Department of Computer Systems Engineering

Permanent URI for this collectionhttp://rda.sliit.lk:8081/handle/123456789/3212

Browse

Now showing 1 - 4 of 4

Embargo
Development of a risk model for different innovator types in textile and apparel industries
(Emerald Publishing, 2023-01) Kumarapeli, U; Ratnayake, V; Jayawardana, S. S
Purpose – Technological innovation is one of the strongest driving forces in the survival and growth of any organization, including textile and apparel industries. However, technological innovation inherits a wide array of risks due to the uncertainty involved in it. In-depth research reveals the existence of a significant relationship between innovation failures and the approach used to innovate, that is, the organization’s innovator type. However, quantitative evidence supporting this concern is still lacking. Hence, the purpose of this paper is to bridge the existing gap in the literature on effective management of technological innovation risk factors and the innovator type of textile and apparel industries. Design/methodology/approach – The risk factors related to technological innovations are identified under different innovator types. Analytic network process (ANP) has been used to evaluate the contribution of risk factors according to the innovator type of the organization. Data was gathered through the literature review and structured and semi structured interviews with textile and apparel industry experts. The contribution of risk factors was determined through priorities, derived according to the ANP using Super Decision software. Findings – Contribution of risk factors takes different values according to innovator type. This provides comprehensive knowledge on developing a risk management strategy according to the innovator type of the organization. Furthermore, this provides insight into the fact that a generalized risk management strategy will not be effective and sensible for all innovator types. Originality/value – The findings provide a thorough understanding of developing a customized risk management strategy by determining the “most to least” criticality of risks based on the innovator type of the organization. Furthermore, findings can be used to adopt the most appropriate innovator type based on the organization’s key competencies. Moreover, this guides the organization in making the best use of internal resources during risk management. Furthermore, this provides insight into the risk factors that must be addressed prior to embarking on new innovative approaches
Embargo
Driving Innovative Culture with Emotional Intelligence
(IEEE, 2023-06-12) Rizwi, A; Lokuliyana, S
This research aims to examine the relationship between employee innovation and positive and negative contagion within supervising roles. Establishing an innovative culture within the organization and having managers with a high level of Emotional Intelligence are essential. As a result, this enables the study to examine the effects of these factors on employees. The study is evaluated the effects of adopting an innovation culture and working with managers who are emotionally quotient on the performance of the employees. In the corporate sector, innovation takes place under different conditions than in the private sector. Human beings experience emotions daily. An employee survey of 40 items (5-point Likert Scale) is distributed. A total of 200 surveys have been evaluated. The validity and reliability of the data were checked using SPSS, and the results were assessed using regression analysis. It involves constructing a confidence interval based on a single sample and a given level of confidence. The findings indicate that Emotional Intelligence, innovative organizational culture, and employee performance are meaningfully related. In conclusion, organizations must create innovative institution cultures and employ managers that have high levels of Emotional Intelligence to increase their employees' performance using the application of innovation.
Embargo
Tamil Grammarly – A Typing Assistant for Tamil Language using Natural Language Processing
(IEEE, 2023-06-12) Mahadevan, P; Srihari, P; Seyon, S; Vasavan, P; Panchendrarajan, R
Tamil is one of the ancient and most convoluted languages in the world. Although it is being the official language of many Asian countries, even native speakers tend to find difficulties in writing Tamil due to its morphologically rich nature. While there are various studies focusing on automatically identifying and correcting a specific typing error, very limited effort has been made to develop a comprehensive solution to assist the native and non-native writers of Tamil. In this paper, we propose a typing assistant tool Tamil Grammarly using Natural Language Processing (NLP) techniques. Specifically, the tool aims to aid the user to fix grammatical errors and spelling errors and recommend the next words and synonyms of the current word in real-time while typing. The NLP-based typing assistant functions of Tamil Grammarly were developed using a transformer-based model, LSTM model, and Word2Vec model. Extensive evaluation performed shows that our tool can assist the users in real-time with an accuracy of 73% - 93% within 0.4 to 5.3 seconds.
Embargo
Smart Waste Segregation for Home Environment
(IEEE, 2023-06-12) Abeygunawardhana, P.K. W; Muhammed Rijah, U.L
The segregation of waste and recycling is essential for effective waste management. Due to the busy schedule most of the people do not have a time to separate their waste. However, there is a significant issue with the segregation of the collected garbage. The implementation of an intelligent trash-management architecture is essential for the removal or reduction of waste and the maintenance of a clean, corporate environment. An IoT-stationed smart waste management device is proposed in this study that uses sensor devices to identify rubbish in the dustbins. With the aid of sensors, the waste substances in it will be separated through IoT as soon as it is discovered. Sensors and the IoT module are connected through a microcontroller. To detect the presence of garbage, an ultrasonic sensor is used. All garbage entered will be caught by the web camera and processed by the machine learning module once it has been processed. Using the model, we can identify the many forms of waste, such as paper, plastic, and glass, which account for most of the garbage materials found in a home area. This aids in removing the trash from the trash can in the most efficient and effective manner possible. This research presents an IoT, and Machine Learning based completely intelligent trash segregation and management System that recognizes the dustbins' wastes using sensor systems. This project aims to develop an automated waste segregation system using a CNN algorithm that will capture waste images from a camera with object detection and classify waste materials such as paper, plastic, and glass so that the waste can be recycled appropriately. The proposed architecture with CNN gives an accuracy of 84.67%. This system will help in garbage disposal by categorizing it, contributing to a cleaner environment.