欢迎来到留学生英语论文网

当前位置:首页 > 论文范文 > Education

Ontology and Mobile Learning

发布时间:2017-06-06
该论文是我们的学员投稿,并非我们专家级的写作水平!如果你有论文作业写作指导需求请联系我们的客服人员

Abstract— Mobile learning is gaining a lot of interest in recent years mainly for its convenience and boundless way of learning. Mobile learning is the achievement of e-Learning on mobile computing devices. M-Learning poses new challenges to be taken into account. This is mainly due to device capabilities, limitations of mobile communication channels in addition to the special requirements of mobile learners. An ontology for the M-Learning processes can be setup in disparate ways, but every ontology will include a dictionary with explanation of the terms and indications how the terms are related to another. The user model ontology presents personal information and learning characteristic of the user which has interaction with the system. The information is available for the system to adapt the learning content presentation and navigation for the learner. Service provider offers M-Learning service and it acts like a server. Service user interface holds the user’s information. In this paper, a semantic based ontology mapping for M-Learning resources is proposed. In this analysis, a fast retrieval is achieved by using semantic mapping ontology and it provides high accurate results using clustered repository. An experimental results shows the performance of semantic mapping ontology.

Index Terms— Clustered Repository, Mobile Learning, Ontology, Semantic Mapping, Sense Matching, Service Provider, Service User Interface.

O

I. INTRODUCTION

ntology is defined as a body of formally represented knowledge, which is based on conceptualization: the objects, concepts and other entities that are presumed to exist in some area of interest and the relationships that hold them. The ontology is a conceptual system or basic knowledge system is a higher level of knowledge of the knowledge based abstract. Maintenance of the ontology model includes scalability and portability of the original ontology. Mobile Learning (M-Learning) involves “any activity that allows individuals to be more productive when consuming, interacting with or creating information mediated through a compact digital portable device that the individual carries on a regular basis, has reliable connectivity and fits in a pocket or purse.

M-Learning is a time constraint exercise and usually done on-the-fly using mobile technologies which restrict significantly the presentation features. M-Learning is becoming readily available in a wide range of mobile devices and is beginning to offer the potential for great change in education. In general, ontology mapping requires that the source ontology and ontology representation using the same language. Information retrieval is the interaction between a user and an information retrieval system that consists of three parts,

  • Document Representation
  • A user requirement
  • Matching function

Ontology is being increasingly used for building the applications for the specific domain. Ontology enables users to capture the semantic of the document. Ontology provides a working model of entities and interactions of a particular topic allowing for the modelling of digital collections and user contexts. Its main purpose is to present knowledge within a specific domain and can be used for the refinement of learning process.

The user interface manager provides a user friendly and adaptive interface for communicating with learners. The architecture depicted in Fig 1 exhibits three layers namely, the context layer, the semantic layer and the resource repository layer. The context layer deals with attributes related to the learner, device and network connectivity. The semantic layer consists mainly of an ontology reasoning component which uses the contextual information sensed by the context acquisition and management module from the user interaction to drive the reasoning process.

Fig 1. The three level architecture of M-Learning System.

Extraction of useful semantics in mobile information for indexing and fast retrieval is another are related to context awareness. Inverted file indexing has been extensively used in information retrieval. An inverted file is used for indexing a document collection to expedite the searching process. The structure of an inverted file consists of two components, namely the vocabulary and the posting list. The vocabulary is composed of all distinct terms in the document collection. For each term, a list of all documents containing this term is stored. The set of all these lists is called the posting list.

II. Related Work

Shvaiko and Euzenat designed the state of the art in ontology matching and made some analytical and empirical comparisons. Ontology matching is a solution to the semantic heterogeneity problem. An ontology typically provides a vocabulary that describes a domain of interest and a specification of the meaning of terms used in the vocabulary. Alzaabi, et al described a M-Learning system that generates multimedia structured learning content from the web, packages it into lightweight learning objects and delivers it on the learner’s mobile handset [1]. M-Learning is a stand-alone learning paradigm that has particular educational characteristics, learning environment constraints and supporting technology. Ontology based learning design is an important ingredient of next generation learning systems. Scott and Benlamri [2] described a cost effective infrastructure for building ubiquitous collaborative learning spaces.

The system described in this paper, was designed to keep the focus on the learning material by offering flexible and efficient learning interactions. The system was designed to implement as much of the functionality for a regular, nonsupernodal peer as possible using web technologies. Yee, et al [3] proposed a generic semantics based service oriented infrastructure. The proposed architecture comprises a knowledge aggregation subsystem and a querying subsystem that are loosely coupled. In this paper, the instant search function was designed specifically to occupy the user’s idle time. It allows the user the fun of trying out of various queries, and receiving disparate responses at each time. It is based on the preposition that M-Learning was usually done in an adventitious manner, when the user is waiting for something.

Xu and Zhang [4] presented the analysis on data integration of the semantic web based on ontology learning technology. Ontology can be used as a universal semantic model web information and application in web information extraction. Web the process of information extraction based on ontology is a web data mapping information in the source to the process of ontology concept. Aljohani and Davis [5] proposed a paper for significance of semantic web in expediting Human Computer Interaction (HCI) in mobile. This paper has theoretically provided useful insights into the importance of the semantic web in enhancing the interaction between mobile learners and mobile devices in M-Learning and ubiquitous environment. Winkler and Herczeg designed the M-Learning Exploration System (MoLES) [6] in semantically modeled ambient learning spaces. The design of the application emerged by adhering to requirements set down by systematic constructivist pedagogy.

Yarandi, et al implied a personalized learning system by analyzing the ability of the learner based on items response theory [7]. Item response theory is a model based approach to select the most appropriate items for examinees based on mathematics relationship between abilities and item responses. This study presented a personalized mobile learning system according to the ability of the user. Frederick and Tan [8] presented a location based learning management system for adaptive and personalized mobile learning. One of the main problems in providing location based mobile learning is the availability of location ware and context aware tagged learning system. Razmerita [9] presented a generic Ontology based User modeling framework (OntobUmf). This framework models the behavior of the users and classifies its users according to their behavior.

Gaeta, et al [10] described an approach to improve assessment in organizations by exploiting semantic web and computational intelligence techniques. Yarandi, et al [11] proposed a new adaptive mobile learning model for learning new languages based on the ability of learners. An ontology based knowledge modelling technique was proposed to classify languages learning materials and describe user profiles in order to provide adaptive learning environment. Mercurio, et al [12] introduced a novel approach for adaptive e-learning content to the features of the device used by learners to perform the activities. Asangansi and Poslad [13] presented a user modeling and personalization framework for providing personalized services to users through their mobile devices during large sports events. The user profiling system consists of the user profile ontology, profile learning ontology, the user profile and the profiling proxy. Verbert, et al presented a survey of context aware recommender systems that have been deployed in Technology Enhanced Learning (TEL) settings[14]. In TEL, such enumeration have been proposed as an attempt to define the context of the learner as an operational term. Many enumerations were defined for mobile learning applications.

Tao and kim [15] proposed a Discriminative Vocabulary Learning for landmark recognition based on the context information acquired from mobile devices. In this analysis, an image rank technique and an iterative code word selection algorithm were developed for DCV learning. Done, et al [16] proposed a paper about human gene ontology annotations using semantic analysis. This paper explored the use of vector space model (VSM) weighting schemes in the context of a semantic analysis of biological annotations. Alila, et al [17] developed an adaptive system based on the semantic modeling of the learning content and the learning context. The use of this ontology facilitates context acquisition and enables a standard based learning object metadata annotation. Ontologies offer a way to cope with heterogeneous representations of resources on web and their interoperability. Choi and Kang presented an adaptive learning system, which supports collaborative learning based on a location based social network and semantic modeling [18]. This paper proposed a system that supports the construction of a social network service using the location information of the smart phone in mobile learning. Sunitha, et al [19] suggested a new approach to extract the underlying text concepts, which are consistent with the low dimensional manifold structure. Domain ontology is a kind of ontology which is used to represent the knowledge for a particular type of application domain. Ontology matching must be redefined to finding a concept with the closest mining in the other schema, when an equivalent one does not exist. Allioui and Beqqali [20] recommended a O’Neurolog technique, to capture semantic knowledge a valuable in neurology domain in order to assist users, when querying neurology knowledge bases in mobile environment.

III. Proposed Method

Mobile learning is the flexible way to teach a new language as it is ubiquitous, readily accessible anywhere and anytime which makes learning a rewarding lifelong process. M-Learning deals with “any activity” that allows individuals to be more productive when consuming, interacting with or creating information mediated through a compact portable device that the individuals carries on a regular basis, has reliable connectivity and fits in a pocket or purse. A fundamental challenge facing the m-learning research community is the creation of pedagogical learning models to handle specificity of mobile learning and the inherent constraints of mobile devices.

Fig 1. Illustrates the architecture of the proposed semantic based ontology mapping for M-Learning resources.

The system contains three components, namely

  • Service Provider
  • Service User Interface
  • User
  1. Service Provider

Service provider offers M-Learning services. M-Learning is learning supported by mobile devices and intelligent user interfaces. The same composite service can be realized by various service components for disparate users and disparate devices. The service profile containing the information about how the service should behave towards specific users and devices. Service discovery is dependent on a realization of logic handling and employing the service equivalence relation. This includes both semantic and syntactic discovery. It is necessary to define ontologies that describe the service concepts in all service domains that should be used to provide mobile services. Service providers distribute semantic descriptions of their service capabilities and interaction protocols, which intended consumers can then interpret when electing relevant services and when formulating their interactions with those services. It must define the capabilities and constraints on offered services.

  1. Service User Interface

Fig 2. Semantic Based Ontology Mapping for M-Learning Resources

  1. Semantic Mapping

Ontology is being increasingly used for building the applications for the specific domain. Ontology enables users to capture the semantic of the documents. Semantic similarity is the weight of relatedness between any two concepts; so that the relation between terms can be examined. Each concept is related to each other in ontology hierarchy; so semantic query expansion can be performed through the concepts that match with query keywords.

IV. Performance Analysis

  1. Information Retrieval – Term Frequency

Fig 3. Information Retrieval – Term Frequency

  1. Information Retrieval – Semantic Mapping

Fig 4. Information Retrieval – Semantic Mapping

  1. Relevancy Analysis

Fig 5. Relevancy Analysis

  1. Semantic Comparisons

Fig 6. Semantic Comparisons

  1. Frequency Comparisons

Fig 7. Frequency Comparisons

  1. Relevancy Level

Fig 8. Relevancy Level

V. Conclusion and Future Work

上一篇:Code Switch in Malaysia and Cellphones in classrooms 下一篇:Parenting in the Faith