UoM Conferences

Permanent URI for this communityhttp://192.248.9.226/handle/123/8847

Browse

Browsing UoM Conferences by Faculty "IT"

Filter results by typing the first few letters
Now showing 1 - 20 of 247
  • Thumbnail Image
    item: Conference-Full-text
    2nd International Conference on Information Technology Research 2017 (Pre Text)
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Sudantha, BH
  • Thumbnail Image
    item: Conference-Full-text
    3rd International Conference on Information Technology Research 2018 ( Pre Text)
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2018) Wijesiriwardana, CP
  • Thumbnail Image
    item: Conference-Full-text
    4onse – 4 times open and non-conventional technology for sensing the environment: an integrated low-cost environmental monitoring system (ems) for developing countries
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Ratnayake, GR; Mahanama, PKS; Warusavitharana, EJ; Weerasinghe, SN; Warnakulasooriya, KMHK; Sudantha, BH; Jayasuriya, YP; Sudantha, BH
    4 times Open & Non-conventional technologies for Sensing the Environment (4ONSE) is an ongoing joint research project between University of Moratuwa, Sri Lanka and University of Applied Sciences and Arts of Southern Switzerland. This project was initiated in a time where the necessity of a low-cost, non-conventional, and precise hydrometeorological monitoring system has been of great demand due to the increased number of weather-related environmental hazards and disasters in Sri Lanka. This work comprises an integrated approach to setting-up an experimental nonconventional Environment Monitoring System (EMS) based on open hardware, open software, open standards and open data which could measure the rainfall, wind speed, wind direction, relative humidity, air temperature, barometric pressure, soil moisture, light intensity, and the water level. With comparison to other available weather stations, this research argues the cost effectiveness of the 4ONSE system, in terms of its technology, hardware and software. Such a fully accessible, royalty-free and low cost system could provide developing countries with accessible technology for the so called ‘Internet of Things’ economy. Even though the use of technologically sound and low system is necessary to monitor the environmental data, less is known about use, validity, accuracy and cost effectiveness of such systems. This research explores the accuracy of 4ONSE’s measurements against those of a reference station and further explores and proves its effectiveness and suitability in terms of environmental monitoring in the context of developing countries.
  • No Thumbnail Available
    item: Conference-Full-text
    4onse as a complementary to conventional weather observation network
    (2019-12) Sudantha, BH; Warusavitharana, EJ; Ratnayake, GR; Mahanama, PKS; Warusavitharana, RJ; Tasheema, RP; Cannata, M; Strigaro, D; Sudantha, BH
    Over the centuries, sensing the weather has been important to mankind for decision making. Weather observations are important to better understand the climate variability and its consequences which ranges over different temporal and spatial scales such as localized rainfall and thunderstorms to large scale storms and droughts. Analysis of climate induced phenomenon is data intensive and the data collected from very sparse network of professional weather stations have become incapable to forecast magnitude of the climate induced events. In this research, we present a 4ONSE network as a complementary to professional, state-owned weather station network. This open network was built on 4 open pillars – open hardware, open software, open standards and open data. Credibility of the network was assessed by analyzing the reliability and accuracy of data, cost incurred in building the station and conformity of measured parameters with WMO standards. Even though the 4ONSE station is not a high tech, professional weather station, these mini stations can be used to filling the gaps left by professional weather stations. Thus, they can be used to improve the coverage of the existing weather network of the country and to obtain the observations at near real time for producing accurate weather and disaster forecasts.
  • Thumbnail Image
    item: Conference-Full-text
    8th International Conference in Information Technology Research 2023 (Per Text)
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
  • Thumbnail Image
    item: Conference-Full-text
    Accelerated adversarial attack generation and enhanced decision insight
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Kumarasiri, NKYS; Premaratne, SC; Wijesuriya, WMRM; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    Adversarial Attack is a rapidly growing field that studies how intentionally crafted inputs can fool machine learning models. This can have severe implications for the security of machine learning systems, as it can allow attackers to bypass security measures and cause the system to malfunction. Finding solutions for these attacks involves creating specific attack scenarios using a particular dataset and training a model based on that dataset. Adversarial attacks on a trained model can significantly reduce accuracy by manipulating the decision boundary, causing instances initially classified correctly to be misclassified. This alteration results in a notable decline in the model's ability to classify instances after an attack accurately. The above process helps us develop strategies to defend against these attacks. However, a significant challenge arises because generating these attack scenarios for a specific dataset is time-consuming. Moreover, the disparity between the model's prediction outcomes before and after the attack tends to lack clear interpretability. In both above limitations, the common limiting factor is time. The time it takes to devise a solution is crucial because the longer it takes, the more opportunity an attacker has to cause harm in real-world situations. In this paper, we propose two approaches to address the above gaps: minimizing the time required for attack generation using data augmentation and understanding the effects of an attack on the model's decision-making process by generating more interpretable descriptions. We show that description can be used to gain insights into how an attack affects the model's decision-making process by identifying the most critical features for the model's prediction before and after the attack. Our work can potentially improve the security of machine learning systems by making it more difficult for attackers to generate effective attacks.
  • Thumbnail Image
    item: Conference-Full-text
    Acoustic signature analysis for distinguishing human vs. synthetic voices in vishing attacks
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Gamage, P; Dissanayake, D; Kumarasinghe, N; Ganegoda, GU; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    Cybercrimes targeting mobile devices are on the rise, with vishing and smishing attacks being particularly prevalent. These attacks exploit social engineering techniques to manipulate individuals into divulging personal information or engaging in unintended actions. To counter this evolving threat landscape, this research proposes a pioneering methodology rooted in voice feature analysis. By distinguishing between human and robotic voices, this approach aims to discern legitimate calls from potential scams, thereby mitigating the associated financial losses and reputational damage. The research delves into the intricacies of voice feature analysis, leveraging natural language processing (NLP) and machine learning (ML) techniques to extract and analyze audio attributes such as pitch, volume, and temporal patterns. The ultimate objective is to create a binary classification model that accurately differentiates between human voice calls and robocalls, incorporating a comprehensive dataset comprising actual call recordings and synthesized scenarios. This research advances beyond conventional practices by championing a holistic analysis of both human and robocalls, contrary to the prevalent assumption of robocalls exclusively constituting scams. The application of various audio features, coupled with nuanced weightage allocation, enhances the model’s discernment capabilities. The resultant binary classifier is an exemplar of the innovative fusion of technology and human expertise. In conclusion, this research introduces a novel dimension to the combat against vishing and smishing attacks, with a robust voice feature analysis methodology capable of accurately identifying human and robotic voices. By effectively distinguishing legitimate calls from potential threats, this approach presents a promising avenue for safeguarding individuals and organizations against the far-reaching consequences of cybercrimes. The comprehensive analysis, validation, and insights presented in this paper contribute significantly to the field of cybersecurity and voicebased communication analysis.
  • Thumbnail Image
    item:
    An ad-hoc network based on low cost wi-fi device for iot device communication
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Elvitigala, CS; Sudantha, BH; Sudantha, BH
    This paper provides an implementation which solves some of the problems in establishing and operation of ad Hoc networks for embedded system based IoT devices. For the implementation of the system, it used the currently famous module of ESP8266 ESP07 version and the module provides all the necessary features and facilities expected to be in such framework. The system also can work independently and it provides most of the operations that is not available in the current systems. This paper also shows one of the applications tested in this research as an implementation of the system. This solves most of the communication issues faced in ad hoc networks of various embedded systems.
  • Thumbnail Image
    item: Conference-Full-text
    Adapting marytts for synthesizing sinhalese speech to communicate with children
    (Faculty of Information Technology, University of Moratuwa., 2021-12) Lakmal, MAJA; Methmini, KADG; Rupasinghe, DMHM; Hettiarachchi, DI; Piyawardana, V; Senarathna, M; Reyal, S; Pulasinghe, K; Ganegoda, GU; Mahadewa, KT
    The majority of the Sri Lankan population speak Sinhala, which is also the country's mother tongue. Sinhala is a difficult language to learn by children aged between 1–6 years when compared to other languages. Text to speech system is popular among children who have difficulties with reading, especially those who struggle with decoding. By presenting the words auditorily, the child can focus on the meaning of words instead of spending all their brainpower trying to sound out the words. In Sri Lanka, however, computer systems based on the Sinhala language especially for children are extremely rare. In this situation having a Sinhala text-to-speech technology for communicating with children is a helpful option. Intelligibility should be considered deeply in this system because this is specific for children. Recordings of a native Sinhalese speaker were used to synthesize a natural-sounding voice, rather than a robotic voice. This paper proposes an approach of implementing a Sinhalese text-to-speech system for communicating with children using unit selection and HMM -based mechanisms in the MaryTTS framework. Although a work in progress, the intermediate findings have been presented.
  • Thumbnail Image
    item: Conference-Full-text
    Adaptive Surveillance System using a Camera Network
    Yatanwala, YWTM; Senadeera, KMSK; Ruhunuwickrama, OPI; Wijepala, NGNP; Ranathunga, L
    CCTV Surveillance Systems have been used in many places to address security issues. Those systems will store a large amount of activities in every moment and most of the times data is stored in separate places without having integrity. Considering large premises, more cameras and more operators are required to handle the situation. Continuous and careful attention is essential to identify the activities of a large crowd. Moreover, there is no proper mechanism to search and retrieve important information from the videos whenever it is needed. In this paper we introduce a new approach to uniquely address those issues, using different image processing algorithms and inter process communication techniques which were implemented to acquire more reliable and accurate timely information from CCTV records in advance.
  • Thumbnail Image
    item: Conference-Full-text
    Agent Based Employee Performance Management and Decision Support System
    Ekanayake, DC; Gunasekara, RGAD; Weerasinghe, KHWMMM; Deemanthi, SHS; Sandanayake, TC; Fernando, S
    Performance appraisal is a process used by companies, in order to evaluate the employees efficiency and productivity. This process can be carried out in different ways, by employees supervisors or by different collectives related to the evaluated employee. When 360-degree performance appraisal approach is used to evaluate employees, different appraisers have different degree of knowledge about the employee. Such knowledge is usually vague, subjective and very limited. To overcome these limitations, this paper presents an agent based employee performance management and decision support system which enables an employee to represent himself in a virtual environment through an autonomous agent. This representation provides an opportunity for a person to justify the marks he/she has allocated for a given attribute to a virtual panel consists of his/her peers and managers. Furthermore, agents in this virtual environment are capable of acquiring the knowledge from other agents and update the beliefs according to feedbacks they receive and recalculate the evaluation marks.
  • Thumbnail Image
    item: Conference-Full-text
    Agent based Primary Education Supporting Platform
    Nanayakkara, MS; Kulawansa, KADT
    Primary Education is the first step of the compulsory education, it is very vital to acknowledge the importance of primary education. Any primary education system, globally, faces some key problems that cannot be addressed via direct human agency or the application of any ordinary information system. Especially, fair distribution of resources, resources utilization, and microscopic concern on small things related to tht psychology of a child are highly concerned in research on modern approaches for ensuring effective Primary education System. Child@EDU is an alias given to a research and development project which has being initiated to find solutions for these matters in primary education fundamentally targeting the children that involve in Primary Education. It proposes a knowledge system that addresses the vital and sensitive attributes of a common primary education system (known as the fundamental characteristics of a child with effective learning abilities). Child@EDU is a web based system that uses the power of multi agent technology and other components of artificial intelligence such as ontology technology and expert decision support based on international WISC®-IV Assessment Standards. .
  • Thumbnail Image
    item: Conference-Full-text
    An agile project management supporting approach for estimating story points in user stories
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Wanigasooriya Arachchi, KJ; Amalraj, CRJ; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    While significant research has been conducted on software analytics for effort estimation in traditional software projects, limited attention has been given to estimation in agile projects, particularly in estimating the effort required for completing user stories. In our study, we present a novel prediction model for estimating story points, which serves as a common unit of measure for gauging the effort involved in completing a user story or resolving an issue. To achieve this, we propose a unique combination of two powerful deep learning architectures, namely LSTM and RHN. What sets our prediction system apart is its end-to-end training capability, allowing it to learn directly from raw input data without relying on manual feature engineering. To support our research, we have curated a comprehensive dataset specifically tailored for story points-based estimation. This dataset comprises 6801 issues extracted from 6 different open-source projects. Through an empirical evaluation, we demonstrate the superiority of our approach over three common baselines. In summary, our study addresses the gap in research regarding agile project estimation by introducing a prediction model that effectively estimates story points. By leveraging the combined power of LSTM and RHN architectures.
  • Thumbnail Image
    item: Conference-Full-text
    Ai-driven user experience design: exploring innovations and challenges in delivering tailored user experiences
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Padmasiri, P; Kalutharage, P; Jayawardhane, N; Wickramarathne, J; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    In today’s digital landscape, providing user experiences is considered paramount in respective of user satisfaction and engagement. Artificial Intelligence (AI) has emerged as a transformative force in the User Experience (UX) design field, offering innovative solutions. Our research delves into key innovations and challenges enabled by AI in UX design particularly guided by Design Thinking (DT) process. The methodology involved administering a questionnaire to UX professionals in Sri Lanka using a snowball sampling method. The questionnaire, distributed through online platforms, explored participants’ familiarity with AI-driven UX design, contributions of AI in the DT process, and challenges faced, and the responses were analyzed using MS Excel and R Studio. The results demonstrate that AI technologies certainly empower UX professionals to design usercentric solutions adhering to DT process. A “Recommendation Guide” is provided, featuring a set of recommended tools for UX professionals to integrate AI technologies into the DT process.
  • Thumbnail Image
    item: Conference-Full-text
    AIEPmora an NLP Knowledge Representation and Retrieval Platform
    (Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2009-07) Maha Arachchi, AI; Attanayake, AMSSAUB; Phillips, GLL; Vithanagama, S; Nanayakkara, V; Gunasinghe, UP
    This paper discusses AIEPmora; a natural language processing system designed to maintain a conversation with a human user. The architecture is much similar to an automated chat bots with several overhauls to integrate vary ing knowledge bases. The system is designed to consume plain text so that knowledge can be added without worrying about its structure or organization. It does not require link to be present in the text and can manage various type of wh questions plus human like expressions like “hi” , “good morning”. This paper presents a high level architecture of AIEPmora and how its component integrates to create a human like chat bot.
  • Thumbnail Image
    item: Conference-Full-text
    Alexza: a mobile application for dyslexics utilizing artificial intelligence and machine learning concepts
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2018) Rajapakse, S; Polwattage, D; Guruge, U; Jayathilaka, I; Edirisinghe, T; Thelijjagoda, S; Wijesiriwardana, CP
    Dyslexia can be explained as a neurological learning disability which causes difficulties in reading, word decoding, comprehension, short-term memory, writing, spelling, and speaking. People who are diagnosed with dyslexia tend to show signs of low self-esteem and anxiety since they can't interact with the society in a way that their peers do. Many applications available in this domain help them by correcting their issues by playing games and reading some hard-coded texts or pdf books. This correcting process takes time and dyslexics become helpless when coping with their day-to-day activities. This paper describes results of an evaluation of a prototype mobile application which helps the dyslexic users to deal with their reading difficulties in real life successfully, while they are receiving proper treatments. This prototype can identify the texts around them and read it loudly so that user can understand and will be allowed to customize the chunking, scrolling and highlighting of words according to their disability levels. By integrating dictionary support with the phonic and morphological structure of the word, the user will be able to comprehend difficult and complex words easily. In addition, the study also explores the use of a machine learning approach to improve the effectiveness of the learning dyslexic complex words.
  • Thumbnail Image
    item: Conference-Full-text
    Alzheimer’s disease detection using blood gene expression data
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Yasodya, GDS; Ganegoda, GU; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    Alzheimer's disease is the most prevalent form of dementia with no established cure. Extensive research aims to comprehend its underlying mechanisms. Genetic insights are sought through gene expression data analysis, leveraging computational and statistical techniques to identify risk-associated genes. This study focuses on accurate AD detection using blood gene expression data. Four feature classification methods—TFrelated genes, Hub genes, CFG, and VAE are employed to identify crucial AD-related genes. Five classification approaches—RF, SVM, LR, L1-LR, and DNN—are used, evaluated by AUC. The VAE + LR model yields the highest AUC (0.76). The study identifies 100 influential AD-associated genes where data is sourced from Alzheimer's Disease Neuroimaging Initiative (ADNI). Findings hold promise for advancing early diagnosis and treatment, enhancing AD patients' quality of life.
  • Thumbnail Image
    item: Conference-Full-text
    Alzheimer’s disease prediction using clinical data approach
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2023-12-07) Perera, LRD; Ganegoda, GU; Piyatilake, ITS; Thalagala, PD; Ganegoda, GU; Thanuja, ALARR; Dharmarathna, P
    Alzheimer's Disease (AD) is a progressive neurodegenerative condition that profoundly affects cognition and memory. Due to the absence of curative treatments, early detection and prediction are crucial for effective intervention. This study employs machine learning and clinical data from Alzheimer's Disease Neuroimaging Initiative (ADNI) to predict AD onset. Data preprocessing ensures quality through variable selection and feature extraction. Diverse machine learning algorithms, including Naive Bayes, logistic regression, SVM-Linear, random forest, Gradient Boosting, and Decision Trees, are evaluated for prediction accuracy. The model resulted with random forest classifier together with filter method yields the highest AUC. The study highlights important analysis using Random Forest and Decision Trees, revealing significant variables including cognitive tests, clinical scales, demographics, brain-related metrics, and key biomarkers. By enhancing predictive capabilities, this research contributes to advancing Alzheimer's disease diagnosis and intervention strategies.
  • Thumbnail Image
    item: Conference-Abstract
    Analysis and prediction of severity of united states countrywide car accidents based on machine learning techniques
    (Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa., 2022-12) Boyagoda, LS; Nawarathna, LS; Sumathipala, KASN; Ganegoda, GU; Piyathilake, ITS; Manawadu, IN
    The number of vehicles and road transportation increases rapidly daily. Hence the frequency of road accidents and crashes also gradually increase with it. Analyzing traffic accidents is one of the essential concerns in the world. Due to the considerable number of casualties and fatalities caused by those accidents, taking necessary actions to reduce road accidents is a vital public safety concern and challenge worldwide. Various statistical methods and techniques are used to address this issue. Hence, those statistical implementations are used for multiple applications, such as extracting cause and effect to predict real-time accidents. In this study, a United States (US) Countrywide car accidents data set consisting of about 1.5 million accident records with other relevant 45 measurements related to the US Countrywide Traffic Accidents were used. This work aims to develop classification models that predict the likelihood of an accident is severe. In addition, this study also consists of descriptive analysis to recognize the key features affecting the accident severity. Supervised machine learning methods such as Decision tree, K-nearest neighbour, and Random forest were used to create classification models. The predictive model results show that the Random Forest model performs with an accuracy of 83.95% for the train set and 80.69% for the test set, proving that the Random forest model performs better in accurately detecting the most relevant factors describing a road accident severity.
  • No Thumbnail Available
    item: Conference-Full-text
    Analyzing the Healthiness of an IT Project Using Self Organizing Maps
    Thilakarathne, HHTD; Wellage, CH; Rupasinghe, JAPNS; Nimantha, KC; Karunaratne, PM; Fernando, S
    This research paper discusses a solution for a problem we have identified that IT companies face when managing their projects. Project managers often find themselves in a tough situation when deciding the current status of a project and making decisions based on the evaluation. But similar situations have happened earlier in other projects and the knowledge about the measures that were taken at those situations and their effect on the success of the project can be used to evaluate similar situations in new projects. Our approach in this regard is analyzing the past data of IT projects using different machine learning techniques to identify the major factors that have affected the success of a project, understand how strongly each factor is bound to success and then training a model with the data. Where it can be used to analyze situations that arise in new projects and identify how like the current situation is to lead the project in to a success or a failure. The machine learning technique we have likely used in this study is Self- Organizing Maps (SOM) and the system was implemented using Python language