Informatics Institute of Technology: Recent submissions

  • Lazy-Koala: A Lightweight Framework for Root Cause Analysis in Distributed Systems 
    Piyarisi, Isala (2022)
    Lazy-Koala is a low overhead Kubernetes framework to collect, store and process telemetry data using deep learning to help system operators detect anomalies earlier to reduce the MTTR when the system is experiencing an ...
  • Proximity — A TinyML Model Transferring Protocol for Dynamic Environments 
    Rajapakse, Visal (2022)
    "The swift miniaturization of Machine Learning (ML) for IoT with limited resources has opened gateways to provide intelligence at the very edge (extreme edge), i.e., closer to the sensors and actuators. Coined as Tiny ...
  • Procedural 2D Map Generator 
    Peries, Aaron (2022)
    "Procedural Content Generation is a technique that was introduced as a method of automatically populating a level with objects without the intervention of the game developer but this method still requires some logical ...
  • Cheattell - Plagiarism Checker for Blogpost Articles 
    Nanayakkara, Akila (2022)
    "Plagiarism detection is a method of finding similar content that has been copied from another source. It is a huge problem when it comes to the search engine optimization. The problem arises when writing a blog, it needs ...
  • PeaceMaker: A Mediator for Organizations with Conflicting Interests in Cross-Silo Federated Learning 
    Shanmugarajah, Akassharjun (2022)
    "Cross-Silo Federated Learning (FL) promotes collaboration between organizations for machine learning (ML) tasks whilst ensuring data privacy. However, organizations are competitive and self-interested in nature, and thus ...
  • MathQ - Answer Generator for Sinhala Arithmetic Problems 
    Anthony, Shenal (2022)
    "Natural Language Processing(NLP) has given the opportunity of letting the machines understand and preform various tasks over text and speech data involving different languages. The research is also based on Natural ...
  • Ensuring Consumer Reliability in the Organic Food Industry Using Blockchain Technology 
    Geeganage, Kavindu (2022)
    "Nowadays, stores sell both organic and non-organic foods. Organic foods are widely recommended and appreciated by consumers. Many people are attempting to purchase organic items from stores. However, while purchasing ...
  • AN Expressive Text To Speech System for Sinhala Language 
    Dias, Danoja (2022)
    This research attempts to investigate creating Text-To-Speech (TTS) System for Low Resource Sinhala Language using FastSpeech2. This project uses already available TTS datasets for the Sinhala Language. This research updates ...
  • VAS Service Prediction for Telco Customers 
    Raterala Mudiyanselage, Sanduni (2022)
    "A mobile telecommunications company's value-added services provide clients a range of services. Annual revenue from value-added services is significant for telecommunications businesses. Value Added Services are offered ...
  • NFT-RecSys: A Trading Recommendations System for Non-fungible Tokens 
    Piyadigama, Dinuka (2022)
    "Non-fungible Token (NFT)s allow people to trace the origin of digital items and with the help of Blockchain technology. Since the items are unique from each other, as expressed by the name itself, they are not fungible. ...
  • CONNERS: Conversationally Explainable Recommendations for Cold-Start Users 
    Manathunge, Dilshan (2022)
    "With the ever-growing bloom of E-commerce in this digital era, users are bombarded with an overload of information. As users grow accustomed to digital service offerings, personalized recommendations offer a way to ...
  • Automated Priority Assessment For Software Defect Reports 
    Perera, Sanuri (2022)
    "Software projects, whether open or closed, often include defects. These defects can degrade the quality and performance of the software systems. In practice, it is hard to design software that is defect-free. Many projects ...
  • Sarcastically 
    Kuruppu, Ryan (2022)
    Sarcasm is one of the most well-known but easily misunderstood parts of the English language. While sarcasm is understood well to a vast majority, the uniqueness of sarcasm is that no one thinks about it the same way, when ...
  • EmoTex - Detecting emotions for a personalized chatbot with a novel approach 
    Marambage, Yomal (2022)
    Dealing with emotions can sometimes be difficult how tough a person can be. Emotions that specially affect your mental health is one of the most concerning things in the current time. Since some of these even can lead to ...
  • Plant Leaf Disease Prediction 
    Kalideen, Jawith (2022)
    "The growers and agricultural experts who labor so hard to develop and create a hunger-free community are the focus of this research endeavor. They don't get the respect they deserve for what they genuinely need. This ...
  • Using Gamification to Manage Stress among College Students during the COVID - 19 Pandemic 
    Muraliharan, Sharanya (2022)
    "The COVID -19 pandemic has become a concern in practically every country, affecting a variety of industries. The education sector is one of the areas where the COVID-19 has had an impact. Due to the epidemic, higher ...
  • VDC Predictor 
    Kumarage, Anushka (2022)
    With the development of the world, machine learning has become a popular technology in almost every field. People have implemented various types of systems which were built based on machine learning to automate the manual ...
  • “SECUREFLOW” A Transfer Learning Approach to Detect Suspicious Criminal Behaviors at an Early Stage 
    Pelpola, Shenal (2022)
    "In recent years, public security has emerged as a critical problem in modern society since it is intimately tied to social stability and economic development. Due to human limitations in visual focus of attention, real-time ...
  • Reservoir Computing-based Ensemble Photovoltaic Power Generation Forecasting 
    Naiduwa Wadu, Ridmi (2022)
    PV power forecasting has been studied in several methods, ML has been popular in recent years. Studies have reviewed that autoregressive moving average, SVM and ANN have been common in predicting data-driven time-series ...
  • Predicting USA GDP and Recession Probability Using Economic and Non-economic Indicators 
    Manoharan, Shajeeran (2022)
    "Over the last seven decades, the world economy has undergone four worldwide recessions: 1975, 1982, 1991, and 2009. Annual real per capita global GDP decreased throughout each of these periods, and this contraction was ...