Research Publications Authored by SLIIT Staff

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4195

This collection includes all SLIIT staff publications presented at external conferences and published in external journals. The materials are organized by faculty to facilitate easy retrieval.

Browse

Filters

2011 - 201943

Advanced Search

Filter by

Settings

Author: search.filters.author.Kasthurirathna, DEnd date: 2019

Search Results

Now showing 1 - 10 of 43
  • Thumbnail Image
    PublicationEmbargo
    Social media based personalized advertisement engine
    (IEEE, 2018-02-19) De Silva, H; Jayasinghe, P; Perera, A; Pramudith, S; Kasthurirathna, D
    Online advertising has become a global phenomenon that affects the retail market substantially. Advertisements engines are an effective solution to the mobile application market to push advertisements. This paper reports evidence that AdSeeker, User Preference Based Advertisement Engine Based on Social Media is an effective solution to improve the business value of the marketing and advertising. Since the internet is used by vast number of people, it essentially needs a comprehensive method to push personalized advertisements to the right people. Adseeker is a system built using ontological mapping and social media content based semantic analysis to direct personalized. Identifying personal relationship hierarchy, and ontological approach for advertisement classification helps to identify the most appropriate advertisement for each user. AdSeeker uses the tweets posted by users to capture the preference of each and every user. Each user pushed advertisements based on their individual preferences. Based on the social experiments done using Adseeker, we could demonstrate that the social media profile based advertising is effective in providing highly relevant advertisements.
  • Thumbnail Image
    PublicationOpen Access
    Agro-Genius: Crop Prediction Using Machine Learning
    (https://ijisrt.com/agrogenius-crop-prediction-using-machine-learning, 2019-10) Gamage, M. P. A. W; Kasthurirathna, D; Paresith, M. M; Thayakaran, S; Suganya, S; Puvipavan, P
    This paper present a way to aid farmers focusing on profitable vegetable cultivation in Sri Lanka. As agriculture creates an economic future for developing countries, the demand of modern technologies in this sector is higher. Key technologies used for this problem are Deep Learning, Machine Learning and Visualization. As the product, an android mobile application is developed. In this application the users should input their location to start the prediction process. Data preprocessing is started when the location is received to the system. The collected dataset divided into 3 parts. 80 percent for training, 10 percent for testing and 10 percent for validation. After that the model is created using LSTM RNN for vegetable prediction and ARIMA for price prediction. Finally, for given location profitable crop and predicted future price of vegetables are shown in the application. Other than the prediction, optimizing for multiple crop sowing according to the user requirements and visualizing cultivation and production data on map and graphs are also given in the application. This paper elaborates the procedure of model development, model training and model testing.
  • Thumbnail Image
    PublicationEmbargo
    Mobile-based Malware Detection and Classification using Ensemble Artificial Intelligence
    (IEEE, 2019-12-05) Somasundaram, S; Kasthurirathna, D; Rupasinghe, L
    The Android operating system is one of the most used operating systems in the world and has become a target to malware authors. Traditional malware detection methods such as signatures find it impossible to deal with detecting complex and intelligent malware which are capable of obfuscating and repackaging to avoid being detected. There is therefore an increase in the need to have more efficient and intelligent forms of malware detection. Artificial intelligence has now been brought to the field of malware detection and classification. Due to its accuracy and intelligence it has become an ideal solution to bridge the gap between traditional classifiers and the intelligent malware. Currently, research is mainly being conducted using either machine learning or deep learning techniques to target all or a given malware family. This paper proposes a methodology which brings an ensemble solution between the Support Vector Machine algorithm and the Convolutional Neural Network to create a solution that provides a higher accuracy than available techniques.
  • Thumbnail Image
    PublicationEmbargo
    Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
    (IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
    Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
  • Thumbnail Image
    PublicationEmbargo
    Plus Go: Intelligent Complementary Ride-Sharing System
    (IEEE, 2019-11-21) Wickramasinghe, V; Edirisinghe, A; Gunawardena, S; Gunathilake, A; Kasthurirathna, D; Wijekoon, J
    Currently the world population is gathering to the cities making huge traffic congestion throughout the day. This has drawn serious attention to the society incurred to implement smart solutions for traffic management. One of the prominent problems for traffic congestion is the number of vehicles entering the cities is high. It is a popular fact that the solitary travelers coming to a defined destination make the vehicles underutilized. Therefore, this study proposes a solution to implement a new ride-sharing platform: Plus Go, to reduce this underutilization. Plus Go matches the travelers by considering the designation, traveler preferences, shortest path details, and the ratings of the users. Moreover, Plus Go intelligently estimates the traveling cost based on the fuel consumption of the vehicle, distance traveled, and the time taken to reach the destination. The proposed solution matches the travelers with 98% accuracy ensuring that ride-sharing is an effective solution to reduce the number of vehicles entering the cities.
  • Thumbnail Image
    PublicationOpen Access
    A User-oriented Ensemble Method for Multi-Modal Emotion Recognition
    (SLAAI - International Conference on Artificial Intelligence, 2019-12-12) Iddamalgoda, N; Thrimavithana, P; Fernando, H; Ratnayake, T; Priyadarshana, Y. H. P. P; Aththidiye, R; Kasthurirathna, D
    Emotions play a vital role in mental and physical activities of human lives. One of the biggest challenges in Human-Computer Interaction is emotion recognition. With the resurgence in the fields of Artificial Intelligence and Machine learning, a considerable number of studies have been carried out in order to address the challenge of emotion recognition. The individual heterogeneity of expressing emotions is a key problem that needs to be addressed in accurately detecting the emotional state of an individual. The purpose of this work is to propose a novel ensemble method to predict the emotions using a multimodal approach. The presented multimodal approach with the modalities of facial expressions, voice variations and, speech and social media content, are used to identify seven emotional states: anger, fear, disgust, happiness, sadness, surprise and neutral emotion. In this study, for the facial expression-based emotion recognition and voice variation-based emotion recognition, Deep Neural Network models have been used, and for emotion recognition using speech and social media content, Multinomial Naïve Bayesian algorithm is used. The mentioned three modalities were integrated using a novel ensemble method that captures the heterogeneity of individuals in how they express their emotions. The proposed ensemble method was evaluated with respect to real states of human emotions of a sample user group and the experimental results suggest that the suggested ensemble method may be more accurate in recognizing emotions. Accurate recognition of emotions may have myriad applications in domains such as healthcare, advertising and human resource management.
  • Thumbnail Image
    PublicationEmbargo
    Quantifying encircling behaviour in complex networks
    (IEEE, 2013-04-16) Piraveenan, M; Uddin, S; Chung, K. S. K; Kasthurirathna, D
    In this paper, we explore the effect of encircling behaviour on the topology of complex networks. We introduce the concept of topological encircling, which we define as an attacker making links to neighbours of a victim with the ultimate aim of undermining that victim. We introduce metrics to quantify topological encircling in complex networks, both at the network level and node pair (link) level. Using synthesized networks, we demonstrate that our measures are able to distinguish intentional topological encircling from preferential mixing. We discuss the potential utility of our measures and future research directions.
  • Thumbnail Image
    PublicationEmbargo
    Standard deviations of degree differences as indicators of mixing patterns in complex networks
    (IEEE, 2013-08-25) Thedchanamoorthy, G; Piraveenan, M; Kasthurirathna, D
    Mixing patterns in social networks can give us important clues about the structure and functionality of these networks. In the past, a number of measures including variants of assortativity have been used to quantify degree mixing patterns of networks. In this paper, we are interested in observing the heterogeneity of the neighbourhood of nodes in networks. For this purpose, we use the standard deviation of degree differences between a node and its neighbours. We call this measure the `versatility' of a node. We apply this measure on synthetic and real world networks. We find that among real world networks three classes emerge -(i) Networks where the versatility converges to non-zero values with node degree (ii) Networks where the versatility converges to zero with node degree (iii) Networks where versatility does not converge with node degree. We find that there may be some correlation between this and network density, and the geographical / anatomical nature of networks may also be a factor. We also note that versatility could be applicable to any quantifiable network property, and not just node degree.
  • Thumbnail Image
    PublicationEmbargo
    A trilateral influence model for online shopping
    (IEEE, 2017-01-27) Samaraweera, S. A. K. G; Gamage, N. G. H. P; Gallage, I. G; Gunathilaka, D. D. T. M; Fernando, N; Kasthurirathna, D
    Application of social influence toward E-commerce has brought a significant benefit for the stakeholders. Consequently, it has enhanced the consumer satisfaction as well as spread of experiences. However, even with the collaboration of social influence there are some visible short comings potentially appearing in such systems. In fact, the contribution of social influence is still in an evolving state. The reliability of products is such recognized key issue that still appears in exiting social E-commerce systems. In this context we introduce a social influence model combined with a built in social network which further improves the customer reliability and satisfaction on available products. Thus, it can propagate reliable knowledge among community and optimize product recommendation process. The implemented model considers the personal preferences of respective consumers, their social influences in social network and external social influences to the system for the execution. Furthermore, it operates as a multi-agent system. The model has been validated by two sample data sets of consumers and products. As the results, majority have picked products suggested by combining external influences, internal social influences, and personal preferences. Therefore it has concluded that recommendation of products considering above three combinations is more effective.
  • Thumbnail Image
    PublicationOpen Access
    Placement matters in making good decisions sooner: the influence of topology in reaching public utility thresholds
    (acm.org, 2019-08-27) Kasthurirathna, D; Piraveenan, M; Law, S. Y
    —Social systems are increasingly being modelled as complex networks, and the interactions and decision making of individuals in such systems can be modelled using game theory. Therefore, networked game theory can be effectively used to model social dynamics. Individuals can use pure or mixed strategies in their decision making, and recent research has shown that there is a connection between the topological placement of an individual within a social network and the best strategy they can choose to maximise their returns. Therefore, if certain individuals have a preference to employ a certain strategy, they can be swapped or moved around within the social network to more desirable topological locations where their chosen strategies will be more effective. To this end, it has been shown that to increase the overall public good, the cooperators should be placed at the hubs, and the defectors should be placed at the peripheral nodes. In this paper, we tackle a related question, which is the time (or number of swaps) it takes for individuals who are randomly placed within the network to move to optimal topological locations which ensure that the public utility satisfies a certain utility threshold. We show that this time depends on the topology of the social network, and we analyse this topological dependence in terms of topological metrics such as scale-free exponent, assortativity, clustering coefficient, and Shannon information content. We show that the higher the scale-free exponent, the quicker the public utility threshold can be reached by swapping individuals from an initial random allocation. On the other hand, we find that assortativity has negative correlation with the time it takes to reach the public utility threshold. We find also that in terms of the correlation between information content and the time it takes to reach a public utility threshold from a random initial assignment, there is a bifurcation: one class of networks show a positive correlation, while another shows a negative correlation. Our results highlight that by designing networks with appropriate topological properties, one can minimise the need for the movement of individuals within a network before a certain public good threshold is achieved. This result has obvious implications for defence strategies in particular.