Kamal Bijlani

A-VIEW: Adaptive bandwidth for telepresence and large user sets in live distance education

bFor distance education, several obstacles in live video conferencing are preventing widespread adoption. These include network bottlenecks, lack of telepresence, proprietary hardware usage, and inability to scale up for large user sets. In this paper, we present A-VIEW, a novel software system that has an architecture with an extensible multi-display video conferencing and telepresence solution customized for distance education, which can be effectively used for real-time teaching and training. We show sample deployments of A-VIEW with variable number of displays. We contend that a hybrid set of adaptive bandwidth techniques and domain-specific heuristics can be effectively used to accommodate a large number of users. For example, for each client, A-VIEW can operate with a constant bandwidth (upload and download) of around 256 kbps. A-VIEW can also be used at high bandwidths to provide a high-resolution telepresence solution. Unlike many other applications, A-VIEW does not use any proprietary hardware. Having a software only system makes A-VIEW extremely versatile for widespread deployment in teaching and training applications.

Yaw Estimation Using Cylindrical and Ellipsoidal Face Models

Accurate head yaw estimation is necessary for detecting driver inattention in forward collision warning systems. In this paper, we propose three geometric models under the ellipsoidal framework for accurate head yaw estimation. We present theoretical analysis of the cylindrical and ellipsoidal face models used for yaw angle estimation of head rotation. The relationship between cylindrical, ellipsoidal, and proposed models is derived. We provide error functions for all models. Furthermore, for each model, over/under estimation of angle, zero crossings of error, bounds on yaw angle estimate, and bounds on error are presented. Experimental results of the proposed models on four standard head pose data sets yielded a mean absolute error between 4° and 8° demonstrating the efficacy of the proposed models over the state-of-the-art methods.

Concept Maps for Learning in a Flipped Classroom

This paper examines how concept maps can be used to facilitate learning in a flipped classroom. Concept maps are a method for visual knowledge representation. In a flipped classroom, learning materials are made available to students for self-learning before class starts, while in-class time is used for student-teacher interaction. In this paper, we consider the role of concept maps created by the teacher in three different ways: a) as learning materials for students in a flipped classroom, b) as an organizational tool for the knowledge representation, and c) as an assessment method in which the questions are created for each concept so that the teacher is able to identify which concept the student has not grasped properly. This methodology was implemented in a pilot study with final year MCA students. The preliminary findings are extremely positive, further research work is in progress and large-scale experimentation is planned.

Virtual Media Enhanced Vocational Education Curriculum

The following paper discusses the development of a virtual media enhanced vocational education curriculum that ultimately aims to reduce the digital and economic divide by targeting the illiterate and neo-literate sectors of India. While the application utilizes enhanced graphics, the end user experiences a simplistic interface. The virtual environment is developed in a modular way, enabling the user to learn methodically and at their own pace. The applications key usability element is that the fully developed virtual media enhanced vocational education curriculum will be web-based, where the user can access the program from any location through the medium of a computer and internet. Such an application has the potential to impart effective vocational training to the masses and at a pace that is at the comfort and pace of individual users. While the following paper discusses a specific application developed to train plumbers, the concept is generic and can be extended to any vocational training.

Enhancing E-learning Education with Live Interactive Feedback System

With the recent technological advancements, the E-learning platform has taken a prominent role in the field of education. There are a number of E-learning software applications available and many of the teaching-learning happens through them. However, most of the E-learning applications lack good interaction mechanisms resulting in providing far less benefits than intended. The students will lose attention as they passively listen to the teacher for a longer duration. Our research work mainly focuses on how to solve this lack of interaction, by introducing a Live Interactive Feedback system (LIF) for online classes. LIF provides Quiz, Polling, interactive white board, chat, question, voting and multimedia modules to help teachers to verify effectiveness of their online classes. In this work, we mainly focuses on implementing the LIF system in the E-learning software A-VIEW [1], to make it a more interactive tool for large scale online learning implementation. In this paper we also present how mobile technologies can be used in a synchronized live e-class room platform.

A-view: real-time collaborative multimedia e-learning

The emergence of collaborative multimedia-based instructional technology has been a catalyst in creating virtual learning environments. Collaborative multimedia has enriched the form of teaching-learning milieu and brought powerful changes to the traditional classrooms emboldening viewer centered and social network based pedagogy. The paper initially delves into the germane effect of real-time collaborative multimedia on different levels of learning. Then we present a case study based on a unique architecture for collaborative multimedia environment. The client side architecture makes use of caching the multimedia content according to the users state and available system resources for creating multimodal interactions for e-Learning. The server side architecture makes it possible to build a Real-Time Collaborative Multimedia e-Learning tool, sustaining support for large number of live users. In addition, we cover how simulations, quizzes, multiplayer games, online content such as graphics and recorded lectures help learners by increasing their autonomy, enhancing their interest in learning on multiple devices which varies from workstations with multiple large displays to mobile devices.

ACE: Architecture for collaborative environments

With the advent of Facebook and Twitter, people are demanding high-performance high-quality online multimedia systems where a large number of users can collaborate with each other. Incorporating these features usually results in the following issues: high bandwidth usage, lower interactivity, higher latency; and often, only low quality compressed multimedia content can be used. In this paper we present the ACE architecture which is implemented in a virtual collaborative environment and tries to overcome the mentioned drawbacks.

Virtual fabric paint environment using touch and gesture for vocational training

The objective of this work is to enhance the pace of learning occupational skills by developing multimedia enriched computerized vocational training programs targeted towards the illiterate and neo-literate sections of a society. This is achieved by developing virtual computer based vocational training environments. The experience of these environments is enriched with touch and gesture based technology. This paper talks about the creation of virtual vocational training scenario of a fabric painting application. We have successfully created a working prototype which brings out the real experience of fabric painting to the end user. Emphasis is placed on human-computer interactions that will allow simplistic interface for illiterate or neo-literate individuals. This approach of ‘virtual’ computer-based vocational training environment has great potential that stimulates self-learning processes of these vocational skills to a diverse audience with varying skill sets.

Student analytics for productive teaching/learning

This paper presents an automated analytics system which monitors the students attending online lectures from a remote location and provides feedback to the teacher. The classroom videos are recorded and analyzed to identify the student trends, which might not be noticed by a teacher during class hours. Student behaviors are classified into five affective states: Active, Transcribing, Unavailing, Distracted and Transition. The student faces are tracked and optical flow of each student is calculated. Displacements and head motion of students are derived using a simple method and each student is automatically mapped to a particular affective state. The state transitions are provided to the educator as a feedback for assessment. Three different experiments were conducted with sessions from online courses, and was observed that the automated system efficiently differentiates the attention level of students and helped the teachers to improve their style of instruction. The engagement states also defined the height of student interest on a topic and classified the attentiveness automatically, without exploiting human effort.

Knowledge representation and assessment using concept based learning

The process of learning can be improved with proper and timely feedback. This paper proposes a system that provides feedback for both teacher and student using concept-based learning. Various types of concepts are defined, and assessment is done for each concept. The level of knowledge acquired by students can be clearly represented using this approach. The feedback provided is goal-oriented, active, personalized, timely, ongoing and consistent, which counts for the novelty of this approach. Results from this study show that concept-based assessment and feedback motivates the students and helps them improve their examination score.