Entity

Time filter

Source Type

Ibrahimpatnam, India

Rawat S.S.,GNIT | Rajamani L.,Osmania University
Journal of Theoretical and Applied Information Technology | Year: 2010

This paper deals with the implementation of a computer program, which employs Genetic Algorithms (GAs) in the quest for an optimal class timetable generator. The program is written in Java and incorporates a repair strategy for faster evolution. This paper also explains an example usage of Genetic Algorithms (GAs) for finding optimal solutions to the problem of Class Timetable. It is seen that the GA could be improved by the further incorporation of repair strategies, and is readily scalable to the complete timetabling problem. The system at present does not take care of other constraints like unavailability of lecturers, small size of rooms and time required by the lecturer to move from one class to other class, which is to be considered in the future up gradations. The automated class timetable is used at the dept. of Computer Science & Engineering, Guru Nanak Institute of Technology (GNIT), Hyderabad, India and in future it will be used by other faculty administrators and proposes solutions to be considered by the parties involved: administration, departments and students. © 2005 - 2010JATIT. All rights reserved. Source


Mishra A.N.,BIT | Shrotriya M.C.,BIT | Sharan S.N.,GNIT
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2010

In view of the growing use of automatic speech recognition in the modern society, we study various alternative representations of the speech signal that have the potential to contribute to the improvement of the recognition performance. In this paper wavelet based features using different wavelets are used for Hindi digits recognition. The recognition performance of these features has been compared with Linear Prediction Coefficients (LPC) and Perceptual Linear Prediction (PLP) features. All features have been tested using Hidden Markov Model (HMM) based classifier for speaker independent Hindi digits recognition. The recognition performance of PLP features is11.3% better than LPC features. The recognition performance with db10 features has shown a further improvement of 12.55% over PLP features. The recognition performance with db10 is best among all wavelet based features. © 2010 Copyright SPIE - The International Society for Optical Engineering. Source


Mishra A.N.,Birla Institute of Technology | Chandra M.,Birla Institute of Technology | Biswas A.,IMS Engineering College | Sharan S.N.,GNIT
International Journal of Signal and Imaging Systems Engineering | Year: 2013

Automatic Speech Recognition (ASR) system performs well under restricted conditions but the performance degrades under noisy environment. Audio-visual features play an important role in ASR systems in the presence of noise. In this paper, Hindi phoneme recognition system is designed using audio-visual features. The Discrete Cosine Transform (DCT) features of the lip region integrated with Mel Frequency Cepstral Coefficient (MFCC) audio features are used to get better recognition performance under noisy environments. Colour intensity, hybrid method and Pseudo-Hue methods have been used for lip-localisation approach with Linear Discriminant Analyser (LDA) as a classifier. Recognition performance using Pseudo-Hue method proved best among all the methods. Copyright © 2013 Inderscience Enterprises Ltd. Source


Ray S.K.,Jadavpur University | Roy D.,GNIT | Shaikh A.R.,Jadavpur University
Proceedings - 2011 Annual IEEE India Conference: Engineering Sustainable Solutions, INDICON-2011 | Year: 2011

Lowering the time and cost of performing pairwise sequence alignment (PSA) on large and exponentially growing DNA Databases poses a big research challenge. Neither the current practice of running the complex programs on highly expensive parallel or networked computers nor the relatively recent proposals for implementing the algorithms on high-speed general-purpose hardware platforms by heavily relying on specialized software can provide the desired cost-time performance. A novel special-purpose hardware system named DNA Sequence Alignment Engine (DSAE) which is based on an associative memory (AM) built with a large collection of content-to-address memory (CTAM) modules has been described. Time-staggered parallelism of the CTAM modules and their independent binary search of deep segments of the DNA database promises highly scalable and very high-speed sequence alignment at a relatively low-cost. Only ungapped alignment has been studied so far in this ongoing research. © 2011 IEEE. Source


Goel S.,BVICAM | Sinha A.K.,GNIT
2015 International Conference on Computing for Sustainable Global Development, INDIACom 2015 | Year: 2015

This work reveals an ANFIS based model for Delhi Urban Area, India (DUA) for trip distribution. This work has been implemented for distribution of passenger's trips in DUA for all the zones. This work shows the application of ANFIS based model on the real set of trips generated/attracted data of DUA passengers. The machine learning result is found quite satisfactory error being as low as. 92%. This paper shows the analysis and comparison of the end results of ANFIS based model with the linear programming (LP) based model for the distribution of passenger's trips. © 2015 IEEE. Source

Discover hidden collaborations