Computing and Technology

Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/15605

Browse

Now showing 1 - 20 of 263

3D Visualization of Human EEG Signals
(4th International Conference on Advances in Computing and Technology (ICACT ‒ 2019), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2019) Pradeep, H.B.A.C.; Meegama, R.G.N.; Kalinga, S.
The brain is the most important and the most complex human organ that is responsible for all the functions that we do in our routine life. Moreover, the brain consists of millions of neurons that utilize electro-chemical signals to transmit information to other parts of the body. Whenever a neuron triggers an electrical impulse to another neuron, it generates electricity, referred to as an EEG wave that can be measured by a sensitive device. Using such brain patterns, it is possible to identify normal day-to-day human behavior. The brain commences its work before birth and works continuously until death during which brain waves are constantly generated according to what we perceive from the environment. By analyzing brain wave patterns, we can predict and identify valuable information on human or animal health. For examples we can monitor coma and brain death in human or animals, various effects of drugs on sleep disorder, day-to-day life human behavior, post-traumatic stress disorders (PTSD), etc. In the experiments conducted, we took the potential differences between the respective channels to identify the variations in brain wave data among the individuals. We used linear interpolation to generate 3D views of the potential data between the locations where the electrodes were placed. A color code is then applied to indicate the range of potential values projected on the human skull. High frequency components were observed near the right parietal and right occipital lobes of the brain. Significant variations were not observed near the frontal or the left region of the brain for a specific activity. The proposed project will introduce a technique to visualize human brain waves in 3D over the skull that will enable us to interpret how these brain waves are associated with various regions on the human brain.
5G Wireless Communication over Heterogeneous Networks: Solutions for Hardware and Software Fallacies.
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2017) Abeysinghe, A.
Proliferating use of mobile communications have urged the need to develop networks able to cater to higher bandwidth, speeds and support a plethora of upcoming technologies. Introduction of 5G networks in a heterogeneous network architecture has been chosen as a viable solution to persistent issues in current implementations. However, these network designs lack several fundamental software and hardware pitfalls associated with problems in designing: associated cell optimizations, schemes on simultaneous base station associations and cooperation between tiers in the architecture. Therefore, this research will focus in fine tuning these software and hardware fallacies for the successful implementation of proposed 5G networks. A main software drawback in current networks is persistence of lazy caching themes. As shown in figure 1, currently user requests are often matched to arbitrary locations without the use of preenabled caching mechanisms. To overcome this issue proactive caching where base stations (BS) identify external clients possessing cached information and dynamic Device-to-Device (D2D) connection creation could be implemented. As shown in figure 2, significant improvements in successful requests could be achieved both under high load and under low load as users are efficiently matched to potential targets. A main drawback in mobile network hardware design is high energy consumption proportional to increasing user requests. To overcome this issue cell zooming could be introduced to 5G implementations. As shown in figure 3, the central cell could use an algorithmic approach to identify the network request density around it and zoom its range in or out to efficiently serve while neighboring cells could be switched off for a predetermined interval and vice versa. T-tests carried under this paradigm proved that significant cost savings in efficient use of energy in these cells could be achieved under this solution
Accessing a Moodle based Learning Management System and Exam Performance by Medical Students: A Retrospective Analysis.
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2017) Hettiarachchi, W.G.; Hettige, S.; Ediriweera, E.P.D.S.; Chandrathilake, M.N.; de Silva, N.R.
Considering the high computer literacy of students and the need for being students centred, the MBBS programme of University of Kelaniya introduced a Moodle-based learning management system (LMS) as a supplementary component to its blended delivery approach of the curriculum. Accordingly, LMS is a parallel component to the curriculum delivered face-to-face. Each module of learning in the curriculum is represented in the LMS by giving lecture notes, PowerPoint presentations, web links and assignments. The broad aim of this study is to determine the relationship between the extent of interactively of learners with LMS and their exam performance. First-year medical students (172 from 2016 intake and 166 from 2017 intake) at University of Kelaniya were considered for the analysis. Student’s access to LMS during the first two modules of the MBBS curriculum and the results of the first continuous assessment were compared. Total LMS access for each student during the two modules were calculated by counting the number of views in the course log. The particular course logs of LMS were downloaded and filtered out the details pertaining to students in the above two modules in both batches. Total access during the two modules were calculated for individual student and used for the analysis. Continuous assessment results ranged from grades A to F and we assigned sequential numerical marks in the descending order from 6 to 1 to denote grade A to F. Total LMS access with respect to assessment grades were visualized using boxplots and median with interquartile ranges were calculated. Association between LMS access and assessment grades were investigated. Statistical analysis was done in R. Median (interquartile range) of LMS access of the students were 43.0 (12.25 – 72.0) times. The number of results grades for the students as follows; A – 3, B – 41, C – 117, D – 122, E – 51 and F – 4 and the respective number of median (interquartile range) access to LMS for the above grades were 110.0 (102.0 – 113.0), 51.0 (21.0 – 76.0), 49.0 (16.0 – 76.0), 39.0 (11.0 – 64.75), 29.0 (6.0 – 59.5) and 6.5 (3.0 – 16.0). There was significant correlation between LMS access and results grades (rho = 0.2, P < 0.01). Students with grade A showed significantly higher LMS access compared to the rest of groups. There was no difference in LMS access between students with grades B and C, C and D, D and E, D and F or E and F. However, grade B showed significantly higher LMS access compared to grades D, E and F; and grade C showed significantly higher LMS access compared to grades E and F. The findings demonstrate that students’ interaction with LMS were significantly associated with the performance in the examination. The learning management system has a positive impact on student performance.
Adaptive Academic Guidance System via Student Activity Performance Analysis and Profiling
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Balasooriya, Saumya K.; Abeysinghe, D.V.D.S.; Sathsara, D.M.S.
In the ever-evolving landscape of education driven by rapid technological advancements, e-learning has emerged as a transformative force. However, it faces challenges, notably the difficulty of personalizing education in a digital environment. This paper introduces an innovative adaptive academic guidance system called "StudyMate." The system analyzes student activity, performance, and profiles to enhance the e-learning experience. The objectives encompass extensive research, surveys for primary and secondary data collection, algorithm development for student analysis, foundational database creation, source code development, and online system hosting. StudyMate leverages learning management system (LMS) functionalities to offer tailored learning experiences and demonstrates its efficacy in the digital realm. The literature review explores adaptive e-learning systems, highlighting the need for personalized education and referencing related research projects. The methodology outlines planning, design, implementation, testing, and critical evaluation phases, including sample code snippets and test cases. The findings confirm the successful implementation of adaptive concepts in StudyMate, addressing the academic question effectively. The limitations lie in the system's scope, primarily focusing on student views, leaving room for future enhancements such as lecturer and admin functionalities. The paper concludes with the potential for expanding StudyMate's features and improving its usability, making it a valuable solution for personalized e-learning.
Adopting SDLC in Actual Software Development Environment: A Sri Lankan IT Industry Experience
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2016) Munasinghe, B.; Perera, P.L.M.
Systems Development Life Cycle (SDLC) and its variant forms have been around in systems development arena as a steadfast and reliable development approach since 1960s and are still widely used in software development process in information technology (IT) industry. IT industry has been adapting SDLC models as a solution to minimize issues aroused in a large number of failure projects. Though SDLC models powerfully model that software projects undergo some common phases during its development process, most software development organizations in the Sri Lankan IT industry today only use SDLC models as a token to show off their process quality but fail to adhere to them in real-time, thus failing to grasp the real benefits of SDLC approach. This study sought to find the causes behind the practical difficulties of a medium Sri Lankan IT Company to find a fitting SDLC model in their development process and the limitation to adhere to such model-based approach. The research instruments were questionnaires that were administered to a sample frame consisting of employees, experts and the managers. Interview schedules were also used. The findings of the study indicate that the main cause behind difficulty in finding a fitting model as extreme customer involvement, which causes regular requirements changes. Company concentrates more on winning the customer than following proper requirements definition approaches suggested by SDLC to define clear-cut requirement specifications, which result in inefficient customer interference throughout the development process demanding inconvenient changes to be addressed down the line. Most of the software projects with version releases involve maintenance and bugs fixing while developing the next release. As customers become system users, their demands become more insisting, making maintenance process tedious and development of next phases more challenging. Lack of proper customer management approaches is strongly visible in all areas of development and customer demands cause poor resource management and increased stress on work force. Study findings suggests that the main reasons behind the limitations in companies to follow a proper SDLC approach are: limitations in budget and human resource, unrealistic deadlines, frequent requirements changes, vague project scope definitions, nature of the project (whether offshore or local), need of using new technologies yet lack of timely availability of knowledge expertise, project team diversity and company’s own business model interfering the project dynamics. Future work will focus on further investigations incorporating number of Sri Lankan IT companies covering all ranges of business magnitudes.
Adoption and reflection of new educational model in Higher Educational sectors at present COVID-19 pandemic.
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2021) Nadesana, Nixsala; Wijayarathna, Gamini
The education in the world was affected by the COVID-19 pandemic, especially higher educational institute process functionality was interrupted by stopping the physical class rooms. As per the COVID-19 effect the large number of higher educational institutes move to the online education like universities in Sri Lanka [1]. Higher educational institutes have taken their course orientation, lectures, registration, examination and assignment submissions or thesis submissions through online platform. The students and lecturers having issues to get the physical materials like reference books through online. Those problems are most identified in science course providing departments. Because the students in science stream have to prepare for their practical work. But they have a struggle to go to their institute and do the practical activities in pandemic situation. Therefore, the practical integrated online education accompanied LMS will help the university students. This paper analyses numerous approaches taken by higher educational sectors to deliver teaching, laboratory practices and semester examinations in consideration of the COVID-19 pandemic, while also considering the potential effects on the student learning experience and lecturers convenient. The mission of Sri Lankan higher educational sectors during the pandemic is offering accessible quality online education delivery, research and innovation in order to produce young leaders in the relevant fields to suit the needs by conducting collaborative learning and examination process without postponing the educational process of the students by charging the current pandemic impact by COVID-19.
Adult Learners’ Perceptions of a Blog-based Assessment in an English as a Second Language Course
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2022) Embogama, R. M. S. N.
This study was conducted in order to gather adult learners’ perceptions on the use of blogs for assessing their English writing skills in terms of the perceived benefits, drawbacks, and technical constraints. Being a case study, the research involved a group of adult ESL learners following an English proficiency course at the undergraduate level in a state university in Sri Lanka. It was conducted by using a survey-type questionnaire shared with the purposive sample of year one arts undergraduates who were in the second semester of study. Descriptive statics were used for data tabulation and percentages were generated to decipher the sample’s reaction to a blog-based assessment given to them during the first semester of study. The findings from the data analysis indicate that these students perceived blogs as a valid, acceptable, and beneficial form of assessment that can also improve and motivate them to write in the second language. However, they also admitted that challenges remain when authoring blogs, such as poor bandwidth and lack of connectivity, difficulty in understanding instructions on creating blog accounts, having their content plagiarized, and technical constraints. From the findings, there is a suggestion to first promote the use of blog entries to assess students’ writing skills as a continued practice and second to formulate strategies to counteract the challenges. To sum up, the main findings reveal that in spite of some difficulties, these ESL learners had a highly positive attitude towards the use of blog-based assessments for testing their English writing skills.
Advanced Real Time Traffic Controller System Based on Fuzzy Logic and Motion Detection Sensors
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2016) Divaagar, P.
Traffic congestion in intersections are becoming a major concern in metropolitan cities. The customary traffic light signals (TLS) are being operated in predetermined traffic light patterns based on the traffic weights calculated through previous statistics on particular junctions. This method becomes inefficient for day to day growing automobile usage in a country like Sri Lanka. Another reason for inefficiency is determining a pattern of traffic flow through statistical analysis is less reliable. A sophisticated solution for this issue is recommended in this paper by controlling the TLS respect to real time traffic flows using motion detection sensors and fuzzy logic technology. The objective is to maximize the traffic flow rate and reduce waiting on junctions. The motion detection sensors are to count the flow rate on the path toward the junction from reasonable distance. Fuzzy logic is the intelligence in the system which acts like a human traffic operator. The Matlab fuzzy logic toolbox is used to design the fuzzy logic. A model of road junction installed with the advanced real time traffic controller system is animated to display the results. The traffic light will act on the decisions made by fuzzy logic system according to the instantaneous traffic load in the roads approaching the junction. The sensors are installed twenty five meters before the intersection in all the paths approaching the junction and this helps the fuzzy logic system to efficiently decide the next signal change time and foresee incoming vehicles to make decision in advance and reduce the vehicle waiting latency. The sample traffic flows applied in a simulation and the response of traffic light signals are observed and these scenarios are compared with a customary traffic light controller system. This model is more efficient than the current traffic light controller system available in Sri Lanka.
Advancements and Challenges in Real-Time Electronic Vision Technologies for Canned Fish Quality Inspection: A Comprehensive Review
(European Modern Studies Journal, 2024-09) Mahatheesan, A. J.; Sharmilan, T.
The global demand for high-quality canned fish products has driven the adoption of advanced inspection technologies to ensure consistency, safety, and compliance with industry standards. This paper provides a comprehensive review of real-time electronic vision technologies employed in the inspection of canned fish quality. It traces the evolution of the canned fish industry from manual inspection methods to sophisticated automated systems, emphasizing the role of technologies such as hyperspectral imaging, machine learning algorithms, and electronic vision systems. The effectiveness of these technologies in detecting defects, assessing quality parameters, and maintaining product integrity is critically analyzed. Despite their benefits, challenges such as high costs, the need for specialized skills, and integration complexities with existing production processes are significant barriers. This review addresses these challenges and proposes solutions, including cost-reduction strategies, workforce training, and the development of adaptable systems. The paper concludes by outlining future research directions, particularly in validating these technologies in real-world scenarios and enhancing their accessibility to the industry. The findings offer valuable insights for researchers and industry stakeholders aiming to advance the quality control of canned fish products through innovative technological solutions.
Advancements and Challenges in Real-Time Electronic Vision Technologies for Canned Fish Quality Inspection: A Comprehensive Review
(2024) Sharmilan, Tharaga; Mahatheesan, Anis Jeluxsha
The global demand for high-quality canned fish products has driven the adoption of advanced inspection technologies to ensure consistency, safety, and compliance with industry standards. This paper provides a comprehensive review of real-time electronic vision technologies employed in the inspection of canned fish quality. It traces the evolution of the canned fish industry from manual inspection methods to sophisticated automated systems, emphasizing the role of technologies such as hyperspectral imaging, machine learning algorithms, and electronic vision systems. The effectiveness of these technologies in detecting defects, assessing quality parameters, and maintaining product integrity is critically analyzed. Despite their benefits, challenges such as high costs, the need for specialized skills, and integration complexities with existing production processes are significant barriers. This review addresses these challenges and proposes solutions, including cost-reduction strategies, workforce training, and the development of adaptable systems. The paper concludes by outlining future research directions, particularly in validating these technologies in real-world scenarios and enhancing their accessibility to the industry. The findings offer valuable insights for researchers and industry stakeholders aiming to advance the quality control of canned fish products through innovative technological solutions.
Advancements in Environmental Technologies for Sustainable Urban Regeneration: A Comparative Assessment
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Edirisinghe, Ruwan Danuka
The present study aims to appraise advancements in environmental technologies applicable to urban regeneration, with a special focus on urban brownfield redevelopment. The rapid literature review technique was employed as the research strategy, in the mixed method research design. Technological solutions proposed in the selected articles were comparatively assessed their practicality in an urban setting, in terms of cost, efficacy, physical space required and potential harm to the neighboring environment, by using a five-point scale scoring system. In this study, nanoremediation, thermal remediation methods (i.e. electrical resistance heating, thermal conduction heating and steam enhanced extraction), non-thermal physical remediation methods (electrokinetic remediation, non-thermal plasma technologies, air sparging, soil washing and replacement and passive treatment technologies such as permeable reactive barriers), chemical oxidation (advanced chemical oxidation and Fenton process), and naturebased solutions or bioremediation or gentle remediation technologies (biodegradation processes methods such as bioaugmentation, bioventing, bioprecipitation, biostimulation, landfarming, and phytoremediation methods such as phytostabilization, phytovolatilization and phytoextraction or phytomining and monitored natural attenuation) are presented. Each environmental restoration strategies provided has its own set of limitations, application possibilities and future development potential, as evidenced by this study. Nanoremediation, bioremediation and radio frequency heating in the current state of the art are found to be feasible for an urban area. Property developers and urban authorities could consider the application potential of these technologies in urban brownfield redevelopment in urban regeneration. An integrated approach for addressing the limitations of these technologies may be worth considering in research and developments in the urban sector.
Age and Gender Related Variations in Human EEG Signals
(3rd International Conference on Advances in Computing and Technology (ICACT ‒ 2018), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2018) Pradeep, H.B.A.C.; Meegama, R.G.N.
There is a significant amount of research focused on discovering the functional behavior inside the human brain and methods to collect brain waves with respect to age. However, due to the lack of research using data-mining and pattern extraction methodologies on such data streams, we may be losing important features from human brain wave pattern data. The proposed research is aimed at collecting different kinds of brain wave patterns from different age categories of human beings and analyzing the correlation between the wave patterns of individuals. All the EEG data were taken from publically available and trusted data sources. The data from 22 subjects, five males and 17 females, within the age range from 3 to 22 years and were recorded with 256Hz and 16-bit resolution. We used FP1 and F7 channels as our main data sources for comparing and classification purposes. In the first phase, we applied a filtering process to clean the EEG data set of young male and female subjects to extract the hidden patterns. As EEG signals are acquired as a continuous stream, we use the sliding dot product or sliding inner product of two wave forms while searching for a long signal for shorter, known feature which is referred to as cross correlation. A correlation function is a function that gives the statistical correlation between random variables. In our research, the correlation between two signal forms (data sets) was used to measure the similarity between two wave forms. Subsequently, the cross correlation between all data pairs was calculated to find hidden relationships between each data group. In the sampling process, We ignored the first 256 data samples which was captured during 1s - 2s time period to compensate for possible errors added to the main brain wave during head movements and early adjustments. Using cross correlation diagrams, we observed similarity of brain wave signals between 11 year male and 22 year female subjects having a peak value of 3.5597e.
Agricultural Call Centres: An Overview Of 1920 Agricultural Advisory Service Usage, Sri Lanka
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Rathnayake, Sanduni; Kamiss, T.A.; Dissanayeke, U.I.; Alahakoon, P.C.B.; Rizwan, M.F.M.
The 1920 Agricultural Advisory Service (AAS) was introduced in 2006, as an ICT initiative of agricultural extension in Sri Lanka. There are no studies assessing the long-term usage of AAS by the community. Therefore, secondary research was carried out to identify the trends and patterns in 1920 AAS usage. Data were collected from internal databases, records, seasonal reports of National Agriculture Information and Communication Centre (NAICC), journal articles and web sources. Results revealed an increasing trend of receiving queries from 2006 to 2012 and, from 2016 to 2018. The trend was decreasing from 2012 to 2015. By the end of 2018, AAS has received 546,473 queries since its inception. Queries on fruits, vegetables and subject specific matters have been highest for several years. The highest number of queries was regarding ‘cultivation’ matters and queries from Colombo district was the highest in every year. There was no seasonal variation of the total number of queries received. Peak hours of AAS were from 8.00 am to 10.00 am where it served 31.6% of the total queries received per month. This study revealed several avenues for primary research. A detailed field level studies on the parameters claimed for the highest number of queries will be helpful to plan tailor-made extension programs. Mapping of queries received by AAS will provide a valuable information source for the policy makers in designing field extension programmes in Sri Lanka.
Air Pollution Monitoring System Using Arduino
(3rd International Conference on Advances in Computing and Technology (ICACT ‒ 2018), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2018) Rishan, U.M.
Arduino based Air pollution system is presented. Air pollution monitoring is old but very useful concept in day to day life. The level of air pollution has increased with times by lot of factors like the increase in population, industrialization, increased vehicle use and urbanization. Air pollution will directly affecting health of population. However the fresh air is necessary for all human being. Actually air pollution monitoring started from early using traditional way but the most sophisticated computer has been used to monitor the air quality. However in this project I am going to make an IOT based air pollution system using Arduino this will monitor the air quality accurately. The main objectives of this project to develop low-cost and ubiquitous sensor networks to collect real time data of urban environment. This air pollution system is connected with internet and we can monitor the air quality over the web server using internet. The alarm also embedded with this system that will trigger when the air quality goes down beyond a certain level, this means there are sufficient amount of harmful gases are present in the air like CO2, alcohol, and NH3.It will display the air quality in PPM on the LCD display and as well as on webpage so that we can monitor it very easily. In this IOT project, you can monitor the pollution level from anywhere using your computer or mobile devices.
Altered Brain Wiring in Alzheimer’s: A Structural Network Analysis using Diffusion MR Imaging
(3rd International Conference on Advances in Computing and Technology (ICACT ‒ 2018), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2018) Mahadevan, J.; Ratnarajah, N.; Ranaweera, R.D.
Alzheimer’s disease is a chronic neurodegenerative disorder and the most common form of dementia. It is characterized by cortical atrophy and disrupted anatomical connectivity as white matter fibre tracts lose axons and myelin degenerates. Biomarker tests are crucial to identify the early stages of the disease. It is currently a key priority in Alzheimer’s research to develop neuroimaging biomarkers that can accurately identify individuals in any clinical stage of the disease. Magnetic resonance imaging (MRI) can be considered the preferred neuroimaging examination for Alzheimer’s disease because it allows for accurate measurement of the 3-dimensional volume of brain structures. Diffusion Magnetic Resonance Imaging (DMRI), one of the methods, provides insights into aspects of brain anatomy that could never previously be studied in living humans. A comprehensive study of structural brain network in Alzheimer’s has been developed using diffusion MR imaging and graph theory algorithms, that can assess the white matter connections within the brain, revealing how neural pathways damaged in Alzheimer’s disease. A range of measurements of the network properties were calculated and the pattern of the community structure and the hub regions of the network were inspected. Global measures of efficiencies, clustering coefficients and characteristic path length confirms the disrupted overall brain network connectivity of Alzheimer’s. Relatively the same pattern of hub regions is preserved in Alzheimer’s, however, non-hub regions are affected, which indicates disease alters the internal pattern of the network especially the community structure. Modular analysis confirms this alteration and produces a different modular structure and increased number of modules in Alzheimer’s. Regional connectivity measures also indicated this change and the measures demonstrated the network centrality shifted from right hemisphere to left in Alzheimer’s. The knowledge gained from this study will support to find the strong imaging biomarkers of the Alzheimer’s disease.
Analysis of Emotional Speech Recognition Using Artificial Neural Network
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2016) Archana, A.F.C.; Thirukumaran, S.
This paper presents an artificial neural network based approach for analyzing the classification of emotional human speech. Speech rate and energy are the most basic features of speech signal but they still have significant differences between emotions such as angry and sad. The feature pitch is frequently used in this work and auto-correlation method is used to detect the pitch in each of the frames. The speech samples used for the simulations are taken from the dataset Emotional Prosody Speech and Transcripts in the Linguistic Data Consortium (LDC). The LDC database has a set of acted emotional speeches voiced by the males and females. The speech samples of only four emotions categories in the LDC database containing both male and female emotional speeches are used for the simulation. In the speech pre-processing phase, the samples of four basic types of emotional speeches sad, angry, happy, and neutral are used. Important features related to different emotion states are extracted to recognize speech emotions from the voice signal then those features are fed into the input end of a classifier and obtain different emotions at the output end. Analog speech signal samples are converted to digital signal to perform the pre-processing. Normalized speech signals are segmented in frames so that the speech signal can maintain its characteristics in short duration. 23 short term audio signal features of 40 samples are selected and extracted from the speech signals to analyze the human emotions. Statistical values such as mean and variance have been derived from the features. These derived data along with their related emotion target are fed to train using artificial neural network and test to make up the classifier. Neural network pattern recognition algorithm has been used to train and test the data and to perform the classification. The confusion matrix is generated to analyze the performance results. The accuracy of the neural network based approach to recognize the emotions improves by applying multiple times of training. The overall correctly classified results for two times trained network is 73.8%, whereas it is 83.8% when increasing the training times to ten. The overall system provides a reliable performance and correctly classifying more than 80% emotions after properly trained.
Analysis of future demand for Sri Lankan ICT undergraduates in ICT industry: Mapping the ACM/IEEE computing degrees with emerging technologies
(2021) Amarasooriya, P.M.D.S.; Werawatta, R.
Sri Lanka is famous for its agricultural economy, but in recent years it is slowly shifting towards a knowledge-based economy. In a knowledge-based economy, Information and Communication Technology (ICT) industry plays a critical role in increasing productivity and economic growth. This sector has generated numerous new job opportunities, led to increased export profits, and attracted international investors for investment. Present Sri Lankan ICT industry consists of over 600 companies [1]. According to reports from Sri Lanka Association for Software and Services Companies, the demand for the ICT sector has increased in recent years. The increase in demand for the ICT sector led to the creation of many ICT job opportunities as well as the opening of new ICT degree-awarding training institutes in Sri Lanka [2]. Government universities, private degree awarding institutes, government vocational and tertiary training institutes, and private diploma and certificate awarding training institutes are major categories of institutions that offer various degree programs in ICT disciplines [3]. According to SLASSCOM, there are fourteen job categories in the present-day ICT industry. Because of this reason undergraduates are unable to choose the most suitable ICT degree program according to the job demand. This research provides the solution for the above problem. The main objective of this research is to analyze the future demand for Sri Lankan ICT undergraduates in the ICT industry. This study will be of great help for undergraduates to choose the ICT discipline according to the demand of the job market. The future demand for ICT graduates in the ICT industry is examined in this research based on ACM/IEEE computing disciplines [4]. The secondary data for this research were collected from the National IT-BPM workforce survey and the university grant commission website. Finally, undergraduates can choose the best path in the ICT field by knowing the most demanding technologies in the ICT industry.
Analysis of Road Traffic Accidents Using Data Mining
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2017) Liyanaarachchi, K.L.P.P.; Charles, E.Y.A.
Accident happens unexpectedly and unintentionally, typically resulting in damage or injury or in fatalities. Data mining is the extraction of implicit, previously unknown, and potentially useful information from data collected for various purposes. The main objective of this research is to identify more accurate and useful patterns that would exists in the road traffic accident data using data mining techniques. It is believed that these patterns can be utilized to take measures to reduce the number of accidents or the severity of the accidents. As part of this research work, details of accidents occurred in Colombo district in the year 2015 were collected from the Traffic Headquarters, Colombo, Sri Lanka. A data set with 9487 accident incidents each detailed with 55 features was created from the collected data. This data consists four types of accidents, namely, Fatal (154), Grievous (877), Non-Grievous (2028) and Vehicle damage only (6428). There are a quite a few published studies on traffic accident analysis using data mining methods. In most of these studies, J48 classifier has produced higher accuracy than other methods. So far no such study has been reported on accidents occurred in Sri Lankan roads. A correlation analysis was performed on the data set and as a result 10 attributes were removed. In this study, the J48 decision tree classifier was usedin two ways. In the first one all four type of accidents were considered. The decision tree built with 70% of the data was able to achieve an average accuracy of 71.4687%. In the second analysis, three types Fatal, Grievous and nongrievous types were combined into one class and named as Injured. This approach was taken to reduce the effect of the vehicle damage only class, which is around 68% of the total data. The decision tree built with this merged classes was able to achieve an accuracy of 78.7288 % using a tenfold cross validation. The decision tree was converted into 20 rules, which can predict the type of accident based on the identified attribute values. The results were found to be helpful to identify the factors influencing traffic accidents and can be further analyzed to find more subtle reasons or situations that are causing accidents.
Analyzing the E-Learning Satisfaction Factors Among University Students’ in Software Engineering Domain
(4th International Conference on Advances in Computing and Technology (ICACT ‒ 2019), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka, 2019) Perera, L.
E-learning has become popular within science faculties in Sri Lanka involve access to computers and significant knowledge of information technology. E-Learning provides a Web-based learning platform with a representative and more flexible framework which could support learning and teaching. Elearning provides various services that are customized by the students ‘needs, knowledge, expertise, and experience. This study focused on the undergraduates‘ analyzing the eLearning as an effective tool. , this study focused on analyzing the e-learning satisfaction factors among university student’s in the software engineering domain at the University of Kelaniya, Sri Lanka. This research aimed to provide a set of factors to be well-thought-out when an E-learning activity is planned and proposed to E-learners in the university of Kelaniya, Sri Lanka. The linear regression techniques were used to test the proposed research hypotheses. The technique run with online course satisfaction as the dependent variable, perceived usability, perceived quality, perceived value and computer self-efficacy as the independent variables. This study was based on a total sample of 150 students who are following Software Engineering degrees in the university Kalaniaya Sri Lanka. Point toward the results, that the effectiveness of e-learning is related to how confident students are while using the computer and the web-based learning software. The results of the study indicate that developers need to consider selfefficacy issues while developing e-learning systems.
Android Shopping Cart Application (ASCA)
(Faculty of Computing and Technology, University of Kelaniya, Sri Lanka., 2017) Bandara, K.; Wijegunasekara, M.C.
Due to the busy lifestyle of people in today’s society it has become more convenient for them to buy all their daily shopping items in one place. Therefore, shopping grocery items in a supermarket has become a common activity in Sri Lanka too. The major problems faced by customers when shopping grocery items in a supermarket, is the effort they have to put and the time consuming tasks to be faced almost every day during shopping. One such difficulty is the need of frequently visiting the supermarket in order to buy day-to-day items. Also when buying the goods, most of the time, a walk around the shop to select the necessary products is an inevitable task. Even after buying, they need to stand in long queues at the counters to do the payments. Therefore, using the modern technology to build a suitable system to solve such problems is valuable. Mainly there are two approaches to solve this problem. First is a web shopping cart application and the other is a mobile application. Today as most of the people always carry smart phones with them, nowadays every business requires to have its own business application for mobile users. This research project has two major parts: the mobile application and the website which acts as a content management system. Using this mobile application, the customers are given the facility to buy online or to get the products delivered to their home by the delivery service provided from the shop or else they can send the order confirmation and get the ordered items by payments done at the shop. This mobile application is being developed using the Android Studio Software. The client side of the application is designed as a website, for the supermarket owners to manage the online database which stores the content for the mobile application. In order to measure the effectiveness of the implementation of this project, questionnaires were distributed to a total population of 50 people who buy their daily groceries in a supermarket and having an android smart phone. With the analysis of data, 32% of the people strongly agreed and 48% agreed that traditional shopping will be superseded with online shopping in near future and only 6% has disagreed the above idea. Half of the population agreed and 16% strongly agreed the fact that only credit card holders being able to buy products online is a major drawback in a shopping cart application. As future enhancements, the application will be developed to run on any type of mobile operating system other than just android. Currently only the bank portal and a link to connect with Paypal is designed and the payment gateway is to be developed further. The client side can also be created as a mobile application. In conclusion, the result of this research project is a user friendly mobile application which runs on Android Operating System and a Content Management System has developed as a Website to interact with the Database. The ASCA was a success in developing an online mobile shopping cart which could satisfy the current problems of customers who buy their daily grocery items in a supermarket.