http://dlib.iit.ac.lk/xmlui/handle/123456789/1614 2026-04-08T18:30:58Z 2026-04-08T18:30:58Z Karagampitiya, Nirmani http://dlib.iit.ac.lk/xmlui/handle/123456789/2195 2024-06-05T04:57:34Z 2023-01-01T00:00:00Z

Voluntary Turnover Prediction System for Tourism Industry with Special Reference to Hotel Industry in Sri Lanka Karagampitiya, Nirmani "Sri Lanka is a popular tourist destination which attracts a high number of tourists. Tourism sector directly contributes 4.3% of Sri Lanka's Gross Domestic Product and ranks third in terms of country's foreign exchange earnings. The hotels and restaurant sector is one of the four sub-sectors which form the tourism and travel sector and the main role in the tourism sector is played by hotels by offering various guest amenities to visitors. In addition, 81% of all direct employment associated with tourism in Sri Lanka are found in hotels and restaurants. Furthermore, as the hotel industry is a service industry, it relies heavily upon human resources. One of the key challenges faced by the Sri Lankan tourism industry is high voluntary turnover, particularly among lower-level workforce. Since the highest productivity of the hotel industry is contributed by lower-level hotel employees as they directly engage with customers, retaining them is vital. When voluntary turnover occurs, hotels experience inability to deliver a quality service to customers and increase in expenses. Even though the need to gain an in depth understanding of employee turnover exists, carrying out research on this issue has been heavily neglected. Therefore, currently no proper systematic approaches are in place for hotel human resources personnel to utilise to address hotel employee turnover effectively . The author implemented machine learning models to accurately predict the turnover rate and the possible retention period of lower-level hotel employees. A classification model was developed to predict the turnover rate and a regression model was developed to predict the possible retention period of employees. Pre-processing tasks such as feature scaling, class imbalance handling was incorporated and hyper parameter tuning was also incorporated to enhance the performance of the models. Out of the classification models, ExtraTreesClassifier exhibited the highest F1 score of 98.8%, whilst XGBRFRegressor produced the highest R2 score of 96.33% out of the selected regression models. Through these models, the author sought to provide turnover insights pertaining to each individual employee and enable hotel Human Resources personnel to successfully address the issue of voluntary turnover among lower-level employees."

2023-01-01T00:00:00Z Gunasekara, Shohan http://dlib.iit.ac.lk/xmlui/handle/123456789/2194 2024-06-05T04:54:18Z 2023-01-01T00:00:00Z

Human Count and Crowd Prediction in Public Transportation Gunasekara, Shohan "The issue of overcrowding and uncertainty about transportation arrival times and crowd levels in public transportation causes people to seek alternative modes of transportation. To address this, our solution introduces an IoT device to provide real-time information on the number of passengers and crowd prediction in public transportation, as well as periods of expected crowding. The methodology used involves implementing the IoT device to count the number of passengers on a bus and integrating this information with a software platform to provide the necessary information to recipients. The main results show that this system can help recipients estimate waiting time periods, use public transportation in less crowded time slots, and plan their tasks efficiently with live location and arrival time information. The system can also help reduce overcrowding in public transport and enhance the efficiency of humans by reducing time wastage. The research concludes that this software can provide valuable information to frequent public transportation users to make efficient transportation decisions, ultimately resulting in a reduction in human traffic in public transportation and a smoother commuting experience."

2023-01-01T00:00:00Z Puvimannasinghe, Roshie http://dlib.iit.ac.lk/xmlui/handle/123456789/1790 2024-02-28T04:27:32Z 2023-01-01T00:00:00Z

Online Shopping System Puvimannasinghe, Roshie "During the period of Covid pandemic people still wanted to move on with their regular activities. Therefore, the technology applications were challenging part for them but to do their regular activities they had no choices so they had to move on with these challenging technology applications. And because of the Covid pandemic, more new online applications with different domains were joining the business market. Based on my research and findings the problem is most customers struggle to find a particular clothing items in traditional clothing shops for their events such as ceremonies, birthday parties, sporting events, Gatherings etc, they are wasting their time, couldn’t get a dress, selected dress is not satisfied and their traveling expenses by searching from other clothing shops based on their preferences. Based on these problem backgrounds, The project aims to analyze the problems faced by the customers. To design and develop a suitable online web application platform solution. The project aim is to develop a fashion recommendation clothing website for an online shopping system that can help customers find clothes that meet their specific needs and preferences to attend their events. To understand more about the existing solutions and technologies in use in the area, a literature review was conducted and with that, a survey with a targeted set of customers was used to review the findings. The website will use machine learning algorithms to provide personalized recommendations. The methodology followed involves collecting and analyzing data on customer behaviors and preferences, identifying relevant attributes for different clothing items. The main result of this project is the development of a recommendation website that can help customers find clothing items that meet their specific needs and preferences based on their event. This project has the potential to improve customer satisfaction and increase sales."

2023-01-01T00:00:00Z Munaweera Arachchilage, Risandu Olitha http://dlib.iit.ac.lk/xmlui/handle/123456789/1789 2024-02-28T04:22:51Z 2023-01-01T00:00:00Z

Muscle score Munaweera Arachchilage, Risandu Olitha "Fitness industry has blooming over last years since more and more customers investing into their own health. As per statistics fitness industry has been growing rate of 8.7% over the recent years due to people focusing more and more on both physical and mental health (22 Fulfilling Fitness Industry Statistics [2023]: Home Workout And Gym Statistics – Zippia, no date). Specially after covid 19 number of people that involves and interest in fitness has been risen suddenly. During the pandemic period all the gyms and fitness centers were down as government took decisions to minimize places that people gather. People tend to work out from home at the time in order to improve their physical and mental health while staying in shape. Even though majority started performing activities at their home most of them was not motivated or haven’t got proper guidance in order to get expected outcome. According to the surveys and research carried out they have found out that most people tend to follow videos and other materials on internet which led them to wrong directions which distract them from achieving their end goal. This happens mainly because information overload. The finding of the evaluation pointed to the necessity of platform where people can find motivation to themselves to carry the momentum and find knowledge from experts in the industry and find out more opportunities that they has to enhance their health and physical appearance. As a result, “Muscle Score” was developed as a mobile application to fulfill clients requirements by allowing them to find nearby gyms to work out and find fitness instructors to guide and motivate when they workout at their home moreover through the application people can raise their question and post blogs related to their fitness problems. The proposed fully functioning application has been using the latest technology and guarantee high rated service for the users. Solution has been tested with proper methods to maintain the quality."

2023-01-01T00:00:00Z