Call For Papers. Vol.5 No.2 2020

Volume 05. Issue 02.

Human Face Recognition to Target Commercial on Digital Display via Gender
Haju Mohamed Mohamed Naleer

Emotion recognition has been applied in many fields such as Medical, Security, and Business etc. There are many complications in evolving a good emotion recognition scheme for the human face in real time. Since most of the time facial features of expression and the style of presentation emotion to the outside world is dissimilar from person to person. Thus, it is very problematic to build a precise scheme for real time emotion recognition. This paper is to distinguish human facial expressions to predict the current emotional state. The system specially focused on reducing fatal road accidents due to drivers' state of emotion. Initially it is built to recognize the human emotion through facial expressions and then evaluated to detect drowsiness using facial landmarks to ensure the safety of the driver. Training has been done with Kaggle dataset for seven emotional states (Neutral, Happy, Angry, Sad, Scared, Surprised and Disgust) called universal emotions. In order to predict drowsiness, it uses specific twelve points on face (six points on each eye) in shape predictor sixty face landmarks. Evaluated system has given 71% accuracy in testing and drowsiness alert also showed a very good success rate.
Keywords:Highways Traffic Surveillance System, IP camera, OpenCV


A Study on Big Data Analytics: Platforms and Tools, Challenges, Technologies and Key Applications
Fathima Sihnas Fanoon Abdul Raheem and Isuri Uwanthika Gatamanna Arachchige

Big data is the paradigm that refers to the data generated not only in terabytes, but in hexabytes and more. Big data has gained an enormous success in numerous application areas including social media, economy, finance, healthcare, agriculture, and many more. Now a days, data are being produced at lighting speed. Data produced in many media are either structured, unstructured or semi-structured, using which the researchers could find the unknown pattern behind these datasets. Big Data is one of the most important applications in parallel and distributed systems. Processes related to analysis are often carried out with a deadline and during the process, it is vital for analytics also to concern about the quality of the data. This paper highlights few platform and tools used in the data analytics process. Further, it explains about the several challenges faced in big data analytics. Data representation, data management, data confidentiality and few other are found to be the major challenges in big data analytics. Also, the paper aims to study the technologies applied for big data analysis in the fields of cloud computing, Internet of Things and Hadoop. Finally, the paper reviews on the key application areas of big data analytics by researchers.
Keywords: Big Data, Cloud Computing, Hadoop, Internet of Things


Involvement of School Students on Social Networks and impact on their performance of studies
Latheef Fathima Zisath Shama, Shafana Muhammed Shareef and Mohamed Jamaldeen Ahamed Sabani

Social network usage is massively increasing among children all over the world. School students usually use the latest technology on Social Networks. School students are using social media for several purposes. Usage of Social Networks impacts their studies and everyday life in a fair and bad manner. Several researches have been done in developed countries which can be seen in the literature review. Moreover, most of the studies intended on the effects of social media on the moral behaviour of the youths. Moreover, most of the research considered the undergraduate students' academic performance and their attitudes. The higher probability of no such research on school level students. This study restricted itself to the study habits of the school students. This study aims to collect the data from Advanced level students by a questionnaire which includes the questions on the impact of Social Networks in studies and performance of students. Moreover, this study analyses those data using SPSS to check the students' involvements on Social Networks and impacts on their studies and performance. The result of this research throughout the survey reveals that the performance of studies of school students and the number of social media is negatively associated. Likewise, spending hours on studies negatively associated with spending hours on social media. Moreover, the performance of the students decreases when the spending hours on social media increase.
Keywords: Social media usage, the performance of students, Facebook, WhatsApp


Factors Affecting the Selection of Web Browsers by University Students: Special Reference to Rajarata University of Sri Lanka
D.M.M.P. Dissanayaka and D.M.J. Wickramasinghe

Web browsers are amazing. They make the World Wide Web accessible to everyone. People can read web pages by means of web browsers. Many different web browsers are available on the Internet, free of charge. In addition to most popular web browsers that have superb features people might like more, such as faster, free, secure, and different by design, better interface and such. So, people need to take time experimenting with diverse web browsers to find the one they like best if still using the device’s default web browser. This study aims to investigate the factors affecting the selection of web browsers by keeping the straight attention on university undergraduates because, web browser usage has deeply penetrated the academicians not only with their academic workloads but also several purposes. A sample of one hundred and thirty undergraduates who are currently studying in Rajarata University of Sri Lanka selected through stratified sampling technique and research data were collected through structured questionnaire for the study purpose. Descriptive Statistics, Correlation Analysis and Multiple Regression Analysis were used to analyze the data. As per the study findings Browser Performance, Security, Awareness and User Friendliness are the factors need to look at when selecting the web browser to go on. From these results it can be concluded that Browser Performance and Awareness factors were positively and significantly impacted to the Selection of Web Browsers and Security and User Friendliness factors positively but not significantly impacted. The researcher recommends the future researchers to conduct same studies on similar topics, academicians and information seekers for enhance their web browser horizons and web browser developers and technology institutions for provide better web browser products and services by getting the key factors which highlighted in this study in order to their web browsers be the selective web browsers of peoples’ web browser list ever.
Keywords: Selection of Web Browsers, Undergraduates


How to Deliver an Engaging Online Presentation?
Mohamed Buhary Fathima Sanjeetha, Samsudeen Sabraz Nawaz and Abdul Jabbar Mohamed Hasmy

After this Covid-19 pandemic, there has been a growing invitation for business people and educators to deliver presentations remotely especially through Webinars instead of in person, as the former offers more benefits particularly the ability to reach out to a geographically more expansive audience and the prospects of time and cost savings for the those who host it, resource persons who deliver the contents and audience. To be able to fully leverage on such benefits, effective webinar presentation strategies are needed. In this article, strategies proposed by many scholars are synthesized and presented in eight points that could enrich the effectiveness of webinars in line with the best practices. In overview, the strategies include: knowing the whereabouts, why and how the webinars are organized, empathizing the audience, delivering clear contents and attracting the audience, staying prepared, getting to know the technology, keeping momentum, and weighing the effectiveness of the delivery. In all, it is hoped that these tips would facilitate presenters in improving the efficacy and quality of their webinar presentations.
Keywords: Webinar, Online Presentation, Effective Presentation, Pandemic, Covid-19


Students’ Intention to Use Social Media for Academic Purposes: A Study of South Eastern University of Sri Lanka
Mohamed Buhary Fathima Sanjeetha and Samsudeen Sabraz Nawaz

In education, social media is increasingly being used to promote creative instruction. This quantitative study utilized the theoretical foundation of social constructivism, connectivism and the Unified Theory of Acceptance and Use of Technology model 2 (UTAUT 2). Research questions investigated the effect of 6 UTAUT2 predictors on behavioural intention on social media and the impact of behavioural intention on the use of social media behaviour. The research used a convenience sample of 291 students from South Eastern University, Eastern Province, Sri Lanka. Survey data was analysed using descriptive statistics, measurement model and structural model, and hypothesis testing. The findings revealed that performance expectancy, social influence, facilitating conditions, hedonic motivation and habit have a significant effect on behavioural intention on social media whilst effort expectancy has a negative effect on behaviour, and that behavioural intention significantly influences usage behaviour. Better understanding may promote social media adoption in education, and thus enhance learning for students at South Eastern University of Sri Lanka.
Keywords: Social Media, Students’ Intention, Academic Purpose, UTAUT, Sri Lanka


Predictive Data Mining for Phishing Websites: A Rule Based Approach
Abdul Raheem Fathima Shafana and Abdul Raheem Fathima Shihnas Fanoon

The rapid advancement in internet has paved way for several serious crimes, of which phishing occupies a very important place. Phishing is a form of cybercrime where an attacker mimicking a legitimate website or a person or an organization redirects the victims to steal confidential data through e-mail, malwares or some other social engineering platforms. Victims prominently suffer from financial loss and private data loss. The serious outbreak of phishing has paved way for many researches, though comprehensive and accurate solution has not been proposed so far for thwarting its impact. This paper aims to develop a resilient model to predict phishing scam by means of classification algorithms of data mining. Five algorithms were chosen for this purpose and a comparative study was undertaken for their performances, accuracy, error rate and efficiency. The rules generated from the algorithms showed up a relatively better performance than the existing phishing detection tools.
Keywords: Phishing, Data Mining, Classification, PART, Website Legitimacy


Movie Success and Rating Prediction Using Data Mining Algorithms
Pirunthavi Sivakumar, Vithusia Puvaneswaren Rajeswaren, Kamalanathan Abishankar, E.M.U.W.J.B. Ekanayake and Yanusha Mehendran

This project developed the models to predict the success and the ratings of a new movie before its release. Since the success of a movie is highly influenced by the actor, actress, director, music director and production company, those historical data were extracted from the Internet Movie Database (IMDb).The Box Office Mojo stores information about the cost of production of a movie and the total income of the movie. This information is helpful to determine whether the movie is successful or not in terms of revenue. A threshold was defined on revenue based on heuristics to categorize the movie into success or failure. Teasers’ and trailers’ comments were extracted from YouTube as those are very helpful to rate a movie. The keywords were extracted from the user reviews using a Natural Language Processing (NLP) technique and those reviews were categorized into positive or negative based on the sentimental analysis. A Random Forest Algorithm was trained using the features extracted from IMDb to predict the success of a movie. Further, the Naive Bayers model was trained using the user reviews extracted from YouTube to predict the rating of a movie. The models were tested on real datasets and the accuracy of those were evaluated respectively. Finally, two conclusions have been met that the rating of a new movie cannot be predicted in advance through the YouTube trailers’ and teasers’ comments and the success of a new movie can be predicted in advance by using the data or features collected from online. The performances of the models are decent enough compared to the existing models in the literature. The Success Prediction model can be used as an early assessment tool of movies since it has gained 70% overall accuracy and hence, useful for the people in the movie industry and the audience of the movies. YouTube allows to extract a limited number of user comments and hence, this factor could be negatively affected on the accuracy of the movie rating prediction. This abstract was presented at International Research Conference of Uva Wellassa University of Sri Lanka(IRCUWU2020).
Keywords: Data Mining, Natural Language Processing, Sentimental Analysis, Naïve Bayers, Random Forest


Conversion of Virtual Writing on a 2D Plane into Real Writing using LED Pen and Web Camera
Abdul Lathief Jubailah Bagum

The use of conversion of virtual writing on a 2D plane into Real writing is becoming a very important need for this contemporary developing community as far as we are looking for. As we see, writing on a vast screen in big letters in front of a huge crowd is essentially needed in a conference for instance. But, because of the lack of facilities for that it becomes impossible unfortunately. So, they just explain the fact to the audience without writing anything which makes the crowd feel uncomfortable. Therefore, we have created a tool to compensate the very essential need that most of the people are looking forward.
Keywords: irtual writing, Web camera, LED pointing pen, Image Processing, C#.Net


Service Oriented Architecture in Enterprise Integration
Meeraa Shahibo Faathima Fayaza

Today in the on demand market, organizations try to achieve competitive advantages using information technology (IT). Nowadays organizations in addition to managing their internal operations use information technology to collaborate with their clients and suppliers. Organizations try to use enterprise applications for these. Moreover organizations expect technology to cooperate with their changing on demand needs. IT faces challenges in integrating different systems into functions that can address organizations' needs on demand and span across organizational boundaries. Service Oriented Architecture (SOA) as architectural frame work addresses the problems in the previous enterprise applications. This paper discusses the key challenges experienced by enterprise applications during its development and necessities of Service Oriented Architecture in the enterprise integration. This paper also discusses service-oriented architecture implementation challenges in enterprise integration
Keywords: Service Oriented Architecture, Enterprise Application, Business processes, integration


IT Managers’ Intention to Use Data Visualization Applications: A Sri Lankan Study
Mohamed Buhary Fathima Sanjeetha and Abdul Jabbar Mohamed Hasmy

This paper presents a preliminary analysis on the behavioral intention of IT managers to use data visualization application. Data visualization entails the visual understanding of data. It is part of the data analytics conducted following data correction. This study aims to determine the effect of effort expectancy, performance expectancy, and other factors in improving performance. The underpinning theory employed to explain the relationship is the Unified Technology Acceptance and Use of Technology. The needed data was collected from IT managers in numerous business sectors in Sri Lanka using a self-administered questionnaire. A total of 278 IT managers make up the active respondents in this study. The Smart PLS 3 software was used to analyze the data. The findings showed that behavioral intention is positively correlated with the factors of facilitating condition, effort expectancy, social influence, and performance expectancy. Theoretically, this study is positively linked to the theory of unified technology acceptance and use of technology. Implications wise, the findings can help boost the behavioral intention of managers in using data visualization software specifically by improving the aspects of facilitating condition, effort expectancy, social influence, and performance expectancy.
Keywords: Data Visualization, UTAUT, Behavioral Intention, IT Managers, Sri Lanka