Research Papers - Dept of Computer Systems Engineering

Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253

Browse

Filters

2019 - 201912020 - 20222

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Prediction

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationEmbargo
    Multilingual Conversational AI incorporated with Visual Questions Answering and Intelligent Disease Prediction for Healthcare Industry
    (IEEE, 2022-07-18) Sasmitha, N. U. A.; Wathasha, H. K. G. V.; Guruge, P. P. L.; Silva, W. J. T.; Rupasinghe, L; Gunarathne, G. W. D. A.
    Artificial intelligence (AI) is becoming more active than ever in everyday life and steadily being incorporated to healthcare. AI, with its seemingly limitless power, affirms a promising future to a revolutionized healthcare system. This paper is proposing a conversational AI solution in two different languages, English and Sinhala, to predict diseases through a conversation, a visual question answering solution to generate answers are based on a given question and a medical image and a disease forecasting module. A robust, accurate prediction is a rather difficult task given the availability of data and absence of preprocessed, clean data. With the aid of outlier rejection, data imputation, vectorization, feature selection and data standardization, the proposed framework gets the advantage of latest machine learning advancements such as AI using DIET classifier and NLU pipelines, for the conversational disease diagnosis which uses support vector machine (SVM) achieved an accuracy of 0.93. Moreover, the visual questions answering module with VGG16 preprocessing, GoogleNews vectors, LSTM networks, scores an accuracy of 0.9721. In addition, time series analysis models such as ARIMA and adaptive models using PROPHET library for forecasting diseases, classification using random forest scoring an accuracy of 0.81, logistic regression scoring an accuracy of 0.84 for predicting diseases. The objective of this research is to compare and select the best fitting models to be used for a centralized framework for healthcare industry.
  • Thumbnail Image
    PublicationEmbargo
    Towards Smart Farming: Accurate Prediction of Paddy Harvest and Rice Demand
    (IEEE, 2019-01-31) Hashini Saranga, A. M; Weerakkody, W. A. N. D; Palliyaguru, S. T; Muthusinghe, R; Rankothge, W
    Rice is the predominant staple food in Asian countries. It has a major impact on the social and economic development of these countries. Therefore, it is very important to keep the sustainability between paddy cultivation and consumer demand. Paddy crop yield and demand for rice of a country depend on numerous factors such as rainfall, humidity, citizen's life styles etc. Hence, the prediction of future harvest and demand is a complex process. There is a requirement for a platform that predicts on future harvest and demands based on all affecting factors. We have proposed a platform that targets the smart farming concepts for paddy, with following modules: (1) a prediction module to predict paddy harvest and (2) a prediction module to predict rice demand. We have developed the prediction modules using two machine learning algorithms: (1) Recurrent Neural Network (RNN) and (2) Long Short-Term Memory (LSTM). The performances of algorithms were evaluated using real data sets for the Sri Lankan context. Our results show that the prediction modules are giving accurate results in a short time.
  • Thumbnail Image
    PublicationEmbargo
    Supply and Demand Planning for Water: A Sustainable Water Management System
    (2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Athapaththu, A.M.H.N.; Illeperumarachchi, D.U.S.; Herath, H.M.K.U.; Jayasinghe, H.K.; Rankothge, W.H.; Gamage, N.
    Sustainable water management requires maintaining the balance between the demand and supply, specifically addressing water demand in urban, agricultural, and natural systems. Having an insight on water supply forecasting and water consumption forecasting, will be useful to generate an optimal water distribution plan. A platform that targets the sustainable water management concepts for domestic usage and paddy cultivation is proposed in this paper, with the following components: (1) forecasting water levels of reservoirs, (2) forecasting water consumption patterns, and (3) optimizing the water distribution. We have used Recurrent Neural Network (RNN) and, Long Short-Term Memory (LSTM) for forecasting modules and, Genetic Programming (GP) for optimizing water distribution. Our results show that, using our proposed modules, sustainable water management related services can be automated efficiently and effectively.