IJITCS Vol. 11, No. 5, May. 2019
Cover page and Table of Contents: PDF (size: 227KB)
The use of Facebook, in higher education, has become common place presumably due to a general belief that the platform can promote information flows between students and with staff as well as increasing a sense of community engagement. This study sets out to examine the academic use of Facebook groups using data analysis in order to determine if there are educational benefits and if Facebook group based learning strategies can be evaluated quickly and relatively easily. The data analysis involved utilising Social Network Analysis (SNA) in examining two Facebook groups; one under-graduate ‘course’ based group with 135 members and one under-graduate first year ‘module’ based group with 123 members. The SNA metrics included degree centrality, betweeness centrality, clustering coefficient and eigenvector centrality. The study also involved conducting a survey and interviews drawn from users of the Facebook groups to validate the utility of the SNA metrics. Results from the validation phase of the data analysis suggested that degree centrality is a useful guide to positive attitudes towards information flows, whilst betweenness centrality is useful for detecting a sense of academic community. The validation outcomes also suggest that high clustering coefficient scores were associated with a lower perception of academic community. The analysis of the data sets also found that the ‘course’ based group had higher scores for degree centrality and betweenness. This suggests that the ‘course’ based group provided a better experience of information access and a sense of academic community. Follow up interviews with respondents suggested that the ‘course’ based Facebook group may have had higher scores because it included more real world acquaintances than the ‘module’ based group.[...] Read more.
In recent years, the use of cloud computing has increased exponentially to satisfy computing needs in both big and small organizations. However, the high amounts of power consumed by cloud data centres have raised concern. A major cause of power wastage in cloud computing is inefficient utilization of computing resources. In Infrastructure as a Service, the inefficiency is caused when users request for more resources for virtual machines than is required. In this paper, we propose a technique for automatic virtual machine sizing and resource usage prediction using neural networks, for multi-tenant Infrastructure as a Service cloud service model. The proposed technique aims at reducing energy wastage in data centres by efficient resource utilization. An evaluation of our technique on CloudSim Plus cloud simulator and WEKA shows that effective VM sizing not only achieves energy savings but also reduces the cost of using cloud services from a customer perspective.[...] Read more.
The article presents the science, technologies and innovations as foundations of modern economic development. The purpose of establishing complex-structured innovation structure and their functions are analyzed. An effective organizational-economic structural model is proposed for the management of their performance. Production functions, allowing central management institution to use the resources effectively and enterprises within the institution to operate with the whole production strength, are developed. Parameters that cannot be assessed directly as innovation, innovation capacity, science capacity and environmental availability are included in the modeling process. Hierarchic models are developed corresponding to the problems posed to each structure. Among models with various levels, a conceptual algorithm is developed for the purpose of finding a coordinated solution on product/service output based on the efficient utilization of scarce resources. Some suggestions have been given on the basis of modeling the activity of innovative enterprises of different levels with complex structure on its perspective development directions.[...] Read more.
The goal of this work is the improvement of the performance of a multimodal biometric identification system based on fingerprints and finger vein recognition. This system has to authenticate the person identity using features extracted from his fingerprints and finger veins by multimodal fusion. It is already proved that multimodal fusion improves the performance of biometric recognition, basically the fusion at feature level and score level. However, both of them showed some limits and in order to enhance the overall performance, a new fusion method has been proposed in this work; it consists on using both features and scores fusion at the same time. The main contribution of investigation this technique of fusion is the reduction of the template size after fusion without influencing the overall performance of recognition. Experiments were performed on a real multimodal database SDUMLA-HMT and obtained results showed that as expected multimodal fusion strategies achieved the best performances versus uni-modal ones, and the fusion at feature level was better than fusion at score level in recognition rate (100%, 95.54% respectively) but using more amounts of data for identification. The proposed hybrid fusion strategy has overcome this limit and clearly preserved the best performance (100% as recognition rate) and in the same time it has reduced the proportion of essential data necessary for identification.[...] Read more.
Due to the enormous growth of social media the potential of social media mining has increased exponentially. Individual users are producing data at unprecedented rate by sharing and interacting through social media. This user generated data provides opportunities to explore what people think and express on social media. Users exhibit different behaviors on social media towards individuals, a group, a topic or an activity. In this paper, we present a social media mining approach to perform behavior analytics. In this research study, we performed a descriptive analysis of user generated data such as users’ status, comments and replies to identify individual users or groups which can be a potential threat. Tokenization technique is used to estimate the polarity of the behavior of different users by considering their comments or feedbacks against different posts on Facebook. The proposed approach can help to identify possible threats reflected by the user’s behavior towards a specific event. To evaluate the approach, a data set was developed containing comments on the Facebook from different users in different groups. The dataset was divided into different groups such as political, religious and sports. Most negative users’ in different groups were identified successfully. In our research, we focused only on English content; however, it can be evaluated with other languages.[...] Read more.
Data on the web is constantly growing which may affect users’ ability to find relevant information within a reasonable time limit. Some of the factors previously studied that affect users searching behaviour are task difficulty and topic familiarity. In this paper, we consider a set of implicit feedback parameters to investigate how document difficulty and document familiarity affects users searching behaviour in a task-specific context. An experiment was conducted and data was collected from 77 undergraduate students of Computer science. Users’ implicit features and explicit ratings of document difficulty and familiarity were captured and logged through a plugin in Firefox browser. Implicit feedback parameters were correlated with user ratings for document difficulty and familiarity. The result showed no correlation between implicit feedback parameters and the rating for document familiarity. There was, however, a negative correlation between user mouse activities and document difficulty ratings.
Also, the dataset of all the participants in the experiment was grouped according to task type and analysed. The result showed that their behaviour varies according to task type. Our findings provide more insight into studying the moderating factors that affect user searching behaviour.[...] Read more.