Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Filters

2014 - 201912020 - 20224

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.prediction

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationEmbargo
    AgroPro: Optimizer for Traditional Agricultural System in Sri Lanka
    (IEEE, 2022-12-09) De Silva, D.I.; Suriyawansa, G.M. T. K. D. S.; Senevirathna, M.R. U. M. T.; Balasuriya, I.D. I.; Deshapriya, A. G. S. P.; Gadiarachchi, G. A. D. K. M.
    Today, in many countries around the world, big data analysis and machine learning methods are used for industrial development. However, such techniques are rarely used in Sri Lankan agricultural industry. The success of agriculture depends heavily on the selection of the right crop. Choosing the right crop depends primarily on predicting future yields. Machine learning methods can be used very successfully to make future predictions about crop yields. Crop prediction mainly depends on the soil, geography, and climate of the growing location. Hence historical data with agricultural facts such as temperature, humidity, pH, and rainfall are used to predict yield as parameters in the machine learning function. Sri Lanka uses a traditional approach to distribute fertilizers among farmers. Not having an organized way to distribute fertilizers to the needed areas leads to many abnormalities along the way. As a result, the country is facing economic losses and resource wastage. Having an optimized distribution network is the key to overcoming those abnormalities. This research assesses the efficiency of the fertilizer distribution system and consists of time-series predictions on fertilizer usage to gain future value. The aim is to identify performance gaps in distribution management that lead to delayed fertilizer distribution affecting agricultural productivity.
  • Thumbnail Image
    PublicationEmbargo
    Machine Learning and Image Processing Based Approach for Improving Milk Production and Cattle Livestock Management
    (IEEE, 2022-12-29) Bandara, W. M. C. S.; Priyasarani, W. A. L.; Dhanarathna, Y. N.; Jaanvi, S. C. H.; Karunasena, A.; Abeywardhana, D. L.
    Dairy products are popularly consumed around the globe since it provides a rich source of vitamins and minerals essential for maintaining human health. Developing countries have grown their proportion of global dairy production in Sri Lanka Cattle Livestock is one of the most prospective subsectors of agriculture in Sri Lanka. Demand for quality milk products in Sri Lanka have especially increased in the recent past due to restrictions in importing dairy products.Under such circumstances cattle farmers are much encouraged to improve their milk production. However, there are many challenges in improving milk production by farmers. These include challenges in identifying breeds of cows for milk production inability of identifying diseases and conditions of farm animals hindering milk production and forecasting milk production of a farm.This research used a machine learning and image processing to identify parasite disease and heat stress of cows hindering milk production and identify breeds capable of producing quality milk. In addition, it will also use machine learning to predict heat stress level of cattle, identifying the breed types, identification of parasitic species and risk level.The machine learning model was generated with higher accuracy
  • Thumbnail Image
    PublicationOpen Access
    Forecasting accuracy of Holt-Winters Exponential Smoothing: evidence from New Zealand.
    (New Zealand Journal of Applied Business Research, 2020) Dassanayake, W; Ardekani, I; Jayawardena, C; Sharifzadeh, H; Gamage, N
    Financial time series is volatile, dynamic, nonlinear, nonparametric, and chaotic. Accurate forecasting of stock market prices and indices is always challenging and complex endeavour in time series analysis. Accurate predictions of stock market price movements could bring benefits to different types of investors and other stakeholders to make the right trading strategies. Adopting a technical analysis perspective, this study examines the predictive power of Holt-Winters Exponential Smoothing (HWES) methodology by testing the models on the New Zealand stock market (S&P/NZX50) Index. Daily time-series data ranging from January 2009 to December 2017 are used in this study. The forecasting performance of the investigated models is evaluated using the root mean square error (RMSE], mean absolute error (MAE) and mean absolute percentage error (MAPE). Employing HWES on the undifferenced S&P/NZX50 Index (model 1) and HWES on the differenced S&P/NZX50 Index (model 2) we find that model 1 is the superior predictive algorithm for the experimental dataset. When the tested models are evaluated overtime of the sample period we find the supportive evidence to our original findings. The evaluated HWES models could be employed effectively to predict the time series of other stock markets or the same index for diverse periods (windows) if substantiate algorithm training is carried out.
  • Thumbnail Image
    PublicationEmbargo
    Effectiveness of artificial intelligence, decentralized and distributed systems for prediction and secure channelling for Medical Tourism
    (IEEE, 2020-11-04) Subasinghe, M; Magalage, D; Amadoru, N; Amarathunga, L; Bhanupriya, N; Wijekoon, J
    Good health and wellbeing, a sustainable development goal introduced by the United Nations to be achieved by 2030. Sri Lanka is a country that highly depends on tourism. A healthcare system which consists of high quality and low-cost services and an abundance of tourist attractions makes Sri Lanka to be one of the best medical tourism destinations. Tourism and travel have contributed to the GDP of Sri Lanka by 11.1 billion USD by 2018. Lack of technological advancements within the medical sector has drawn back the ability to smoothly cater medical tourism. The proposed system aims for an advanced technological improvement that would help in further developing and contributing to medical tourism. To this end, this paper introduces an Intelligent System for Secure Channeling platform that aids medical tourism with the help of artificial intelligence and blockchain technologies. System proposes a treatment prediction and suggesting the best doctor for it and a secured network to store and access electronic health records (EHR). The yielded results show that the proposed method successfully performed treatment prediction with 79-88% accuracy.
  • Thumbnail Image
    PublicationEmbargo
    A router-based management system for prediction of network congestion
    (IEEE, 2014-03-14) Harahap, E; Wijekoon, J; Tennekoon, R; Yamaguchi, F; Ishida, S; Nishi, H
    Network Management System (NMS) plays an important role in networks to maintain the best performance of a network. It employs variety of tools, applications, and devices in order to support network administrators to monitor and maintain the stability of a network. Fault management is part where the NMS dealing with problems and failures, such as congestion, in the network. Generally, most NMSs use Simple Network Management Protocol (SNMP) to monitor and map network availability, performance, and error rates. In the existing NMS process, an SNMP agent is deployed to get information about the network condition and then send them to the administrator for taking further action on solving the problems. However, deploying such agent to the network may increase the traffic density. On the other hand, packet latency and RTT will increase as well. In this paper, we implemented a prototype of the proposing novel system that no need to deploy such agent to obtain network information. Our system analyze the streaming traffic by implementing a Service-oriented Router (SoR). Our objective is to predict a congestion in the specific link in the network through a router-based data traffic analysis using a Bayesian network model. The purpose of the prediction is to support the network administrator to notify the early warning regarding to the fault in the network as long as possible before it actually happening. By this prediction, the network administrator can immediately taking action to avoid the problems.We provided simulation experiment to demonstrate the performance of the proposed system. Our simulation results show that the proposed system can predict a congestion link caused by a particular problem, before hand it is getting congested.