Purpose: With the rapid development of technology in the 21st century, an ever-growing number of organisations are adopting digitalised technologies. The global economy connected with digitalisation is moving towards sustainable development. Individual firms adopt innovative technological strategies to consolidate their position in the competitive market. The study aimed to examine the management perception of the impact of E-commerce adoption (EC) on business performance (BP) – the moderating role of using artificial intelligence (AI).Design/methodology/approach: A quantitative study using the deductive approach and the data collected from senior managers of the small and medium-sized enterprises (SMEs) in Sri Lanka, and 389 samples were collected using a simple random sampling method. EC, BP and AI were named as the independent, dependent and moderating variables in the model. Porters' generic strategies and resource-based views (RBVs) were applied as the foundation of the study.Findings: The independent and moderating variables significantly influenced the BP. Managers' age, gender, education level and job position affect their perception.Originality/value: The global economy is moving towards sustainable development using digitalisation. The firms should blend their strategies with digitalised platforms to survive in the competitive market.Peer review: The peer review history for this article is available at the following link: https://publons.com/publon/10.1108/IJSE-12-2021-0752
1 February 2019 in Journal of Physics: Conference Series
The utilization of the internet in education world is able to facilitate the increased intensity of educational activities. The lecture process that was previously only in a classroom, is currently undergoing a transition. A mix of teaching methods and materials of direct learning or face-to-face in class and e-learning by online methodologies in formal education as called blended Learning has been popular in educational practice. Regarding to the adequacy of mixed learning have prompted an expanding number of concentrates on this theme. The objective of this paper are to review about characteristics in Blended Learning and evaluation about the issues and challenges in it. There are three databases found for this studies which are Science Direct, IEEExplore and Google Scholar. After the databases filtered, there are 19 papers selected for this review as there are appropriate to the criteria needed. This studies aims to bring the knowledge for developer or research groups about Blended Learning and as intructional media in Learning for manage, create, and deliver courses.
5 December 2020 in Mathematical Problems in Engineering
On the basis of studying datasets of students' course scores, we constructed a Bayesian network and undertook probabilistic inference analysis. We selected six requisite courses in computer science as Bayesian network nodes. We determined the order of the nodes based on expert knowledge. Using 356 datasets, the K2 algorithm learned the Bayesian network structure. Then, we used maximum a posteriori probability estimation to learn the parameters. After constructing the Bayesian network, we used the message-passing algorithm to predict and infer the results. Finally, the results of dynamic knowledge inference were presented through a detailed inference process. In the absence of any evidence node information, the probability of passing other courses was calculated. A mathematics course (a basic professional course) was chosen as the evidence node to dynamically infer the probability of passing other courses. Over time, the probability of passing other courses greatly improved, and the inference results were consistent with the actual values and can thus be visualized and applied to an actual school management system.
1 January 2025 in International Journal of Data Warehousing and Mining
To improve photovoltaic (PV) power forecasting under variable meteorological conditions, this paper proposes a hybrid model combining signal decomposition, clustering, and deep learning. An improved complete ensemble empirical mode decomposition with adaptive noise method is used for multi-scale decomposition of meteorological inputs such as temperature, solar radiation, and wind direction. Sample entropy-guided K-means clustering segments signals into high, medium, and low-frequency components, with high-frequency parts further denoised using variational mode decomposition. A convolutional neural network-bidirectional long short-term memory network is then optimized by the crown porcupine optimization algorithm to fine-tune key hyperparameters. Experiments on real PV data show a 20% root mean squared error reduction (to 7.30 kW), demonstrating strong adaptability and robustness for intelligent PV scheduling.
31 December 2021 in Innovation Journal of Social Sciences and Economic Review
The purpose of this study is to investigate the relationship between risk management practices and the sustainability of the microfinance industry in Sri Lanka. Given the rapid growth of the microfinance sector over the past two decades, understanding how effective risk management contributes to long-term sustainability is crucial. The study employed a quantitative research design, utilizing simple regression analysis to explore the hypothesized relationship between risk management (independent variable) and sustainability of the microfinance industry (dependent variable). The sample consisted of 376 women microfinance borrowers from three districts in Sri Lanka, selected using a cluster sampling approach. Primary data were collected through surveys, while secondary data were obtained from the Central Bank of Sri Lanka (CBSL), MFI annual reports, and the Microfinance Information Exchange (MIX). The analysis revealed a significant positive relationship between effective risk management and the sustainability of the microfinance industry in Sri Lanka. The results indicate that improvements in risk management practices are likely to enhance the long-term viability of microfinance institutions, ensuring their capacity to continue serving low-income clients effectively. The findings underscore the importance of robust risk management frameworks for the sustainability of the microfinance industry in Sri Lanka. Despite the growth of the sector, without effective risk management, the long-term success and stability of microfinance institutions may be compromised. This study highlights the need for microfinance institutions to prioritize risk management as a critical component of their operational strategies. Policymakers and industry regulators should encourage and support the development of risk management capacities within MFIs to safeguard the industry’s future. Further research could expand the scope to include more districts and a broader range of MFIs to validate these findings and explore additional factors influencing sustainability.
1 February 2019 in Journal of Physics: Conference Series
Expert systems are a branch of artificial intelligence, namely by storing expertise from human experts into computers and storing knowledge in computers so that users can consult like human experts. Expert systems are now being applied to diagnosing diseases in humans, animals, and plants. With this system users becoming more practical and knowledgeable in diagnosing natural diseases. a good expert system must provide a good and accurate result so that it can be use. Factors that influence system accuracies such as classification methods, input analysis, and technology are considered for the development of a good expert system to serve it functions as an expert. The purpose of this paper is to analyze these factors for the development of a better system.