SLIIT Conference and Symposium Proceedings

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/295

All SLIIT faculties annually conduct international conferences and symposiums. Publications from these events are included in this collection.

Browse

Search Results

Now showing 1 - 10 of 26

Open Access
Fitness Warrior: Fitness and Nutrition Tracker with Personalized Goal Generation
(SLIIT City UNI, 2025-07-08) De Mel, Y.D; Nallapperuma, P.M
Fitness Warrior is a comprehensive mobile fitness tracking application developed using React Native and Firebase that addresses critical limitations in existing solutions through the innovative integration of machine learning, gamification, and social features. Traditional fitness applications suffer from inaccurate step detection (with error rates exceeding 20% error rates), inefficient nutrition tracking interfaces, poor user retention (with 73% abandonment within three months), and a lack of adaptive personalization. This project uniquely implements ondevice machine learning via TensorFlow.js for privacypreserving step detection, combines TF-IDF vectorization with cosine similarity for efficient food searching, and incorporates principles of Self-Determination Theory through a cohesive social motivation framework. Development followed the Agile Scrum methodology, implementing a CNN-based model processing sensor data at 50Hz sampling rate, creating a database of 2,395 food items with optimized search algorithms, and designing gamified social features. The application achieves 95.2% real-world step counting accuracy compared to manual counting, significantly outperforming conventional threshold-based approaches (48.3% accuracy), while the calorie tracker delivers 92.7% relevant results in top-5 suggestions with 126ms search latency. Evaluation with 21 users demonstrated exceptional impact: 95.3% reported increased daily steps, 90.4% experienced greater calorie intake awareness, and 71.4% found social features strongly motivating. The application received outstanding approval with 90.5% of testers rating overall satisfaction at 8 or higher on a 10-point scale. This research successfully demonstrates how integrated, machine learning-enhanced fitness applications can meaningfully impact user health behaviours while overcoming significant limitations in existing solutions.
Open Access
Smart Chat: A Mobile Chat Application Based on Machine Learning
(SLIIT City UNI, 2025-07-08) Yathuraj, G; Abeysinghe, A
In an increasingly digital world, communication is primarily conducted through messaging apps, but these platforms cannot often convey emotional nuance. This limitation can lead to misunderstandings, emotional disconnects, and deteriorating relationships. SmartChat addresses this gap by integrating machine learning-based emotion recognition into a mobile chat app, allowing users to send and receive voice messages enriched with emotional context. Built using React Native and compatible with both Android and iOS, SmartChat analyzes voice cues such as tone, pitch, and cadence to detect and display emotions to the user. This innovation improves the clarity and empathy of conversations, making digital communications more humancentered. Beyond general messaging, SmartChat has the potential to be used in critical contexts such as education, mental health support, and emotional literacy. By making emotionally aware communication accessible across languages and cultures, SmartChat contributes to fostering healthy interpersonal relationships and supports the broader goal of social sustainability through technology.
Open Access
AI-Driven To-Do List: Optimizing Task Categorization and Prioritization Using Ensemble Models
(SLIIT City UNI, 2025-07-08) Vishaliney, P.; Pemasiri, C.S; Kanthakumar, M; Yatigammana, N
This paper introduces the AI-driven smart todo list that can cluster and prioritize activities by using the machine-learning methods. Traditionally, to-do list services are immovable and have an element of compromising users to input the information themselves; this sort of bare tool can easily lead to unproductiveness in accomplishment of duties. To address this situation, we supplement ensemble modeling, namely Logistic Regression, XGBoost, and Multilayer Perceptron, to delegate the tasks to the desired categories and define priorities by their urgency. Measured based on standard measures, the ensemble will achieve 47.7 percent accuracy when doing classification and 72.8 percent when predicting priority, and High Priority tasks will gain in this evaluation. Using BERT-based embeddings in combination with TF-IDF-based vectorization, the system should improve its effectiveness because it understands the semantics of described tasks. Together these blocks form a superb ensemble architecture that can beat stand-alone model when it comes to classification and forecasting. More importantly, the system still leaves itself potential to adjust to user behavior and therefore it can improve task management, and it is a feasible platform in real time organization of tasks.
Open Access
Paddy Disease Identification and Impact Calculation Using Machine Learning
(SLIIT Business School, 2023-12-14) Sandeepanie, N; Rathnayake, S; Gunasinghe, A
Rice is a crucial staple crop globally, providing over half of humanity's caloric intake. It supports the livelihoods of small-scale farmers and landless laborers worldwide. With the growing population, there is a high demand for rice production. Sri Lanka is renowned for its high- quality rice and has a long history of paddy cultivation. However, not all the country's 708,000 hectares of land dedicated to paddy cultivation are utilized due to water scarcity and unstable terrain. The objective of this paper is to explore the ways of enhancing the quality of the paddy crop during its vegetative phase by early identification of diseases through the utilization of emerging technologies. The vegetative phase constitutes a critical stage in the growth of paddy, exerting significant influence on the overall yield, resistance to pests and diseases, nutrient assimilation, and the environmental implications of agricultural practices. The primary emphasis of this paper is to identify diseases to which paddy crops are susceptible during the vegetative phase and subsequently present avisual representation of their locations on a map, serving as the output for end-users. Early identification of paddy diseases is crucial for effective crop management and high yields. These diseases, caused by different pathogens, can significantly hinder plant growth and productivity if not detected and treated promptly. Identifying them early allows farmers and experts to take timely and targeted actions, like applying suitable fungicides or implementing cultural practices, to control their spread and minimize crop damage.
Embargo
Banana Disease Identification Using Machine Learning Based Technologies and Weather-Based Dispersion Analysis
(IEEE, 2022-12-09) Kothalawala, M.U.; Gaveshith, M.G. K; Tharaka, A.H.D.H.; Punchihewa, I.A; Sriyaratna, D
Banana is the fourth most important food crop in the world as well as the most important and popular fruit crop in Sri Lanka. Banana leaf diseases are becoming one of the most important factors affecting agricultural products. As a result of these diseases, the quantity and quality of agricultural produce have drastically decreased. Hence, early detection and classification of banana leaf diseases are becoming more important than ever. But the ancient method of disease identification, visual observation is no longer helpful in this matter as it requires significant knowledge and experience related to banana diseases and symptoms which present farmers severely lacks. Therefore, using ICT-based approaches such as autoML, deep learning, natural language processing and APIs are very important towards the efficiency of the disease identification process and the accuracy of the diagnosis as well as keeping farmers synced with the information related to their plantation such as recent threats and nearby threats.
Open Access
Cryptocurrency Price Prediction: A Comparative Study using LSTM, GRU and Stacking Ensemble Algorithm for Time Series Forecasting
(SLIIT, 2022-02-11) Ashikul Islam, M. D
Technology has significantly reshaped how humans interact with their tangible and intangible surroundings. Cryptocurrency is considered to be one of the most recent technological inventions which revolutionized how we perceive currencies and their functionality. It has become popular because of its safety, security and anonymity. However, volatility remains one of the major issues with cryptocurrencies to this day. Therefore, the primary aim of this paper is to develop LSTM (Long ShortTerm Memory), GRU (Gated Recurrent Units) and a Stacking Ensemble Learning algorithm that efficiently predicts the price of a cryptocurrency for a given period of time. The predictions are then observed and analysed to determine the comparative performance of the said algorithms.
Open Access
Support Vector Machine Based an Efficient and Accurate Seasonal Weather Forecasting Approach with Minimal Data Quantities
(SLIIT, 2022-02-11) Chandrasekara, S; Tennekoon, S; Abhayasinghe, N; Seneviratne, L
Climate change makes a big impact in our daily activities. Therefore, forecasting climate changes prior to its actual occurrences is important. Even though highly accurate weather prediction systems throughout the world are available, they require mass amounts of data exceeding thousands of data points to obtain a significant accuracy. This study was aimed at proposing a Support Vector Machine based approach to carryout seasonal weather predictions up to thirty-minute intervals, the results of which would be considerably effective with respect to predictions carried out with models trained with annual datasets. The model was trained utilizing a dataset corresponding to the district of Kandy which consisted of 136 samples, 20 features, and 5 labels. By means of carrying out numerous data preprocessing steps, the model was trained, and the relevant hyperparameters were optimized considering the grid search algorithm to yield a maximum accuracy of 86%, once tested via the k-fold cross validation. The performance of the Support Vector Machine was also then compared for the same dataset with that of the K-Nearest Neighbor algorithm which consumed relatively fewer computing resources. An optimal accuracy of 61% was observed for this model for a K-value of 27. This approach supported the concept of a Support Vector Machine’s ability to perceive time series forecasts to a relatively higher degree and its ability to perform effectively in higher dimensional datasets with smaller number of samples. As per the future work, the Receiver Operating Characteristic analysis is proposed to be carried out to evaluate the performance of the model and the dataset size is proposed to be further enhanced to a maximum of a thousand samples to yield the best performance results.
Open Access
Special Event Item Prediction System for Retails – Using Neural Network Approach.
(SLIIT, 2022-02-11) Alwis, T; Pemarathna, P
Selling and buying is the general process marketing field follows. Nowadays marketing field bonded with the modern technology, and it highly effected to field expandability. Marketing become fruitful when it achieves its key points which are called sales and profit. Mostly people are move to the retails because all the essentials and other things can buy from one place. There are many technological concepts involve with marketing field as an enhancement. Prediction processes, data analysis, item designing and profit calculation are some representatives for those concepts. This study is a prediction process, developed for retails using machine learning approaches. Item sales data analyzed and generated prediction results on set of items which are given maximum or expected profit margins and which items satisfy the customer most. Item suppliers are key stakeholder type a retail can have, there is a recommender system in this approach for suppliers and the recommendation is based on past sales data. There are certain types of machine learning approaches used in sales item prediction, sales item feature prediction, sales price prediction and etc. Novelty of this research is, it focused only special event items such as items in Christmas season, items specialized for Mother’s Day, Valentine Day, Sinhala, and Tamil new year and etc. This research process had completely followed the machine learning neural network concept. Recurrent Neural Network is subpart of neural networks and this research study followed up through this RNN method. Neural network had applied using a form of machine learning called deep learning. This model had worked on sequential data therefor LSTM (Long Short-Term Memory) layers were used and to avoid overfitting issue several dropout layers were used. The results prove neural network method has highest accuracy.
Open Access
Utalk: Sri Lankan Sign Language Converter Mobile App using Image Processing and Machine Learning
(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Dissanayake, I.S.M.; Wickramanayake, P.J.; Mudunkotuwa, M.A.S; Fernando, P.W.N.
Deaf and mute people face various difficulties in daily activities due to the communication barrier caused by the lack of Sign Language knowledge in the society. Many researches have attempted to mitigate this barrier using Computer Vision based techniques to interpret signs and express them in natural language, empowering deaf and mute people to communicate with hearing people easily. However, most of such researches focus only on interpreting static signs and understanding dynamic signs is not well explored. Understanding dynamic visual content (videos) and translating them into natural language is a challenging problem. Further, because of the differences in sign languages, a system developed for one sign language cannot be directly used to understand another sign language, e.g., a system developed for American Sign Language cannot be used to interpret Sri Lankan Sign Language. In this study, we develop a system called Utalk to interpret static as well as dynamic signs expressed in Sri Lankan Sign Language. The proposed system utilizes Computer Vision and Machine Learning techniques to interpret sings performed by deaf and mute people. Utalk is a mobile application, hence it is non-intrusive and cost-effective. We demonstrate the effectiveness of the our system using a newly collected dataset.
Embargo
NoFish; Total Anti-Phishing Protection System
(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Atimorathanna, D.N.; Ranaweera, T.S.; Pabasara, R.A.H.D.; Perera, J.R.; Abeywardena, K.Y.
Phishing attacks have been identified by researchers as one of the major cyber-attack vectors which the general public has to face today. Although many vendors constantly launch new anti-phishing products, these products cannot prevent all the phishing attacks. The proposed solution, “NoFish” is a total anti-phishing protection system created especially for end-users as well as for organizations. This paper proposes a machine learning & computer vision-based approach for intelligent phishing detection. In this paper, a realtime anti-phishing system, which has been implemented using four main phishing detection mechanisms, is proposed. The system has the following distinguishing properties from related studies in the literature: language independence, use of a considerable amount of phishing and legitimate data, real-time execution, detection of new websites, detecting zero hour phishing attacks and use of feature-rich classifiers, visual image comparison, DNS phishing detection, email client plugin and especially the overall system is designed using a level-based security architecture to reduce the time-consumption. Users can simply download the NoFish browser extension and email plugin to protect themselves, establishing a relatively secure browsing environment. Users are more secure in cyberspace with NoFish which depicts a 97% accuracy level.

SLIIT Conference and Symposium Proceedings

Browse

Filters

Advanced Search

Filter by

Settings

Sort By

Results per page

Search Results