https://ir.kdu.ac.lk/handle/345/5053 2026-04-22T01:07:59Z 2026-04-22T01:07:59Z Abeyrathne, EMUWKM Perera, BHD Kulasekara, DMR Goonatilleke, MAST https://ir.kdu.ac.lk/handle/345/5259 2023-04-26T10:58:36Z 2021-01-01T00:00:00Z

An Optimum Train Selection and Management Platform Abeyrathne, EMUWKM; Perera, BHD; Kulasekara, DMR; Goonatilleke, MAST Sri Lanka, as a developing country faces rapid urbanization, which leads to high mobility requirements. Due to increased traffic congestions during peak hours, people tend to select the railway system as their mode of transportation. As a considerable amount of people choose railway as their preferred platform in their daily routine, it is highly crucial to maintain an efficient and timely railway system. Unfortunately, the Sri Lankan Railway system is not known for its efficiency. As a result, considerable number of daily users of the system are affected in their daily routines. Increasing the efficiency of underlying infrastructure has been going on for decades, yet it has not been a solution for the inefficiency of the railway system itself. Hence, the only logical approach to address this issue is to introduce a common platform, which the users and Railway department can communicate, while maintaining a stand-alone system which can select optimum trains for the users. The objective of this research is to discuss the necessity of the proposed solution, ultimately providing a solution to the inefficiency of the railway system of Sri Lanka. The proposed platform will comprise of two parts; A web application for the railway department and an Android-based mobile Application for railway users. The web application will be powered by a ESP8266 and NRF-24 based hardware modules with a firebase Backend. A mobile application will gather required inputs via the hardware modules to provide users with an optimum train to travel at any given time of the day towards the required destination. System will be running using dynamic data acquired from the train stations with a dynamic train schedule. Users will have the opportunity to get notified about train delays, unavailability and breakdowns. The aim of this research is to provide a common communication platform to railway department and public, ultimately making railway platforms more efficient.

2021-01-01T00:00:00Z Fernando, RM Ilmini, WMKS Vidanagama, DU https://ir.kdu.ac.lk/handle/345/5258 2023-04-26T11:44:06Z 2021-01-01T00:00:00Z

Air Quality Prediction Using Machine Learning Fernando, RM; Ilmini, WMKS; Vidanagama, DU The main basis of human survival is Air. The Air Quality Index is the value that qualitatively describes the condition of air quality. The greater the Air Quality Index, the more threatening risk to human health and environment. In Sri Lanka, poor air quality is a huge concern, especially in cities like Colombo and Kandy. Accurate Air Quality prediction will minimize health issues that can occur due to air pollution. This research has attempted to identify the best-suited machine learning algorithmbased approach to predict accurate air quality based on PM2.5 concentration in Colombo. In order to identify the most influenced air pollution concentrations for the air quality prediction purpose, correlation analysis was conducted. In this research, PM2.5 was predicted in Colombo city using 4 related air pollution concentrations including SO2 concentration, NO2 concentration, PM2.5 concentration & PM10 concentration. In order to get higher prediction accuracy, the gathered dataset was pre-processed by prediction beforehand. The prediction model trained and tested using machine learning algorithms such as KNN, Multiple Linear Regression, Support Vector Machines, and Random Forest. Multiple Regression was identified as the most suited prediction model which was able to gain 94% higher accuracy.

2021-01-01T00:00:00Z Denipitiya, IN Gunathilake, HRWP Senanayake, C https://ir.kdu.ac.lk/handle/345/5257 2023-04-26T11:02:39Z 2021-01-01T00:00:00Z

Toothcare: A Toothbrush Quality Identifying App Using Machine Learning and Image Processing Denipitiya, IN; Gunathilake, HRWP; Senanayake, C Toothbrushes of varied qualities, designs and standards are globally available, yet majority of them do not conform to international standards. There is no proper guidance or awareness given for the people with this regard. So, generally people do not know to choose the suitable toothbrushes they need, when they require to replace the used toothbrush, and whether the existing toothbrush is suitable for use. Therefore, the Toothbrush Standard Monitoring App provides a solution for all the above mentioned issues. This app is capable to scan the user’s toothbrush and identify its condition. Machine learning and one of image processing techniques, image classification are mainly used for development of the app. Android Studio, Java programming language and firebase are used as development platform, backend development language and database platform respectively. The main purpose of implementing this app is to improve the dental health of human beings with the help of modern technology, and this will be the very first such solution implemented, addressing the above-mentioned health and social issues. This app functions in order to make people aware about the quality of toothbrushes and the conditions, hence reducing dental health issues and acknowledging people regarding the time period when they need to replace the existing brush with a new one. Accordingly, the app suggests certified toothbrushes following the user’s data, monitoring the quality and damaged capacity of the toothbrush using image processing and informs the user whether the toothbrush can further be used or needs to be replaced. For this process, a TensorFlow Lite model with 83.48% of accuracy has been developed.

2021-01-01T00:00:00Z Kawya, MVT Wedasinghe, N Samaraweera, WJ https://ir.kdu.ac.lk/handle/345/5256 2023-04-26T11:17:23Z 2021-01-01T00:00:00Z

Knowledge Management Systems in the Agricultural Context to Face Resilience in the New Normal Kawya, MVT; Wedasinghe, N; Samaraweera, WJ The COVID-19 pandemic has given a forceful full stop to all daily routines, while shutting downing workplaces, entertainments and meetings among others. Amidst the revolution of the Coronavirus, the active parts of the world are only the essential services such as health, food production and supply. The continuation of the pandemic has created a New Normal with lapses in the production lines evoking the value of cultivation and their need to engage in self-productions. Therefore, farmers and the public have attempted at taking steps to cultivate at their best as they do have to survive. Though the start-up was a success, issues arise with the continuation of their cultivation due to the lack of precise knowledge and experience. Primarily, the issue arises with the lack of knowhow knowledge for cultivation. Therefore, this research provides a critical analysis of how knowledge management systems can support sustainable progress in cultivation. This paper attempts to define the meaning of knowledge management and knowledge management systems in national and international perspectives to guide the unguided public in critical New Normal conditions.

2021-01-01T00:00:00Z