Research Papers - Dept of Information Technology
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593
Browse
34 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Automated Child Social Attention Evaluation(IEEE, 2022-12-09) Sandunika Wasala, K; Dhanawansa, V; Velayuthan, M; Samarasinghe, PProviding proper care for children with attention difficulty disorder is crucial, one way to ensure this is early identification of these disorders. In Sri Lanka, a developing country, it is difficult to find resources such as clinics, clinical expertise, and other resources which are essential for diagnosis. The absence of these apparatuses risks the mental well-being of the child as well as access to help. Hence a need arises to develop an automated social attention evaluation system. This will serve as the first line of diagnosis and help the parents/guardians secure the help required from an early age for the child. To the best of the authors’ knowledge, no solution of this nature is readily available for the Sri Lankan community so far. Keeping the low-income bracket of the country in mind, we propose a solution that can be easily deployed even on a cheap mobile/tablet-like device. It is difficult to perform these evaluations for children in similar settings as adults, as they are easily distracted. Therefore, care must be taken to grab the child’s attention throughout the evaluation process. In this research, we developed applications for children at different levels and each level assesses child attention between social objects and non-social objects through a child-friendly game, as they have sufficient visual stimuli to hold the child’s attention. In this study we investigated the screen time spent by the child, the attention of the child on different categories of images (High Autism Interested or Low Autism Interested images), and the switching patterns of the attention between these images. Only typical children were evaluated for this research due to the pandemic situation as well as other internal problems in the country. This system will test and evaluate atypical children in our future work.Publication Embargo Model Development for Child Developmental Milestone Assessment(IEEE, 2022-12-09) Mudannayake, M; Kumari, G; Abeygunawardana, S; Amaranayake, N; Samarasinghe, P; Mohottala, S; Wijethunga, SThis paper presents the implementation of models for assessing the developmental milestone of children below age five on physical, cognitive, social, and emotional factors, which is a crucial aspect of human development. To the best of our knowledge, we are the first to design and evaluate models assessing the developmental delays of Sri Lankan children. The primary goal of this study is to analyze the ability of children to reach the relevant milestones in their childhood using video recordings and parents’ feedback. Out of the different models we experimented with, we selected the best models in our final evaluation. As the principal contribution, we developed a model to decide whether the child has typical developmental growth or otherwise using parents’ feedback and obtained 92.31% accuracy. Furthermore, we achieved 92.76% for the social and emotion detection model and 88.44% accuracy for the child action recognition model using video-based datasets. In the future implementation, the derived models will be integrated to build a mobile application.Publication Embargo Development of Low Resource Machine Learning Models for Child Cognitive Ability Assessments(IEEE, 2022-12-09) Kahawanugoda, A; Gnanarathna, K; Meegoda, N; Monarawila, R; Samarasinghe, P; Lindamulage, A.GAutomated cognitive assessment tools are state-of-the-art in assessing cognition development. Due to the low availability of resources, building automated cognitive ability evaluation tools is challenging. This study focuses on developing machine learning models using a limited amount of data to assess Reasoning IQ, Knowledge IQ, Mental Chronometry and Attention-levels of Sinhala-speaking children between the age of 7 to 9 years. Our solution includes Sinhala speech recognition systems, image classification models, gaze estimation, blink count detection and facial expression recognition models to evaluate the above four cognitive ability measuring factors. Open domain speech recognition has been used to evaluate complex Sinhala child verbal responses and limited vocabulary responses were assessed using an end-to-end speech recognition system, respectively achieving 40.1% WER and 97.14% accuracy. Additionally, the image classification models for handwritten Sinhala letter recognition and two shape recognition models have gained 97%, 89% and 99% accuracy. The linear regression model for attention level evaluation that utilizes the inputs from a combination of eye-gaze estimation, facial expression recognition and blink rate detection models has gained 85% accuracy.Publication Embargo Qualitative Analysis of Automated Visual Tracking of Objects Through Head Pose Estimation(IEEE, 2022-12-09) Abeysinghe, A; Arachchige, I. D; Samarasinghe, P; Dhanawansa, V; Velayuthan, MAn automated approach for object tracking and gaze estimation via head pose estimation is crucial, to facilitate a range of applications in the domain of -human-computer interfacing, this includes the analysis of head movement with respect to a stimulus in assessing one’s level of attention. While varied approaches for gaze estimation and object tracking exist, their suitability within such applications have not been justified. In order to address this gap, this paper conducts a quantitative comparison of existing models for gaze estimation including Mediapipe and standalone models of Openface and custom head pose estimation with MTCNN face detection; and object detection including models from CSRT object tracker, YOLO object detector, and a custom object detector. The accuracy of the aforementioned models were compared against the annotations of the EYEDIAP dataset, to evaluate their accuracy both relative and non-relative to each other. The analysis revealed that the custom object detector and the Openface models are relatively more accurate than the others when comparing the number of annotations, absolute mean error, and the relationship between x displacement-yaw, and y displacement-pitch, and thereby can be used in combination for gaze tracking tasks.Publication Embargo Mobile-Based Analysis of Visual Attention in Young Children(IEEE, 2022-12-09) Jayakody, K; Dhanawansa, V; Velayuthan, M; Samarasinghe, PThere is a crucial need to screen young children for attention impairments given that the ability of a child to deal with the demands of everyday life is dependent on the development of the child’s attention. Intervention at a young age facilitates the training and enhancement of attention, as young brains are the most responsive to treatment. Sri Lanka, a low-income country, lacks accessible, home-based screening tools which can be used to assess the attention of young children. Moreover, most Sri Lankan parents are not aware of attention impairments. To bridge this gap, this paper proposes an easily accessible, home-based attention assessment tool in the form of a mobile application. The application provides a series of engaging tasks for assessing and training, the aspects of visual attention (focused attention, selective attention, divided attention, sustained attention and shifting attention). The assessments were carefully designed to suit the age and the attention span of the child. The performance analysis performed on the data collected showed the varied responses of children of different ages on different assessments. Clustering was performed in identifying the varying performance levels of typical children and this project will be extended to evaluate atypical child performance.Publication Embargo Graph Neural Network based Child Activity Recognition(IEEE, 2022-08-25) Mohottala, S; Samarasinghe, P; Kasthurirathna, D; Abhayaratne, CThis paper presents an implementation on child activity recognition (CAR) with a graph convolution network (GCN) based deep learning model since prior implementations in this domain have been dominated by CNN, LSTM and other methods despite the superior performance of GCN. To the best of our knowledge, we are the first to use a GCN model in child activity recognition domain. In overcoming the challenges of having small size publicly available child action datasets, several learning methods such as feature extraction, fine-tuning and curriculum learning were implemented to improve the model performance. Inspired by the contradicting claims made on the use of transfer learning in CAR, we conducted a detailed implementation and analysis on transfer learning together with a study on negative transfer learning effect on CAR as it hasn’t been addressed previously. As the principal contribution, we were able to develop a ST-GCN based CAR model which, despite the small size of the dataset, obtained around 50% accuracy on vanilla implementations. With feature extraction and fine tuning methods, accuracy was improved by 20%-30% with the highest accuracy being 82.24%. Furthermore, the results provided on activity datasets empirically demonstrate that with careful selection of pre-train model datasets through methods such as curriculum learning could enhance the accuracy levels. Finally, we provide preliminary evidence on possible frame rate effect on the accuracy of CAR models, a direction future research can explore.Publication Embargo Automated Analysis of Children Emotion Expression Levels(IEEE, 2022-08-25) Nadeeshani, N; Kalaichelvan, K; Karunasena, A; Samarasinghe, PDespite the advancement in the field of facial emotion expression analysis, less attention has been given for facial emotion expression and emotion level analysis in children. This paper presents three novel findings in the area of child emotion expression. Identifying and validating the AU stimulation of children, automating the child emotion and level of emotion prediction and age wise analysis of child emotion expression. Emotion predictions were compared resulting through deep learning methods such as 3DCNN and machine learning approaches using EFA.AU stimulation results generated through EFA are consistent with the FACS. Through AU analysis, the paper shows that a child video or image can be predicted for the expressed emotion and its level with 91.04% accuracy through KNN classifier. While the 3DCNN approach resulted in 82.64% accuracy, the age wise emotion prediction through CNN resulted in the range of 60% to 86.6%. Though all approaches evidenced comparable results in emotion prediction, the emotion level prediction through EFA and AU outperformed 3DCNN and CNN approaches in all cases. Happy emotion prediction in age wise emotion analysis resulted in a higher accuracy over sad and disgust emotions. As emotion level prediction in age wise analysis display mixed results, a further research on age wise AU stimulation is encouraged.Publication Embargo Optimum Music: Gesture Controlled, Personalized Music Recommendation System(IEEE, 2021-12-09) Wijekoon, R; Ekanayaka, D; Wijekoon, M; Perera, D; Samarasinghe, P; Seneweera, O; Peiris, AMusic plays an important role in everyone’s life since it helps to relax the mind when appropriate music is played. This paper presents a music recommendation system based on the user’s current emotions, activities as well as demographic information such as age, gender, and ethnicity. In addition, the system can be controlled by hand gestures and vocal commands. Unsupervised learning methods in were used to recommend music according to the demographic data and emotions of the user. Finally, the important idea is to recommend music based on all of the user’s data, such as demographics, emotions, and activities. The overall system performance was manually tested and evaluated with a group of individuals, yielding a 70% satisfaction rate for the recommendation; additionally, supporting models such as demographic identification, emotion identification, and hand gesture identification have received a higher proportion of accuracies, contributing to the research’s success. Unlike other systems, ours utilizes all of the user’s information while making music recommendations.Publication Embargo Non-Verbal Bio-Markers for Automatic Depression Analysis(IEEE, 2021-12-02) Yashodhika, G. B. O; De Silva, L. S. R.; Chathuranaga, W. W. P K; Yasasmi, D. L. R; Samarasinghe, P; Pandithakoralage, S; Piyawardana, VDetection of early depression risk is essential to help the affected individual to get timely medical treatment. However, automatic Depression Risk Analysis has not received significant focus in prior studies. This paper aims to propose an Automatic Depression Risk Analyzer based on non-verbal biomarkers; facial and emotional features, head posture, linguistic, mobile utilization, and biometrics. The analysis has shown that facial and emotional features can learn to identify depression risk better when compared with the head pose and emotional features. Moreover, the study shows that Depression Risk Analysis based on linguistic performed well with 95% accuracy for Sinhala content and 96% accuracy for contextual in English. Identifying the depression risk based on the biometrics, the sleep pattern analysis obtained 95% accuracy with the K Nearest Neighbour (KNN). Further, the mobile utilization analysis with the KNN model achieved 81% accuracy towards the Depression Risk Analysis. The accuracy of Depression Risk Analysis can be improved by extending analytic models to work as a single model. Furthermore, The models have been integrated with a mobile application that allows users to get a comprehensive Depression Risk Analysis based on each biomarker. These additional methods will function together to provide a more accurate on assessing depression risk.Publication Embargo Skeleton Based Periodicity Analysis of Repetitive Actions(IEEE, 2022-04-07) Wedasingha, N; Samarasinghe, P; Seneviratne, L; Puiatti, A; Papandrea, M; Dhanayaka, DThis paper investigates the problem of detecting and recognizing repetitive actions performed by a human. Repetitive action analysis play a major role in detecting many behavioral disorders. In this work, we present a robust framework for detecting and recognizing repetitive actions performed by a human subject based on periodic and aperiodic action analysis. Our framework uses focal joints in the human skeleton for the analysis of repetitive actions which are substantiated by the principles of human anatomy and physiology. Using Non-deterministic Finite Automata (NFA) techniques, in this paper, we introduce a novel model to transform repetitive action count to differentiate the periodicity in human action. Experimental results on a dataset consisting of 371 video clips show that our algorithm outperforms the state-of-art (RepNet) [1] in simultaneous multiple repetitive action counts. Further, while the proposed model and RepNet give comparable results in counting periodic repetitive actions, our model performance surpass RepNet significantly on analysing non-periodic repetitive behavior.