Browsing by Author "Lunugalage, D"

Now showing 1 - 7 of 7

Embargo
Career Aura–Smart Resume and Employment Recommender
(IEEE, 2021-12-09) Dissanayake, K; Mendis, S; Subasinghe, R; Geethanjana, D; Lunugalage, D; Kasthurirathna, D
Recruitment and Job seeking are two major factors that are directly proportional to each other. Due to the competitive nature of the present world, the process of acquiring the best resource effectively and efficiently has become a challenging aspect for the companies. As a result, modern job portals have become increasingly popular to address the challenges identified in the early recruitment and job search process. The purpose of this research is to introduce an optimal solution to address the ineffective areas identified in the job and recruitment domain which can further enhance the recruitment and job seeking decisions by utilizing deep learning and sentiment analytic approach along with descriptive analysis. The proposed system recommends the relevant job opportunities by omitting the irrelevant job advertisements for job hunters who are interested in the IT job domain while they input their resume to the system and additionally, they can improve their career decisions by adhering to the prediction schemes. Moreover, the system facilitates recruiters to headhunt top talents efficiently once they input job requirements to the system and candidate suggestions are not only made depending on their resume information but also analyzing their LinkedIn endorsements.
Open Access
Computer vision based indoor navigation for shopping complexes
(acm.org, 2020-12-09) Perera, G. S. T; Madhubhashini, K. W. R; Lunugalage, D; Piyathilaka, D. V. S; Lakshani, W. H. U; Kasthurirathna, D
Smartphone-based indoor navigation systems are frantically required in indoor situations. This limitation of clients is significant. Global Positioning System (GPS) isn't plausible for indoor areas as it gives exceptionally helpless outcomes for indoor restriction. In this research paper, we present a Computer Vision-Based Indoor Navigation System for shopping complexes. Computer vision is used in this system to find the exact location/current location of the user. It contains a mobile android application for positioning, navigating, and displaying the current location for showing on 2D Map. The system will detect the user's position, generate a GIS map, display the shortest path using A* search algorithm, and provides step-by-step direction to the destination using audio instruction for localization with Augmented Reality (AR) map and navigation using mobile phone sensor technologies like accelerometer, gyroscope, and magnetometer. The audio instructions include active guidance for upcoming turns in the traveling path, distance of each section between turns. This system uses a suggestion-based Chabot that uses a trained model to improve the user's experience. Thus, this research expects to build a cost-effective, efficient, and timely response system that will help the users for a smart shopping experience.
Embargo
Deep Learning-Based Surveillance System for Coconut Disease and Pest Infestation Identification
(IEEE, 2021-12-07) Vidhanaarachchi, S. P.; Akalanka, P. K. G. C.; Gunasekara, R. P. T. I.; Rajapaksha, H. M. U.D; Aratchige, N. S.; Lunugalage, D; Wijekoon, J. L
The coconut industry which contributes 0.8% to the national GDP is severely affected by diseases and pests. Weligama coconut leaf wilt disease and coconut caterpillar infestation are the most devastating; hence early detection is essential to facilitate control measures. Management strategies must reach approximately 1.1 million coconut growers with a wide range of demographics. This paper reports a smart solution that assists the stakeholders by detecting and classifying the disease, infestation, and deficiency for the sustainable development of the coconut industry. It leads to the early detections and makes stakeholders aware about the dispersions to take necessary control measures to save the coconut lands from the devastation. The results obtained from the proposed method for the identifications of disease, pest, deficiency, and degree of diseased conditions are in the range of 88% - 97% based on the performance evaluations.
Embargo
Health Care – A Personalized Guidance for Non-Communicable Diseases
(IEEE, 2022-12-09) Dakshima, D.D.T.D; Seliya Mindula, K; Rathnayake, R.M.S.J; Kasthuriarachchi, S; Buddhi Chathuranga, A.K; Lunugalage, D
All people expect to live a healthy life. But today about eighty million people a year suffer from non-communicable diseases. Among non-communicable diseases, heart disease and diabetes are at the forefront, and the number of deaths due to heart disease is rising in people with diabetes. Changes in lifestyle, work-related stress and bad food habits, and smoking addiction contribute to the increase in the rate of several heart diseases and diabetes diseases. Therefore, a reliable and accurate system is needed to identify such diseases in time for proper treatment. The methodology proposed in this research is based on Machine learning classification techniques using Random Forest (RF), Logistic Regression, Gradient Boosting, etc. It is an android mobile application. The prognosis process gives a cardiac risk analysis percentage based on the patient’s heart condition and a diabetic risk analysis percentage based on the diabetic condition by the Kaggle dataset. Accordingly, a system was proposed with daily guidelines including calculation of risk level, Exercise recommendation, Meal planner, and stress-releaser. The accuracy of the proposed system was risk calculation of heart at 82,75%, risk calculation of Diabetics at 81.66%, Meal planner at 89.8%, the exercise scheduler Cardiac status prediction at 73.57%, diabetic status prediction at 78.57%, body performance prediction 74.68% and stress release 100%. This system helps to prevent the associated risk levels and keep healthy life.
Embargo
IoT-Based Disease Diagnosis and Knowledge Dissemination System for Coconut Plants
(IEEE, 2022-12-09) Ekanayaka, S; Anawaratne, A; Ayeshmanthi, T; Dilanka, M; Aratchige, N.S.; Wijekoon, J; Lunugalage, D
The coconut plant plays a significant role in the Sri Lankan domestic and export industries. It is a major livelihood crop of which more than 65% is consumed locally. However, most coconut trees suffer from various pest and disease outbreaks, which have an impact on the economy of coconut production. Out of them, infestations of Whiteflies, Plesispa Beetle, and Red Palm Weevil are destructive to the coconut plant at different stages, so early detection of those infections is a major task. To this end, the paper describes an IoT-based prediction system for detecting and classifying infections in the coconut industry.; Internet of Things (IoT), image processing, audio processing, and deep learning were used as techniques to utilize for the detection of those infestations. Audio and Image-capturing devices are developed to collect audio and image data. Additionally, there’s a knowledge dissemination system to identify the main coconut pests in Sri Lanka and share this knowledge with farmers. With the audio and image datasets gathered from the mentioned diseases, performance evaluation of the Deep Learning (DL) models revealed that the accuracy of the identifications of Red Palm Weevil infestation Plesispa beetle and Whitefly infestations is 88, 96, and 98% respectively.
Embargo
Sales Optimization Solution for Fashion Retail
(IEEE, 2021-12-09) Ganhewa, N. B; Abeyratne, S. M. L. B; Chathurika, G. D. S; Lunugalage, D; De Silva, D. I
The Fashion industry is one of the extensive, changeable, and growing businesses to exist. It encompasses fashion retailing which functions as a mediator between the manufacturers and clients. On account of the inconsistency of this industry, maximizing sales has been a crucial task. The objective of this research study is to analyze and explore product and consumer behavior and thereby maximize sales in the fashion retail industry for women’s clothing to overcome the struggles regarding gaining sales confronted by the industry. The emergence of big data and machine learning has a positive influence on fashion retailing. ML has been utilized in this research to implement a web application that aids in optimizing sales. It comprehends sales forecasting, customer segmentation, and customer demand analytics. Each research component obtains diverse inputs to initialize the prediction and visualization procedure. The models are built employing the Extra Trees Regressor algorithm, K-means algorithm, and Naïve Bayes algorithm. Finally, for specified inputs, results will be predicted that comprise sales forecasts for products, segmentation of consumers, and forecasts about most demanded fashion item’s characteristics. This paper portrays the proceedings of data preparation, model development, and results of each research component.
Embargo
Smart Snake Identification System using Video Processing
(IEEE, 2021-12-07) Deshan, P.D.R.; Pabasara, D. V. H.; Yapa, N. A.; Perera, D. S. R. C. V.; Lunugalage, D; Wijekoon, J. L
There is a common fact in the world that all snakes are venomous and dangerous to humans. This is due to a lack of awareness about snake species among the general public. However, based on the literature, the reality is that only 41 out of 108 reptiles are venomous and dangerous to humans. The challenge is specifically identifying the various snake species instead of considering all of them to be venomous. With the population growth frequency of snakebites reported in hospitals have arisen because of people attempt to harm snakes. This paper proposes an approach to help people in identifying snakes in panic situations using video processing, and then alert the nearest rescuer teams. This study has been carried in Sri Lanka, with a contribution to the scientific world to save both snakes and humans. The implemented system comprises of a mobile application with features including offline real-time snake identification, online real-time snake identification using video processing, manual snake detection, and alert nearest rescuers. The obtained results indicate that this application has an offline snake identification accuracy of 75%-80% and an online snake identification accuracy of 90%- 95%.