Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2684

Browse

Now showing 1 - 20 of 34

Open Access
2D Pose Estimation based Child Action Recognition
(Institute of Electrical and Electronics Engineers Inc., 2022-11) Mohottala, S; Abeygunawardana, S; Samarasinghe, P; Kasthurirathna, D; Abhayaratne, C
We present a graph convolutional network with 2D pose estimation for the first time on child action recognition task achieving on par results with LRCN on a benchmark dataset containing unconstrained environment based videos.
Embargo
Accuracy of Diabetes Patient Determination: Prediction Made from Sugar Levels Using Machine Learning
(Springer, Cham, 2022) Krishnananthan, S; Puvanendran, S; Puvanendran, R
This study focuses on the prediction of the Diabetic Patients through the sugar levels. The Dataset is analyzed using the data mining techniques such as feature extraction, associate rule mining and classification. The Fast Blood Sugar (FBS) and Post-Prandial Blood Sugar (PPBS) sugar levels are selected as the important features, identification of a rule depending on the selected feature is identified and the performance metric for three classifiers is analyzed based on the selected attributes and choose the classifier with high accuracy. Classification algorithms like random forest, decision tree (J48), and Naïve Bayes were utilized to identify the patients with diabetes disease. The performance of these techniques is considered using the factors relating to the accuracy from the applied techniques. The accuracy is seeming to be higher for Naïve Bayes. The outcomes acquired demonstrated that Naïve Bayes outflanks from different strategies with most noteworthy precision of 74.8%.
Embargo
AI-Based Child Care Parental Control System
(IEEE, 2022-12-09) Jayasekara, U; Maniyangama, H; Vithana, K; Weerasinghe, T; Wijekoon, J; Panchendrarajan, R
Due to the prevalence of the COVID-19 epidemic around the globe, children were compelled to engage in remote learning through online platforms, hence mobile phone has become one of their predominant devices. Mobile device with Internet access offers a major outlet for education, entertainment, and social connection, but this combination can lead to several significant bad sequences such as online exploitation, harmful addictions, and other negative impacts of online social networking. To address harmful effects, parental controls are becoming more crucial, yet Sri Lankan parents are less aware of this. Consequently, this study proposes a parental control system to monitor their child’s activities. Android, Microsoft Azure, Java, Python, OpenCV, MySQL, and FastAPI are among the most prominent technologies utilized in the proposed application’s development. The suggested approach focuses primarily on the Sri Lankan context and aims to enhance parental digital literacy while safeguarding children from cyber threats. Yielded results showed the proposed mobile application for the identification of toxic words, drugs & alcohol content, game character images, and Instagram Sinhala comments severity as 94%, 95%, 97%, and 55% respectively in controlled experiments.
Embargo
Algorithmically Navigating Complex Tabular Structures in Images for Information Extraction
(IEEE, 2022-12-26) Nugawela, M; Abeywardena, K. Y; Mahaadikara, H
Computer vision has been in the forefront of automating workflows to replace manual repetitive tasks with convenience and accuracy. Recognizing text from images of commercial documents through optical character recognition (OCR) form the initial step of most such workflows where majority of their information are in the form of complex data structures such as tables and nested tables. Although OCR technology has evolved to effectively capture text from images, there is still room for improvement in recognizing complex data structures and extracting tabular data from images. This paper proposes an algorithmic approach based on keyword detection and the position of words relative to each other in order to recognize nested structures and successfully extract tabular data into a program and human readable format, which aims to take a different approach as opposed to using machine learning models or pre-defined templates for layout recognition. Furthermore, this approach is shown to yield successful results in correctly comprehending the layout and data of nested table structures in multiple rows in a table.
Embargo
Anonymo: Automatic Response and Analysis of Anonymous Caller Complaints
(IEEE Computer Society, 2022-08-17) Azhar, A; Maweekumbura, S; Gunathilake, R; Maddumaarachchi, T; Karunasena, A; Nadeeshani, M
Customers are considered as the most valued asset in any business organization. Therefore, attending especially to negative feedback provided by customer in form of complaints is important for an organization to identify areas to improve and retain customers. To quickly respond to customer complaints many business organizations have made hotlines available. Such caller hotlines are dedicated for the purpose of receiving complaints or allowing whistleblowers to reveal information. Due to the fear of being identified, there is a hesitancy in the public to use these hotlines. From the perspective of the organizations when a customer complaint is received it is required to evaluate the validity of the call made to hotlines. Furthermore, when complaints are made, it is required to handle them efficiently by transferring them to relevant departments and prioritize complaints This research proposes 'Anonymo', a system to handle customer complaints in a secure and an efficient manner. To do so, the system analyses the complaints obtained by a caller and provides the end users with the appropriate responses and output, that includes the following: i. Conversational AI agent to respond to callers, ii. Wanted and unwanted call classification, iii. Department-based Complaint classification, iv. Caller Emotion detection and caller complaint analysis while establishing the caller's anonymity. An accuracy of 88.26% was obtained for identification of wanted complaints using SVM algorithm, an accuracy of 85% was obtained for department-based classification using SVM algorithm and 67% accuracy was obtained for emotion analysis by LSTM algorithm
Embargo
An Approach of Enhancing the Quality of Public Transportation Service in Sri Lanka using IoT
(Institute of Electrical and Electronics Engineers, 2022-10-15) Weligamage, H. D; Wijesekara, S. M; Chathwara, M.D.S.; Isuru Kavinda, H.G.; Amarasena, N; Gamage, N
Traveling is one of the necessary and common behavior of any society. Thus, there are many ways of human travel. Due to the fact that Sri Lanka is still a developing country, the vast majority of the population rely on public transit as opposed to private transportation options. In this situation, public and private bus services are the most common means of transportation for people. People who use bus service for daily traveling face lot of issues due to the delays in bus arrivals, missing the bus or excessive crowd in the bus. This proposed system is intended to make bus travel more efficient and convenient for those who rely on buses as their primary means of public transit. This system provides a mobile application for passengers to utilize in order to observe the real-time position of the buses, as well as their anticipated arrival time, current passenger count, and a visualization of the available seat locations within the vehicle prior to the arrival of the bus. Besides, traditional manual ticketing procedure also cause many difficulties for the passengers like need of carrying changed money each time they travel. To avoid this serious problem, this system introduces a non-interactive automated ticketing system which has a smart card that can be tracked in a RFID zone and an automated fee calculating system using a logical conceptual algorithm considering environmental factors. Along with this a digital ticket is issued including all the required details of a journey. In addition to that, this system has a two-factor authentication process that makes use of face recognition to validate the user's identity before granting access to their smart card. The goal of this application is to provide a systematic solution for the typical challenges that public transportation users face in order to improve the service quality by using IoT-based technologies and image processing.
Embargo
The Automated Temporal Analysis of Gaze Following in a Visual Tracking Task
(Springer, Cham, 2022-05-15) Dhanawansa, V; Samarasinghe, P; Gardiner, B; Yogarajah, P; Karunasena, A
The attention assessment of an individual in following the motion of a target object provides valuable insights into understanding one’s behavioural patterns in cognitive disorders including Autism Spectrum Disorder (ASD). Existing frameworks often require dedicated devices for gaze capture, focus on stationary target objects, or fails to conduct a temporal analysis of the participant’s response. Thus, in order to address the persisting research gap in the analysis of video capture of a visual tracking task, this paper proposes a novel framework to analyse the temporal relationship between the 3D head pose angles and object displacement, and demonstrates its validity via application on the EYEDIAP video dataset. The conducted multivariate time-series analysis is two-fold; the statistical correlation computes the similarity between the time series as an overall measure of attention; and the Dynamic Time Warping (DTW) algorithm aligns the two sequences, and computes relevant temporal metrics. The temporal features of latency and maximum time of focus retention enabled an intragroup comparison between the performance of the participants. Further analysis disclosed valuable insights into the behavioural response of participants, including the superior response to horizontal motion of the target and the improvement in retention of focus on the vertical motion over time, implying that following a vertical target initially proved a challenging task.
Embargo
Blockchain-based Secure Environment for Electronic Health Records
(IEEE, 2022-11-26) Jayasinghe, J. G. L. A; Shiranthaka, K. G. S.; Kavith, T; Jayasinghe, M. H. D. V.; Yapa Abeywardena, K; Yapa, K
Electronic health records (EHRs) have become the de facto standard for storing patient data in hospitals because of the data technology revolution. Many hospitals use server-based systems to keep track of patient medical records, however, this limits the scalability of those systems because they require a lot of storage space. Interoperability and security and privacy concerns, as well as cyber-attacks on the centralized storage, are among the issues they are dealing with. Lab report downloads can be compromised by a poor authentication mechanism that can be easily shared with a third party. Highlighted issues will be addressed by the proposed system, a Blockchain-based private patient information management system. Using a distributed, immutable, and secure ledger, the solution promises efficient system access and retrieval. Consensus can be achieved without consuming a big amount of energy or causing network congestion thanks to an enhanced consensus technique. Because of their tight zero-knowledge requirement, near-perfect data interchange across many platforms is possible thanks to Non-Fungible Tokens, which encourage openness and immutability in the data flow. In addition, the proposed system uses a mix of a hybrid access control system and public key cryptography to ensure high levels of data protection. Additionally, it is a fantastic accomplishment when Lab Report Download Portal and the report generator for medical lab reports can be connected to the main system, which can dynamically modify the report template format with multi-factor authentication enabled. Know your customer verification is also used to authenticate the user to the system. Decentralizing the medical industry’s data storage, sharing, and record-keeping is the general goal of this solution; this method eliminates the need for paper records.
Embargo
BlossomSnap: A Single Platform for all Anthurium Planters Based on The Sri Lankan Market
(Institute of Electrical and Electronics Engineers, 2022-10-15) Rathnayake, R.M.S.T; Tharika Pramodi, M.L.A.D.; Gayathree, I. R; Rashmika, L.K.R; Gamage, M; Gamage, A
The popular and extensively grown flowering plant known as the Anthurium is prized for its beauty. In Sri Lanka, anthuriums have a substantial international market. Although it is a significant field that can be further developed by expanding the market, but it has led to a lack of attention, resources, and a moderate cost of production, as well as from the absence of an appropriate market channel, all of which have led to lower productivity and quality. As a result, Anthurium growers have numerous challenges both in terms of production and marketing. This paper introduces a novel mobile application 'BlossomSnap' which involves automating and significantly enhancing the outdated manual process. Using natural language processing, machine learning, and deep learning approaches, the proposed system analyzes the diseases, pests, varieties, and the highest quality plants to create a more secure growing environment. It will provide high-quality, cost effective, and timely services. The first step of anthurium plant disease and pest diagnosis is carried out using image processing, deep learning, and machine learning technologies. In order to identify the infection stage, the following steps involve extracting, classifying, and detecting images of Anthurium flowers and leaves. The accuracy was checked by comparing actual results taken from experts with the predicted results obtained from the proposed system. 'BlossomSnap' achieves an average accuracy of more than 80% and produces a better overall result. An in-place chatbot technology is intended to assist new planters with their problems. The Anthurium plant variety and quality detection methodology is used in concert with to determine the optimum market opportunity.
Embargo
CertiMart: Use Computer Vision to Digitize and Automate Supermarket with Fruit Quality Measuring and Maintaining
(IEEE, 2022-12-09) Rathnayake, W.P.D.N. P; Geeth Dulanjana, D; Punchihewa, A.V.B.W. G; Anjana, N.W. G; Suriya Kumari, P. K.; Samarakoon, U
Sri Lanka has a tropical environment, which makes it easy for fruit and vegetable plants to thrive. Vitamins, proteins, and other nutrients are abundant in fruits. However, there is a time when the fruit is considered to be fresh. During this time, many fruit supplier firms continue to supply fruit that is unsafe for ingestion due to inaccuracy in the sorting process when the fruit is taken from the plantation and the introduction of other fruit into an incorrect packing. As a result, detecting food rotting from the point of production to the point of consumption is critical. Inside the market we realize that there is unavailability of sorting of fruits. Just after receiving the fruit into the supermarket, we should have a way to measure freshness of fruit and maintain it. In addition to this ripened method identification and disease identification will be great help to this help.
Embargo
Child Head Gesture Classification through Transformers
(Institute of Electrical and Electronics Engineers Inc., 2022-11-04) Wedasingha, N; Samarasinghe, P; Singarathnam, D; Papandrea, M; Puiatti, A; Seneviratne, L
This paper proposes a transformer network for head pose classification (HPC) which outperforms the existing SoA for HPC. This robust model is then extended to overcome the limited child data challenge by applying transfer learning resulting in an accuracy of 95.34% for child HPC in the wild.
Embargo
Children's Behavior Analysis Through Smart Toys
(Institute of Electrical and Electronics Engineers Inc., 2022-11) Ramesha, M. D. D; Kavindi, M. V; Somawansa, R.P; Yadav, A; Samarasinghe, P; Wedasinghe, N; Jayasinghearachchi, V
Analyzing children's behavior is a major part of pediatric psychological studies. Here we are going to use the hand movements of the child to understand the behavioral pattern with the help of IoT-based toys. © 2022 IEEE.
Embargo
Comparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimation
(Institute of Electrical and Electronics Engineers Inc., 2022-11-04) Lindamulage, A; Kodagoda, N; Reyal, S; Samarasinghe, P; Yogarajah, P
Magnitude-based pruning is a technique used to optimise deep learning models for edge inference. We have achieved over 75% model size reduction with a higher accuracy than the original multi-output regression model for head-pose estimation
Embargo
Comparison of CPU Scheduling Algorithms: FCFS, SJF, SRTF, Round Robin, Priority Based, and Multilevel Queuing
(IEEE, 2022-11-03) Rajapaksha, U. U. S. K; Pemasinghe, S
In this article, we are discussing various aspects of CPU scheduling. We first introduce the concept of CPU scheduling, different types of schedulers and the typical terminology used in relation to processes. Scheduling criteria, the optimization of which is the ultimate goal of a CPU scheduling algorithm, are also discussed. We then discuss various types of research studies that have been carried out with respect to CPU scheduling algorithms. Different CPU scheduling algorithms are examined with examples to highlight their characteristics. Advantages and disadvantages of each of these algorithms are also explored. The scheduling algorithms discussed are, first come first served, shortest job first, shortest remaining time first, priority based, round robin, multilevel queue, and multilevel feedback queue.
Embargo
Deep Vision-Data Mining To Find Insights and Visualization in Code Repositories
(Institute of Electrical and Electronics Engineers, 2022-09-16) Ariyarathne, I.G.P.S; Wimalasuriya, M.K; Abesinghe, N.D.N.S; Edirisinghe, E.A.S.H.; Kodagoda, N; Kasthurirathna, D
Deep Vision is a code mining system for analyzing and visualizing a repository's codebase so that its users may obtain a sense of the repository's insights. This system will examine codebases and support as many languages as feasible. This system visualizes the file structure, vocabulary and length change rates, comprehensibility and defect rates, etc. It is vital to have a comprehensive grasp of the codebase to manage the program's complexity by calculating multiple factors and presenting them in a descriptive and engaging dashboard to enhance the quality of the software process and the project's controllability. Improved code visualization may help improve code understandability while lowering development costs. In addition, our visualization regions and methodologies are one-of-a-kinds. To get rapid and reliable results, we will create new machine learning models and algorithms for analysis and new categories of a code repository. Our dataset for this research will be GitHub open-source code repositories
Embargo
E-Learning Education System For Children With Down Syndrome
(Institute of Electrical and Electronics Engineers, 2022-09-16) Sampath, A.S.T; Vidanapathirana, M.W.; Gunawardana, T.B.A; Sandeepani, P.W.H.; Chandrasiri, L.H.S.S; Attanayaka, B
The World Health Organization assesses that Down Syndrome (DS) affects about 1 in 1000 births worldwide. Children with DS cannot learn, as usual, instigating numerous inadequacies that lead to formative issues such as trouble encoding information and low intelligence to interpret data for decision-making. As a superior technique for these kids' intercom-municating and logical intellect, free-hand sketch drawing, Voice training, and word prediction activities can be success-fully utilized. As the best way to express the mindset of such chil-dren, introducing an E-Learning system makes a friendlier ac-tivity than learning about the past. Because of the improvement of Artificial intelligence and its encouragement, E-Learning-re-lated exploration and applications are moving at an enormous advancement rate. The main objective of this project is to de-velop a reliable and efficient approach to predicting the devel-opment of DS children. Classifying and identifying those hand-written images and voice samples and those samples are given by children with DS compared to the teacher through the construction of a model structure. This research project specially considered local down syndrome children's hand-drawn images, voice samples, letters, numbers, and words as the input. As a result, it gives accuracy and similarity with the teacher's sam-ples and relates parts in the down syndrome children's samples. The system uses artificial intelligence technologies. Through that, the knowledge capacity of the DS children and their con-veyed articulation of that knowledge can be assessed for additional correlations and investigation.
Embargo
Face Skin Disease Detection and Community based Doctor Recommendation System
(IEEE, 2022-12-09) Udara, M.A.A.; Wimalki Dilshani, D.G.; Mahalekam, M.S.W.; Wickramaarachchi, V.Y.; Krishara, J; Wijendra, D
In our country, skin diseases are more common than other diseases because of the climate. Skin diseases are occurring almost on all groups of ages among people. It is one of the most common types of diseases where some can be painful, and some can cause fatal to human life. The delay of the disease detection, difficulties of identify the infected area, Ignorance of the spread of the disease and treatments may threat to the patient’s life. Most of the time this process is performed manually which can lead to human errors and takes days for providing the results. This paper reports a smart solution that assists the patients by detecting the disease, identify the current infected area of the disease, recommend best doctors, provide community-based prevention guidelines, and predict the future risk. Also due to this economic crisis, we suggest that it’s much easier if the patient can do these skin check-ups systematically to continuously monitor and detect skin disease to get proper medical attention. As treatment procedures can be different from each doctor and impact will be different, we are working on community-based platform where we can get patients’ reviews about doctors and preventive guidelines. Depending on the performance evaluations, the results obtained from the proposed method for disease identifications are in the range of 90% - 95% of accuracy.
Embargo
Farming Through Technology Driven Solutions For Agriculture Industry Ceylon E-Agro mobile application-find technology based solutions for agricultural problems
(Institute of Electrical and Electronics Engineers, 2022-09-16) Imalka, L.A.; Gunawardana, K.G.A.; Kodithuwakku, K.M.S.K; Arachchi, H.K.E; Harshanath, S.M.B; Rajapaksha, S
Many developing countries are based on the agricultural sector. More than 60 percent of the population depends on this sector. This project is focused on maize cultivation. In agriculture, farmers play the most important role. Currently, farmers are facing many problems related to maize cultivation in Sri Lanka. This mobile application will help the maize farmers to overcome these difficulties and provide a good consumer demand for maize cultivation. Through this mobile application, the farmer can find solutions for pest & diseases in maize, fire threat in the farm field. AI based Agri Agent will be provide real-time solutions, bring the farmers and the buyers into the one platform, and provide price prophesying, price index feature. IoT based smart farming features will be provided to remain soil moisture and quality of soil for maize plantation.
Embargo
A Framework for Tracking And Summarizing Daily Activities with Mobile Phone for Healthy Life of a User
(Institute of Electrical and Electronics Engineers, 2022-09-16) Wickramasinghe, K.E.T.; Albertjanstin, N; Wijethunga, L.P. P. L; Rajapaksha, U.U.S.K; Panduwawala, P.K.K.G; Harshanath, S.M.B
People nowadays have incredibly busy lifestyles with little time to do their activities, and smartphones have become a need for many people all over the world as new features and controls have been developed, and smartphone usage has rapidly increased by individuals. People that lead complex lifestyles find it difficult to balance their activities. As a consequence, an automated method of tracking user activity on a smartphone can give a better solution for managing a user's daily life while also saving time. We take a look at some of the previous studies on user behaviour tracking methods approaches. Derived from the previous studies, we noticed some important challenges, including smartphone addiction and unhealthy posture, battery drainage concerns, managing educational activities, and finding necessary information from the huge data. In this paper, we proposed an automated monitoring approach to track user activities on smartphones and give solutions to the aforementioned difficulties. We developed different algorithms such as ANN to understand smartphone usages and battery interactions, CNN for detecting unhealthy neck postures and Word2Vec for generating similar meanings for fast search
Embargo
Identifying Objects with related Angles using Vision-based System integrated with Service Robots
(2022) Lakshan, K.K. Pasindu
Manipulation an object can be done with the collaboration of a human to a robot by introducing the object in a proper way. To do this in an easy way, we can model the object inside the robot head and add some sensors and cameras to identify the specific object. But when it comes to the real world, we cannot model all the objects in the world inside a robot head. If we can manipulate every object there can be more work would have done by the robots in efficient way. This research will present a strategy to identify the unknown objects using a visionbased system and with the perspective angles of the detected object and the system is integrated with service robots. This will go in a way when the robot should be able to identify the objects around the robot in an asynchronous manner with rotational angles and the pitch and roll angles, perspective to the robot standing surface. The research will be based on Artificial intelligence, Machine learning, and Robotics. Robotics operating system is used for simulating the robots and identification. For the identification process, a few ways can be used. Vision-based identification using color and depth images from an RGB camera, and this research is mainly based on this RGB, and depth feature integrated with YoloV5. And there are some other ways to identify objects like using a 3D-LiDAR laser scanner. However, this learning process, should have a stable object to model and train the object. After the object recognition, by using the proposed methodology robots can calculate and estimate the angles of the detected object. After the acquisition, the robot should be able to identify the object any time when it sees the object. Since this is a robot, we can use this to model unknown objects and retrieve the data from its database and manually name them if there is no one to name it in the time being