Showing papers by "Mayank Dave published in 2011"

A Comparative Study of Various Routing Protocols in VANET

Abstract: Vehicular Ad Hoc Networks (VANET) is a subclass of Mobile ad hoc networks which provides a distinguished approach for Intelligent Transport System (ITS) The survey of routing protocols in VANET is important and necessary for smart ITS T his paper discusses the advantages / disadvantages and the applications of various routing protocols for vehicular ad hoc networks It explores the motivation behind the designed, and traces the evolution of these routing protocols F inally the paper concludes by a tabular comparison of the various routing protocols for VANET

Using Gaussian Mixtures for Hindi Speech Recognition System

Abstract: The goal of automatic speech recognition (ASR) system is to accurately and efficiently convert a speech signal into a text message independent of the device, speaker or the environment. In general the speech signal is captured and pre-processed at front-end for feature extraction and evaluated at back-end using the Gaussian mixture hidden Markov model. In this statistical approach since the evaluation of Gaussian likelihoods dominate the total computational load, the appropriate selection of Gaussian mixtures is very important depending upon the amount of training data. As the small databases are available to train the Indian languages ASR system, the higher range of Gaussian mixtures (i.e. 64 and above), normally used for European languages, cannot be applied for them. This paper reviews the statistical framework and presents an iterative procedure to select an optimum number of Gaussian mixtures that exhibits maximum accuracy in the context of Hindi speech recognition system.

Acoustic modeling problem for automatic speech recognition system: conventional methods (Part I)

Abstract: In automatic speech recognition (ASR) systems, the speech signal is captured and parameterized at front end and evaluated at back end using the statistical framework of hidden Markov model (HMM). The performance of these systems depend critically on both the type of models used and the methods adopted for signal analysis. Researchers have proposed a variety of modifications and extensions for HMM based acoustic models to overcome their limitations. In this review, we summarize most of the research work related to HMM-ASR which has been carried out during the last three decades. We present all these approaches under three categories, namely conventional methods, refinements and advancements of HMM. The review is presented in two parts (papers): (i) An overview of conventional methods for acoustic phonetic modeling, (ii) Refinements and advancements of acoustic models. Part I explores the architecture and working of the standard HMM with its limitations. It also covers different modeling units, language models and decoders. Part II presents a review on the advances and refinements of the conventional HMM techniques along with the current challenges and performance issues related to ASR.

Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part II)

Abstract: In automatic speech recognition (ASR) systems, hidden Markov models (HMMs) have been widely used for modeling the temporal speech signal. As discussed in Part I, the conventional acoustic models used for ASR have many drawbacks like weak duration modeling and poor discrimination. This paper (Part II) presents a review on the techniques which have been proposed in literature for the refinements of standard HMM methods to cope with their limitations. Current advancements related to this topic are also outlined. The approaches emphasized in this part of review are connectionist approach, explicit duration modeling, discriminative training and margin based estimation methods. Further, various challenges and performance issues such as environmental variability, tied mixture modeling, and handling of distant speech signals are analyzed along with the directions for future research.

Mobile Agent as an Approach to Improve QoS in Vehicular Ad Hoc Network

Abstract: Vehicular traffic is a foremost problem in modern cities Huge amount of time and resources are wasted while traveling due to traffic congestion With the introduction of sophisticated traffic management systems, such as those incorporating dynamic traffic assignments, more stringent demands are being placed upon the available real time traffic data In this paper we have proposed mobile agent as a mechanism to handle the traffic problem on road Mobile software agents can be used to provide the better QoS (Quality of Service) in vehicular ad hoc network to improve the safety application and driver comfort

Reducing Network Overhead with Common Junction Methodology

Abstract: In structured and unstructured Peer-to-Peer P2P systems, frequent joining and leaving of peer nodes causes topology mismatch between the P2P logical overlay network and the physical underlay network. This topology mismatch problem generates high volumes of redundant traffic in the network. This paper presents Common Junction Methodology CJM to reduce network overhead by optimize the overlay traffic at underlay level. CJM finds common junction between available paths, and traffic is only routed through the common junction and not through the conventional identified paths. CJM does not alter overlay topology and performs without affecting the search scope of the network. Simulation results show that CJM resolves the mismatch problem and significantly reduces redundant P2P traffic up to 87% in the best case for the simulated network. CJM can be implemented over structured or unstructured P2P networks, and also reduces the response time by 53% approximately for the network.

Discriminative Techniques for Hindi Speech Recognition System

Abstract: For the last two decades, research in the field of automatic speech recognition (ASR) has been intensively carried out worldwide, motivated by the advances in signal processing techniques, pattern recognition algorithms, computational resources and storage capability. Most state-of–the–art speech recognition systems are based on the principles of statistical pattern recognition. In such systems, the speech signal is captured and preprocessed at front-end for feature extraction and evaluated at back-end using continuous density hidden Markov model (CDHMM). Maximum likelihood estimation (MLE) and several discriminative training methods have been used to train the ASR, based on European languages such as English. This paper reviews the existing discriminative techniques like maximum mutual information estimation (MMIE), minimum classification error (MCE), and minimum phone error (MPE), and presents a comparative study in the context of Hindi language ASR. The system is speaker independent and works with medium size vocabulary in typical field conditions.

Application of genetically optimized neural networks for hindi speech recognition system

Abstract: Automatic speech recognition (ASR) can be formulated as statistical pattern classification problem. In this approach, normally short term features are derived from the speech signal at front-end and then evaluated at back-end using the hidden Markov models (HMMs) or artificial neural networks. In this paper, we present a novel approach by using multilayer perceptrons optimized with the help of genetic algorithm. A combination of both short term and long temporal context features has been used as a sequence of acoustic feature vectors. Experimental result shows significant improvement by using the proposed framework for spoken Hindi digit recognition in general field conditions as well as in noisy environment.

Knowledge Based Framework for Data Aggregation in Vehicular Ad Hoc Networks

Abstract: Most data aggregation and dissemination techniques for Vehicular Ad Hoc Networks (VANETs) attempt to create and utilize a structure for collecting information. Conventional data aggregation schemes are not appropriate for mobile network. In this paper, we design a cooperative model to facilitate the aggregation of adjacent traffic reports. The idea behind this work is that we can adaptively change the forwarding delay of individual reports in a manner that a report can have a better chance to meet other reports. Simulation results based on realistic map data and traffic models demonstrate that proposed scheme can effectively reduce communication overhead with acceptable delay.

A Novel Approach for Information Dissemination in Vehicular Networks

Abstract: Vehicular Networks or simply VANETs are important component for the development of Intelligent Transportation System. Due to the features of VANET, data dissemination is an important issue that has to be addressed. In this paper we discuss the types of information involved in the dissemination process. We discuss the existing approaches of data dissemination. A new approach is proposed for the dissemination of data using network coding. In the proposed solution the packet is forwarded to vehicles after coding only. The simulations show that the proposed method reduces the number of broadcast packets being sent on the network. Also increases the channel throughput.

Rescuing data of mobile agents blocked by malicious hosts in e-service applications

Abstract: Mobile agents are software programs that may move from host to host as necessary to carry out their functions. Such systems violate some of the assumptions that underlie most existing computer security implementations. Full-scale adoption of mobile agent technology in untrustworthy network environment, such as Internet, has been delayed due to several complexities. Problem of Malicious Host (POMH) (i.e. how to protect agents against the malicious hosts) is a serious security problem in mobile agent system. The protection of mobile agents against the attacks of malicious hosts is considered a very challenging security problem. It has inspired lot of research interest, but very few measures exist to counter blocking attack where a host with malicious intentions refuses to transmit a mobile agent to the next host. It is significant and important requirement of the agent owner to rescue the data collected by the agent under custody and redeem a loss. In this paper, we present our scheme that aims to rescue the results being carried by blocked agent. The significant contribution of the scheme is the real time applicability in mobile agent based applications and maximum reduction of data loss in case of blocking attacks.

Platform independent non blocking mechanism for prevention of blocking attacks in mobile agents based e-service applications

Abstract: In recent years many researchers are incorporating the mobile agents in e-service applications especially in e-learning and e-commerce to improve the network latency and to reduce the network traffic. On the other side, the security issues degrade the mobile agent usage. The main intention of the attacker is to kill or modify the behaviour of the agent in the middle of the journey to degrade the trustiness of the agent environment. In this paper, we propose fault tolerance mechanism for preventing the agent blocking in scenarios where the agent is captured by malicious host in the network. This approach makes use of acknowledgements and partial result retrieval and when implemented in mobile agent platform allows the originator to retrieve partial results and track the location of mobile agent at any time during the process of transaction execution. During the recovery of the mobile agent all the components (agent code, itinerary, credential information, collected information and state) are able to recover. The proposed mechanism is capable of improving fault tolerant time, reliability and performance, especially for mobile agents in e-commerce Internet applications.

Optimizing handoff latency for mobile IPv6 based environments

Abstract: The ever growing number of Internet subscribers through mobile devices has led to the requirement of better mobility management protocols. Mobile IP version 6 (MIPv6) by IETF supports IPv6 mobility by providing mobile nodes with uninterrupted Internet connectivity and services. MIPv6 provides network layer mobility but handoff from one network to another network causes handoff latency. Due to this latency some packets may be lost or delayed in transfer affecting the performance of transport layer. In this paper, we present a low-latency handoff scheme for MIPv6. The scheme requires access point to facilitate movement detection and access router to implement tentative addresses pool and neighbor cache table for faster address configuration with faster duplicate address detection. The performance analysis shows that proposed scheme provides with lower latency and packet loss as well as improved signaling cost and packet delivery cost.