2021

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2163

Browse

Now showing 1 - 20 of 44

Embargo
AI Based Monitoring System for Social Engineering
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Yapa, K.; Udara, S.W.I.; Wijayawardane, U.P.B.; Kularatne, K.N.P.; Navaratne, N.M.P.P.; Dharmaphriya, W.G.V.U
Social media is one of the most predominantly used online platforms by individuals across the world. However, very few of these social media users are educated about the adverse effects of obliviously using social media. Therefore, this research project, is to develop an advisory system for the benefit of the general public who are victimized by the adverse impacts of their ignorant and oblivious behavior on social media. The system was implemented using a decision tree model with the use of customized datasets; and for the proceeding operational implementations, Python programming language, Pandas, Natural Language Processing and TensorFlow were used. This advisory system can monitor user behaviors and generate customized awareness reports for the users based on category and level of their behaviors on social media. Furthermore, the system is also capable of generating graph reports of the use behavior fluctuations for the reference of the user. With the help of these customized awareness reports and the graph reports, the users can identify their potential vulnerabilities and improve their social media habits.
Embargo
Artificial Intelligence-based Business Strategy for Optimized Advertising
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Kannangara, L.; Harsha, S.; Isuru, T.; Wijesiriwardhane, C.; Wijendra, D.R.; Kishara, J.
Television commercials are a passive type of advertising technique that does not consider consumer demographics who are viewing the television at a specific time. As a result, the user sees irrelevant advertisements, which tends to reduce user engagement and sales conversions.As Sales ,which is the expected target of any advertisement campaign, a user-based advertising approach can be considered as a solution to mitigate the negative aspects. A user-based advertisement suggesting system for television, which is extensively utilized in every other digital media, is expected to be given as the solution. For the suggestion process, user attributes such as age, gender, peer group, and the mood identified in which the advertising is shown were taken into consideration. This will result in more relevant commercials for consumers, making television advertisements more user-friendly, resulting in greater sales conversion for the advertising agency.
Embargo
Aspect Based Sentiment Analysis for Evaluating Movies and TV series Publisher: IEEE Cite This PDF
(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Cooray, T.; Perera, G.; Chandrasena, D.; Alosius, J.; Kugathasan, A.
Aspect-based sentiment analysis (ABSA) is used in different fields for analyzing customer reviews to project an overall customer opinion on certain products. With the expansion of the internet, people are provided with an inexpensive and time-saving method to express their opinion to a larger audience, while various industries are handed with the opportunity to gather free information from it to obtain market value. The implementation of machine learning methods for the evaluation of aspects related to movies and television series has not been commenced, and it could be a new development for the industry. This study focuses on conducting an ABSA on a movie or a television series based on genre, story as well as cast and crew aspects. The data collected from social media through web scraping is processed to produce adequate results to get a broad understanding on how the popularity of the movie or the television series related to above mentioned aspects. Then, each aspect is further analyzed to gather precise information belonging to each aspect. The accuracy of the results of the proposed system has been achieved over 79%. The results proved that the solution is highly successful than the former works with high business value.
Embargo
Assisting Wheelchair: Assist W
(IEEE, 2021-12-07) Ranaweera, D; Athalage, C; Sri Virajamana, M; Kaveesha, C; De Silva, D. I; De Silva, H
Traditional wheelchairs used by disabled people are required to be controlled manually. Hence, continuous monitoring and assistance of a caretaker is a mandatory requirement. This paper introduces an autonomous assisting wheelchair - Assist W, which would facilitate disabled people to do their day-to-day activities independently in a very safe manner, thereby managing their mental and physical health. Assist W can scan the location and design a 2D map of the house using SLAM algorithm and LIDAR sensor. After generating the map, Assist W is able to move automatically according to the commands (Voice and touch) given by the user, with the help of the map data. There is an AR (Augmented Reality) chat-bot that acts as a good companion to manage the mental health of the disabled person. Assist W is also able to manage the security and physical health of the disabled person by providing a fall detection system and automatic lifting system, and sending emergency alerts to the caretakers. This system was tested using simulation.
Embargo
Consumer and Farmer Centric Subscription Based Organic Vegetable/Fruit Delivery System
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Karunarathna, T.M.N.P.; Kumari, M.M.A.; Kulasinghe, W.D.K.A.; Liyanage, T.L.P.; Kodagoda, N.; Suriyanwsa, K.; Kumari, D.
For centuries, the economy of Sri Lanka has been backed by the agricultural sector. Even though it has contributed to the development of the nation on a large scale, the economies and living standards of the farmers have not been improved much. Most of the farmers remain poor mainly due to not knowing the market demand and the low buying prices of the middleman. Meanwhile, the consumers in Sri Lanka are buying non-organic vegetables and fruits which are highly contaminated with dangerous chemicals which in turn has contributed to the rapidly increasing non-communicable disease rates in both consumers and farmers. The proposed system is an attempt to solve these problems faced by both farmers and consumers by reducing the farmers-consumer knowledge gap and providing consumers a trustworthy and personalized subscription for organic vegetables/fruits with a donation platform.
Embargo
Credit Card Fraud Prevention Using Blockchain
(IEEE, 2021-04-02) Balagolla, E. M. S. W; Fernando, W. P. C; Rathnayake, R. M. N. S; Wijesekera, M. J. M. R. P; Senarathne, A. N; Abeywardhana, K. Y
With the advancement of online payments in various products and services, the likelihood of credit card fraud has risen compared to the decades-long history of credit cards. When blockchain systems' immutability meets smart contracts, third-party removal and decentralization could be met as a high level of security. Proposed blockchain with fraud detection technology will assist to mitigate fraudulent credit card transactions due to its intermediate parties. Authors propose a solution (B-Box.com) where credit card transactions are modeled on a blockchain so that the credit card processing can be decentralized and verifiable with an accredited set of computing nodes. This solution reduces fraud due to ambiguous contracts with the use of a smart contract between the bank and the customer. Also, this project includes a scaling mechanism to blockchain because the current projects have a lack of scalability. Moreover, the solution introduces a proactive anomaly detection to detect fraudulent credit card transactions, in which the system will resist frauds before the fraudulent transaction enters the blockchain. So the proposed solution will make transparency between the banks and the end-users and at the same time prevents frauds before it happens which helps the banks to save millions in otherwise lost due to fraud.
Embargo
Cricket Shot Image Classification Using Random Forest
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Devanandan, M.; Rasaratnam, V.; Anbalagan, M.K.; Asokan, N.; Panchendrarajan, R.; Tharmaseelan, J.
Cricket is one of the top 10 most played sport across the world regardless of age and gender. However, learning cricket has been quite challenging as the majority of the cricket-playing individuals are unable to afford quality infrastructure. While this has opened up many research opportunities to provide solutions to automatically learn cricket, very little work has been done in this era. In this paper, we focus on the batting skills of cricket players. We develop a Random Forest model to classify the cricket shot images using human body keypoints extracted with MediaPipe. Experiment results show the proposed model achieves an F1-score of 87% and outperforms the existing solution in a 5% margin. Further, we propose a similarity estimation approach to compare the user’s cricket image with popular international cricket players’ cricket shot images of the same type and retrieve the most similar one. The mobile application we developed based on our solution will enable cricket-playing individuals to analyze, improve and track their batting performances without the need of having a coach.
Embargo
Cyber Forensics Tools: A Review on Mechanism and Emerging Challenges
(IEEE, 2021-05-18) Fernando, V
With the development of technology, "Data", also interpreted as "Information" has become a major role played in the field of Cyber Forensics. One of the most crucial incidents which needs data to be important is, when it is taken as evidence in cyber-crimes. These crimes can be occurring in the fields of digital media and network in many instances related to crime scenes. Crime and forensic both investigators need the help of digital forensics to investigate in order to identify, whether the victim has committed a crime or not. Therefore, it is a requirement for an investigator to use a suitable, accurate, affordable and a reliable cyber forensic tool for the forensics investigations conducted with respect to crimes. Many researchers have done experiments on different functionalities, a forensic tool should have and have come up with various tools specifically for each branch in cyber forensics. Furthermore, with time, these cyber forensic tools have been identified with drawbacks due to the invasion of crimes, especially related to the sophisticated technology expansion. Therefore, the acquiring process of forensics tools is in lack of advanced features to detect evidence. This paper describes on some timely Digital Forensics tools and discusses emerging challenges in advanced areas of Digital Forensics.
Embargo
Deep Transfer Learning Approach for Facial and Verbal Disease Detection
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Manage, D.M.; Alahakoon, A.M.I.S.; Weerathunga, K.; Weeratunga, T.; Lunugalage, D.; De Silva, H.
Millions of people have been subjected to different kind of acute diseases, some of them are eye diseases, facial skin diseases, tongue diseases and voice abnormalities. Most of eye diseases cause fully or partial blindness. Skin and tongue complications can be signs of cancers. Voice abnormalities can be cured at initial stages. Well-practiced medical practitioners have the ability of diagnose these diseases, but due to the pandemic situations and high consultation costs people do not tend to consult doctors. This research is predominantly focused on development of an application for automatic detection of eye, skin, tongue and verbal diseases using transfer learning (TL) based deep learning (DL) approach. Deep learning is a part of machine learning (ML) which has been used in most computer vision approaches. Transfer learning has been used to rebuild the existing convolutional neural network (CNN) models and used in disease detection. DenseNet121, MobileNetV2, RestNet152V2, models have been used to detect eye, skin and tongue diseases respectively and a new model has been used to detect voice abnormalities. CNN models are capable of automatically extracting features from the given images and voice data. All the trained models have been given accuracy rate of 80%-95%.
Embargo
Digital Preservation and Noise Reduction using Machine Learning
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Aravinda, K.P.; Sandeepa, K.G.H.; Sedara, V. V.; Chamodya, A.K.Y.L.; Dharmasena, T.; Abeygunawardhana, P.K.W.
This paper proposes a digital preservation solution for Sinhala audios to conserve those as documents with noise reduction. The solution has implemented multiple noise reduction techniques as a pre-processing step to remove unwanted internal and external noises. A two-step, two-way noise reduction process is applied to produce clean audios based on Deep Convolutional Neural Network (DCNN) and adaptive filter-based techniques. This approach implements two separate noise reduction models for internal and external noises. After that, the speech recognition decoder recognizes the speech and converts it to a Unicode document by acoustic, language, and pronunciation models using extracted audio features from the denoised audio. Further, noise reduction models are decoupled from the preservation solution and exposed as a sub solution for multilingualism noise reduction, supporting English and Sinhala audios.
Embargo
Dogodo: IoT Based Mobile Application to Provide Essential Health Services to Dogs
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Thilakarathne, L.V.I.S.; Salay, M.S.; Wijethilaka, M.G.R.; Fernando, T.S.C.; Sriyaratna, D.; Rupasinghe, S.
Voice of dogs can be heard by people who listen to them. The more you listen, the more you learn about the dogs. This study proposes a platform to identify and observe dogs’ behavior and their activities by using the newest technologies. The proposed system will mainly cover the relevant areas that are supposed to be covered to full fill the pet owners’ expectations by providing necessary services such as internal health, voice recognition, and emotion translations and external issues such as skin diseases, breeding patterns, and breeding outcomes. Our priority is to emphasize necessary services in the mobile application and provide fluid services with fewer interruptions. Primarily research will offer an IoT device and a mobile application that covers the dog’s internal health and external health consecutively. The study revealed current developments and
Embargo
E-Agrigo
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Kartheepan, T.; SirigajanK, B.; Subangan, K.; Mohammed Azzam, M.A.; Bandara, P.; Mahaadikara, M.M.D.J.T.H.
To feed this population, food production should be increased by at least 70%. Developing nations have a vast potential to increase the amount of food produced by doubling the current production. However, the traditional methods of farming are making agriculture unviable and inefficient. The increasing food production needs to be met by double the current level of farming. The conventional of farming is making industry uncompetitive and inefficient. This paper aims to analyze the various factors that affect the implementation of autonomous machinery in agriculture. The development of autonomous machinery for agriculture has emerged as vital step towards achieving this goal. Now a day’s farmers are planning their cultivation by finding proper weather and geographical condition on their own experience, but they are failing to cultivate profitable crop and unaware of the diseases that will affect their crops, sometimes these diseases may affect their whole crops and let the farmers to sink in zero profit. Despite these issues plays a major role, there are some other problems also have an impact like, lack of irrigation plans and question of how and where to sell their cultivated crops. By considering these major threats we have planned to propose a solution to some of the selected issues. This can be achieved by applying machine learning algorithm, Image processing and IOT systems. By using our platform farmers will get a chance to plan their yield in a profitable way by using our optimized weather and geographical data.
Embargo
E-Learn Detector: Smart Behaviour MonitoringSystem to Analyze Student Behaviours DuringOnline Educational Activities
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Bamunuge, H.K.T.; Perera, H.M.; Kumarage, S.; Savindri, P.A.P.; Kasthurirathna, D.; Kugathasan, A.
With the rise of online education more attention is being paid to the deficiencies in online learning platforms. Online Learning environments aim to deliver efficacious instructions, but rarely take providing a conventional classroom experience to the students into consideration. Efficient detection of students’ learning situations can provide information to teachers to help them identify students having trouble in real-time. This idea has been exploited several times for Intelligent Tutoring Systems, but not yet in other types of learning environments that are less structured. “E-Learn Detector is a web application solution to these existing issues in online learning which consists of unique features such as verifying the user during logging procedure and throughout an examination, detecting suspicious behaviors and presence of multiple users during online examinations and detecting low engagement levels of students during online lectures. “E-Learn Detector” is developed with the aim to provide guidance to students to improve their academic performance and behavior during classroom activities and to induce the best out of the educational activities.
Embargo
E-Learning Platform for Hearing Impaired Students
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Krishnamoorthy, N.; Raveendran, A.; Vadiveswaran, P.; Arulraj, S.R.; Manathunga, K.; Siriwardana, S.
With the Spread of global pandemic Covid-19, the traditional education was transformed to online from traditional learning drastically. Hence the use of e-Learning platforms was increased. But this idea has issues with certain communities of people around the world. The hearing-impaired people have many issues with eLearning platforms because of their deficiency in hearing sound. Therefore, through this paper authors are introducing a learning platform for hearing impaired communities to aid in learning effectively. The proposed platform uses sign language to facilitate communication among students and tutors while providing sign language learning materials, practicing opportunities and Q&A sessions. The system has a low light enhancement module to enhance the videos uploaded by the tutor, module to convert the uploaded videos to American Sign Language and it also converts the questions asked via sign language to text.
Embargo
Early Warning for Pre and Post Flood Risk Management by Using IoT and Machine Learning
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Ilukkumbure, S.P.M.K.W.; Samarasiri, V.Y.; Mohamed, M.F.; Selvaratnam, V.; Rajapaksha, U.U.S.
Flooding has been a very treacherous situation in Sri Lanka. Therefore, developing a structure to forecast risky weather conditions will be a great aid for citizens who are affected from flood d isasters. I n t his s tudy, t he a uthors explore the use of Machine Learning (ML), Deep Learning (DL), Internet of Things (IoT), and crowdsourcing to provide insights into the development of the pre and post flood r isk management system as a solution to manage and mitigate potential flood risks. Machine learning and deep learning algorithms are used to predict upcoming flooding s ituations and r ainfall occurrences by using predicted weather information and historical data set of flood a nd r ainfall. Crowdsourcing i s u sed a s a n ovel method for identifying flood t hreatening a reas. Weather i nformation is gathered from citizens and it will help to build a procedure to notify the public and authorities of imminent flood risks. The IoT device tracks the real-time meteorological conditions and monitors continuously. The overall outcome showcases that machine learning models, deep learning algorithms, IoT and crowdsourcing information are equally contributing to predict and forecast risky weather conditions. The integration of the above components with machine learning techniques, together with the availability of historical data set, can forecast flood occurrences and disastrous weather conditions with above 0.70 accuracy in specific areas of Sri Lanka.
Embargo
EduHelp – An Online Tutoring Application
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Fernandopulle, S.R.; Warnasooriya, W.M.C.D.B.; Jayasinghe, J.M.H.N.; Theeraj, S.M.D.; Samarakoon, U.; Kumari, S.
E-learning via electronic mail, the Internet, the Worldwide Web (WWW), and multimedia has emerged as a result of the convergence of digital technologies and growing interest in the computerized delivery of higher education. The rapid emergence of Covid-19, a lethal disease caused by the Corona Virus, shocked the entire world. It was labeled a pandemic by the World Health Organization. This has posed a challenge to the global education system, forcing instructors to switch to an online form of instruction overnight. Many academic institutions that had previously been hesitant to adapt their traditional pedagogical method now have no choice but to fully embrace online teaching-learning. Because the platform is new to students and teachers, it appears that they are having some difficulties conducting their classes. Hence in this paper, we proposed an E-learning Application called EduHelp to design and build a tutoring platform that includes payment validation for each student, lesson summaries with a video summary note, and more. Upload relevant files and papers by automatically identifying and directing them, as well as creating automated questions and monitoring student attention.
Embargo
Effectiveness of Stock Index Forecasting using ARIMA model: Evidence from New Zealand
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Dassanayake, W.; Ardekani, I.; Gamage, N.; Jayawardena, C.; Sharifzadeh, H.
Time series of stock market indices are dynamic, interdependent, and considered sensitive to many factors. Thus, the prediction of such indexes is always challenging. A comprehensive review carried out by the authors finds that no attempts have yet been carried out to test ARIMA models’ predictive efficacy applied to the New Zealand financial markets. Thus, technical analysis based ARIMA prediction models are developed and empirically tested on the New Zealand stock market (NZX50) index. Daily NZX50 index data are used, and the forecasting precision of the models is assessed based on Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE]. Our study finds that ARIMA (1, 1, 0) plus intercept is the best order forecasting model out of the models we examined. Once a substantiate algorithm training is implemented, formulated ARIMA models could be successfully employed to forecast the time series of other stock market indexes or the same index for varied periods. Future researchers could compare the forecasting efficiencies of ARIMA with a deep-learning model such as long short-term memory (LSTM). The presence of limited published research of ARIMA applied to the financial markets of New Zealand validates the need and the contribution of this paper.
Embargo
Enhance the Safety Measurements in Railways with the Aid of IoT and Image Processing
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Vedasingha, K. S.; Perera, K. K. M. T.; Hathurusinghe, K. I.; Akalanka, H. W. I.; Amarasena, N.; Dissanayake, N.R.
Railways provide the most convenient and economically beneficial mode of transportation, and it has been the most popular transportation method. According to the past analyzed data, it reveals a considerable number of accidents which occurred at railways, caused damages to not only precious lives but also to the economy. The goal of this research is to minimize the railway accidents by developing “Railway Process Automation System” while ensuring human safety with use of Internet of Things (IoT) and image processing techniques. The system can detect the current location of the train and close the railway gate automatically. As usual, if the system fails to close the rail gate due to any failure, the proposed system can identify the current location and close the rail gate through decision making system by using past data. The proposed system introduces further two features which named as Railway track crack detection and motion detection which play a significant role in reducing the risk of railway accidents. Moreover, the system is capable of detecting rule violations at a level crossing by using sensors. The proposed system is implemented through a prototype and tested with real-world scenarios to gain the above 90% of accuracy.
Open Access
Estimating the Delay to the Mainstream Traffic due to Jaywalking Pedestrians on Urban Roads
(ASCE, 2021-06) Jayatilleke, S; Wickramasinghe, V; Madushani, H; Dissanayake, S
Growth of road users in urban areas results in consequential higher interactions between pedestrians and vehicles causing delay to the mainstream traffic flow. The delay caused by pedestrians who make random jaywalking along the carriageway is substantial when such behavior exists. Thus, the prime objective of this research was to study the interaction and develop a delay model to estimate the collective delay caused to the mainstream traffic which encounters jaywalking pedestrians. This delay is influenced by the characteristics of the crossing pedestrians and the behavior of on-coming vehicles. The data collection was done in a suburban city near Colombo, Sri Lanka. The data were extracted from video footages taken using a drone camera. Both the movement of the vehicles and crossing pedestrians on the subject lane were tracked using automated software in order to enhance the accuracy of the results. The delay caused to mainstream vehicle was derived using the deceleration and acceleration behavior. The proposed delay model exemplifies that the pedestrian-vehicle gap and the pedestrian speed along with other relevant pedestrian characteristics such as age, pedestrian speed at the start of the vehicle speed drop, and vehicle-related characteristics such as vehicle speed at the start and end, veh-ped gap at the vehicle speed drop, subject lane, and vehicle type are highly significant to the delay of the subject vehicle on the mainstream. The overall R value of 0.63 was observed from the regression analysis of the proposed delay model. The applicability of the proposed model for each pedestrian and vehicle characteristic has been determined and evaluated based on their level of significance.
Open Access
Evaluation of Ecosystem-Based Adaptation Measures for Sediment Yield in a Tropical Watershed in Thailand
(MDPI, 2021-10-06) Babel, M. S; Gunathilake, M. B; Jha, M. K
Ecosystem-based adaptation (EbA) can potentially mitigate watershed degradation problems. In this study, various EbA measures were evaluated using a bio-physical model called the Soil and Water Assessment Tool (SWAT), in a small, forested watershed named Hui Ta Poe, in the northeastern region of Thailand. The developed watershed model was first used to investigate the effect of various degraded watersheds due to land-use changes on the sediment yield in the study area. The most degraded watershed produced an annual average sediment yield of 13.5 tons/ha. This degraded watershed was then used to evaluate the effectiveness of various EbA measures such as reforestation, contouring, filter strips, and grassed waterways in reducing the sediment yield. Under all individual and combined EbA scenarios analyzed, there was a significant reduction in sediment yield; however, the maximum reduction of 88% was achieved with a combined scenario of reforestation, grassed waterways, and filter strips. Reforestation alone was found to be the second-best option, which could reduce the sediment yield by 84%. Contouring alone was the least effective, with a reduction in sediment yield of only 23%. This study demonstrates the usefulness of implementing EbA measures for sediment management strategies to address watershed degradation, which is a severe problem across the globe.