International Research Symposium on Pure and Applied Sciences (IRSPAS)
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/15650
Browse
3 results
Search Results
Item Modelling and forecasting the income of pepper exports in Sri Lanka(4th International Research Symposium on Pure and Applied Sciences, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Weerasinghe, W. P. M. C. N.; Jayasundara, D. D. M.Pepper is the most significant and widely used spice in the world. Currently about 60% of pepper production of Sri Lanka is exported while the remainder is consumed domestically. Sri Lanka is the fifth largest exporter of pepper in the world where India buys 62% of pepper exports from Sri Lanka. In 2018 Sri Lanka exported a total pepper crop which had brought in earnings to the tune of Rs.11.5 billion. Fluctuations in export income of different commodities are a matter of concern for consumers, farmers and policymakers in a country. Hence an accurate forecast is extremely important for efficient monitoring and planning of export commodities. The demand for Sri Lankan pepper is increasing rapidly due to its richer piperine content which is two to six times higher than in the other pepper producing countries. Thus, Sri Lanka has the potential to become a key player in the high value export markets. There is no existing literature about forecasting the pepper export income of Sri Lanka. This study presents a statistical time series model for forecasting the income of pepper exports in Sri Lanka by using Seasonal Auto Regressive Integrated Moving Average (SARIMA) model. The data used in this study are monthly export income of pepper in Sri Lanka from January 2000 to December 2018 that were obtained from Sri Lanka Exports Development Board. 80% and 20% of data was used in model building and model validation respectively. ARIMA(4,1,4)(1,1,1)12 was selected as the best model with the lowest Akaike Information Criterion (AIC) for forecasting the income of pepper exports in Sri Lanka among many candidate models that were evaluated by the investigation of Auto Correlation Function(ACF) and Partial Auto Correlation Function (PACF) of the differenced series. Forecasting accuracy of the model was evaluated with error metrics, Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) which are equal to 5.70 and 4.76 and it suggests that the ARIMA(4,1,4)(1,1,1)12 model has a strong potential in forecasting the income of pepper exports in Sri Lanka. As the forecasts from the model shows an increasing pepper export market which will need a higher production of pepper, the government can improve the awareness of farmers about the requirements of pepper in export market by providing infra-structure facilities. Forecasts also depicts an important piece of information for Sri Lankan pepper exporters and potential investors to consider about long term investment decisions in the pepper export marketItem Route optimization of solid waste collection in Gampaha(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Hakmanage, N. M.; Jayasundara, D. D. M.For this study, we have selected Gampaha municipal area. According to the estimates and the enumerated population 2012 (census) in Sri Lanka, among the 25 districts, the highest population is reported from Colombo district. The second highest population is reported from Gampaha district. Even though there are several waste management problems, before a huge disaster due to unsustainable disposal waste in second populated district in Sri Lanka, we propose an optimal waste collecting path. The main objective of this research is to optimize Municipal Solid Waste (MSW) collection routes using mathematical model to maximize collected solid waste amount and minimize the cost and collection time. To use route optimization process, data related in collection process such as type of vehicles used to waste collection and capacity, the amount of solid waste production and the number of inhabitants for each route are essential. Lack of such data leads us to estimate the solid waste production amount per each route by considering the number of houses/buildings in each route. For 10 sections in the Gampaha Municipal area, the modified maximum flow amount technique and the shortest path model were used to optimize solid waste collection process with minimum cost. The Geographic Information System (GIS) and Google map were used to identify routes, count number of houses/buildings in each route, and to find route distance between each connected junctions/intersections. Total traveled distance for the waste collection at each day was calculated as 858 km after finding the optimum routes by proposed model which is more than 10% efficient compared to the current traveled distance. In the current system, 10 vehicles are being used for collection whereas proposed model needs only 8 vehicles. According to this study, 14.2% and 20% thrift can be obtained via distance and vehicle allocation respectively. The consequences of the reductions in travelled time, total time and travelled distance were savings in costs related to fuel consumption.Item Prediction of daily gold prices in Sri Lanka: A comparison of time series and artificial neural network models.(International Research Symposium on Pure and Applied Sciences, 2017 Faculty of Science, University of Kelaniya, Sri Lanka., 2017) Shashikala, M. A. G.; Chandrasekara, N.V.; Jayasundara, D. D. M.Gold is an ancient and one of the most precious and popular commodities in the world. Investors at all levels are attracted to gold in all times as gold is a solid and tangible long term store of value. Gold can be used in portfolios to reduce volatility, to protect global purchasing power and minimize losses during times of market shock. Therefore, a more accurate forecast of gold prices can help the investors in their decision making. The main objective of this study is to develop a more accurate and efficient model to forecast daily gold prices in Sri Lanka. For this study, the daily gold prices (LKR/Troy Ounce), published by the Central Bank of Sri Lanka from 10th June 2014 to 30th November 2016 were used. During the past decades, Traditional Time Series Modelling was used in forecasting financial data but recently, Artificial Neural Networks are used in many researches of forecasting. Hence, both traditional time series modelling and artificial neural network approaches were considered in developing a more accurate and efficient model in the study. Autoregressive Integrated Moving Average model (ARIMA); a traditional time series model and Feed Forward Neural Network model (FFNN); an artificial neural network model, were compared. The model evaluation was carried out using performance measures; Normalized Mean Squared Error (NMSE) and Directional Symmetry (DS). ARIMA (2,1,2) model with NMSE and DS values, 0.1358 and 71% respectively, was selected as the best model among the fitted traditional time series models. FFNN model containing two hidden layers, with 4 and 5 neurons respectively in each layer with model parameters; mu of 0.00061 and minimum gradient of 0.7e-7 was selected as the best model among the trained FFNN models. The NMSE is 0.000139 and DS is 78% of the final ANN model. The deviation between the actual and forecast values (NMSE) is very low in the fitted FFNN model and the accuracy of the predicted direction (DS) is more than that of ARIMA (2,1,2) model. The above results prove that the ANN outperforms traditional time series modelling techniques in forecasting highly volatile financial data such as daily gold prices.