Statistics & Computer Science
http://repository.kln.ac.lk/handle/123456789/3751
2024-03-29T09:51:49ZThe impact of self-efficacy beliefs of employees on contextual issues of online learning: with reference to the banking sector in Sri Lanka
http://repository.kln.ac.lk/handle/123456789/26308
The impact of self-efficacy beliefs of employees on contextual issues of online learning: with reference to the banking sector in Sri Lanka
Rathnasekara, K.; Suraweera, N.; Yatigammana, K.
Purpose – The paper aims to clarify the relationship between perceived contextual issues and the self-efficacy
beliefs of the employees with e-learning engagement for their competency development. It proposes a model for
the banks to utilize their e-learning interventions more effectively by managing the identified contextual issues.
Simultaneously, this study aims to expand the domain of self-efficacy beliefs and apply its principles to dilute
the impact of the negative contextual issues which were not addressed through similar research.
Design/methodology/approach – The paper focuses on an exploratory study using a deductive approach
grounded on self-efficacy – one of the main dimensions of Bandura’s social cognitive theory. It adopted a mixed
methodology, and primary data were collected through an online survey (792 responses analyzed through
Statistical Package Social Science [SPSS]) and semi-structured interviews (20 respondents analyzed through
thematic analysis). The population comprises employees of private commercial banks who have recently
introduced e-learning.
Findings – The paper provides empirical insights about the contextual issues influencing e-learning and how
self-efficacy beliefs can be utilized to enhance the effective engagement of employees. Contextual issues related
to technological, organizational, personal and time-intensive factors influence e-learning engagement. The
strengthening of self-efficacy beliefs (learners’ enthusiasm and gaining) can be utilized to manage personal and
time-intensive factors. However, technological and organizational factors cannot be managed through a similar
approach as they did not report a significant relationship with self-efficacy.
Originality/value – This paper fulfills an identified need to study how e-learning can be utilized as an
effective competency development tool in the banking sector.
2023-01-01T00:00:00ZIdentifying Medicinal Plants and Their Fungal Diseases
http://repository.kln.ac.lk/handle/123456789/26307
Identifying Medicinal Plants and Their Fungal Diseases
Senanayake, M. M. V.; De Silva, N. M. T.
Today, with the development of technology, most manual methods are replaced by automated computer systems for the easiness of human beings. Plant identification and disease classification are two major agricultural research areas, focusing on introducing computerized systems rather than manual methods. Many researchers used various identification and classification techniques using computer-based systems as human classification errors lead to risk and high cost. Medicinal plant identification needs an expert to correctly identify plants because misidentifying poisonous plants as medicinal plants causes fatal cases. Further, taking diseased medicinal plants to prepare medicines and herbal products may have adverse effects. Therefore, this study proposed a computerized method to identify medicinal plants and classify their diseases to overcome such shortcomings. In this work, a comparison is done with Convolutional Neural Network (CNN) architecture from scratch and Transfer Learning with several experiments. Transfer learning models achieved higher accuracy than CNN architectures for medicinal plant identification with 99.5 % accuracy and medicinal plant disease classification with 90% accuracy, respectively.
2022-01-01T00:00:00ZVaccination Coverage for COVID-19 in Sri Lanka: With and Without Age Stratification on Susceptible-Infectious-Recovered Simulation
http://repository.kln.ac.lk/handle/123456789/25348
Vaccination Coverage for COVID-19 in Sri Lanka: With and Without Age Stratification on Susceptible-Infectious-Recovered Simulation
Attanayake, A.M.C.H.
Background: Vaccination against COVID-19 is as a key solution to interrupt its spread.
This study aimed to describe the vaccination coverage required to stop the spread of COVID-19 in Sri Lanka using a mathematical modeling strategy.
Materials & Methods: This longitudinal study used age-stratified and unstratified Susceptible-Infectious-Recovered (SIR) models. Data on the population's age distribution were acquired from the census report of the Census and Statistics Center of Sri Lanka, consisting of groups: below 30, between 30-59, and over 60. Models with differential equations forecasted the spread of COVID-19 with vaccination based on parameter estimates and numerical simulation, assuming fixed population, infection, and recovery rates.
Results: Simulations investigated how the susceptible, infected, and recovered populations varied according to the different vaccination coverages. According to the results, 75% vaccination coverage was required in the entire population of Sri Lanka to interrupt the transmission of COVID-19 completely. The age-stratified SIR model showed that over 90% of vaccination coverage in each age group (below 30, between 30-59, and over 60) was required to interrupt the transmission of COVID-19 in the country altogether.
Conclusions: The number of COVID-19 infections in each age group of Sri Lanka reduces with the increase in vaccination coverage. As 75% vaccination coverage is required in Sri Lanka to interrupt the transmission of the disease, precise vaccination coverage measurement is essential to assess the successfulness of a vaccine campaign and control COVID-19.
2022-01-01T00:00:00ZApplication of fuzzy goal programming model to assess optimal multi crop cultivation planning
http://repository.kln.ac.lk/handle/123456789/25319
Application of fuzzy goal programming model to assess optimal multi crop cultivation planning
Hakmanage, N.M.; Chandrasekara, N.V.; Jayasundara, M.
Importance of the work: Planning for the optimal use of resources in agricultural systems considering uncertainty, with the objective of maximizing profit and production, will improve the social and economic conditions of farmers. Objectives: A rural farming area in Sri Lanka was used as a study site to apply the fuzzy goal programming (FGP) approach to identify the optimal cultivation plan and land resource allocation under uncertainty to optimize profit, production, labor, water use, fertilizer costs and land allocation. Materials & Methods: A tolerance-based FGP technique was used to quantify the fuzziness of different goals for the model. This study was carried out using 24 crops on a total land area under cultivation of 47.4 ha. These crops were categorized into three varieties: vegetable, fruit and other. Furthermore, the crops were classified into seven groups according to the required period of cultivation. Results: The proposed model suggested statistically significant increments of 11% and 10.6% for the net return and harvest amount, respectively, for the 24 crops compared to existing cultivation techniques.Main finding: The FGP multi-crop cultivation planning approach is a new application for the Sri Lankan rural farming community and it should be useful for agricultural planners, by allowing them to make more informed recommendations to the farming community. Crops that provide higher levels of production and profit than those currently being cultivated should be developed to extend cultivation under the supervision of agricultural experts or officers to obtain sustainable development of cultivation.
2022-01-01T00:00:00Z