Browsing by Author "Kaushalya, K. D."

Now showing 1 - 2 of 2

An Approach for Prediction of Weekly Prices of Green Chili in Sri Lanka: Application of Artificial Neural Network Techniques
(The Journal of Agricultural Sciences - Sri Lanka, 2022) Basnayake, B. R. P. M.; Kaushalya, K. D.; Wickaramarathne, R. H. M.; Kushan, M. A. K.; Chandrasekara, N. V. C.
Purpose: Predicting the prices of crops is a principal task for producers, suppliers, governments and international businesses. The purpose of the study is to forecast the prices of green chili, which is a cash crop in Sri Lanka. Artificial neural networks were applied as they help to extract important insights from the bulk of data with a scientific approach. Research Method: The Time Delay Neural Network (TDNN), Feedforward Neural Network (FFNN) with Levenberg-Marquardt (LM) algorithm and FFNN with Scaled Conjugate Gradient (SCG) algorithm were employed on weekly average retail prices of green chili in Sri Lanka from the 1st week of January 2011 to the 4th week of December 2018. The performance of models was evaluated through the Mean Squared Error (MSE), Mean Absolute Error (MAE) and Normalized Mean Squared Error (NMSE). Findings: Among the three methods implemented, the FFNN model using the LM algorithm exhibited the highest accuracy with a minimum MSE of 0.0033, MAE of 0.0437 and NMSE of 0.2542. The model built using the SCG algorithm fitted data with a minimum MSE of 0.0033, MAE of 0.0458 and NMSE of 0.2549. Among the fitted TDNN models, the model with 8 input delays were a better model with an MSE of 0.0036, MAE of 0.0470 and NMSE of 0.3221. FFNNs outperformed TDNN in forecasting green chili prices of Sri Lanka. Originality/ Value: The neural network approach in forecasting the prices of green chili provides more accurate results to make decisions based on the trends and to identify future opportunities.
Survey on the acceptance of online education in state universities of Sri Lanka during the COVID-19 pandemic situation
(Faculty of Science, University of Kelaniya, Sri Lanka., 2021) Mahanama, K. R. T. S.; Mohamed, A. R. W.; Wickramarathne, R. A. S.; Pathirana, G. P. N. M.; Kumara, H. H. D.; Pathirana, M. P. R. L.; Wickramanayaka, M. P. A. T.; Gunawardena, S. L. H.; Dias, M. J. R.; Ihsan, M. I.; Kaushalya, K. D.; Kumara, M. S. M. S.
Online education is a mode of electronically facilitated distance education method. Due to the COVID-19 pandemic situation, global educational institutions transformed into online platforms. As a developing nation, Sri Lanka had to make a rapid transition from face-to-face to the online teaching-learning process. According to the Department of Census and Statistics, Sri Lanka, only 22.2% of households owned desktop or laptop computers (2020). Consequently, the availability and accessibility of infrastructure to transform into an online education platform are at a question. Hence, to appraise this current situation based on students’ points of view, a sample survey was conducted to explore the acceptance of online education mechanisms in state universities of Sri Lanka during the COVID-19 pandemic situation. As a first step, a pilot study was conducted on 44 undergraduates, who were selected by convenience sampling. With the experience of the pilot survey, the final questionnaire was fine-tuned with 27 questions, and it was delivered to the undergraduates in 14 state universities employing the snowball sampling technique. Based on observation of the pilot study, the required minimum sample size was found to be 570 with a margin of error of 0.04. Finally, a descriptive analysis was performed using 574 responses using Minitab software. Most of the students are more inclined to use online lectures (33%) and videos (55.3%). From 64.2% who had online sessions for practical courses, 38.9% are dissatisfied. Even though 36.3% had faced network problems, regular and usual participation figures were approximately 70%. 57.6% of the respondents in the sample are females, and among them, a higher percentage (44.8%) were participating in online lectures regularly compared to that of males (25.4%). The majority of the student has complained of difficulties in health problems (81%), inability in raising questions (64.9%), understanding course contents (86.9%), and heavy workload (89.4%). Overall, comparisons of face-to-face and online lectures revealed that the majority preferred face-to-face lectures (43.8%), and a significant proportion accepted both study modes (39.3%). On average, the acceptance of online education is ranked 2.86 on a scale of 1 (highly reject) to 5 (highly accept). Based on the findings, it is recommended to strengthen the interactions between students and lecturers, conduct break-through room assignments during the lectures, and use multiple communication platforms. In addition, student grievances can be accommodated by relaxing deadlines on assessment, aiding of educational, technical, and financial needs.