Smart Computing and Systems Engineering (SCSE)
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/18936
Browse
10 results
Search Results
Item Factors Influencing the Success of Software Startups in Sri Lanka: A Comparative Analysis using SmartPLS & SEMinR(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Attygalle, T.I.; Withanaarachchi, A.S.; Jayalal, S.IT industry is one of the fast-growing industries in Sri Lanka. In that industry the software development sector plays a massive role. Out of these software development firms, a considerable number of companies are startups. But compared to other countries, the contribution from software startups to the country’s economy is very low in Sri Lanka. Further with the current economic crisis Sri Lanka faces it is even harder for startups to continue their businesses and also it is challenging for an entrepreneur-minded person who wants to establish a software startup in Sri Lanka. This study focuses on the factors influencing the success of software startups in Sri Lanka and how those factors will be affected by the current economic crisis in Sri Lanka. The study has been conducted using a systematic literature review to discover and validate influential factors from past studies. Then the conceptual framework was formed to assess the variables. To validate the model, data was collected through an online questionnaire survey. Testing and validation of collected data were done using a comparative analysis between Smart PLS and SEMinR. The results of both studies show that the availability of finance is the only factor that has a significant relationship with the success of software startups in Sri Lanka. With that the study also recommends taking necessary actions to improve the availability of funds for software startup companies.Item Interpretation of Sri Lankan Sign Language: A Wearable Sensor-based Approach(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Kusalanga, M.N.; Jayalal, S.; Wijayasiriwardhane, T. K.Hearing-impaired and speech-impaired people communicate not only with themselves but also with ordinary people using visual languages. Sri Lankan Sign Language (SSL) is the standard visual language used in Sri Lanka. Like other sign languages, the SSL relies on a distinct combination of hand gestures, body movements, and facial expressions for communication. As a result, SSL is more challenging for individuals without knowledge of SSL to understand. On the other hand, the steep learning curve associated with SSL makes it even more difficult to acquire. Thus, the interpretation of SSL has become a need. However, Sri Lanka is suffering from a severe dearth in the availability of SSL interpreters. This justifies the need to use either vision- based or sensor-based technological approaches to help the interpretation of SSL. However, vision-based approaches are susceptible to conditions such as skin tone, background color, ambient light intensity, and real-time constraints, whilst the sensor-based solutions are generally better in gesture recognition. Further, there is no attempt has been made on developing a cost-effective, portable, and real-time solution to accurately interpret the hand gestures of SSL. In this paper, we, therefore, present a novel, wearable, sensor-based, real-time gesture recognition glove, and a machine-learning Long Short-Term Memory (LSTM) model to recognize the hand and finger positions in three-dimensional space for classification and interpretation of SSL. The proposed approach has achieved 320ms of lowest inference time while showing a promising result of 83% for categorical accuracy. Our aim is to help the interpretation of SSL with an affordable, portable as well as a real-time solution.Item Dengue mosquito larvae identification using digital images(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) De Silva, W.D.M.; Jayalal, S.Dengue is one of the highest spreading mosquitoborne diseases in tropical and subtropical regions all over the world. This disease is mainly spread by the mosquito vector called ‘Aedes’. In Sri Lanka, the number of infected patients reported is increasing, and it has become a public health problem. Health Inspectors are using different methods to reduce the spread of this viral disease and one of the main methods used is the fumigation by identifying the Aedes Larvae breeding locations. Currently, this identification is done manually by the specialized health inspectors and it is totally observer-biased and consumes a considerable amount of time, which could lead to false decision making and inefficient identification. The purpose of this research is to build an automated computational model to identify Aedes Larvae in real-time with more accuracy and convenience. Even though there are good results in previous researches done in Convolutional Neural Networks (CNN) on Aedes Larvae identification, the method of capturing Larvae Images is a bit complicated since they have used a Microscope lens of amplification capacity 60-100 times to get the magnified images. In this research, we propose the method of identifying Aedes mosquito larvae with a digital amplification of 8-12 times without using any microscope lenses attached, using ResNet50 CNN. The proposed model will identity the mosquito larvae by their genus ‘Aedes’ or ‘non- Aedes’ using a digital photo taken by a smartphone or camera in the upside of the larvae body. Hence it would help Health Inspectors, even the general public on identifying Aedes Larvae more efficiently, accurately and conveniently than the traditional method. This study shows that the trained model can identify images of Aedes and Non-Aedes Larvae separately with an accuracy of 86.65%. Furthermore, with using pre-processing techniques, the accuracy level can be enhanced to 98.76% for magnified images.Item Grammatical error detection and correction model for Sinhala language sentences(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Pabasara, H.M.U.; Jayalal, S.As the national language of Sri Lanka, the greater part of the exercises at most of all the services are completed in Sinhala whereas it is imperative to guarantee the spelling and syntactic accuracy to convey the ideal significance from the perspective of automated materials with the unavailability of resources even though there are enough amount of available materials as hard copy and books. With the high multifaceted nature of the language, it sets aside extensive effort to physically edit the substance of a composed setting. The necessity to overcome this problem has risen numerous years back. But with the complexity of grammar rules in morphologically lavish Sinhala language, the accuracy of the grammar checkers developed so far has been contrastingly lower and thus, to overcome the issue a novel hybrid approach has been introduced. Spell checked Sinhala active sentences being pre-processed, separated nouns and verbs were analyzed with the help of a resourceful part-of- speech-tagger and a morphological analyzer and alongside the sentences were sent through a pattern recognition mechanism to identify its sentence pattern. Then a decision tree-based algorithm has been used to evaluate the verb with the “subject” and output feedback about the correctness of the sentence. To train this decision tree, a dataset consisting of 800 records which included information about 25 predefined grammar rules in Sinhala was used. Finally, the error correction was provided using a machine learning algorithm-based sentence guessing model for the three possible tenses. Conducted research results paved the way to identify the sentence pattern, grammar rules and finally, suggest corrections for identified incorrect grammatical sentences with an acceptable accuracy rate of 88.6 percent which concluded that the proposed hybrid approach was an accurate approach for detecting and correcting grammatical mistakes in Sinhala text.Item Sinhala Handwritten Postal Address Recognition for Postal Sorting(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Ifhaam, M.F.A.; Jayalal, S.Sri Lankan post office mail sorting process is done manually, even today. Though employees are well experienced, it takes considerable time and employees need to work overtime in places like Central Mail Exchange (CME). With major issues like unclear handwriting, having trouble to recognize some uncommon or ambiguous names, and carrying these duties twice a day create a negative impact on the efficiency of the postal delivery system. In the prevailing system, forward mails and delivery mails are the two categories of separating mails at the sorting centers. Delivery mails are the posts which can be delivered to its destination directly. Forward mails are the ones which need to be sent to an appropriate post office that can deliver the particular post to its destination. Majority of Sri Lankans use Sinhala language for their day to day activities. The primary objective of the research is to identify the automatic way of forwarding the letter to the next post office from the current post office. Proposed system is focused on the recognition of Sinhala handwriting using Optical Character Recognition (OCR) and image processing technologies. Data collected under different criteria were used for training and testing the solution. Genetic Algorithm (GA) was used to generate more optimized results faster with higher accuracy. Given addresses are written in the default format. This format can be extended to more formats as improvements in future. The algorithm shows accuracy over 92% for addresses which are recognized with 3 misrecognized characters. This algorithm can be used on practice scenario as the AI Recognition has more than 79 % of accuracy.Item Passion Fruit Disease Detection using Image Processing(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Dharmasiri, S.B.D.H.; Jayalal, S.Fruit diseases are a major problem in economic and production losses in the agricultural industry worldwide. In this paper, an image processing approach is proposed for identifying passion fruit diseases. According to the Sri Lankan context, treatment details are taken by the farmers from the field officers. However, it can take a few days. So, this proposed system can be used to identify passion fruit diseases quickly and automatically. This proposed approach is composed of the following main steps; Image Acquisition, Image Preprocessing, Image Segmentation, Feature Extraction, Dataset Preparation, Training & Testing. Healthy and two types of passion fruit diseases, namely passion fruit scab and woodiness images were used for this approach. This approach was tested according to passion fruit disease type and its’ stages, such as mild, moderate and severe. K-Means clustering was used for segmentation. Images were clustered according to k values, such as 2, 4, 6 and 8. Before the segmentation, images were converted to RGB, L*a*b, HSV and Grey colour models, because of find out the most suitable colour model for this approach. Local Binary Pattern was used for feature extraction and Support Vector Machine was used for creating the model. Seventy percent (70%) of each dataset was used to train the SVM and the other thirty percent (30%) was used to test the model. According to this approach, passion fruit diseases can be identified in the average accuracy of 79% and its’ stage can be identified in average accuracy 66%.Item Prediction of User Intentions Using Web History(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Samarasinghe, K.T.C.S.; Jayalal, S.In the present internet has become much more necessary thing to humans and we use it as a way of sharing information and way of communication. If the networks can identify the user’s intentions, it will be affecting to increase productivity and personalization. Predicting user intention(s) is interesting and useful for many applications such as threat identification, imposing restrictions and cashing web details. The aim of this research is to develop a method to predict user intention using supervised machine learning methods with user’s past historical behaviours. Experiments in this study used access log on a local server and focused on creating single user prediction and multiuser generalize prediction models. Experimental models were created based on several multi-classifier algorithms, such as Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbor (KNN). KNN based models outperform other used algorithms. Also results in this study show that there is some sort of behavioural patterns for peoples to use the internet according to the time and the groups they interactItem Classification of vehicles by video analytics for unorganized traffic environments(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Arachchi, I.M.R.; Jayalal, S.; Rajapakse, C.Traffic monitoring is essential for infrastructure planning and transportation. The objective of traffic monitoring is to have an effective traffic management system. Traffic management systems would be effective in well-organized traffic environments, where it has very disciplinary behaviors and less in inefficiencies. But in unorganized urban environments like Sri Lanka, road traffic behaviours are varying from standard structured ways which lead to discompose the traffic management. An effective monitoring system requires short processing time, low processing cost and high reliability. The paper proposes a novel vehicle detection and classification algorithm based on background filtering and re-engineered with suitable changes in order to be applicable to challenging unorganized traffic environments. The solution is successfully classifying vehicles individually and their trajectories in unorganized traffic environments in order to monitor the behaviors of the drivers. The system gives 74.4% average accuracy in vehicle detection and 55% accuracy in vehicle classification while counting each vehicle passed by. We used OpenCV functions for implementing and testing algorithms. Data was collected through pre-recorded video clips from footbridge crossing at Colombo Fort in western province Sri Lanka, for the testing. The ultimate objective of this research was to come up with a best-suited algorithm for vehicle detection and classification (hybrid solution) in unorganized traffic environments which would help to analyze the behaviors of road users. The solution will lead to help reduce unorganized traffic congestions by enhancing the efficiency and effectiveness of traffic monitoring and analyzing systems those are used for intelligent traffic management systems and traffic simulation models.Item Study of machine learning algorithms for Sinhala speech recognition(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Shaminda, S.; Jayalal, S.Speech is the primary mode of communication among humans and the most natural and efficient form of exchanging information. Therefore, it is logical that the next technological development in natural language speech recognition for Human Computer Interaction is, Artificial Intelligence. Speech recognition can be defined as the process of converting speech signal to a sequence of words by an algorithm implemented using a computer program. Speech processing is one of the challenging areas of signal processing. The main objective of the study was to conduct a study on speech recognition approaches to improve the accuracy level of Sinhala speech recognition. This study was conducted in order to find the optimal algorithm for accurate Sinhala speech recognition. According to the implementation architecture of speech recognition, feature extraction and the pattern recognition phases can be varied with different algorithms. The study identified that Linear Predictive Coding (LPC) and Hidden Markov Model (HMM) gives most accurate results than other combine algorithms.Item Analysis and detection of potentially harmful Android applications using machine learning(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Kavneth, G.A.S.; Jayalal, S.With the rapid advancement of technology today, smartphones have become more and more powerful and attract a huge number of users with new features provided by mobile device operating systems such as Android and iOS. Android extended its lead by capturing 86% of the total market in 2017 (Gartner, 2017) and became the most popular mobile operating system. However, this huge demand and freedom has made the hackers and cybercriminals more curious to generate malicious apps towards the Android operating system. Thus, research on effective and efficient mobile threat analysis becomes an emerging and important topic in cybersecurity research area. This paper proposes a static-dynamic hybrid malware detecting scheme for Android applications. While the static analysis could be fast, and less resource consuming technique and dynamic analysis can be used for high complexity and deep analysis. The suggested methods can automatically deliver an unknown application for both static and dynamic analysis and determine whether Android application is a malware or not. The experimental results show that the suggested scheme is effective as its detection accuracy can achieve to 93% ∼ 100%. The findings have been more accurate in identifying Android malwares rather than separating those two static and dynamic behaviors. Furthermore, this research compares the machine learning algorithms for static and dynamic analysis of the Android malwares and compare the accuracy by the data used to train the machine learning models. It reveals Deep Neural Networks and SVM can be used for and higher accuracy. In addition, era of the training and testing dataset highly effect the accuracy of the results regarding Android applications.