http://dlib.iit.ac.lk/xmlui/handle/123456789/2305 2026-04-08T18:30:58Z 2026-04-08T18:30:58Z Guruge, Shehan Fernando, Pumudu http://dlib.iit.ac.lk/xmlui/handle/123456789/2262 2025-05-02T08:17:03Z 2022-01-01T00:00:00Z

GlucoFriend: Glycaemic Variability Prediction for Diabetes Patients Guruge, Shehan; Fernando, Pumudu Glycaemic Variability is one of the main complication diabetes patients’ face frequently. Even though smart equipment has been invented for blood glucose levels management, majority of the diabetes patients rely on Glucometer and other manual methods to measure and record their blood glucose levels in Sri Lanka. This research focuses on providing a solution for people in need, for predicting their blood glucose levels to benefit them in managing their Glycaemic levels. This study further focuses on the prediction ability of a sparser dataset (only 3 recordings per day) and proposes a methodology for predicting the blood glucose values for new patients. Entire study is divided into four broader categories as, personalized prediction with carb, personalized prediction without carb, non-personalized prediction with carb, and non-personalized prediction without carb. Out of the above four modules, personalized prediction with carb obtained the maximum prediction accuracy of mean rate of 85.3% for 8 patients. non-personalized prediction module obtained the maximum Glycaemic prediction accuracy mean rate of 79%.

2022-01-01T00:00:00Z Silva, Ravidu Suien Rammuni Fernando, Pumudu http://dlib.iit.ac.lk/xmlui/handle/123456789/2261 2025-05-02T09:04:22Z 2022-01-01T00:00:00Z

Effective Utilization of Multiple Convolutional Neural Networks for Chest X-Ray Classification Silva, Ravidu Suien Rammuni; Fernando, Pumudu Imaging for medical purposes (Medical Imaging) involves various technologies and processes that capture different areas/organs of the human or the animal body. These imaging modalities contain various types of visual representations corresponding to different structural and qualitative properties of the scanning area. These are very helpful in identifying and confirming a disease’s presence or keeping track of the progression of an already diagnosed disease. Radiography, Magnetic resonance imaging (MRI) and Ultrasonography are typical examples of Medical Imaging Technologies. A Report by UNICEF in 2019 [1] shows that a child dies because of pneumonia every 39 s. It further shows that pneumonia causes more deaths, especially in children more than any other infectious disease. Tuberculosis is another dangerous disease like that. Even though deadly diseases like Pneumothorax have a comparatively low death rate, [2] shows that it has a high recurrence rate which can be very harmful. Most chest-related diseases can be controlled or sometimes completely cured if identified early and treated well. The most used method in diagnosing chest-related diseases is Chest Radiography. The advantages of chest radiography are the low cost and its convenient operation. Nevertheless, as shown in [3], confusions can occur when diagnosing chest-related diseases using chest radiography due to the complex structural representations in chest radiography images, which can differ from one person to another.

2022-01-01T00:00:00Z Tennakoon, Sachini Rupasinghe, Sulochana http://dlib.iit.ac.lk/xmlui/handle/123456789/2260 2025-05-02T09:04:55Z 2022-01-01T00:00:00Z

Comprehensive Review on Tea Clone Classification Systems Tennakoon, Sachini; Rupasinghe, Sulochana A wide range of tea clones have been developed over the years. As each tea clone produces a distinct quality of tea, it is critical to identify them in the field. Tea clones may have extremely similar characteristics, making it difficult for tea farmers and tea estate owners to distinguish them manually. This problem can be resolved by using machine learning to create an application that recognizes tea clones automatically. This paper conducts a comparative review of existing tea clone classification systems, followed by a study that identifies research gaps and potential future works.

2022-01-01T00:00:00Z Ananda, Kalana Gayantha Ratnayake, Gayashini Shyanka http://dlib.iit.ac.lk/xmlui/handle/123456789/2247 2025-05-02T09:05:59Z 2022-01-01T00:00:00Z

Predictive Tool to Overcome Negative Thinking of Employees with Anxiety Ananda, Kalana Gayantha; Ratnayake, Gayashini Shyanka Among significant portion of the population, anxiety disorder can be considered as the most prominent psychological condition. Anxiety may limit many people's activities and make it difficult for them to enjoy their lives. An increase in negative thoughts would raise people's fear and worry, which potentially leading to anxiety disorder. The number of remote workers has risen as a result of the pandemic situation. A considerable number of employees are faced with anxious thoughts because of the workplace isolation. This was proved by a pilot study done among 102 employees in Sri Lanka. The proposed solution is a mobile application that employees can use to diagnose the anxiety level using machine learning and support to overcome their negative thinking behavior, through cognitive behavioral therapy exercises by allowing them to do self-improvement activities. The visually represented dashboard can monitor the positive thinking improvement of the user.

2022-01-01T00:00:00Z