Mining VRSEC student learning behaviour in moodle system using datamining techniques

Predicting the performance of the students and helping them to improve their knowledge in subjects is one of the jobs of the educational universities. It is a laborious work to track many students in the universities. So, the universities started using content management systems to track the record of the student’s marks, grades and performance. Even then, the tutor have to evaluate manually to finalize the list of low grade students. As this is a problematic method, in this paper, the best method is explained for this purpose. There are many e-learning systems helping the institutions to evaluate their student’s skills. In this paper, the comparison for those existing ones are made and the better one is selected i.e., Moodle.

Being an open source software, providing the users flexibility in updating the tasks and excelling in its security it is opted to store VRSEC student’s performance records. The further step is to analyze the students’ performance and predict the grades. For this, Rapid miner an open source tool is used. Primarily the records of the VRSEC students are stored in the Moodle and are then extracted into Rapid miner environment. Certain parameters are defined to complete the pre-processing concept. Then classification algorithm is applied to predict the grades of the students. By applying various classification algorithms, it is observed that decision tree algorithm gave greatest accuracy of 85% and with weighted mean of recall and precision as 75.00% and 89.63% respectively.

An Efficient Approach for Supervised Learning Algorithms Using Different Data Mining Tools for Spam Categorization

Spam is the major problem and a big challenge for researcher to reduce spam. Spam is commonly defined as unsolicited email messages and the goal of spam categorization is to distinguish between spam and legitimate email messages. This paper shows classification of spam mail and solving various problems is related to web space. This paper also shows measures parameter which are helpful for reduce the spam or junk mail. Many machine learning algorithm are using to classified the spam and legitimate mail.

This paper proposes the best classifier and better classification approach using different data mining tools using bench mark dataset. The dataset consist of 9324 records and 500 attributes used for (training and testing) to build the model. In this paper, a procedure that can help eliminate unsolicited commercial e-mail, viruses, Trojans, and worms, as well as frauds perpetrated electronically and other undesired and troublesome e-mail. This paper shows analyzing of different supervised classifiers technique using different data mining tools such as Weka, Rapid Miner, and Support Vector Machine. This paper shows Weka data mining tool give highest accuracy over different data mining tools.

A Novel Application Framework for Educational Data Mining Towards Automated Learning System

Educational Data mining (EDM) is playing a vital role in education management system as well in course management system with its theoretical and practical aspects. Here the system can store enormous amount of information about the peoples who are so called learners and learning creativities. Since resources available for learning creativities are vast and huge, hence the Data mining usage is necessary. The maxim of our work is to propose an automated learning system in EDM to accomplish the appropriate learning CMS to the learners.

Our proposed system is deployed in application of EDM for the University in order to automate the whole eLearning CMS system with an aggregate of 350 faculties and 8500+ learners. We have achieved our result through a cluster developed using RHadoop and association of binded resources using Rapid miner 5.0. Here various DM techniques were adopted and trained in order to achieve higher accuracy rate.

Smartphone Security: An overview of emerging threats.

The mobile threat landscape has undergone rapid growth as smartphones have increased in popularity. The first generation of mobile threats saw attackers relying on various scams delivered through SMS.

As the technology progressed and Web browsers, e-mail clients, and custom applications became standard on smartphones, attackers started exploiting new possibilities beyond traditional e-mail spam and phishing attacks. The landscape continues to evolve with mobile bitcoin miners, botnets, and ransomware.

Empirical rapid and accurate prediction model for data mining tasks in cloud computing environments

With the arrival of big data and cloud computing as a computing concept, it is becoming ever more critical to efficiently choose the most optimum machine on which to execute a program, for example in the healthcare environment. This process of choice is also complicated by the fact that numerous machines are available as virtual machines. Hence, predicting the most optimum choice of machine based on a target application is a challenge.

Prediction techniques consume large amount of computing resources when operating with multi-dimensional data that can cause long delays compounded by cross validation process in evaluating and choosing the most optimum prediction model. We propose a model of prediction techniques to predict and classify some of the health datasets to retrieve useful knowledge to illustrate how a data miner can choose a suitable machine especially in cloud environment with good accuracy in a timely manner. Our results show that the execution time has an inverse relation with the use of resources of a machine and the accuracy of prediction could be different from one machine to another using the same predicting technique and dataset.

Production strategies for maximizing recovery from a strong bottom water drive reservoir

This paper examines the effect of production rates on the ultimate gas recovery from a high permeable strong bottom water drive reservoir. A real gas field simulation model was history matched applying manual history matching techniques .Well behavior and recovery were observed for different prediction scenarios. It was found that cumulative recovery with additional wells would be higher during the initial years but ultimate recovery will be lowest because of a faster rate of water table movement.

Maximum ultimate recovery can be achieved by continuing the production with timely and sequential workover of high water cut wells to plug back the lower perforations. High permeability and rapid movement of water table have made the reservoir highly rate sensitive and lower production rate may result in higher ultimate recovery.

Analysis for classification of similar documents among various websites using rapid miner

The Web was intended to improve the management of general information about accelerators and experiments. It is also considered the most precious place for Information Retrieval and Knowledge Discovery. While retrieving information through queries inserted by the users, a search engine results in a large and non manageable collection of documents. Several web mining tools are used to classify, analyse and order the documents so that users can easily navigate through the search results and find the desired documents.

A more efficient way to organize the documents can be a combination of similarity and ranking, where similarity can group the documents in terms of contents or distance and ranking can be applied for ordering the pages within each cluster or set. Based on this approach, in this paper, an analysis is being shown that provides ordered results in the form of similar documents among several set of website which are of users interest using an open source web mining tool called as rapid miner. This approach helps user to restrict their search to navigate less number of pages instead of huge documents in particular which are of their interest.

Building and evaluating P2P systems using the Kompics component framework

We present a framework for building and evaluating P2P systems in simulation, local execution, and distributed deployment. Such uniform system evaluations increase confidence in the obtained results. We briefly introduce the Kompics component model and its P2P framework. We describe the component architecture of a Kompics P2P system and show how to define experiment scenarios for large dynamic systems. The same experiments are conducted in reproducible simulation, in real-time execution on a single machine, and distributed over a local cluster or a wide area network.

This demonstration shows the component oriented design and the evaluation of two P2P systems implemented in Kompics: Chord and Cyclon. We simulate the systems and then we execute them in realtime. During realtime execution we monitor the dynamic behavior of the systems and interact with them through their Web-based interfaces. We demonstrate how component-oriented design enables seamless switching between alternative protocols.

Dynamic power and performance back-annotation for fast and accurate functional hardware simulation

Virtual platform prototypes are widely used for early design space exploration at the system level. There is, however, a lack of accurate and fast power and performance models of hardware components at such high levels of abstraction. In this paper, we present an approach that extends fast functional hardware models with the ability to produce detailed, cycle-level timing and power estimates. Our approach is based on back-annotating behavioral hardware descriptions with a dynamic power and performance model that allows capturing cycle-accurate and data-dependent activity without a significant loss in simulation speed. By integrating with existing high-level synthesis (HLS) flows, back-annotation is fully automated for custom hardware synthesized by HLS.

We further leverage state-of-the-art machine learning techniques to synthesize abstract power models, where we introduce a structural decomposition technique to reduce model complexities and increase estimation accuracy. We have applied our back-annotation approach to several industrial-strength design examples under various architecture configurations. Results show that our models predict average power consumption to within 1% and cycle-by-cycle power dissipation to within 10% of a commercial gate-level power estimation tool, all while running several orders of magnitude faster.

User-specific QoS aware scheduling and implementation in wireless systems

In this paper, we explore user-specific QoS requirements and associated schedulers that are very critical in optimizing the spectral allocation for wireless systems. Two user-specific QoS aware schedulers are proposed that considers the user-specific QoS requirements in the allocation of resources. Depending upon whether improving the MOS (Mean Opinion Score) or both the system capacity and the MOS is the goal, a MOS improvement scheduler or MOS-plus-capacity improvement scheduler is proposed for VoIP applications.

Detailed system implementation analysis based upon LTE system specification is performed, and it is shown that very modest modifications to current protocols are needed to support user-specific QoS aware scheduling. System simulations are performed for a set of VoIP users assigned specific QoS target levels in the OPNET Modeler for LTE systems. Simulation results show that appreciable MOS or/and system capacity improvement can be achieved if such user-specific QoS requirements are considered in the proposed user-specific QoS aware schedulers. Also, it is shown that the scheduling period of up to 1000 ms doesn’t significantly impair the system performance.