Prof. Arindam's Blog

Edutainment and collaborative interaction are powerful paradigms to promote learning in young kids. In the age of transformation we are more dependent on reality of technology. In our country children are budding with conventional mode of learning and getting education in schools and colleges. In the current scenario, existing teaching model is not sufficient for our children. Statistics shows that today’s children are digital native – born in the digital world as opposed to a person in his 30s being a digital immigrant. Students are using sophisticated gadgets at a young age. This may puts pressure on the education system to make content available on gadgets rather than on black boards. Multimedia animation technology is developing very rapidly which need to be synchronized and redirect also for education industry. Market survey report says foremost children are fond of animation. My research is deeply focused to build up a model which can incorporate learning through entertainment. My target learner group is kids. The model will provide educative atmosphere through amusement by capturing the affective state of learner. Through this technology system can automatically suggest the next learning module. So edutainment has emerged into the picture. Appropriate environment building with feedback technology, Learning Management System with auto identification module, is the continuous research area.

In our country children are budding with conventional mode of learning and getting education in schools and colleges. In the current scenario, existing teaching model is not sufficient for our children. Statistics shows that today’s children are digital native – born in the digital world as opposed to a person in his 30s being a digital immigrant. Students are using sophisticated gadgets at a young age. This may puts pressure on the education system to make content available on gadgets rather than on black boards. Now education exposed more flexible way – education for all. If we provide education to all then same learning model cannot fit but different pedagogy has to be chosen for different learner group. Moreover the shortage of skilled teachers is also one reason, so technology is the alternative. Information Technology is developing at such rapid way that if we are not avail we will go down. Our government is also forcing to introduce ICT (Information Communications Technology) in school and college. By compiling these all instances we can conclude that Technology Enabled Learning is compulsory.

If you need compelling evidence of how information technology is affecting the delivery of learning, you need look no further than higher education, where many colleges and universities are experiencing double-digit growth in technology-enabled courses and programs. Government agencies have discovered that technology assists with learning at a significant cost savings.

E Learning is emerging as a heavily learner-centric, emphasizing pervasive and personalized learning technology. Affective learning outcomes in a nutshell, involve attitudes, motivation, and values. In the same tune we can also define the affective E-learning, as a strategy, which implies recognition of learner’s emotion and selection of pedagogy in a best possible way. For the best delivery, learner’s affective state needs to be identified where the key solution is emotion recognition. The work focuses on emotion detection using biophysical signals which further explores the evolution of emotion during learning process, to generate a feedback that can be used to improve learning experiences. The research is deeply focused into the aspects of operative content delivery mechanism by using physiological facial signals for the detection of learner’s emotion but without detecting the face. It is proposed that a key technique to detect learner’s facial expression, based on neural network classification and selection of appropriate learning style, which shows reasonable results in comparison with the other existing systems. The result manifests that the recognizer system is effective.

A fundamental tenet of this design is that one method does not fit to all learners. Different pedagogy has to be chosen for different learner. Facial emotion recognition is desired to get the effective state of learner. The proposed model can able to recognize learners’ emotion to identify the effective state. In this article it is proposed a technique to detect learner’s facial expression based on neural network and also selection of the course using SVM (Support Vector Machine) and PCA (Principal Component Analysis). As per the psychological theory that human emotions – can be classified into twelve typical emotions ‘‘happy,’’ ‘‘sad,’’ ‘‘approving,’’ ‘‘disapproving,’’ ‘‘proud,’’ ‘‘ashamed,’’ ‘‘grateful,’’ ‘‘angry,’’ ‘‘impressed,’’ ‘‘confused,’’ ‘‘remorseful,’’ and ‘‘surprised’’. To select the appropriate course of delivery by the system, it is needed to identify the learner’s psychology. There are number of parameters involved for psychological emotion. But the work is to scan the facial gesture and that can correlate with emotions using neuro-fuzzy logic. After identification of the psychological emotion system that will automatically detect the learning style. That detection will be held automatically. The total proposal fastens in twofold operations. One is identification of learners’ emotion and second is selection of learning style.

The technological landscape of modern E-Learning environment is dominated by Learning Management System. Efficient and effective handling of text, audio and video documents depends on the availability of indexes. Manual indexing is unfeasible for large video collections. Content organization is also an important issue. In the existing environment, Learning Management System, there is a lack of proper searching of contents. The multimedia contents are stored along with the subsequent text information in the database. When learner searches the multimedia content then it searches that text from the database. In case of spontaneous uploading of multimedia content along with instant retrieval is not possible. It is not acceptable for content based retrieval. The Grid architecture is used which is based on ontology technology, Grid technology, Semantic Web technology. The content based retrieval is categorized into basic three types of multimedia content Audio, Video and Text. For each category same type of searching methodology is used.

Architecture on E-Learning Grid has been proposed by Victor Pankratius, Gottfried Vossen [1] in the year 2003. In that article they proposed the basic architecture of Grid Computing (Figure 1). The grid computing paradigm essentially aggregates the view on existing hardware and software resources. The proposed architecture is the combination of Core Grid Middleware and Learning Management System which content two set of database one maintain in grid level operation and another one maintain the content retrieval. In this article our focus is to present efficient and fast search the content as per the learner’s requirement. It can only be done if I can organize the content with appropriate architecture.

Figure 1: Learning Management System (LMS) – Grid Model

I reviewed learning management system architecture and their file system. Content organization is one of the major concerns in E-Learning paradigm. E-Learning Portal has resulted in a substantial progress in the multimedia and storage technology that has led to building of a large repository of digital image, video, and audio data. There is a controlled vocabulary or thesaurus provided. Hybrid search systems are also found among search engines; however, it is the popularity of full text searching that has changed the road map to information access. However, searching for a multimedia content is not as easy because the multimedia data, as opposed to text, needs many stages of pre-processing to yield indices relevant for querying. Since an image or a video sequence can be interpreted in numerous ways, there is no commonly agreed-upon vocabulary. Thus, the strategy of manually assigning a set of labels to a multimedia data, storing it and matching the stored label with a query will not be effective. As per the grid architecture [1], the large volume of video data makes any assignment of text labels a massively labor intensive effort. In recent years, research has focused on the use of internal features of images and videos computed in an automated or semi-automated way [2]. Automated analysis calculates statistics, which can be approximately correlated to the content features. The common strategy for automatic indexing had been based on using syntactic features alone. However, due to its complexity of operation, there is a paradigm shift in the research of identifying semantic features [3]. Web based courses are now developed and presented through so-called Learning Management Systems such as Blackboard or WebCT (Web Course Tools). Learning Management systems are powerful integrated system that supports a number of activities performed by teachers and students during the E-Learning process. Our proposed searching algorithm is based on the proposed architecture on E-Learning Grid [1]. This article put forward the efficient searching mechanism to retrieve data from the content based portal

References:

[1] Victor Pankratius , Gottfried Vossen, “Towards E-Learning Grids: Using Grid Computing in Electronic Learning”, Pages 4-15,Oct 2003

[2] M. Flickner et al., “Query By Image and video Content: the QBIC system”, IEEE Computer, September 1995, pages 23–32.

[3] J. Fan, A. K. Elmagarmid, X. Zhu, W. G. Aref, and L. Wu.,” Classview: Hierarchical video shot classification, indexing, and accessing”, IEEE Transactions on

Multimedia, vol. 6, 2004, pages 70–86.

In face to face teaching the learner’s emotion can be captured but it is the challenge in E-Learning mode of delivery. My research begins from this point on words. My work is to get and capture the learner’s emotion, speech and facial expression, which could support expert to deliver lesson which makes perfect learning environment and the objective of the learning will be rewarded.

Proposed Model:

The proposed research model can able to recognize learner’s emotion. Emotion can be classified by speech emotion and facial emotion. During or after the one lesson delivery learner’s emotion can be recognized. Separate method for speech and facial emotion recognition has to be adopted. Here I am focusing about the facial emotion recognition. The Emotion recognition Tree can distinguish the activity.  

Figure 01: Emotion Recognition Tree

Different erudite have different conduit but ultimate objective is learning. From Gurukul to Modern age wisdom, learning continues and it will continue in far future also. In the age of transformation we are more dependent on reality of technology. Now kid’s learning starts with Joystick, mouse, keyboard, smart class instead of chalk & blackboard. From kids to aged everyone likes amusement for entertainment. So, we can target the same as a tool. That tool can be used for learning. Why not we use this glee to provide educative environment? So Edutainment has emerged into the picture. Current scenario needs innovative technology which had not required earlier. So it is mandatory to change the techniques, presentation of concepts, and way of thinking as per the current scenario. Technology is everywhere, so why not in education? The virtual and augmented reality environment is used in education as well as entertainment. We will be introduced education through entertainment. Irrespective of the location technology has provided a venue for the mode of teaching and learning where information access, enhanced searching of resources and enthusiasm for the learners very easily if used in an appropriate and premeditated manner. Appropriate environment building, Learning Management System, is the continuous research area. As per my observation, learning can be done in four different ways:

1) Formal learning takes place in education and training institutions, leading to recognized qualifications and uses structured and organized learning situations by face to face teaching.

2) Non-formal learning takes place alongside the official systems of education and training and does not typically lead to formalized certificates. Non-formal learning may be provided in the workplace and through the activities of civil society organizations and groups. Non-formal learning activities can also be produced by the learners themselves.

3) Informal learning describes a lifelong process whereby individuals acquire attitudes, values, skills and knowledge from daily experience and the educative influences and resources in their environment, from family and neighbours, from work and play, from the market place, the library and the mass media.

4) Accidental learning happens when in everyday activities an individual learns something that we had not intended or expected.

My proposed model does not include the one of the above singly but it blends the above four. My model will provide education through entertainment. The E Mode of learning is possible any time anywhere. I am presenting pedagogy by clubbing education and entertainment. I have identified some attributes of both the entities:

By keeping in the mind that I have proposed multimodal learning pedagogy using VERK (Visual, Aural, Read-Write & Kinesthetic). Edutainment system is the duel combination of entertainment media and learning pedagogy. Initially learner selects the entertainment media. Our model is independent of entertainment media. The model will work in all media.
The model retrieves the learner’s query and pass to Requirement Analysis. The Requirement Analysis section analyze the proposal and check syntax and semantic analysis. If (input) error, it returns control to Entertainment Media otherwise the control comes to Module Identification. This section identifies the appropriate learning pedagogy. After proper selection of pedagogy it comes to Result Composition section. After composition of the result control comes for Presentation Strategy Fixation. This section fixes the strategy of presentation and then it goes to the media again for output. The following diagram shows the complete module operation. One learner may use multiple media in due course is also applicable in this model.



There is a lot of challenges in Edutainment implementation which includes learnability, different Age Groups, Graphic appearance and layout, Technical requirements , Intuitive efficiency, Suitability for different learners and different situations , Interactivity, Objectiveness, Sociality, Motivation etc..

We need teacher to perform the tasks of presenting information en-masse and grading assessments. But in applying Technology in Education we can provide teachers with liberations of doing worksheets, short answer, true/false, m/c tests, etc. at their ease and free to their time, teachers could spend more time on one by one with topics that a student needs extra help with or could perhaps direct a gifted student to an area of study that suits his/her talents. This will give more value to the teachers than doing today to-do-lists. Through Technology in Education we can educate students while their still work with great change with time and change in knowledge. Utilization of technical education will give us an opportunity to do more in less time. Having a tablet or mobile learning device in the hands of all the students of school, location, course, costs or age does not mean of diminishing the role of teachers union in the education process.

Edutainment implementation is the huge research area. Students are encouraged to come and join this research work.

We are now moving from the first generation eLearning systems towards the second generation systems. A fundamental tenet of this design is that one size does not fit all as the learning process varies considerably from learner to learner. The aim was to investigate the commitment and actual use of information and interactive communications technology for learning as well as what key actors think are the major challenges for successful large scale implementation of that technology for learning. The system will assist and guide learner and spontaneously add supplementary material to the initial course to better learner understanding.

E-Learning portal is the full of content of different formats like text, metadata, image, audio, and video. Current search methodologies have a direct impact on the fundamental retrieval issues that information seekers encounter in their use of the vast number of search systems on the web today. Recently, information retrieval for text and multimedia content has become an important research area. Content-based retrieval in multimedia is a challenging problem since multimedia data needs detailed interpretation from pixel values. In this paper, Content-Based Retrieval will be presented along with the different strategies in terms of syntactic and semantic indexing for retrieval. The matching techniques used and learning methods employed are also analyzed, and key directions for future research are also presented. Based on several new technologies, such as ubiquitous computing, ontology engineering, semantic web and grid computing, it is obvious for flexible educational platform architecture for e-learning, which is called OntoEdu. It is coined by five different components:  user adaptation, automatic composition, education ontology, service module and content module, among which educational ontology is the core.