Research Papers - Dept of Computer Systems Engineering

Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253

Browse

Search Results

Now showing 1 - 10 of 12
  • Thumbnail Image
    PublicationEmbargo
    Performance evaluation on machine learning classification techniques for disease classification and forecasting through data analytics for chronic kidney disease (CKD)
    (IEEE, 2017-10-23) Gunarathne, W. H. S. D; Perera, K. D. M; Kahandawaarachchi, K. A. D. C. P
    Chronic Kidney Disease (CKD) is considered as kidney damage which lasts longer than three months. In Sri Lanka, CKD has become a severe problem in the present days due to CKD of unknown aetiology (CKDu) that can be seen popularly in North Central Province. Identifying CKD in the initial stage is important to provide necessary treatments to prevent or cure the disease. In this work main focus is on predicting the patient's status of CKD or non CKD. To predict the value in machine learning classification algorithms have been used. Classification models have been built with different classification algorithms will predict the CKD and non CKD status of the patient. These models have applied on recently collected CKD dataset downloaded from the UCI repository with 400 data records and 25 attributes. Results of different models are compared. From the comparison it has been observed that the model with Multiclass Decision forest algorithm performed best with an accuracy of 99.1% for the reduced dataset with the 14 attributes.
  • Thumbnail Image
    PublicationEmbargo
    AD Mini: Memory Improvement Tool for Alzheimer's Patients
    (IEEE, 2018-08-08) Weerakoon, D. S. D; Kahandawaarachchi, K. A. D. C. P; Thilakasiri, W. P. M; Dissanayake, J. D. S. Y; Shanthakumara, W. D. M. B
    According to National Center for Health Statistics, Alzheimer's disease is one of the major causes of deaths among elderly people. The current medicine does not provide any cure to this disease. Hence, managing the progression of disease is more important for the wellbeing of the patient. Approximately there are 44 million people are suffering with Alzheimer's or a relevant Dementia in the world. Which has triggered many institutions and associations forming to provide treatments. However, in Sri Lanka there is less attention to the disease because of the cultural reasons and the cost associated with the disease management process. With the limited amount of resources available most of the activities are paper base activities and care giver always should give his or her attention to the patient. All Sri Lankan Alzheimer's patients will not be able to get opportunity to go for that Alzheimer's foundation or else all patients might not attend to the clinics on date. At clinics in Sri Lanka, doctors are providing paper base activities for patient to answer. Then doctor gives marks for each activity and compare with the patient's earlier results. Furthermore, in Sri Lanka there is no computer based application tool for patients to use by themselves to keep them in touch with relevant information and develop their memory/Skills. To solve this problematic situation the research group has decided to develop an online memory improvement tool especially for Alzheimer's patients in Sri Lanka. For this researchers are observing Lanka Alzheimer's Foundation Secretariat and Service Center to gather issues related to there current paper base activity process issues and we are getting advices from Consultant Psychiatrists in Sri Lanka. Under supervision of the Psychiatrists the research team is developing an online application with recommended activities for specific areas in Alzheimer's. At the end of each game, the score save to the database and the system will generate the report.
  • Thumbnail Image
    PublicationOpen Access
    Motor Skill Improvement Tool for Apraxia
    (IEEE, 2018-09-26) Shanthakumara, M; Kahandawaarachchi, K. A. D. C. P
    Apraxia is one of the cognitive defects that characterizes Alzheimer’s disease. Despite its prevalence and importance for diagnosing Alzheimer’s disease (AD), this has devoted little attention among research community. Apraxia was more common in the Alzheimer’s disease (32.3%) than in both Subcortical Vascular Dementia (SVaD) (16.7%) and Mild Cognitive Impairment (MCI) (4.8%). The present study discusses a new experimental study on fine motor-skill learning in patients with dementia and Alzheimer’s disease. Prior studies found intact fine motor-learning capacities. Subsequently, it is elaborated how these intact learning abilities can be exploited in the patient’s rehabilitation with respect to the variables day today practice and feedback. The article concludes that if training programs are adjusted to specific needs and abilities, older people with AD can (re)learn practical motor skills, which may enhance their autonomy in life.
  • Thumbnail Image
    PublicationEmbargo
    DiabiTech-Non-Invasive Blood Glucose Monitoring System
    (IEEE, 2019-12-05) Udara, S. S. W. I; De Alwis, A. K; Silva, K. M. W. K; Ananda, U. V. D. M. A; Kahandawaarachchi, K. A. D. C. P
    Diabetes is one of the largest chronic diseases threatening 84 million patients in South East Asia alone. By the year 2045, this is expected to rise to 156 million. Lack of a permanent cure and impractical, expensive, painful measuring techniques are among the reasons behind these alarming statistics. Almost 58% of diabetes patients are not diagnosed in this South Asian region, mainly due to lack of motivation caused by the above issues. This research focuses on finding a solution, which is non-invasive, portable, practical, accurate, and cost-effective with the help of sensors and accessible technology platforms. The research started upon discovering the medical classifications, parameters, contributing factors, and external dynamics that could affect the result. Upon research, an algorithm was developed to calibrate and measure the blood glucose level, which is compatible with dynamic factors of the patients. Later on, the hardware device was built using NIR and red LEDs accompanied by a user-friendly mobile application, which can be accessible by patients of all ages. The results obtained were validated by using statistical techniques. The analysis showed a strong linear correlation between the voltage output and blood glucose level. The overall accuracy of the system accounts for above 90%. Since this solution is noninvasive, it provides a reusable and portable platform which can constantly monitor blood glucose levels conveniently in a painless manner, without any repetitive costs. Further, this solution will help patients to adjust medication based on their current blood glucose levels to reduce both the unnecessary damage of organs and additional costs being incurred.
  • Thumbnail Image
    PublicationEmbargo
    Air Visio: Air Quality Monitoring and Analysis Based Predictive System
    (IEEE, 2019-12-05) Dissanayaka, A. D; Taniya, W. A. D; De Silva, B. P. A. N; Senarathne, A. N; Wijesiri, M. P. M; Kahandawaarachchi, K. A. D. C. P
    Sri Lanka is facing a serious air pollution problem that severely impacts the daily life of every Sri Lankan. The main source of ambient air pollution in Sri Lanka is vehicular emissions. A methodology to monitor the air quality in real-time with an overall coverage of Sri Lanka, and automatically process these huge data to identify air quality levels in a specific area is now becoming a timely research topic. An air quality monitoring and analysis based predictive system is proposed to monitor the ambient air quality, provides the best route with minimum polluted air, maps the heatmaps to identify the current air quality of an area easily and predict the future air quality of each area. The prototype was implemented by hierarchically deploying two different gas sensors, an Arduino Uno board and a wifi module, to implement in open spaces between smart buildings, and transfers the sensor data back to the information processing center by using IoT technology for real-time display. The information processing center stores real-time information which is collected from the sensors to the database. By reading sensor data stored in the database, the front-end system draws real-time, accurate air quality levels included maps and predicts the less polluted routes and the air quality level over an area. Further, an energy harvesting system is also presented for the power consumption of the device. A route is suggested in an accuracy of 70% from this system. The final product provides a low cost, highly portable and easily maintainable system for the users.
  • Thumbnail Image
    PublicationEmbargo
    Employee Readiness towards Artificial Intelligence in Sri Lankan Banking Context
    (IEEE, 2019-12-17) Mathipriya, B; Minhaj, I; Rodrigo, L. D. C. P; Abiylackshmana, P; Kahandawaarachchi, K. A. D. C. P
    As technology improves an economy's performance, the changes it brings needs to be addressed. This Study focuses on how employees should be ready for the Artificial Intelligence implementations in banks. As Sri Lankan banks are still in the foundational level this study will make them aware of the current situation of what employees thinks of AI and whether they are ready to accept the technology or whether they are insecure about their job due to the change. Study have collected information through secondary sources and primary sources through a questionnaire. People readiness comprises of three variables, which are AI mind set, Employee skills, and their current job role. Based on the different factors analyzed, it can be seen that employees are ready to adopt AI in Sri Lankan banks but there are some restrictions, the employees are comfortable with the changes but they are insecure about their job.
  • Thumbnail Image
    PublicationEmbargo
    Therapy Tool for Adolescents with ADHD
    (IEEE, 2019-12-05) Nugawela, R. C. W. M. R. H. E; Fonseka, W. G. S; Perera, G. U. C; Mihirangi, S. K. S; Kahandawaarachchi, K. A. D. C. P
    Attention deficit hyperactivity disorder (ADHD) is one of the most common disorders widespread among children and adolescents. Adolescence is the transitional phase between childhood and adulthood. The main three symptoms of ADHD are hyperactivity, impulsivity and inattention. Prevalence of ADHD among adolescents is approximately 5% in Sri Lanka. Treatment is a vital factor in any ADHD patient's lifestyle which involves a combination of pharmaceutical medications as well as therapeutic treatments with the help of the patient's family and friends. With no proper treatment, children and adolescents with ADHD are faced with the risk of carrying on the symptoms of the disorder into adulthood. Hence, the importance of treatments for patients diagnosed with ADHD is clearly evident. The solution derived at is an Android Application to provide a therapeutic treatment acceptable to the three groups of symptoms in ADHD and to track and maintain a log of records of the patient's performance and progression. For this research, one participant each was dedicated for each testing module in order to eliminate subjectivity and ensure accuracy. The Android Application developed consists of activities targeted at treating all main groups of ADHD symptoms and offers a feasible solution for patients, parents and specially for doctors to monitor the patient's progress.
  • Thumbnail Image
    PublicationEmbargo
    Wedaduru-An Intelligent Ayurvedic Disease Screening and Remedy Analysis Solution
    (IEEE, 2019-12-05) Bandara, R. I. S; Prabagaran, S; Perera, S. A. K. G; Banu, M. N. R; Kahandawaarachchi, K. A. D. C. P
    Heart disease is one of the most common diseases worldwide. According to Ayurveda, behavior of humans associated with food habits are root causes of heart diseases. This research focuses on providing a diagnostic tool for heart diseases through a web- based application, where the diagnosis will be directed through the practices of Ayurveda. The proposed web-based solution `Wedaduru' uses artificial intelligence (AI), which analyses the physical appearance of the patient through image processing, and symptoms using a model with questionnaires. Thereby, the solution/application identifies remedies and treatments using supervised learning and provide herb details including the commonly grown areas of herbs using Google API. Heart diseases are predicted with an accuracy of over 86% and classified into four categories as Vataja, Pitaja, Kaphaja and Krimija. The proposed system provides a detailed report of the diagnosed Heart disease along with remedy treatments, diet plan and herbal plants along with locations where herbs can be found. At the end, `Wedaduru' will provide awareness in Ayurveda medicines and its values to common people.
  • Thumbnail Image
    PublicationEmbargo
    Secured, Intelligent Blood and Organ Donation Management System-“LifeShare”
    (IEEE, 2020-12-10) Wijayathilaka, P. L; Gamage, P. H. P; De Silva, K. H. B; Athukorala, A. P. P. S; Kahandawaarachchi, K. A. D. C. P; Pulasinghe, K. N
    The scarcity and exigency for blood and organs has created many discrepancies in current approaches. These have created the criteria for malpractices such as organ trafficking and black market selling. This research presents a solution with a secured-smart blood and organ donation web developed system, allowing both patients and healthcare providers to access information about the blood and organ processing records. The database would be managed using the Blockchain technology which could be only accessed by authorized users. Finally, tracking all registered donors, the proposed system generates a smart identity developed by Ethereum Smart Contract (ESC). System predicts blood demand for the future ten years using Linear Regression Model with 0.998 of high R-squared accuracy value. This reduces shortages and wastage of blood. Also, using global positioning system and K-Nearest Neighbors Machine Learning algorithm, the system finds the best matches among donors and seekers according to the nearest location. Further, the system will automatically send questionnaires for registered users to identify and evaluate their awareness and issues about organ donation. Overall, this study aims for a secured and transparent web application. Thus, it facilitates an innovative and a productive blood donation and organ transplantation process in Sri Lankan healthcare sector.
  • Thumbnail Image
    PublicationEmbargo
    Memory Improvement Tool for Dementia Alzheimer’s Patients
    (Elsevier, 2018-01-01) Weerakoon, D. S. D; Kahandawaarachchi, K. A. D. C. P; Dissanayake, J. D. S. Y; Thilakasiri, W. P. M; Shanthakumara, W. D. M. B
    The Alzheimer’s disease is one of the top ten causes of death among the elderly. Studies show that there is a significant increase in deaths reported after early 1990s due to the lack of a cure in preventing the disease in modern medicine. Hence, there are numerous attempts made towards managing the progression of the disease which results in improving the wellbeing of the patient. One of the recommended methods of managing it long-term is through providing many memory related activities to the patients. With the limited amount of resources and investments, Sri Lanka is finding it difficult to manage the significant number of patients. Furthermore, not all patients get the opportunity to visit the Alzheimer’s Foundation and receive treatments. This research is a small step towards creating a computer-aided platform for Alzheimer’s patients to improve their livelihood thorough activities focusing on 4As of Alzheimer’s (long-term memory, short-term memory, language and communication skills and fine motor skills) disease under the guidance of clinical Psychiatrists (1). The application is tested with over 75 Alzheimer’s patients under the guidance of their physicians. The comprehensive record keeping for patient condition analysis, gamification-based environment for patients and assistive tool for memory management are among the benefits of this application.