Author
A. P. Sarath Chandar
Bio: A. P. Sarath Chandar is an academic researcher from Sri Venkateswara College of Engineering. The author has contributed to research in topics: Petri net & Scalability. The author has an hindex of 1, co-authored 2 publications receiving 1 citations.
Papers
More filters
••
07 Sep 2010TL;DR: A domain specific application illustrating the potential of CDPN to model adaptive e-learning system is presented and the declaration and utilization of global variables and functions has been used in the paper to augment the existing DPNs with the communicating feature.
Abstract: The programmable Dynamic Petri Nets(DPN) can efficiently model interactive and iterative distributed multimedia presentations. However, the dynamic adaption of the presentation is not possible using isolated DPNs. This paper proposes the concept of communicating Dynamic Petri Nets (CDPN). The declaration and utilization of global variables and functions has been used in the paper to augment the existing DPNs with the communicating feature. There are several distributed systems that can be modeled using the proposed CDPN. In this paper a domain specific application illustrating the potential of CDPN to model adaptive e-learning system is presented.
1 citations
••
14 Jul 2011TL;DR: The Distributed Spiking Neural P System (DSNP) is proposed, a variant of the existing Distributed P System that can be used to represent dynamic and distibuted systems.
Abstract: The motivation behind the proposed research work is the need for an innovative e-learning system that can adapt to the learning capability of every individual. Adaptive e-learning systems create new opportunities and at the same time have several research challenges that need to be addressed. The primary requirement of such adaptive systems is the need to create and represent adaptable content effectively. This paper presents a membrane computing model to demonstrate how adaptable content can be represented and used efficiently. The Spiking Neural P System (SNP) is a membrane computing model inspired by the way neurons communicate by means of spikes. This paper proposes the Distributed Spiking Neural P System (DSNP), a variant of the existing Distributed P System, that can be used to represent dynamic and distibuted systems. Temporal relations captured on a time line during authoring of the ecourse, can be automatically converted into an SNP system using the algorithm presented in the paper. An algorithm for the automatic generation of the DSNP from the e-course compositions represented using a linked list of SNPs is also presented in the paper along with experimental results to prove the efficiency and scalability of the proposed model.
Cited by
More filters
••
01 Dec 2014TL;DR: This paper proposes an efficient context-aware open e-learning environment to do the same to author and deliver courses for diverse learners with varied backgrounds dynamically.
Abstract: With the explosive growth in the World Wide Web over the past few decades, a predominant part of the pedagogical arena is making a transition from stereotype textbook learning to massive open online learning. Efforts are being made to develop and foster crowd sourced massive open repositories of learning objects, which can be tapped to author courses for diverse learners with varied backgrounds dynamically. Developing systems to author and deliver such courses has been of rising importance to contemporary researchers and this paper proposes an efficient context-aware open e-learning environment to do the same. The learning objects having high aptness to the particular course and high content-based predicted rating pertaining to the particular learner's preferences are picked from the open repository and the course structure is modeled using communicating dynamic Petri nets. Ratings and feedback from the user are obtained during presentation, based on which the course delivery is made adaptive. Rating prediction through Collaborative filtering is used for this purpose. The ratings are also used to implicitly learn the learner's preferences and to establish an aptness score for each learning object.
2 citations