Akila Devi T.R.,Bsa University |
Akila R.,Bsa University |
Geetha A.,Bsa University
Proceedings of the 2017 2nd International Conference on Computing and Communications Technologies, ICCCT 2017 | Year: 2017
The current research trend is about intelligent devices. There is a need to interconnect these intelligent embedded devices using the Internet and hence IoT devices have become more essential. Web of Things and Wisdom Web of Things are two technologies in their growing stages. This paper is a study on integration of IoT devices with WoT and W2T. An architecture has been designed to implement the interaction between the intelligent Iot devices via WoT and W2T. © 2017 IEEE.
Nadana Ravishankar T.,Bsa University |
Shriram R.,Bsa University
Journal of Theoretical and Applied Information Technology | Year: 2014
As the information flooding onto worldwide web is growing fast, it is very difficult to find the hidden knowledge from huge data stored. In traditional clustering techniques, the task for clustering algorithm is to find the relevant data, describing relationships among the elements between two input datasets. During unsupervised learning process, metadata may play a significant role in the context of data retrieval. In this work, we proposed a methodology of metadata based clustering model (MBCM) for large datasets. The proposed model is validated with few standard datasets like IEEE, ACM and Cluto etc. Experimental results show that it is possible to achieve better cluster quality without significant overhead in terms of execution time. Finally, the performance of our proposed model is evaluated using F-measure and the performance of our method is compared with existing clustering models. © 2005 - 2014 JATIT & LLS. All rights reserved.
Chakraborty P.,Bsa University |
Tharini C.,Bsa University
Sensor Review | Year: 2015
Purpose - The purpose of this paper is to find out the use of compressive sensing (CS) algorithm for wireless sensor networks (WSNs). As energy-efficient algorithms are required for WSNs, CS is very much useful as less than 25 per cent of the entire input data alone is required to be transmitted, and reconstruction at the receiver with this reduced data set is of good quality. But, the usefulness of the algorithm with suitable modulation schemes is not analyzed so far in the literature. Hence, this work concentrated on the algorithm performance with different modulation schemes and different channel conditions. Design/methodology/approach - Compressive sensing encoding is performed by using suitable transform on the input signal. Here, DCT and DWT are used to generate the sparse signal. Random measurement matrix is used to generate the compressed output, which is reconstructed using the Basis Pursuit (BP) method. Also, an analysis for the energy-efficient modulation scheme is performed by modulating the compressed output using QPSK/BPSK/QAM and transmitted by considering the Gaussian and Rayleigh Channels. Energy required per bit transmission is modeled and computed for different schemes. Findings - Simulation result shows that the use of CS algorithm for data compression tremendously reduces the number of transmission bits and, hence, enhances the transmission and bandwidth efficiency in WSN. Results show that DWT is a much suitable transform to be used for sparse measurement generation. In comparison with DCT, DWT is computationally simple and takes very less time, which is expected in real-time application. The reconstruction result shows that about 25 per cent of the data sample is sufficient to recover the original image, perhaps which is the most surprising result. An extensive analysis of various modulation schemes based on the energy model shows that QPSK is in the AWGN channel, and QAM modulation in the Rayleigh channel is a much suitable modulation scheme to be used in WSN for further reduction of energy consumption. Originality/value - Compressive sensing is recently gaining importance for quantization, compression and noise removal in images. In this paper, this technique was used along with modulation schemes to analyze the suitability of the algorithm for WSN. © Emerald Group Publishing Limited.
Zeenathunisa S.,Bsa University |
Jaya A.,Bsa University |
Rabbani M.A.,Bsa University
IAMA 2011 - 2011 2nd International Conference on Intelligent Agent and Multi-Agent Systems | Year: 2011
Face Recognition plays a vital role in criminal detection is considered to be the most useful and eminent techniques for identifying a criminalized person. An intelligent system that recognizes such criminals from a large database out of which the dataset is considered under the various illumination conditions, is a challenging task. The idea of this research is to recognize such human faces under different dim light conditions. An intelligent agent helps in perceiving the environment where the captured faces subject to various illumination conditions and acts upon that environment. This can be illustrated by an intelligent approach towards integrating various techniques for the agent to perceive Illumination Normalization, Feature Extraction and Classification. The Illumination Normalization technique is useful for removing the dimness and shadow from the facial image which reduces the effect of illumination variations still retaining the necessary information of the face. The robust local feature extractor which is the gray-scale invariant texture called Local Binary Pattern (LBP) is helpful for feature extraction. K-Nearest Neighbor classifier is utilized for the purpose of classification and matching the face images from the database. Thus, the agent tends to identify the input face image from the available database after preprocessing the image and feature extraction. Various images for the agent from Yale-B database are used for testing to achieve the face recognition system. © 2011 IEEE.
Sathik Ali I.,Bsa University |
Sheik Abdul Khader P.,Bsa University
2011 International Conference on Computer, Communication and Electrical Technology, ICCCET 2011 | Year: 2011
Real-time applications such as multimedia streaming and video conferencing have quite stringent Quality of Service (QoS) requirements from the network, because they are more sensitive to available bandwidth and loss rate than non real-time traffic. To provide scalable and simple Quality of Service (QoS) mechanism for multicast services, Probe-Based Multicast Admission Control (PBMAC) scheme was proposed. In this paper, PBMAC is studied and so-called subsequent request problem found in PBMAC, which degrades system performance significantly when the network traffic is heavily loaded, is further investigated. Based on the analysis on subsequent request problem, a variant of Enhanced PBMAC (VEPBMAC) scheme is proposed, in which when a subsequent request arrives, the request is accepted without probing the link further instead of complementary probing devised in Enhanced PBMAC (EPBMAC) to solve this problem. This leads to further reduction in the bandwidth requirement for probe flows. Simulation results on the study conducted on PBMAC are presented. © 2011 IEEE.
Zeenathunisa S.,Bsa University |
Jaya A.,Bsa University |
Rabbani M.A.,Bsa University
Proceedings of International Conference on Electronics Communication and Computing Technologies 2011, ICECCT'11 | Year: 2011
Face Recognition is a computerized biometric modality which automatically identifies an individual's face for the purpose of recognition. The ability to recognize human faces can be categorized under two senses, the former is the biometric identification and the later is the visual perception. The biometric identification can be done by obtaining a person's image and matching the same against the set of known images whereas the later is how the system percepts the familiar faces and recognize them. This paper presents such a biometric identification of the frontal static face image subjected in various dark illuminations. Face Recognition Biometric Systems automatically recognize the individuals based on their physiological characteristics. The research on such areas has been conducted for more than thirty years, but still more processes and better techniques for biometric facial extraction and recognition are required. This paper presents a framework on such issue by integrating the preprocessing method, local feature extractor and a recognizer for face recognition. An automatic FRBS has been developed that uses 1) Local Binary Pattern and 2) k - Nearest Neighbor classifier. Experimental results based on the Yale - B database show that the use of LBP and k-NN is able to improve the face recognition performance in various dark illuminations. © 2011 IEEE.