Research Papers - Dept of Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593

Browse

Filters

20226

Advanced Search

Filter by

Settings

Start date: 2020Subject: search.filters.subject.Development

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    PublicationEmbargo
    Development of Low Resource Machine Learning Models for Child Cognitive Ability Assessments
    (IEEE, 2022-12-09) Kahawanugoda, A; Gnanarathna, K; Meegoda, N; Monarawila, R; Samarasinghe, P; Lindamulage, A.G
    Automated cognitive assessment tools are state-of-the-art in assessing cognition development. Due to the low availability of resources, building automated cognitive ability evaluation tools is challenging. This study focuses on developing machine learning models using a limited amount of data to assess Reasoning IQ, Knowledge IQ, Mental Chronometry and Attention-levels of Sinhala-speaking children between the age of 7 to 9 years. Our solution includes Sinhala speech recognition systems, image classification models, gaze estimation, blink count detection and facial expression recognition models to evaluate the above four cognitive ability measuring factors. Open domain speech recognition has been used to evaluate complex Sinhala child verbal responses and limited vocabulary responses were assessed using an end-to-end speech recognition system, respectively achieving 40.1% WER and 97.14% accuracy. Additionally, the image classification models for handwritten Sinhala letter recognition and two shape recognition models have gained 97%, 89% and 99% accuracy. The linear regression model for attention level evaluation that utilizes the inputs from a combination of eye-gaze estimation, facial expression recognition and blink rate detection models has gained 85% accuracy.
  • Thumbnail Image
    PublicationEmbargo
    SmartPredi – Development of Agricultural Crop Wastage Reduction System using Machine Learning
    (IEEE, 2022-12-09) Weerasinghe, W.M.K.I.B.; Somawansha, K.W.A.M.; Chandrasiri, K.A. Jayanga; Thalagahagedara, T.M.S.Y.B.; Chathurika, K.B.A Bhagyanie; Swarnakantha, N.H.P Ravi Supunya
    The culture and economy of Sri Lanka heavily depend on agriculture. The All-Island Farmers Federation (AIFF) claims that post-harvest produce loss is a problem that has plagued farmers in all regions of Sri Lanka and occurs both on farms and in commercial locations. The lack of a suitable system to handle produce, such as fruits and vegetables, has been identified as the key problem. The process of sowing seeds to generating the harvest and transporting it to the consumers is an overly complex process. If this process is not correctly identified the demand and supply may not be at equilibrium. Farmers tend to take decisions based on their experiences or from the knowledge gathered from past generations. Over the year environmental factors as well as economic factors have changed, therefore there is a high chance that the decisions taken by farmers might lead to wastage of crops. This research hopes to produce a mobile application for the farmers by considering some factors that affect the wastage in crops and try to provide timely relevant information to minimize the crop wastage by deploying machine learning, one of the advanced technologies in crop prediction.
  • Thumbnail Image
    PublicationEmbargo
    Developing A User-Friendly Interface from Robotic Applications Development
    (IEEE, 2022-10-04) Fernando, W. A. M.; Jayawardena, C; Rajapaksha, U. U. S.
    In this research, we have developed a web-based Robot Operating System (ROS) learning environment with its own set of tools. Our system is a comprehensive learning environment where students can go through the tutorials using the web interface and use our web-based development environment for writing scripts. Furthermore, students can use the web-based Gazebo simulator to visualize the robots. In addition, our learning environment also has its own set of tools that students can utilize for testing and troubleshooting robots. One of the other benefits of our system is that it is platform independent, and hence it can be accessed from either computer, mobile phone or tablet. Our system also has a dropdown for selecting commands. In this, all the descriptions and syntaxes of the commands are predefined and populated whenever a command is added from the dropdown. In addition, we have developed multiple other features that make this system much easier to use and user-friendly. In order to verify the usability of the system, we have performed a heuristic evaluation, and our findings show that the system complies with nine of the ten heuristics in Nielsen’s framework. In addition, our system complies with twelve of the fourteen heuristics in Zhang’s framework. We performed a performance evaluation as well. In this, we compared the performance of simulating our web-based system against running the same simulation directly from a Linux-based ROS server using the Gazebo client. The results showed that our system was faster by a small margin.
  • Thumbnail Image
    PublicationEmbargo
    Deep Learning Approach for Designing and Development of Risk Level Indicator for Patients with Lung Diseases
    (IEEE, 2022-02-23) Chathurika, K. B. A. B; Gamage, A
    "Lung disease" as a medical term, discusses as several disorders that affects both lungs. There are different types of lung disease like Asthma, lungs infections like Influenza, Pneumonia, Tuberculosis, and numerous other types of breathing problems including Lung cancers. These lung diseases can be the main reason for failure in breathing. Due to COVID19 pandemic, Pneumonia and COVID19 were highlighted mostly as fatal diseases if not detected on time. Newly identified COVID19 diseases has caused many deaths and confirmed detections reported worldwide, followed with a greatest risk to community wellbeing, especially for patients with lung diseases. Process of developing a clinically accepted vaccine or specific therapeutic drug for this disease are not finalized, which will contribute to the expansion of actual prevention action plans. Thus, methods to detect lung illness accurately and efficiently is important. Proposed solution will easily and precisely detect the risk level of patients with these two lung diseases Pneumonia and COVID19 using a mobile application with chest radiography (Chest X-rays), which is considered as a cheap, easy to access and speedy manner. Proposed solution will identify, classify and evaluate the risk level of the patient suffering with the use of Image Processing, Machine Learning techniques and Convolutional Neural Networks. So, anybody who use the proposed solution may have the ability to have a precious decision about own medical condition accurately, quickly with low cost. Proposed solution can calculate severity level of a patient with more than 97% accuracy with chest radiography analysis together with patient’s current symptoms and breath holding time evaluation.
  • Thumbnail Image
    PublicationEmbargo
    Development of Agent-Based Centralized Tool For Analyzing and Managing Security-Enhanced Linux Policies using WebSocket Protocol
    (IEEE, 2022-02-23) Rajapaksha, S; Kularatna, I. M
    The SELinux facilitates and includes an extensible "MAC" structure built within the Linux kernel. An application or a process life cycle that runs as a user has the specific authority to access objects such as files, sockets, and other processes with Linux’s default Discretionary Access Control (DAC). SELinux prescribes the access and the progress privileges of each user, application, process, and the files on the system and administers the communications of these elements utilizing a security strategy that determines how severe or indulgent a given Red Hat Enterprise Linux establishment ought to be. However, its constraints such as, not being user-friendly, having too complicated policies, and complex policy description language, are limiting the implementation of SELinux policies in the Information Technology industry. As a result, there is only a little research available on User Interface-based policy management tools. Even those researches have limitations such as the inability to remotely manage a host/server, manual documentation, and the inability to monitor the systems automatically from a dashboard. In order to overcome said research gap and problems, this research will implement a system using a web-socket technology that facilitates the ability to converse in full-duplex through just one TCP connection. This system is included with a web socket-agent, which can be installed in server endpoints and can change SELinux policies, a web-socket server: which can do live communication with the agent to perform policy changes along with the UI component: to manage policies using the user interface and a database component to store policy details.
  • Thumbnail Image
    PublicationEmbargo
    Development of Agent-Based Centralized Tool For Analyzing and Managing Security-Enhanced Linux Policies using WebSocket Protocol
    (IEEE, 2022-04-14) Kularatna, I. M; Rajapaksha, S
    The SELinux facilitates and includes an extensible "MAC" structure built within the Linux kernel. An application or a process life cycle that runs as a user has the specific authority to access objects such as files, sockets, and other processes with Linux’s default Discretionary Access Control (DAC). SELinux prescribes the access and the progress privileges of each user, application, process, and the files on the system and administers the communications of these elements utilizing a security strategy that determines how severe or indulgent a given Red Hat Enterprise Linux establishment ought to be. However, its constraints such as, not being user-friendly, having too complicated policies, and complex policy description language, are limiting the implementation of SELinux policies in the Information Technology industry. As a result, there is only a little research available on User Interface-based policy management tools. Even those researches have limitations such as the inability to remotely manage a host/server, manual documentation, and the inability to monitor the systems automatically from a dashboard. In order to overcome said research gap and problems, this research will implement a system using a web-socket technology that facilitates the ability to converse in full-duplex through just one TCP connection. This system is included with a web socket-agent, which can be installed in server endpoints and can change SELinux policies, a web-socket server: which can do live communication with the agent to perform policy changes along with the UI component: to manage policies using the user interface and a database component to store policy details.