arXiv subjects

Mohammad Nasiruddin

Publications and source records attributed to Mohammad Nasiruddin.

3 recordsLinked to original sources

arXiv2014

Impact of Two Realistic Mobility Models for Vehicular Safety Applications

Vehicular safety applications intended for VANETs. It can be separated by inter-vehicle communication. It is needed for a vehicle can travel safety with high velocity and must interconnect quickly dependably. In this work, examined the impact of the IDM-IM and IDM-LC mobility model on AODV, AOMDV, DSDV and OLSR routing protocol using Nakagami propagation model and IEEE 802.11p MAC protocol in a particular urban scenario of Dhaka city. The periodic broadcast (PBC) agent is employed to transmit messages between vehicles in case of emergency or collision avoidance for vehicular safety communication. The simulation results recommend numerous concerns such as lower packet drop rate, delay, jitter, route cost and mean-hop is necessary to be measured before developing a robust safety application of VANET.

cs.NI↗

arXiv2013

A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages

Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP). Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications. Indeed, improvement over current performance levels could allow us to take a first step towards natural language understanding. Due to the lack of lexical resources it is sometimes difficult to perform WSD for under-resourced languages. This paper is an investigation on how to initiate research in WSD for under-resourced languages by applying Word Sense Induction (WSI) and suggests some interesting topics to focus on.

cs.CL↗

arXiv2013

Local Feature or Mel Frequency Cepstral Coefficients - Which One is Better for MLN-Based Bangla Speech Recognition?

This paper discusses the dominancy of local features (LFs), as input to the multilayer neural network (MLN), extracted from a Bangla input speech over mel frequency cepstral coefficients (MFCCs). Here, LF-based method comprises three stages: (i) LF extraction from input speech, (ii) phoneme probabilities extraction using MLN from LF and (iii) the hidden Markov model (HMM) based classifier to obtain more accurate phoneme strings. In the experiments on Bangla speech corpus prepared by us, it is observed that the LFbased automatic speech recognition (ASR) system provides higher phoneme correct rate than the MFCC-based system. Moreover, the proposed system requires fewer mixture components in the HMMs.

cs.CL↗