ICAPS 2022
Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/25482
Browse
3 results
Search Results
Item Sign language generator for video platforms(Faculty of Science, University of Kelaniya Sri Lanka, 2022) Mohamed, Z. Y. J.; Munasinghe, L.Over 5% of the world population (430 million people) suffer from hearing loss and deafness. Therefore, communication with them is a challenging task. One of the popular communication methods with deaf people is sign language. It is achieved by simultaneously combining hand gestures, body language, and facial expressions. Even though it is possible to communicate in written format, deaf people still find difficulties in reading natural language texts. Therefore, formal sign languages have been introduced to fill this gap. There are different standards for sign languages. For example, the USA has American Sign Language (ASL), UK has British Sign Language (BSL), and Sri Lanka has Sri Lanka Sign Language (SSL). However, modern video platforms do not have sign language support. This research introduces and evaluates the user experience of a customizable sign language converting extension for video platforms. The proposed machine translation model translates English sentences in videos into equivalent Sri Lanka Sign Language. Moreover, the position, size, and background colour of the 3D human animator are customizable. This system was evaluated with deaf people from different demographics. The user test was conducted as a questionnaire survey. The participants were deaf or hard-of-hearing under three categories (deaf, hard-of-hearing, and severely deaf) and belonged to different age groups (0-10 years,11-20 years, 21-30 years, 31-40 years, 41-50 years, 51-60 years, and above 60). Personal health information and accessibility barriers faced by each participant was questioned in the questionnaire. The user test was conducted by providing participants with three videos with the proposed extension, where participants should complete a series of tasks according to the provided guidelines. The video platform considered for the evaluation was YouTube. The usability issues of the proposed extension were recorded. In addition, new requirements requested by the participants were also recorded. According to the results, 88% of participants identified the correct and incorrect Sinhala sign language generators based on the accuracy of Sinhala sign language, 96% of participants identified the sign language generator as user-friendly. Participants found that the most critical features of this extension were adjusting background colour according to the video and the human animator.Item Predicting the execution time complexity of a computer program using Machine Learning(Faculty of Science, University of Kelaniya Sri Lanka, 2022) De Ranasinghe, I. M. M. P.; Munasinghe, L.Performance enhancement of a computer program is an important aspect of today's world. The developers produce programs and there is a lack of accurate methods for predicting the execution time of a computer program prior to its execution in an executable environment. Predicting the execution time of a particular program before execution would be great to develop the program with the highest performance efficiency and the lowest execution latency. Theoretically, there are a lot of ways of calculating the complexity of a computer program. Mathematically it is impractical to find a universal method to compute the complexity of all types of programs. Therefore, this research introduces a Machine Learning based solution to predict an execution-time-based label for a given computer program. There are three main types of parameters in a computer program that affect the execution time, such as Static Code Features, Hypertext Transfer Protocol (HTTP) Calls, and the Hardware Performance of the execution environment. In this research, the Machine Learning (ML) model was trained for the parameters of the above types (Programs with Static Code & HTTP calls) by executing them on a fixed hardware infrastructure execution condition. We analysed the number of if conditions, methods, breaks, switches, loops, nested-loop-depth, frequencies, and the behaviour of HTTP calls, kind of features of a computer program in order to generate an accurate execution time complexity prediction label of a computer program. The label is forecasted based on five pre-defined complexity classes by considering the minimum and the maximum overall execution time of the considered dataset, such as Execution Time is Higher, Execution Time is High, Execution Time is Medium, Execution Time is Low, Execution Time is Lower. Further, in the collected dataset, the most prominent features which affect the complexity among the features that we considered are the number of HTTP calls and nested loop depth, followed by loops. Accuracy Score, Precision, Recall, and F1 Score values of the ML model were generated for the traditional classification algorithms such as Decision Tree Classifier, K Nearest Neighbour Classifier, Random Forest Classifier, Naive Bayes Classifier, Support Vector Classifier, and MLP Classifiers in order to verify the effectiveness of the model. The best accuracy score was achieved with an overall 88% by using the approach of Random Forest. The findings of this research can be optimized for implementing an Integrated Development Environment (IDE) plugin or a developer tool that can forecast the exact execution time of a given computer program live by integrating the specifications of the execution device. It will help developers to optimize a particular computer program and develop it for a minimum execution latency and enhance the performance of the program.Item A way forward for Sustainable Human-Computer Interaction(Faculty of Science, University of Kelaniya Sri Lanka, 2022) Arambepola, S. N. M. N. D. K.; Munasinghe, L.Sustainability has become a buzzword in the modern world. In fact, the United Nations (UN) has proposed seventeen Sustainable Development Goals (SDG) to achieve by 2030. SDG can be achieved through different approaches. As modern society is moving forward with a digital world through novel technologies, one promising way of achieving SDG is Sustainable Human-Computer Interaction (SHCI). SHCI is a relatively new research area that is trying to address sustainability issues mainly through sustainable social transformation. Thus, we conducted this research with two main objectives. 1) To analyse how Human-Computer Interaction (HCI) researchers have contributed to this evolving research area 2) To find further opportunities to address sustainability issues using HCI designs. Then finally, we suggested novel approaches to address sustainable energy goals through technological device usage. At the initial stage, research articles were collected through mainly five (05) databases: Google Scholar, IEEE Xplore, Scopus, ACM Digital Library, and ResearchGate. There, keywords such as "Sustainable HCI", "Sustainable Human-Computer-Interaction", "Sustainable interaction design" and "SHCI" were used for collecting research papers through keyword-based filtering. In addition, other research papers were collected through the references of the selected most cited papers. We considered research papers published in top-ranked HCI research conferences and journals for this review. The total collected number of 56 research articles was filtered through the inclusion and exclusion criteria of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method. Out of 30 papers, most of the articles were published in 2014 and 2015. The bibliographic results show a decrease in SHCI research publications after 2015. According to the findings, SHCI can be achieved mainly through Sustainable Interaction Design (SID). There are two main categorizations of SID. 1) Sustainability in design 2) Sustainability through design. "Sustainability in design" aims to find solutions to social, economic, and environmental issues in our own design, implementation, and evaluation practices. For example, "Affordable and Clean Energy" can be achieved by reducing the energy consumption of the computerized machines used in our daily routines. For instance, introducing lightweight mobile apps can be a successful move for reducing data usage and energy consumption in daily-using mobile apps as a suggestion aligned with the identified opportunities for future development. "Sustainability Through Design" means designing interactive products that promote the sustainable behaviour of its users. For instance, we can consider designing mobile applications as a tool for awareness and encouraging behavioural changes favouring sustainability. One of the key findings of this study is that “sustainable energy” is the specific area that most researchers have addressed through SHCI. The results of this study are beneficial for researchers in different disciplines, such as HCI, sustainability, digital technology, and interaction designs, to contribute to sustainability by reducing energy consumption.