Manuscripts

Recent Papers

Research Paper

Analysis of Different Classifier for the Detection of Double Compressed AMR Audio

An digital audio can be easily recorded by handheld devices such as digital voice recorders and Smartphone. A nd these audio are using as evidence in courts in many cases . One of the most important problem is that many audio often contains content forgery. Here we analyze the authenticity of AMR audio . A AMR is a audio codec for speech compression ,these format is widely used in today's handheld devices such as digital audio recorder or in Smartphone etc . Designing hand-crafted features is a challenging and time-consuming problem. In this paper, instead of manually extracting the features, we investigate how to use deep learning techniques in this audio forensics problem.. For an audio clip with many frames, the features of all the frames are aggregated and classified by classifier . Here we use three classifier and compare them .Instead of hand-crafted features, we used the SAE to learn the optimal features automatically from the audio waveforms. Audio frames is the input to feature extractor and the last hidden layer’s output constitutes the features of a single frame. At last the features of all the frames are aggregated and classified by either UBM-GMM or SVM or Bayesian classifier . when comparing and analyzing these three classifier the SVM and Bayesian classifier shows high degree of accuracy for detecting the authenticity of an audio .

Published by: Fathima Najiya P, Vipin Kishnan. C. V

Author: Fathima Najiya P

Paper ID: V4I2-1170

Paper Status: published

Published: March 10, 2018

Full Details
Research Paper

Synthesis of Stannic Oxide and its Application as Adsorbent to Study Adsorption of Copper (II) and its Separation from other Elements

A method has been developed for the quantitative adsorption, of Cu (II)and its separation from other elements.Spectrophotometric determination of Cu(II) has been carried by employingtetraethylenepentamine (TEPA)as a spectrophotometric reagent. Stannic oxide has been prepared by co-precipitation method which is nanomaterial. Stannic oxide is found to be stable towards acids, bases and most of the common chemical reagents. The effects of different parameters such as pH, time of contact, amount of stannic oxide in the adsorption of 50.0µg of Cu (II) has been studied. It has been observed that 250 mg of stannic oxide is sufficient for maximum adsorption (94.34 ± 1.34%) of 50.0µg Cu (II) at pH 5.0 and contact time of 5.0 minutes. Under the optimum conditions of adsorption, effect of various anions and cations in the adsorption of Cu (II) also has been studied. Interfering cations has been masked by using suitable masking agents so as to make the process more selective. Distribution co-efficient values has been determined for various cations under experimental conditions which enable to predict affinity of various cations for the adsorption on stannic oxide.

Published by: Dr. S. D. Ajagekar

Author: Dr. S. D. Ajagekar

Paper ID: V4I2-1169

Paper Status: published

Published: March 10, 2018

Full Details
Research Paper

Intelligent Voice Controlled Robot using HMM Recognizer

The Robots are used more commonly in all the fields. In this paper we are implementing systematicway for the voice base robotic vehicle, whichconsistshardware as well as software interfacing with clarity of voice commands spoken by human being, this voice commands are recognized by electronic circuit containing HM2007 voice recognition IC When we come to the recognition of speech, many recognizers are available for improvement of voice recognition. The main task is to find sequence of commands given by human being. The purpose of this paper is to recognize voice commands given to the robotic vehicle with the combination of techniques to enhance control of robotic vehicle.

Published by: Shubham Thakare, Swapnil Pathak, Anmol M. Borkar, Shubham Meshram, Amar Gupta, M. M. Baig

Author: Shubham Thakare

Paper ID: V4I2-1159

Paper Status: published

Published: March 10, 2018

Full Details
Research Paper

Causes of Stress among the Nurses Working in Intensive Care Units 2015

Stress is everyday life’s reality. Everyone is struck by it in one way or the other. No one is safe from it. This study aimed to assess factors that can cause stress among nurses working in critical care unit and to find the relation between these factors and demographic data, it is a descriptive study done in Khartoum, hospital and Omdurman hospital June -July 2015. 56 nurses enrolled in the study, selected randomly. data were collected after applied self-administer questionnaire .in the results most of the respondents strongly agreed that lack of practice and a shortage of staff and prolonged period of working without break, and lack of support and improper communications between their college and improper environments all these factors cause stress for nurses in the critical care unit. Conclude: majority of the nurses had severe stress with different stress factors and highly significant association between these factors and the demographic variable which support our hypothesis

Published by: Manal Bilal Mohamed

Author: Manal Bilal Mohamed

Paper ID: V4I2-1148

Paper Status: published

Published: March 10, 2018

Full Details
Research Paper

Video Based Face Detection Process

The project entitled “Movie Character Discovery” is used to identify movie characters in videos. Automatic face identification of characters in movies has drawn significant research interests and led to many interesting applications. It is a challenging problem due to the huge variation in the appearance of each character. Although existing methods demonstrate promising results in clean environment, the performances are limited in complex movie scenes due to the noises generated during the face tracking and face clustering process. In this paper we present two schemes of global face-name matching based framework for robust character identification. The contributions of this work include: Complex character changes are handled by simultaneously graph partition and graph matching. Beyond existing character identification approaches, we further perform an in-depth sensitivity analysis by introducing two types of simulated noises. The proposed schemes demonstrate state-of-the-art performance on movie character identification in various genres of movies.

Published by: S. P. Deepika, M. Ananthi, P. Rajkumar

Author: S. P. Deepika

Paper ID: V4I2-1160

Paper Status: published

Published: March 9, 2018

Full Details
Research Paper

E-Payment System for Municipality

Local bodies are classified in to municipal co-operation, municipalities of different grades depending upon the population and income of the urban local body. Local bodies like municipalities needs to collect different kinds of information from citizens for applications like marriage, death, birth, ration card etc. But it’s difficult to store all information and it will take long time for processing.To solve this problem we have to develop a web based system “E-Payment System for Municipality”. By using this system which we can collect tax information from different authorities based on their house num and house owner name. Data are stored in databases and the user has a unique user-id and password. The user can login and check the data.

Published by: Abhirami TK, Dr. A. V. Senthil Kumar

Author: Abhirami TK

Paper ID: V4I2-1175

Paper Status: published

Published: March 9, 2018

Full Details
Request a Call
If someone in your research area is available then we will connect you both or our counsellor will get in touch with you.

    [honeypot honeypot-378]

    X
    Journal's Support Form
    For any query, please fill up the short form below. Try to explain your query in detail so that our counsellor can guide you. All fields are mandatory.

      X
       Enquiry Form
      Contact Board Member

        Member Name

        [honeypot honeypot-527]

        X
        Contact Editorial Board

          X

            [honeypot honeypot-310]

            X