Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Singhal, H.Has files: No

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Learner centered design approach for E-learning using 3D virtual tutors
    (IEEE Computer Society help@computer.org, 2013) Mukherjee, S.; Singhal, H.; Jha, P.; Kokane, A.; Rastogi, P.; Mittal, R.; Guddeti, G.
    Most of the existing E-learning system designs have focused on the development of feature-rich, but usable systems with little effort in motivating students to develop interest in the teaching-learning process. This paper discusses the learner centered design approach for web-based tutoring to motivate young learners using 3D virtual tutors in a requirement-based, flexible pedagogical model. Students can choose course(s) and the study-mode. In the guided mode, the student is mentored by a human tutor, whereas a student in un-guided mode is tutored by 3D avatar. The student has access to study materials, educational videos and applets that are provided by the tutors, the student also has access to forums for doubt clearing and online assignments to be submitted for tutors' evaluation. Tutors can track students' progress using online quiz and reports modules. Further, tutors have access to teaching aids like online chat system and whiteboard-based teaching in a virtual classroom environment. © 2013 IEEE.
  • No Thumbnail Available
    Item
    Modified MapReduce framework for enhancing performance of graph based algorithms by fast convergence in distributed environment
    (Institute of Electrical and Electronics Engineers Inc., 2014) Singhal, H.; Guddeti, G.R.M.
    The amount of data which is produced is huge in current world and more importantly it is increasing exponentially. Traditional data storage and processing techniques are ineffective in handling such huge data [10]. Many real life applications require iterative computations in general and in particular used in most of machine learning and data mining algorithms over large datasets, such as web link structures and social network graphs. MapReduce is a software framework for easily writing applications which process large amount of data (multi-terabyte) in parallel on large clusters (thousands of nodes) of commodity hardware. However, because of batch oriented processing of MapReduce we are unable to utilize the benefits of MapReduce in iterative computations. Our proposed work is mainly focused on optimizing three factors resulting in performance improvement of iterative algorithms in MapReduce environment. In this paper, we address the key issues based on execution of tasks, the unnecessary creation of new task in each iteration and excessive shuffling of data in each iteration. Our preliminary experiments have shown promising results over the basic MapReduce framework. The comparative study with existing solutions based on MapReduce framework like HaLoop, has also shown better performance w.r.t algorithm run time and amount of data traffic over Hadoop Cluster. © 2014 IEEE.
  • No Thumbnail Available
    Item
    Effective E-learning using 3D Virtual Tutors and WebRTC Based Multimedia Chat
    (Institute of Electrical and Electronics Engineers Inc., 2014) Kokane, A.; Singhal, H.; Mukherjee, S.; Guddeti, G.R.M.
    This paper discuss the novel implementation of Learner Centered Design Approach of E-learning System using 3D Virtual Tutors [1] and further enhances this work in facilitating young learners to interact with human tutors using WebRTC Based Multimedia Chat system. The present work adds three main features such as: Firstly, addition of live video lecture session by which students can interact with the tutor just like video call of Skype system. Secondly, the presentation of 3D virtual tutors' narrations of articles in the text form of live transcriptions of avatars' speech. Thirdly, introduction of timed quiz by which a real-life objective examination can be mimicked and thereby evaluating the performance of students. Lastly, we present a comparative evaluation of the original system and its improved version with respect to responses received from a large pool of young learners using the system. © 2014 IEEE.