Lotia P.,SSCET |
Khan M.R.,Government Engineering College
International Journal of Multimedia and Ubiquitous Engineering | Year: 2011
In speaker Identification systems both parametric and nonparametric probability modeling is used. The Gaussian model is the basic parametric model that is used and this model is the basis of other sophisticated and it can be performed in a completely text independent situation. However, it sounds efficient to speaker identification application, but it results long time processing in practice. In this paper, we propose a decision function by using vector quantization (VQ) techniques to decrease the training model for GMM in order to reduce the processing time. In our proposed modeling, we take the superiority of VQ, which is simplicity computation to distinguish between male and female speaker. Then, GMM is applied into the subgroup of speaker to get the accuracy rates. Experimental result shows that our hybrid VQ/GMM method always yielded better improvements in accuracy and bring reduce in time processing. All the experiments have been done in both direct recording speech and mobile phone speech signals.
Kumar R.,S.S.C.E.T |
International Journal of Applied Engineering Research | Year: 2012
The recent advances in sensing, computing and communication technology coupled with the need to continuously monitor the physical phenomena have led to the development of wireless sensor networks.WSN works on real time information and by using this information they control the situations at remote location. WSN is great enabling technology that can revolutionize information and communication technology. WSN will remove the wired technique used for controlling process. This paper provides an overview about WSN network and challenges that governs when WSN are used for long geographically area. In this paper, we also define the architecture and various applications of wireless sensor network. © Research India Publications.
Barakkath Nisha U.,PSNA College of Engineering and Technology |
Umamaheswari N.,PSNA College of Engineering and Technology |
Venkatesh R.,PSNA College of Engineering and Technology |
Yasir Abdullah R.,SSCET
Journal of Theoretical and Applied Information Technology | Year: 2014
Inconsistent data caused by compromised nodes in Wireless Sensor Networks can be detached to improve data reliability, accuracy and to make effective and correct decisions. Multivariate Outliers normally describe the data behavior abnormality. Data aggregation is frequently used for the reduction of communication overhead and energy expenditure of sensor nodes during the process of data collection in Wireless Sensor Networks and also to improve the lifetime of the WSN. For the delivery of accuracy in base station, the outlier detection protocol must be incorporated with secure data aggregation. Aggregation will also try to increase the circle of knowledge and the level of accuracy. In this paper we use multivariate data analysis technique, data to handle outlier in correlated variables. To achieve the reliability and accuracy, a two phase algorithm is proposed. First, to build up a well conditioned PCA model for fault detection. Second, we use various statistical techniques to determine similarity between the sensed data against the real data set. We have evaluated our algorithm based on synthetic and real data injected with synthetic faults collected from a WSN. Our results concludes that the proposed algorithm achieves high true alarm rate and low false alarm rate and outperforms all the existing methods in terms of data accuracy and reliability. © 2005 - 2014 JATIT & LLS. All rights reserved.
Dhugga P.K.,SSCET |
Sharma M.,SSCET |
Proceedings of the 2015 IEEE 3rd International Conference on MOOCs, Innovation and Technology in Education, MITE 2015 | Year: 2015
Vehicular Ad-hoc Networks (VANETs) which nowadays showed distinct researches around the globe. Advancements in wireless networks globally, which gave a new dimension to researchers. This paper reviewed the basic concepts of VANET and clustering. It presented various types of clustering which could be implemented for the efficient running of VANET. Using static clustering dividing geographical city area into various clusters based on the criterion of density of the city. The proposed algorithm implements the above explained method to design an architecture known as an Architecture design Algorithm for (Geographical Static clustering (AAGS). The AAGS outperformed when compared with both Locations based Multipath Flooding (I.MF) on the various performance measures like packet drop, packet delivery ratio, throughput, and delay analysis and energy consumption. The results so produced paved the way for future research in the field of static clustering in VANETs. © 2015 IEEE.
Warathe S.,Government Polytechnic Durg |
Advances in Intelligent Systems and Computing | Year: 2016
In this paper we have described the cause of Indian grid failure during the stressed condition and developed the algorithm for numerical relay to prevent the unforeseen blackout. Indian power grid is consists of five regional grids and one of the largest power supply utility in the world. There was a major grid disturbance occurred in the Northern Region of India causes major shut down in many state leading to a entire blackout in eight states. The regional wise power import, export and generation give the idea of stressed condition and skewed power generation among the grid. The voltage profile of regional buses also indicates the insufficient reactive power compensation. In this work the impact of increase of load and loss of generation on angular separation is observed and the performance of developed algorithm for numerical relay is tested for different stressed condition and gives the expect result. © Springer India 2016.
Sinha K.,SSCET |
2014 IEEE Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2014 | Year: 2014
This paper is concentrated mainly to the cause of variations in machine speed and formation of power swing when gust and ramp occurs in wind mill distributed generation (DG). The performance analysis of electrical torque of the synchronous generator and mechanical torque of the turbine in wind farm has been done. This paper presents the different condition of disturbances due to ramp and gust in specified time period. In power system the damping oscillations modes are excited due to variations in machine speed. In this paper there is a focus to reduce the effects of ramp and gust in wind mill, the power system stabilizer (PSS) is used to damp out the rotor oscillations modes to maintain the stability in the system. This paper also does the analysis about machine speed, power, and load angle during ramp and gust condition with or without using PSS. The proposed stabilizer is evaluated by simulation using PSCAD software. © 2014 IEEE.
Sharma M.,SSCET |
ICROIT 2014 - Proceedings of the 2014 International Conference on Reliability, Optimization and Information Technology | Year: 2014
Due to the speedy growth of the WWW, the web hasn't only 'broaden' but also 'deepened' in its size. But only a portion of the web is included in the indices of current web search engines, a huge portion of the web hidden behind web search form (search interface). This paper proposes a prototype DWCE which interacts with different websites in order to build efficient search query interface which in turn extract deep web pages that would be of great value to human users. In addition to this, a comparative study of DWCE with Google search engine is also discussed. © 2014 IEEE.
Shrivastava S.,SSCET |
Proceedings - 2011 International Conference on Communication Systems and Network Technologies, CSNT 2011 | Year: 2011
We present a general method to improve watermark robustness by exploiting the masking effect of surface roughness on watermark Visibility, Watermarking technology has been successfully used for this purpose for other kinds of media such as images and video, but, a lot of work is again necessary to reach robustness and industrial applicability for 3D watermarking algorithms. In this paper we treat a specific aspect of 3D watermarking technology: the visual quality of the watermarked models. In particular, after a panoramic on 3D watermarking technology we present some ideas about this issue and we propose a method based on multiresolution analysis to improve this aspect in future watermarking algorithms. © 2011 IEEE.
Kaur K.,GIMET |
Singh J.,SSCET |
2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 | Year: 2015
the research in Mobile Ad-hoc Network remains winsome due to the crave to obtain better performance and scalability. Mobile ad hoc network is an unstructured self-forming radio mesh of moving nodes. There is no median approach for interaction of mobile nodes. In MANET nodes are mobile in nature and it became challenging to handle them while preserving the energy. Misbehavior, Mobility, Congestion are some factors that always degrade the performance of network. In this paper we propose a WSEEC (Weightage based Secure Energy Efficient Clustering) algorithmic approach towards energy efficient clustering and security of nodes. The aim of this algorithm is to build secure and energy efficient cluster head. Where rely value of each node is calculated to know the behavior of the node. The performance of proposed WSEEC algorithm is compared with WCA under five metric such as a Network life time, Energy consumption, throughput, delay and packet delivery ratio. © 2015 IEEE.
Proceedings - 2015 5th International Conference on Communication Systems and Network Technologies, CSNT 2015 | Year: 2015
Face detection and emotion selection is the one of the current topic in the security field which provides solution to various challenges. Beside traditional challenges in captured facial images under uncontrolled settings such as varying poses, different lighting and expressions for face recognition and different sound frequencies for emotion recognition. For the any face and emotion detection system database is the most important part for the comparison of the face features and sound Mel frequency components. For database creation features of the face are calculated and these features are store in the database. This database is then use for the evaluation of the face and emotion by using different algorithms. In this paper we are going implement an efficient method to create face and emotion feature database and then this will be used for face and emotion recognition of the person. For detecting face from the input image we are using Viola-Jones face detection algorithm and to evaluate the face and emotion detection KNN classifier is used. © 2015 IEEE.