Browsing by Author "Silva, C."

Now showing 1 - 3 of 3

Embargo
Academic Depression Detection Using Behavioral Aspects for Sri Lankan University Students
(2021 3rd International Conference on Advancements in Computing (ICAC) -SLIIT, 2021-12-09) Gamage, M.A.; Matara Arachchi, R.; Naotunna, S.; Rubasinghe, T.; Silva, C.; Siriwardana, S.
Academic Depression is a widespread problem among undergraduate students in Sri Lanka. It is exhausting and has a detrimental impact on students' academic life. Therefore, the development of a technique to estimate the probability of depression among undergraduates is a blessed respite. Depression is mostly caused by a failure to check students' psychological well-being on a regular basis. Identifying depression at the college level, leading the students to get proper therapy treatments. If a counselor detects depression in a student early enough, he/she can successfully assist the student in overcoming depression. However, keeping track of the substantial changes that occur in students because of depression becomes challenging for the counselor with a considerable number of undergraduates. The advancement of image processing and machine learning fields has contributed to the creation of effective algorithms capable of identifying depression probability. Depression Possibility Detection Tool (DPDT) is considered an effective automated tool that brings the depression probability of a certain student. In DPDT, the result is generated by concerning four main strategies. They are facial expressions, eye movements, behavior changes (step count and phone usage), and physical conditions (heart rate and sleep rate). Convolutional Neural Network (CNN) with Visual Geometry Group 16 (VGG16) model, Residual Neural Network (ResNet-50), Random Forest (RF) classifier is the main models and techniques used in the system. More than 93% of accuracy was generated in every trained model. The paper concludes the system overview along with four strategies, literature review, methodologies, conclusion, and future works.
Embargo
Auto Training an AI for Detecting Plant Disease Using Twitter Data Annexed With a Plant Anthology
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Vasanthan, N.; Shimran, Mohamed; Ahkam, A.; Ishak, I.; Silva, C.; Kuruppu, T.A.
Agricultural productivity plays a vital role in contributing to a nation’s economy. Farmers nowadays are concerned due to disease persistence in crops and plants, and it also affects the economy indirectly, so it is important to come up with a solution to detect plant diseases and educate the farmers about the solutions to retaliate against the diseases. Proper care is mandatory to safeguard the quality of plants. The existing traditional methods consume a massive amount of time and resources hence, it’s costly. Due to the importance of continuous monitoring, it seems impractical for a farmer to implement the traditional methods on large scale. The Traditional systems which are used lack the ability to identify diseases out of their predefined scope. As a solution, we came up with an autolearning system that identifies new plant diseases and provides remedies. This paper showcases the image processing techniques to detect plant diseases, Auto ML techniques to create new models for plants and corresponding diseases, Diseases are identified using image processing, Remedies are extracted for the given plant diseases using unstructured data from web data crawling. The business intelligence model uses NLP to provide ideas about the trending plants and plantrelated diseases are also discussed in this paper.
Embargo
Non-Communicable Diseases Detection System
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Thudawehewa, H.R.; Pathmakulasooriya, U.C.B.; Jayawardhana, W.A.P.T.; Wellehewa, G.C.; Silva, C.; Rathnayake, P.
This research paper presents a Non-communicable Diseases Detection System which is a centralized medical system designed for general public usage. The system aims to provide help for people with non-communicable diseases. In a pandemic situation like this where people find it difficult to reach medical facilities and staff, the system is more advantageous. The system covers areas related to the medical report analysis, BMI value prediction, and breast cancer analysis related to noncommunicable diseases. Presently health reports are taken for every disease. BMI is a factor essential to everyone to lead a healthy life. The majority of women suffer from breast cancer. As per the findings of the report, the report analysis predicts possible diseases that can occur in the person concerned. In BMI prediction, particularly the possible BMI value and weight value for the next month is predicted. In Mammogram detection, it gives the current status of the breast. The report analysis model has 90.6% accuracy while the BMI prediction model has 99.7% accuracy. The mammogram detection model proved that it has 96.5% accuracy. All the aforesaid procedures were carried out by analyzing related data systematically. Machine learning, Deep learning, and Image processing techniques were used to develop this system. The main purpose of this system is to make the persons aware of their current health status and to prevent them from having non-communicable diseases.