M Tech Dissertations

Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/3

Browse

Subject: search.filters.subject.Network architecture

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Testing synchronously communicating distributed systems
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2018) Vishwakarma, Nikita; Bhateja, Puneet
    In our work we are supposed to test whether the generated distributed implementation(or distributed network) behaves similar to that of given specification. We are doing this over synchronously communicating FSMs(Finite State Machines). Synchronous distributed implementation is the set of FSMs and specification is a single known FSM. Commonality in the behaviour of given FSM and DFSM(Distributed Finite State Machine) has been checked by conformance. We are also aimed to define a method for testing the global behaviour of the given network in a distributed and concurrent manner. This is achieved by independently performing some operations in each component FSM and later combining these information to get the information of our distributed network. Further this information of distributed network can be used to match its behaviour with specification FSM.
  • Thumbnail Image
    ItemOpen Access
    Human Action Recognition Using Deep Neural Networks
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2017) Thakkar, Shaival; Joshi, Manjunath V.
    "In this thesis, we present a hierarchical approach for human action classification using 3-D Convolutional neural networks (3-D CNN). Human actions refer to positioning and movement of hands and legs and hence can be classified based on those performed by hands or by legs or, in some cases, both. This acts as the intuition for our work on hierarchical classification. In this work, we consider the actions as tasks performed by hand or leg movements. Therefore, instead of using a single 3-D CNN for classification of given actions, we use multiple networks to perform the classification hierarchically, that is, we first classify an action into a hand or leg action and then use two separate networks for hand and leg action classes to perform classification among target action categories. In particular, we train three networks to classify six different actions, comprising of three actions each for hands and legs. The use of 3-D CNN enables automatic extraction of features in spatial as well as temporal domain, avoiding the need for hand crafted features. This makes it one of the better approaches when it comes to video classification. We use the KTH dataset to evaluate our approach and comparison with the state of the art methods shows that our approach outperforms most of the state of the art methods."
  • Thumbnail Image
    ItemOpen Access
    Decoupling delay and bandwidth in stateless core networks
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2006) Shah, Parag; Jotwani, Naresh D.
    The use of network applications like VoIP, video conferencing and online stock marketing has greatly increased over the past few years. These applications require performance bounds on bandwidth, delay and delay variations otherwise they become useless. The solutions proposed by IETF, an authorized Internet body, for providing performance guarantees are not in favor of Internet’s scalability and robustness. In an attempt to provide guaranteed services Dr. I. Stoica had proposed the Stateless Core (SCORE) architecture as a part of his doctoral work at CMU. The SCORE can support all functionalities of the current Internet. Moreover, it can support guaranteed services proposed by IETF without affecting current Internet’s scalability and robustness. Core Jitter Virtual Clock (CJVC) is the scheduling discipline that provides absolute service guarantee in SCORE domain. The delay bound provided by CJVC depends on the reserved rate of the flow. The coupling of delay and bandwidth is considered to be a drawback of CJVC as the flows requiring low delay bound need to reserve large bandwidth. The well-known stateful guaranteed service disciplines like Weighted Fair Queueing (WFQ) and Delay Earliest Due-Date (D-EDD) also have the same problem. Several solutions like Service Curve based Earliest Deadline (SCED) and Rate Controlled Static Priority (RCSP) have been proposed for the mentioned coupling problem but they are limited to stateful networks. In this thesis, we propose a new scheduling discipline for the same problem but in stateless core network. The proposal is to emulate RCSP scheduling discipline algorithm in SCORE domain. Basic admission control algorithm has also been proposed in the course of emulating the behaviour of RCSP in SCORE architecture.