A. Sai Sabitha

Delivery of learning knowledge objects using fuzzy clustering

Abstracte-Learning industry is rapidly changing and the current learning trends are based on personalized, social and mobile learning, content reusability, cloud-based and talent management. The learning systems have attained a significant growth catering to the needs of a wide range of learners, having different approaches and styles of learning. Objects delivered by these systems should provide a variety of learning content to satisfy different learners and should also have a pedagogical value than simple course content to empower learning. The Knowledge Objects of Knowledge Management Systems can be combined and delivered with existing Learning Objects of Learning Management System to provide better and more holistic user experience. Choosing a suitable object in accordance with learner category is a complex task. The paper encompasses data mining approach, fuzzy clustering technique to combine Learning and Knowledge objects based on attributes of metadata. These objects are further mapped with various learning styles and an appropriate set of objects are delivered to the learners. Thus, a personalized and more authentic learning experience is achieved emphasizing the content reusability.

Chronic Kidney Disease analysis using data mining classification techniques

Data mining has been a current trend for attaining diagnostic results. Huge amount of unmined data is collected by the healthcare industry in order to discover hidden information for effective diagnosis and decision making. Data mining is the process of extracting hidden information from massive dataset, categorizing valid and unique patterns in data. There are many data mining techniques like clustering, classification, association analysis, regression etc. The objective of our paper is to predict Chronic Kidney Disease(CKD) using classification techniques like Naive Bayes and Artificial Neural Network(ANN). The experimental results implemented in Rapidminer tool show that Naive Bayes produce more accurate results than Artificial Neural Network.

An ensemble approach in converging contents of LMS and KMS

Currently the challenges in e-Learning are converging the learning content from various sources and managing them within e-learning practices. Data mining learning algorithms can be used and the contents can be converged based on the Metadata of the objects. Ensemble methods use multiple learning algorithms and it can be used to converge the Learning Objects from Learning Management Systems (LMS) and Knowledge Objects from Knowledge Management System (KMS). This can increase the performance of the learning system, especially when there is different content available from a variety of models. In this research, Data mining ensemble techniques are used so that an appropriate learning content is delivered to the learner. By converging, the learning content from various sources the Learning system pedagogies can also be revolutionized and a right learning path can be provided to the learners. This research work uses various classification techniques for converging and are evaluated using statistical measures.

Learner Groups in Massive Open Online Courses

ABSTRACT The open nature of Massive Open Online Courses (MOOCs) attracts a large number of learners with different backgrounds, skills, motivations, and goals. This has brought a need to understand such heterogeneity in populations of MOOC learners. Categorizing these learners based upon their interaction with the course can help address this need and suggest possible improvements in course design and delivery. In this article, the K-means clustering technique with careful seeding is used to obtain clusters of learners having similar interaction in the course. Learners are grouped based on their interaction with course material, video lectures, discussion forums, and assessments. In the analysis of thirteen courses, the proposed method identified learners’ classes as Uninterested, Casuals, Performers, Explorers and Achievers. Each class of learners had distinct interaction with the course and followed a certain learning approach. The learners’ classes were mapped to the standard surface, deep, and strategic learning approaches.This article also highlights the data preparation phase and its importance in data mining.

Application of learning analytics using clustering data Mining for Students' disposition analysis

Learning Analytics (LA) is an emerging field in which sophisticated analytic tools are used to improve learning and education. It draws from, and is closely tied to, a series of other fields of study like business intelligence, web analytics, academic analytics, educational data mining, and action analytics. The main objective of this research work is to find meaningful indicators or metrics in a learning context and to study the inter-relationships between these metrics using the concepts of Learning Analytics and Educational Data Mining, thereby, analyzing the effects of different features on student’s performance using Disposition analysis. In this project, K-means clustering data mining technique is used to obtain clusters which are further mapped to find the important features of a learning context. Relationships between these features are identified to assess the student’s performance.

A review on knowledge extraction for Business operations using data mining

The Knowledge Economy is of great importance in various business fields which had resulted in increased demand for the people having high order thinking skills and unpredicted-problem-solving at workplace. Every organization has a Knowledge Management (KM) department as Knowledge itself is a precious resource of the organization. The latest trends in KM include Customer and Vendor knowledge, Mobile Applications for KM, Collaborative Knowledge Management System (KMS) and Social intranet which can be integrated with business processes. The knowledge extracted can be stored and processed to enhance business intelligence. KM works with various business fields like Marketing, Sales, Human Resource, Operations, Supply Chain, etc. Due to frequent changes in operation of processes and Quality policies, the knowledge extracted from these processes can play a vital role in enhancing business processes. In this paper we had proposed various models of KM & Business Operations and the need of data mining technique which can be used to deliver appropriate knowledge to the user.

Analysis and clustering of PingER network data

The PingER project was started by the SLAC National Accelerator Laboratory, Stanford, California for the purpose of monitoring end to end network performance. For the last eighteen years PingER has generated an enormous amount of data that has been stored in space separated files. However due to the difficulties faced in retrieving data efficiently, it has been proposed that all the data be put into the form of RDF triples. Interpreting and analyzing such large volumes of data becomes a primary concern. By making using of clustering algorithms new and interesting patterns can be observed in the data sets. Outlier analysis can be performed giving insight to the exceptions occurring in the dataset and analyzing the probable causes of such. Patterns could be observed based on the country to which the data belongs and comparisons can be drawn between the patterns between the different countries.

Connecting the Gap Between Formal and Informal Attributes Within Formal Learning with Data Mining Techniques

Formal and informal attributes are two distinct forms of learning which famed on the basis of the learning content, by where, when, and how learning happened. Formal attributes is a traditional learning which has official course work which should be completed in specified time. This study aimed at evaluating the challenges that students face while working for achieving good grades in exams. Data mining techniques are used to identify the challenges. The methods of collection working in this study were qualitative which involved testing and comparing.

An Efficient Way to Find Frequent Patterns Using Graph Mining and Network Analysis Techniques on United States Airports Network

We are currently in the Information Age where massive amounts of data is being collected and analyzed to find interesting and frequent patterns. The need for mining data has been steadily increasing over the past few years. Graphs are one of the best studied data structures in the fields of mathematics and computer science. And due to this, in the recent years graph-based data mining has become quite popular. Graph data mining uses the graph nodes and the links between them to represent the entities, their relationships with other entities and their attributes and discovers interesting patterns in the graphs. Transportation networks are networks of routes from one location to another through various modes of travel. In this article, we use a transportation network of airports in United States of America and apply graph data mining techniques and network analysis techniques on US airports and flights datasets.

Terrorist Attacks Analysis Using Clustering Algorithm

The factors that are affecting the world are terrorism, economy, political changes, pollution, etc. Out of which terrorism is one the biggest factor which is affecting the economy, society along with loss of precious human lives. In this paper, the data mining techniques are implemented to infer certain trends and pattern of terrorist attacks in India. K-means clustering is used to determine the year in which the terrorist groups were most active and also which terrorist group has affected the most. The experimental result is implemented in Rapidminer tool to determine the active group and the affected year.