Aditya Khamparia

Knowledge and intelligent computing methods in e-learning

E-learning is the use of technology that enables people to learn at anytime from anywhere. Various single knowledge-based methods KBM such as rule-base reasoning RBR and case-base reasoning CBR; and intelligent computing methods ICM such as genetic algorithm GA, particle swarm optimisation PSO, artificial neural network ANN, multi-agent systems MAS, ant colony optimisation ACO, fuzzy logic FL etc. Integrated KBM-ICM methods such as GA-CBR, ANN-RBR, GA-Ontology and ANN-Mining have been used in various e-learning contexts such as: the learning path generation, adaptive course sequencing and personalisation of recommended learning object etc. We have made a study of different individual KBM and ICM methods; and integrated KBS-ICM methods applicable to e-learning domain right from the mid 1990s to 2014. The study is presented in a tabular form, showing the KBM-ICM methods, e-learning problems to be addressed, specific features and the implementation in the e-learning domain. From the results, it is observed that a single KBM is not deployed to solve any e-learning problem. A single ICM and integrated KBM-ICM methods are used to solve various e-learning problems. The study and its presentation in the context help the novice researchers to resume their work in the area of e-learning systems.

A novel method of case representation and retrieval in CBR for e-learning

In this paper we have discussed a novel method which has been developed for representation and retrieval of cases in case based reasoning (CBR) as a part of e-learning system which is based on various student features. In this approach we have integrated Artificial Neural Network (ANN) with Data mining (DM) and CBR. ANN is used to find the relationship between student characteristics and learning performance, DM to generate classification rules for learning outcomes which are further used to generate cases for the case base and CBR for reasoning. This adaptive system helps in facilitating the course content of different difficulty level to individuals according to their features. The result shows the above method provides the learning material to student as per their need and helps them to enhance their learning.

Architecture based Comparison of Semantic Web Service Composition Processes

ABSTRACT Semantic web services development become rapidly increased as dynamic changes are occurred. Various approaches are adopted to develop composite service systematically. This paper aims to make development process easier by classifying the literature on web services composition based approaches like selection, discovery, orchestration, choreography, mediation, automatic composition to facilitate the end to end semantic web service composition easier. Applying semantics in web process cycle helps to address critical issues in reuse, integration and scalability. In order to find best approach, various composition approaches on these requirements were evaluated and suggestions were provided on what approach can be used in which scenario to achieve best results. Keywords Semantic web service, Service Composition approaches, Selection, Discovery, Orchestration, Choreography. 1. INTRODUCTION Semantic web is an extension of current web, in which information is given well defined meaning, better enabling computer and people to work in cooperation [1]. The objective of used to find services available for clients input request and research around semantic web service is to facilitate automatic handling of web services. Semantic web transforms the web into repository of computer readable data, while web services provide tool for automatic reuse of that data. Sometimes single service component unable to satisfy user needs then some mechanisms like discovery [4], selection [18], mediation [12], matchmaking etc. are used for finding service component and semantic composition helps to aggregate the component of various services according to tasks. In previous work we have made a survey on different approaches of semantic web services [18]. The main objective of this paper is to discuss some existing composition techniques like Workflow based, Artificial Planning, Context based, Agent based, Ontology based, Orchestration and Choreography to solve semantic web composition problem with their attributes. In addition, we have also classified and compared different web service composition methods. Apart from introduction part, section 2 deals with various composition based method for semantic web service, section 3 covers framework of service composition methods, section 4 covers classification and comparison among several approaches and conclusion in section 5.

Blended e-Learning Training (BeLT): Enhancing Railway Station Controller Knowledge

With the growing economy, e-learning consequently gained increasing attention as it conveys knowledge globally with improved interactivity, assistance and reduced costs. For the past few years, accidental challenges have become the severe problem with railway units due to irresponsibility, lack of knowledge and improper guidance of station controllers (learners). While focusing on e-learning technologies railway units failed to admit learners need, cultural diversity and background skills by creating ethnically impartial e-learning environments, which resulted in inadequate training and degraded performance. The purpose of this study is to understand the vision of a global diverse group of station traffic controllers about e-learning courses developed by their individual railway units. The opinions of these officials have been verified by questionnaires on the basis of course organization, course accuracy, course effectiveness, course relevance, course productivity and course interactivity. The results obtained show that the developed e-learning course was highly helpful, interactive, creative, and user-friendly for learners. This leads to making e-learning conquered among independent learners.

Performance analysis on agriculture ontology using SPARQL query system

Ontologies are used to represent domain knowledge with help of object, their behaviour and properties. This paper represents web enabled approach on agriculture semantic web using SPARQL and specified tools to increase productivity of farmers. This work focuses on assessment of query optimization tools and results predicted from them to determine the suitability of each method for different users where structured ontologies are used as querying aids for agriculture based dataset.

CBR based approach for adaptive learning in E-learning system

C Programming also known as Structured programming is one of the most widely used programming languages of all time. Our approach proposes an adaptive learning based C programming e-learning system that considers various student characteristics. Case based reasoning is used to optimize and improve learning performance of students. Different types of errors like syntax, logical and application usage feasibility are categorized at different levels on basis of mistakes committed by students while designing programs. Feasibility of proposed system governed by comparing the result of students those are in control group with the adaptive learning experimental group. Results show that the experimental group used e-learning system had better performance than control group who relied on c programming regular course to optimize learning outcome and performance of students.

Effects of visual map embedded approach on students learning performance using Briggs–Myers learning style in word puzzle gaming course

Abstract Many researchers have indicated in their studies that there is a need to integrate knowledge construction tools to improve knowledge and enhance learning performance of students in life science courses. Due to improper integration of learning strategies, educational games effectiveness could be affected in comparison to conventional interactive systems. In present study, a visual map embedded matching based interactive word puzzle system was deployed to reduce students cognitive load, enhance learning motivation skills to gain understanding on novel concepts, improve personality to foster interpersonal skills, improve learning achievements and compare them with conventional puzzle system in intelligent gaming courses. The efficacy of presented approach has been assessed by designing an experiment which involves mixed dimensions of Briggs–Myers learning style. The experimental results showed that the approach based on visual maps can improve overall students grooming and they could adopt gaming based educational technology with ease in contrast to traditional learning systems.

Effects of visual mapping placed game-based learning on students learning performance in defence-based courses

Many recent studies have reported that improper integration of learning strategies with digital gaming scenarios, affect or might even worsen the effectiveness of digital computer games used for educational purposes when compared to the traditional or technology enabled instructional systems. In this study, a visual mapping game-based learning environment is developed to reduce students anxiety and cognitive load, thereby enhancing their motivation level to learn a concept, overall personality to foster interpersonal skills and knowledge on life skills to encourage practical application of technology, in learning defence and military-based courses. The proposed approach efficacy has been evaluated by conducting an experiment on defence-based courses. On basis of experimental results, it is concluded that the gaming approach based on embedded visual map can significantly improve a students composite grooming. Students who adopt the visual mapping approach can easily understand the usage of technology in educational systems as compared to those who employ traditional learning approach for the same.

Comprehensive Analysis of Semantic Web Reasoners and Tools: A Survey.

Ontologies are emerging as best representation techniques for knowledge based context domains. The continuing need for interoperation, collaboration and effective information retrieval has lead to the creation of semantic web with the help of tools and reasoners which manages personalized information. The future of semantic web lies in an ontology which describes relationship between terms, and will serve as a foundation for establishing a shared understanding between applications. In this paper, we surveyed and compared numerous reasoning models, ontology tools and express well defined Web services for user with different annotations. We compared latest and traditional reasoners like Pellet, RACER, HermiT, FaCT++ with respect to their features supported by them. Similarly, different variety of ontology development, querying and designing tools like Protégé, Jena, SWOOP, Oiled, Apollo, etc. have been compared to predict the inference support through utilizing several features backed up by them. Finally, this paper presents visualized comparison among all reasoners, tools with the aid of their supporting features or characteristics and classified them as strong, average or weak. In addition, we have also classified the reasoner on the basis of their response time and it was observed that Pellet has lowest response time whereas Racer has highest response time.

Architecture and performance based comparison of semantic web service processes

The Semantic Web is a compilation of various technologies designed to work together. Research on Semantic Web proposes to advance individual web services or technologies to integrate them to promote rapid development of semantic web services as flexible changes are occurring. Diverse methods are considered in order to construct systematic composition of services. The intent of paper is to differentiate various web service based composition approaches like discovery, selection and ontology mapping at end user level to provide high level web services. The integration of semantics in web service cycle addresses the variety of critical issues in reuse, integration and scalability. The different approaches are comparable on the basis of three parameters costs, computational overhead, accuracy and performance index. The computed results are shown in graphical form.