IJMECS Vol. 8, No. 11, Nov. 2016
Cover page and Table of Contents: PDF (size: 216KB)
This study aimed to compare 5th graders’ scores obtained from Scratch projects developed in the framework of Information Technologies and Software classes via Dr Scratch web tool with the scores obtained from Computational Thinking Levels Scale and to examine this comparison in terms of different variables. Correlational research model was utilized in the study that 31 students participated in. Students were taught basic programming by using Scratch during a 6-week period. At the end of training, students’ programming skills were measured via Dr. Scratch web tool. Computational thinking skills were measured using Computational Thinking Levels Scale which includes 5 factors: creativity, problem solving, algorithmic thinking, collaboration and critical thinking. Data were analyzed for internal reliability to calculate scale reliability. Cronbach Alpha reliability coefficient was found to be 0.809. It was found that scores obtained by students by using any of the measurement tools did not differ according to gender or period of computer use, however, a high level significant relationship was observed between students’ programming skills with Scratch and their computational thinking skills.[...] Read more.
The study formulated a computational model for English to Yorùbá text translation process. The modelled translation process was designed, implemented and evaluated. This was with a view to addressing the challenge of English to Yorùbá text machine translator. This machine translator can translate modify and non-modify simple sentences (subject verb object (SVO)).
Digital resources in English and its equivalence in Yorùbá were collected using the home domain terminologies and lexical corpus construction techniques. The English to Yorùbá translation process was modelled using phrase structure grammar and re-write rules. The re-write rules were designed and tested using Natural Language Tool Kits (NLTKs). Parse tree and Automata theory based techniques were used to analyse the formulated model. Unified Modeling Language (UML) was used for the software design. The Python programming language and PyQt4 tools were used to implement the model. The developed machine translator was tested with simple sentences. The results for the Basic Subject-Verb-Object (BSVO) and Modified SVO (MSVO) sentences translation show that the total Experimental Subject Respondents (ESRs), machine translator and human expert average scores for word syllable, word orthography, and sentence syntax accuracies were 66.7 percent, 82.3 percent, and 100 percent, respectively. The system translation accuracies were close to a human expert.
The aim of this paper is to propose an efficient method for identification of web document topics which is often considered as one of the debatable challenges in many information retrieval systems. Most of the previous works have focused on analyzing the entire text using time-consuming methods and also many of them have used unsupervised approaches to identify the main topic of documents. However, in this paper, it is attempted to exploit the most widely-used Hyper-Text Markup Language (HTML) features to extract topics from web documents using a supervised approach.
Hiring an interactive crawler, we firstly try to analyze HTML structures of 5000 webpages in order to identify the most widely-used HTML features. In the next step, the selected features of 1500 webpages are extracted using the same crawler.
Suitable topics are given to each web document by users in a supervised learning process. A topic modeling technique is used over extracted features to build four classifiers- C4.5, Decision Tree, Naïve Bayes and Maximum Entropy- which are separately adopted to train and test our data. The results of classifiers are compared and the high accurate classifier is selected. In order to examine our approach in a larger scale, a new set of 3500 web documents is evaluated using the selected classifier. Results show that the proposed system provides remarkable performance which is able to obtain 71.8% recognition rate.
Universities in South Africa (SA) are facing several challenges due to the influx of students with diverse backgrounds entering the first year. One of such challenges is the use of technologies for teaching and learning. Institutions in the rural areas are flooded with first year students characterized as under-prepared, educationally underprivileged and had little or no access to computer usage prior to their enrolment. These qualities impedes their transition into the computer-based learning system and other technologies that supports teaching and learning. Moreover, the students are not given the needed assistance when enrolled. Orientation programme that would have been a leverage is only informative and not supportive in nature. Thus, an effective solution requires orientation programme to be supportive. It should involve assessing students’ profile during their first year registration to provide them with the needed assistance in terms of technologies usage. This paper conducted a pilot survey over a sample of first year entering students in the University of Venda (UNIVEN). The objective was to assess students in terms of technology-related uses, expectations, experiences, skill levels and training needs. Data collected were analyzed and the results show students’ have not used computers or had experience on technologies for teaching and learning in their previous schools. Additionally, students are only technologically identified with their mobile phones. The study proposed a new programme called First Experience Computer Literacy (FECOL) to facilitate students’ transition into the computer-based learning of the university.[...] Read more.
The main objective of this study is to apply data mining techniques to predict and analyze students' academic performance based on their academic record and forum participation. Educational Data Mining (EDM) is an emerging tool for academic intervention. The educational institutions can use EDU for extensive analysis of students’ characteristics. In this study, we have collected students’ data from two undergraduate courses. Three different data mining classification algorithms (Naïve Bayes, Neural Network, and Decision Tree) were used on the dataset. The prediction performance of three classifiers are measured and compared. It was observed that Naïve Bayes classifier outperforms other two classifiers by achieving overall prediction accuracy of 86%. This study will help teachers to improve student academic performance.[...] Read more.
Big data has emerged as an important paradigm for analyzing and predicting customer’s behavior. Based on the customer’s behavior various campaigns are made to target them. This paper presents a model for telecom companies which will insist them in how to target customers based on analyses of their data collected. Proposed model gathers information from various customers through preconfigured devices and then it manages and provides required insights to telecom companies on basis of which they can target customers of particular segment. Its feedback model in which companies can change their campaign strategy according to the response they receive in real time.[...] Read more.
Virtualization is a core technology used for the implementation of cloud computing. It increases the utilization of resources such as processor, storage, network etc. by collecting various underutilized resources available in the form of a shared pool of resources built through the creation of Virtual Machines (VMs).
The requirements in cloud environment are dynamic therefore there is always a need to move virtual machines within the same cloud or amongst different clouds. This is achieved through migration of VMs which results in several benefits such as saving energy of the host, managing fault tolerance if some host is not working properly and load balancing among all hosts. In this experimental study, effort has been made to analyze the performance of offline and live VM migration techniques with respect to total migration time and downtime of VM migration. Kernel-based Virtual Machine (KVM) hypervisor has been used for virtualization and a series of experiments have been carried out in computer service center of IIT Delhi on their private cloud Baadal. The experiment results show that downtime during live migration is very less in comparison to the offline migration while the total migration time is more in comparison to the offline migration.
Sentiment analysis is a popular research problem to find out within the natural language processing that is dealing with identifying the sentiments or mood of people’s towards elements such as product, text, services and the technology. However, there are few researches conducted on the sentiment analysis of technical article review, so to overcome this deficiency conducts the sentiment analysis over the technical article review and classifying the sentence by overall sentiments that is representing the review is positive or negative. The paper presents the combination of SVM and KNN and find out how much given article sound technically good. The proposed technique is compared with other existing techniques and results shows that the proposed technique is better as compared to the other technique.[...] Read more.