Browsing by Author "Jayasundara, D. D. M."

Now showing 1 - 11 of 11

Developing regression models to estimate leaf area of split/ partially split fronds of coconut seedlings
(Faculty of Science, University of Kelaniya, Sri Lanka, 2021) Gunarathe, K. M. U.; Waidyarathne, K. P.; Jayasundara, D. D. M.
Leaf area (LA) is an important parameter measuring plant growth as it is highly responsive to the environment. Evaluation of leaf area is essential in plant research as it also helps in estimating plant productivity with net assimilation rate and total photosynthetic area of leaves. Coconut is a major plantation crop widely grown in Sri Lanka. To date, there is no non-destructive method of measuring leaf area of partially/fully split leaves of coconut seedlings. This is a drawback in coconut research as measuring LA is highly time consuming in the field. Therefore, the aim of this study was to determine an easy, accurate, cost-effective, and non-destructive formula to estimate leaf area of split/partially split leaves in 1 - 3 years old seedlings of three commonly grown coconut hybrids; Tall*Tall (TT), Dwarf Green*Tall (DT), and Dwarf Yellow*Tall (DY). Sixty leaf samples were randomly collected from each hybrid from the nurseries of Coconut Research Institute of Sri Lanka. Leaf parameters including maximum length (A), distance between two tips (B), midrib height (C), average length of first two leaflets (D), average length of last two leaflets (E), average length of middle three leaflets (F), average width of middle three leaflets (G), width between middle two leaflets (H), width between first two leaflets (I), and number of leaflets ((J) were collected from each frond. Actual leaf area was measured by LI-COR 3000 electronic leaf area meter. Linear polynomial model and multiple linear regression (MLR) analysis was used to define leaf area estimation models using different variable selection techniques such as the best subset method. Data were normalized (for TT and DY) and log- transformed (for DT) to satisfy the model assumptions. The lowest MSE and the highest R2 values were considered to evaluate the results of the polynomial model and MLR approach. Models with better combinations of variables were developed for both TT and DY varieties by the best subset method. The polynomial model was carried out with the product of F, G, and H variables as an independent variable for DY variety as it did not produce satisfactory results with MLR analysis. Accordingly, the study revealed that the leaf area of Tall*Tall variety was best represented by the equation, Area (TT) = 0.46* (A) - 0.23*(E) + 0.54*(G) with 86% R2 and 0.15 MSE. The best regression model for DY variety acted for; Area (DY) = -0.96 + 1.09*(A) – 0.59*(E) + 0.14*(B) + 1.22*(G) + 0.72*(F). This model had 94.3% R2 as accuracy and 0.01 MSE. The adjustment with product of F, G and J represented 80.63% R2 value, and 0.006 MSE for leaf area of DT hybrid. The model was ln (area) = 2.10 + 0.52*(ln (FGJ)). Neural network approaches with the same parameters will be evaluated to further improve the accuracy of the formula estimating leaf area.
Estimating the optimum plot size for coconut field experiment
(Faculty of Science, University of Kelaniya Sri Lanka, 2023) Fernando, K. M. T. L.; Waidyarathne, K. P.; Jayasundara, D. D. M.
Coconut stands as a prominent plantation crop in Sri Lanka, contributing to around 12% of the country's total agricultural output, as reported by the Sri Lanka Export Development Board (2021). A significant focus should be drawn towards designing the field research with coconut palms because coconut is a highly heterogeneous perennial crop. The efficient testing of treatment effects in field studies depends on experimental precision. On the other hand, coconut crops show considerable vulnerability to weather and spatial fluctuations. Weather fluctuation affects experimental units depending on the degree of severity, enhancing the yield variability within experimental plots. This causes a high experimental error, masking true treatment effects. Therefore, a proper plot size should be used to treat and handle this uncertainty and improve the coconut experimentation. Remarkably, prior to this research, there was no predetermined optimal plot size for agricultural coconut experiments. Thus, this study bridges this need by carrying out extensive research into the optimal plot size for these experiments. Using optimum plot size helps minimize the yield variation between the individual coconut palms inside a plot. The aim of minimizing yield variance among individual coconut palms is to detect the treatment effects in a precise way. Two methods are available to determine the optimum plot size: The Maximum Curvature Method and Fairfield-Smith’s variance law. The Maximum Curvature Method was selected to determine the optimal plot size for coconut experiments, as it has been frequently used for plot size determination in various field crops. The study analysed 26 years of coconut yield data from 1975 to 2000. The method was illustrated using a data set consisting of annual coconut yield from a design-free area at the Coconut Research Institute, Sri Lanka. The coconut palms were 16 years old and belonged to a “tall by tall” coconut cultivar. The obtained optimum plot sizes from the Maximum Curvature Method for coconut vary between four and ten palms per plot for 26 different years. According to the post Runs test, the sequence of optimal plot sizes stable over the years at a significance level of 5%. The results showed that the optimum plot size in coconut field experiments for a huge acreage of agroecological regions is six palms per plot. Thus, the disclosed finding can be defined as the optimum plot size for the Randomized Complete Block Design (RCBD). The practical implications of the result are for resource management, precision agriculture, sustainability, and adaptation to changing conditions. It will also contribute to the existing knowledge base by refining agricultural practices and enabling the integration of technology for improved coconut farming. Result consistency will be enhanced by analyzing additional similar datasets and employing variograms to examine spatial fluctuations in addition to the statistical analysis.
Forecasting air pollutant concentrations in Colombo, Sri Lanka: A time series analysis of major air pollutant parameters
(Faculty of Science, University of Kelaniya Sri Lanka, 2024) Priyadarshana, D. A. D. S.; Hewageegana, P.S.; Jayasundara, D. D. M.
Sri Lanka’s commercial capital is Colombo and virtually all significant lines of financial and business activities take place in Colombo or within its periphery. However, the daily developing city of Colombo is incurring the harm of atmospheric pollution, which is one of the most dangerous disasters due to urbanization. As regards the issues of air pollution, people have diseases that affect their respiratory tracts. According to the World Health Organization, concerns have indicated that air pollution is considered one of the most lethal pollutants globally. The poisonous air particles could cause human deaths. Hence, the quantity of pollutants in the air and the conditions that affect air quality need to be analyzed. Therefore, the major aim of this research is to estimate the values of the major air pollutant parameters in the Colombo district by building predictive models for them. As for this, the historical weekly air pollutant parameters of the Colombo district were collected from the National Building Research Organization (NBRO) for the period of April 2020 to September 2023 with an aim to quantify as well as to understand the typical patterns of the air pollutants concentration in that region. Major air pollutant parameters such as PM2.5, PM10, NO2, and SO2 were considered in this study. Then, univariate time series models were fitted for the weekly data related to the air pollutants in the short time duration, and the accuracy of the models were assessed using RMSE, MAPE, and MAE values. For each parameter, ten candidate models were created separately, and the model with the lowest AIC value and all significant coefficients was selected as the best model. Also, the diagnostic tests recommended that the residuals of all models were normally distributed, exhibited no heteroscedasticity and no autocorrelation of residuals. Indicating that these models can be used in future predictions. Here, ARIMA(2,1,0), ARIMA(2,1,0), ARIMA(2,1,2), and ARIMA(3,1,1) models were discovered, for PM2.5, PM10, NO2, and SO2, respectively. The MAPE values are 15.434, 16.374, 21.130 and 17.902, respectively. The predictive modes suggest that these air pollutants have increased and decreased over time during our testing period. When analyzing the univariate time series model of various air pollution components, it was noted that the forecasted measurement values were slightly higher. The main reason is that other factors such as different air pollution parameters and meteorological factors from past data were not considered. Therefore, the accuracy of future predictions may be compromised if past data on these additional factors are not incorporated into the modeling process. Therefore, as future works, further analysis using multivariate models has been used to determine the relationship between meteorological factors and air quality parameters.
Instrument to Measure Safety Climate: An Application to a Tyre Manufacturing Plant
(Department of Statistics & Computer Science, Faculty of Science, University of Kelaniya, Dalugama, Kelaniya (SRI LANKA);, 2021) Madurangee, L. H. L. S.; Attanayake, A. M. C. H.; Jayasundara, D. D. M.
ABSTRACT Occupational health and safety is a key feature in good governance. It depends on the safety culture of each and every person relevant to a work place. Culture means people think or act according to their opinions and beliefs by themselves without any external force. Positive safety culture gives benefits to both employee and employer. Therefore, measure the current status of safety culture is important to identify the areas which already improved and areas need to be improved. Safety climate is a descriptive measure that implies the status of the safety culture. Safety climate in a work place can be measured through the employees’ attitudes regarding the work place. A selfadministrative questionnaire can be used to collect the data as a productive method. The objective of the study was to develop a questionnaire as an instrument to measure safety climate in a work place through employees’ attitudes and validate the theoretical structure of safety climate with five dimensions. The questionnaire was designed based on literature survey under five dimensions. 30 Likert item questions were used to measure the 5 dimensions and Likert scaling technique was used to measure those five dimensions. Data were collected based on a tire manufacturing plant. Since these dimensions are highly correlated a pilot survey was conducted to identify ambiguities and difficult questions. A representative sample was selected using stratified sampling technique. The reliability of the questionnaire was measured using Chonbach’s Alpha statistic and Split –half Test. Confirmatory factor analysis was used to validate the theoretical structure. According to its results common factor was explained more than 80% of variance in each variables and model diagnostic tests showed that errors were satisfied the assumptions. The goodness of fit statistics showed that fitted model was acceptable. It can be concluded that the theoretically assumed structure to measure the safety climate with five dimensions is acceptable. This study provides a complete guidance on how to measure safety climate through a questionnaire and any interested parties may able to make their own measuring system based on the study.
Modeling the Best ARIMA Modeling Approach for Forecasting Market Indices in Colombo Stock Exchange, Sri Lanka.
(8th International Conference on Business & Information ICBI – 2017, Faculty of Commerce and Management Studies, University of Kelaniya, Sri Lanka., 2017) Madushani, M. L. P.; Erandi, M. W. A.; Madurangi, L. H. L. S.; Sivaraj, L. B. M.; Weerasinghe, W. D. D.; Jayasundara, D. D. M.; Rathnayaka, R. M. K. T.
Generally, the movements of the stock prices are highly volatile and make much more dynamics. As a result day by day the large number of companies has been listed on stock exchanges across the world. Under this scenario, examine a suitable model for forecasting stock prices is a biggest challenge in the modern world. The propose of this study is to examine a suitable model for forecasting stock prices in the Colombo Stock Exchange (CSE), Sri Lanka. Since the data has a non-seasonal linear trend, an autoregressive integrated moving average model was used for modeling and forecasting. The empirical results suggested that ARIMA model is more accurate for forecasting ASPI index than other traditional regression methods.
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 market
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.
Prevalence of known diabetes in Sri Lanka: results from the Sri Lanka demographic and health survey 2016
(Faculty of Graduate Studies, University of Kelaniya Sri Lanka, 2022) Munasinghe, M. A. H. C.; Nugawela, M.; Jayasundara, D. D. M.; Dissanayaka, D. M. P. V.; Sivaprasad, S.
Diabetes is a major global public health burden. According to International Federation of Diabetes (IDF), Sri Lanka shows an increasing prevalence of diabetes. There is a paucity of contemporary data on the prevalence of diabetes in Sri Lanka. Therefore, this study was conducted to estimate the national and provincial level prevalence of diabetes and establish the demographic risk factors of diabetes in Sri Lanka. We used data from the Sri Lanka Demographic and Health Survey (SLDHS) 2016 conducted by the Department of Census and Statistics Sri Lanka. A total of 106,466 individuals were included in this survey. From the survey data, a total of 71066 individuals aged 20 years and older were identified from all the nine provinces and the diabetes status in the questionnaire was used to define people with known diabetes. Age, gender, ethnicity, religion, education level, smoking history, marital status, urban or rural location, province of residence was included as potential exposures. The outcome was defined as self-reported prevalence of diabetes status. Age adjusted prevalence values were obtained by multiplying the crude age-specific prevalence of diabetes by age-specific weights. Weights were calculated using the Census of Population and Housing (CPH) 2012 data. Multivariable logistic regression was fitted, and Odds Ratios (ORs) were derived to examine the relationship between the covariates and outcome (diabetes status). The age adjusted national prevalence of diabetes is 10.6%. The prevalence of diabetes was higher in women than in men. Provinces with higher GDP (Gross Domestic Product), seemed to have a higher prevalence of diabetes. Prevalence of diabetes was higher in urban residents (14.39%: 95% CI: 13.72% -15.06%) compared to their counterparts in rural (11.38%: 95% CI: 11.10%-11.66%) and estate areas (9.15%: 95% CI: 8.25%-10.04%). The multivariable logistic regression analysis showed that age, urban area, moors, females, province, and high level of education as independent risk factors for diabetes. Moors had 43% increased odds of diabetes compared with Sinhalese (OR:1.43, 95% CI 1.30,1.58). Compared to residing in Rural areas, Urban sector had 19% increased odds of diabetes (OR:1.19, 95% CI (1.11, 1.28)). Females’ risk of getting diabetes was 72% higher than males (OR:1.72, 95% CI 1.62,1.82). Individuals who had a high level of education had 10% of increased risk of getting diabetes (OR:1.1,95% CI 1.04,1.17) than others. People living in Western province, were 64% more likely to have diabetes compared to other provinces. Smoking status of the individuals was not related to diabetes in this analysis. The findings clearly show that known diabetes prevalence in Sri Lanka varies between provinces, with most urban and economically developed regions showing a high prevalence of known diabetes. Given the limited resources available in the health system in Sri Lanka, this study highlights how the population can be stratified for efficient optimization of diabetes care in the country.
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.
Study on tension detection and acceptance of glove liners
(Faculty of Science, University of Kelaniya Sri Lanka, 2023) Pathirana, G. P. N. M.; Jayasundara, D. D. M.; Chandrasekara, N. V.
The glove industry plays a leading role in the Sri Lankan economy. The quality of the final product is crucial when it comes to mass production. A significant shrink or extension of a glove can cause great losses to the company by increasing the number of defective products. The dimensions of knitted liners vary due to various factors in the knitting process. In finding a solution to this problem, the Six Sigma “DMAIC” approach is being used. This research investigated how the tension of the main yarn and yarn conditioning time affect liner dimension changes in a controlled temperature and humidity level. As for finding the dimension changes, the total length, cuff length, and the cuff width of the liners were considered. Relevant data was gathered from a leading glove manufacturing company in Sri Lanka. The Randomized Complete Block Design with 9-12 replicates, considering yarn conditioning time as blocks and tension ranges as treatments, was set up. Analysis of Variance suggested that there is a significant difference among the population means in all three dimensions. Hence, a multiple comparison test (Tucky’s test) is used to compare means. The results confirmed that the changes in yarn conditioning time had a significant impact on total length and cuff width. Nonetheless, factorial designs suggested that the interactions of tension and yarn conditioning time had a significant impact on the dimensions of knitted glove liners. As the tension increased, the length of the liners decreased. As tension levels increased, cuff lengths began to shorten. In contrast, the increase in tension of the main yarn caused the cuff widths to lengthen. Low-conditioned yarns contained significantly different dimensions than the rest of the liners knitted with yarns that had been conditioned for at least 24 hours. Generally, industries determine the optimal tension values of the main yarn manually using test gloves, which is time-consuming and costly. As a solution, this research used statistical modelling concepts, which aided in the development of a model to predict the level of tension required when the relevant liner length parameters and conditioning times were provided. Multiple linear regression and data mining techniques were used, and the models were compared. By having the lowest Root Mean Square Error, the Generalized Regression Neural Network (GRNN) outperformed the regression model and decision tree model. The error of the implemented GRNN model is 0.1521, and the independent variables explained more than 90% of the mean tension.
Time series forecasting of farm gate prices of fresh coconuts in three major coconut growing areas of Sri Lanka
(Faculty of Science, University of Kelaniya, Sri Lanka, 2021) Perera, D. H. N.; Waidyarathne, K. P.; Jayasundara, D. D. M.; Hewaarachchi, A. P.
Coconut is a perennial crop with important food value and other endless uses for human beings. Hence, this has led to the emergence of a diversified set of industrial activities. All over the world, Sri Lanka is the fourth largest coconut producing country. The major part of Sri Lanka's coconut production comes from the Coconut Triangle, which consists of Puttalam, Kurunegala and Gampaha districts. Forecasting coconut prices can provide critical and useful information to coconut growers making production and facing real situations and uncertainties of the coconut industry. The objective of this study is to build accurate univariate or multivariate time series models to forecast the farm gate prices of fresh coconut in three major coconut growing areas (Puttalam, Kurunegala, and Gampaha) of Sri Lanka. This study evaluated the times series data on monthly farm gate prices of fresh coconut in the selected districts from January 2009 to December 2019.This paper examines three time series modelling approaches, Autoregressive Integrated Moving Average (ARIMA), Generalized Auto Regressive Conditional Heteroskedasticity (GARCH) and Vector Error Correction (VEC) model. Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) were used to evaluate the performance of fitted models. As the univariate time series approach, ARIMA (1,1,5) and ARIMA (2,1,2) were identified as the better models for forecasting prices of Puttalam and Gampaha based on Akaike Information Criterion (AIC) where RMSE (5.83,5.77) and MAPE (12.60,10.99) respectively. In contrast to the other two districts, Kurunegala showed a non-constant variance with the time, hence GARCH model approach was tested for the particular data series. It was found that all model coefficients were not significant in the GARCH model thus univariate models were not applicable for Kurunegala District. Therefore, multivariate time series model was carried out to find a suitable model. First, the Johansen co-integration test was applied and the results proved that there were two co-integration equations at 5% level of significance. As there were significant cointegration detected between series, VECM was applied in order to evaluate the short run properties of the cointegrated series. According to the lag selection criteria, lag 7 was selected as the optimum lag value. Considering the VEC models, the RMSE and MAPE in Puttalam, Kurunegala and Gampaha were 6.30,5.41,5.85 and 12.81,10.76,11.14 respectively. Results revealed that VECM approach worked well for forecasting Kurunegala price series. Even with long-term equilibrium relationship exists between series, VECM approach was less accurate in defining the relationship in comparison to ARIMA models for Puttalam and Gampaha price series. Therefore, that the study recommends the ARIMA models as the appropriate models to forecast the monthly farm gate prices of fresh coconut in Gampaha and Puttalam districts.