussed in order to prove our claims. Status: Completed.


  • A Secure Electronic Voting Software Application based on Image Steganography and Cryptography (2011-2013): (Source of funding: Swinburne University of Technology Studentship Grant, Malaysia)
    This project implemented an online voting system based on image steganography and visual  cryptography. The system was implemented in Java EE on a web-based interface. After considering the requirements of an online voting system, the cryptographic and steganography techniques best suited for the requirements of the voting system were chosen, and the software was implemented with techniques like the password hashed based scheme, visual cryptography, F5 image steganography and threshold decryption cryptosystem. The analysis, design and implementation phases of the software development of the voting system are done. The user acceptance testing of the system was also done. Status: Completed.


  • Analyzing Corporate Reports in a Three-Dimensional Perspective using Data Mining and Statistical Approach towards Sustainability Reporting (2009-2010): (Source of funding: Swinburne University of Technology Internal Grant, Malaysia)
    This project intended to measure the corporate environmental reports (CERs) in terms of economic, environmental and social performance indicators using Global Reporting Initiative (GRI) guidelines. A large sample (N=2415) is used to perform text mining so as to analyze the reports to come up with a scoring. The significant contribution made in the study indicates that by adopting the GRI guidelines, it is observed that global CERs is now undergoing fragmented reporting in its incremental approach. Bayesian estimate confirms the probability that the true value of all the selected variable parameter falls within the confidence interval of 95%. Status: Completed.


  • Robust Spam Detection Filter – Analysis and Implementation on Large Spam Corpus (2008-2009): (Source of funding: Swinburne University of Technology Internal Grant, Malaysia)
    This project developed a spam detection algorithm and its implementation using Java, along with its performance test results on two independent spam corpora – Ling-spam and Enron-spam. We used the Bayesian calculation for single keyword sets and multiple keywords sets, along with its keyword contexts to improve the spam detection and thus to get good accuracy. We also used the Porter Stemmer algorithm. Status: Completed.

  • A CSI-based Throughput and QoS Enhancement Scheme for TCP over Cooperative Broadband Wireless Networks (2008-2010): (Source of funding: eScience Fund, Malaysia)
    This project (No. 901-01-09-SF0039) was led by Dr. C. E. Tan of University Malaysia Sarawak, Malaysia along with the Swinburne University of Technology as a collaborator, to work on enhancing the performance of broadband wireless networks through CSI based throughput and QoS enhancement of TCP.  The project was for a two-year duration. Status: Completed. 


  • Optical Tomography Research Project: (Source of funding: Department of Science and Technology (DST)/Council of Scientific and Industrial Research (CSIR), India)
    This funded research project was led by Prof. R. M. Vasu of the Department of Instrumentation, Indian Insitute of Science (IISc), Bangalore, India. The project looked at the non-interferometric methods of estimation of the phase of transmitted wavefronts through refracting objects for application in optical tomography, among other things. I worked as a project assistant at the Tomography Lab, whose responsibility was to convert the MATLAB programs/algorithms into C programs to make it compatible with TMS320C40 (fourth generation Digital Signal Processor from Texas Instruments, designed primarily for parallel processing) processors so as to make the program run faster. Status: Completed. 


bottom of page