Browsing by Author "Sumathipala, S."

Now showing 1 - 4 of 4

Approach to study the efficacy and safety of new complementary and alternative medicine formulations: Lesson during COVID-19 from Sri Lanka
(Wolters Kluwer - Medknow, 2023) Pilapitiya, S.; Jayasinghe, S.; Silva, A.; Wickremasinghe, R.; Paranagama, P.; de Silva, J.; Lekamwasam, S.; Kularatne, S.A.M.; Wanigasuriya, K.; Kaluthota, S.; Sumathipala, S.; Rathnnasooriya, C.; Siribaddana, S.
COVID-19 affected Sri Lanka from early 2020, a time of considerable ignorance accompanied by wide media coverage of a devastating epidemic in Italy and Europe. Many were attracted to complementary and alternative medicine (CAM) or traditional medicine (TM) in this desperate situation. Several preparations were claimed to be effective against COVID-19 globally. Dammika Bandara Syrup© was one such preparation promoted for preventing and treating SARS-CoV-2 infection. It was based on bees' honey, pericarp and mace of Myristica fragrans (nutmeg), the seed of Foeniculum vulgare and fresh rhizome of Zingiber officinale, all believed to have anti-viral properties. Following an unpublished clinical study claiming efficacy, Dammika Bandara Syrup© gained wide media publicity and political patronage. The producer claimed of Goddess Kali revealing the formula added an anthropological, cultural, and religious complexity to the issue. The demand for the product increased rapidly as a debate raged both in public and in the parliament on utilizing such products in combating COVID-19. The Department of Ayurveda, which is statutorily responsible for regulating CAM/TM had to respond to the situation. The legislation to regulate such indigenous medicinal products was weak, and the crisis deepened as thousands converged to the production facility, defying mobility restrictions introduced to control COVID-19. This led to the Ministry of Health requesting academics to form a team and conduct a clinical trial to prove its efficacy. This paper outlines the process and issues faced during the regulatory approval for the trial in a polarized political environment. Some health professionals accused the researchers of bowing to political pressure and questioned the scientific justification for the trial. However, the team considered this as an opportunity to streamline a path for research into CAM/TM therapies in situations such as COVID-19. Several processes were identified and addressed, such as the provisional registration of CAM preparations, assessing the potential efficacy of a CAM product, confirmation of authenticity and safety, standardization and supervision of production respecting cultural identities, obtaining approval for human use, choice of comparators, and ethical issues. We believe the study has helped set standards and a benchmark for CAM and TM research in Sri Lanka.
Deep Learning Based Student Attention Monitoring and Alerting System During a Lecture
(3rd International Conference on Advances in Computing and Technology (ICACT ‒ 2018), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2018) Vettivel, N.; Ravindran, V.; Jeyaratnam, N.; Sumathipala, S.
Mindfulness is the ability to fully aware and focuses on the present moment. For students, it is essential to pay full concentration during the lectures. Staying focused while studying is vital for the better performance of any student. In this study, focuses on developing a deep learning-based attention monitoring and alerting system. The proposed system monitors attention of students during a lecture and gives an alert when attention is diverted. The study used mainly three aspects namely Heart Rate Variability, Brain Waves and Facial Expressions to capture the attention level of students while attending a lecture. By using three different aspects, it is expected to overcome the limitations of each aspect. Each aspect is further divided into several parameters, and most significant parameters that respond to the loose of students’ concentration was chosen using principal component analysis to train the deep neural network to measure the students’ concentration level. As the parameters cannot be able to label accurately with concentration, study used an unsupervised learning methodology and it considers the concentration drifting moment as an anomaly and detect it by deducing the pattern of the parameters. When the concentration drops below the threshold system will alert the user. The preliminary experiments reveal how the Facial Expressions, Heart Rate Variability and Brain Waves change with students’ concentration.
Features of Covid-19 patients detected during community screening: A study from a rural hospital in Sri Lanka.
(The Sri Lanka Medical Association., 2020) Senanayake, A.P.; Indrakantha, D.; Sumathipala, S.; Wanigasuriya, K.; Kularathne, S.; Lekamwasam, S.; Jayasinghe, S.; de Silva, H.J.; Siribaddana, S.
ABSTRACT: We studied the clinical course and virus shedding of all patients referred to Welikanda Hospital, in one month. There were 53 positives for Covid-19 by PCR. 24 (45%) were male, with an age range of 11-94 years. Of these, 41 (77%) were asymptomatic, 9 had cough, 4 had sore throat and six had fever. Pulse, blood pressure, respiratory rate and capillary oxygen were normal in all. A proportion of them had poor prognostic factors: asthma (n=4), hypertension (n=11), age above 60 years (n=9), and diabetes (n=11). Lymphopenia was seen in 20 and elevated CRP in 14. Viral shedding continued beyond 14 days in several persons and continued in symptomatic patients for a significantly longer time than asymptomatic patients. Covid-19 was an asymptomatic or mild illness in this group of people. Several of them continued to be RT-PCR positive even after 14 days. Such cases are an important source of community spread.
Language identification at word level in Sinhala-English code-mixed social media text
(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Shanmugalingam, K.; Sumathipala, S.
Automatic analyzing and extracting useful information from the noisy social media content are currently getting attention from the research community. It is common to find people easily mixing their native language along with the English language to express their thoughts in social media, using Unicode characters or the Unicode characters written in Roman Scripts. Thus these types of noisy code-mixed text are characterized by a high percentage of spelling mistakes with phonetic typing, wordplay, creative spelling, abbreviations, Meta tags, and so on. Identification of languages at word level become a necessary part for analyzing the noisy content in social media. It would be used as an intimidate language identifier for chatbot application by using the native languages. For this study we used Sinhala-English codemixed text from social media. Natural Language Processing (NLP) and Machine Learning (ML) technologies are used to identify the language tags at the word level. A novel approach proposed for this system implemented is machine learning classifier based on features such as Sinhala Unicode characters written in Roman scripts, dictionaries, and term frequency. Different machine learning classifiers such as Support Vector Machines (SVM), Naive Bayes, Logistic Regression, Random Forest and Decision Trees were used in the evaluation process. Among them, the highest accuracy of 90.5% was obtained when using Random Forest classifier