Time filter

Source Type

Raghuveera T.,Anna UniversityTamil Nadu | Vidhushini S.,Anna UniversityTamil Nadu | Swathi M.,Anna UniversityTamil Nadu
International Journal of Intelligent Information Technologies | Year: 2017

Real-Time Facial and eye tracking is critical in applications like military surveillance, pervasive computing, Human Computer Interaction etc. In this work, face and eye tracking are implemented by using two well-known methods, CAMSHIFT and RANSAC. In our first approach, a frontal face detector is run on each frame of the video and the Viola-Jones face detector is used to detect the faces. CAMSHIFT Algorithm is used in the real- time tracking along with Haar-Like features that are used to localize and track eyes. In our second approach, the face is detected using Viola-Jones, whereas RANSAC is used to match the content of the subsequent frames. Adaptive Bilinear Filter is used to enhance quality of the input video. Then, we run the Viola-Jones face detector on each frame and apply both the algorithms. Finally, we use Kalman filter upon CAMSHIFT and RANSAC and compare with the preceding experiments. The comparisons are made for different real-time videos under heterogeneous environments through proposed performance measures, to identify the bestsuited method for a given scenario. Copyright © 2017, IGI Global.


Sridhar R.,Anna UniversityTamil Nadu | Janani V.,Anna UniversityTamil Nadu | Gowrisankar R.,Anna University | Monica G.,Anna UniversityTamil Nadu
International Journal of Intelligent Information Technologies | Year: 2017

In this paper, we propose to develop a Story Generator from hints using a machine learning approach. During the learning phase, the system is fed with stories which are POS tagged and are converted into a Language Relationship model that is represented as a conceptual graph. During the synthesis phase, the input hints which are delimited using hyphen and converted to a conceptual graph. This graph is matched with the conceptual graph of the corpus and probable words, its sequences along with the relationship are determined using three proposed methods namely Randomized selection, Weighted Selection using Bigram Probability of hint phrases and Weighted Selection using product of Bigram Probability of Conceptual Graph and Bigram Probability of hint phrases. Using the words, sequences and relationships, a sentence assembler algorithm is designed to position the words to form a sentence. To make the story complete and readable, suffixes are added using Tamil grammar to the assembled words and a story is generated which is syntactically and semantically correct. Copyright © 2017, IGI Global.


Sasikala S.,Anna UniversityTamil Nadu | Geetha S.,Vellore Institute of Technology
Neural Network World | Year: 2016

This work is motivated by the interest in feature selection that greatly affects the detection accuracy of a classifier. The goals of this paper are (i) identifying optimal feature subset using a novel wrapper based feature selection algorithm called Shapley Value Embedded Genetic Algorithm (SVEGA), (ii) showing the improvement in the detection accuracy of the Artificial Neural Network (ANN) classifier with the optimal features selected, (iii) evaluating the performance of proposed SVEGA-ANN model on the medical datasets. The medical diagnosis system has been built using a wrapper based feature selection algorithm that attempts to maximize the specificity and sensitivity (in turn the accuracy) as well as by employing an ANN for classification. Two memetic operators namely "include" and "remove" features (or genes) are introduced to realize the genetic algorithm (GA) solution. The use of GA for feature selection facilitates quick improvement in the solution through a fine tune search. An extensive experimental evaluation of the proposed SVEGA-ANN method on 26 benchmark datasets from UCI Machine Learning repository and Kent ridge repository, with three conventional classifiers, outperforms state-of-the-art systems in terms of classification accuracy, number of selected features and running time. © 2016 CTU FTS.


Jansi Rani S.V.,SSN College of Engineering | Narayanasamy P.,Anna UniversityTamil Nadu
International Journal of Applied Engineering Research | Year: 2016

Transmission control protocol (TCP) is implemented as a reliable data transfer protocol in wired networks which uses congestion control algorithms. Whenever there is a packet loss, it retransmits the lost packet. Packet loss is identified by two ways, on receiving three duplicate acknowledgments and on expiry of retransmission timeout. TCP is no longer reliable in wireless networks. The non-congestion retransmission timeout have been reported as one of the main problem of performance degradation of TCP in wireless network. Mainly there are two types of non-congestion retransmission timeout. They are spurious retransmission timeout due to sudden delays and random packet loss due to transmission errors. On spurious retransmission timeout, if multiple packets gets delayed continuously there occurs false fast retransmission which degrades TCP’s performance drastically. The proposed method identifies spurious retransmission timeout and improves TCP throughput. © Research India Publications.


Rajamanickam V.,Anna UniversityTamil Nadu | Marikkannan S.,Anna UniversityTamil Nadu | Rajavelu T.,Anna UniversityTamil Nadu
International Journal of Applied Engineering Research | Year: 2015

Due to the rapid growth of the multimedia service, the video compression becomes an essential process for reducing the required bandwidth for transmission and storage in many applications. In H.264 Video coding standard, Motion estimation is the very important part of video compression technique that provides improved bit rate reduction and coding efficiency when compared with the other existing standards such as H.261, H.262,H.263. Several algorithms have been developed for the process of motion estimation to improve better compression quality with less number of computational time. In this paper, a new hybrid algorithm for motion estimation process is been proposed which combines the two or more search patterns to reduce the motion estimation time and thereby reducing the number of search points. The simulation results shows that proposed motion estimation scheme achieves an reduction of motion estimation time when compared to existing algorithms. The proposed Motion estimation algorithm is developed and analyzed using MATLAB environment. © Research India Publications.


Shanthi T.,King's College | Krishnamurthi V.,Anna UniversityTamil Nadu
International Journal of Applied Engineering Research | Year: 2015

Wireless Sensor Network (WSN) is basically an energy starving network. The key issue in WSN is energy management, as these devices are battery operated devices and most of their powers are utilized in transmission and reception of radio signals. In heterogeneous environment, since each heterogeneous wireless sensor node (HWSN) has its own transmitting and receiving capability, they loss their energy faster than the homogeneous nodes. Behavior of radio conditions makes HWSN to drain their battery power which is the primary concern. Introducing Cognitive Radio Science into a heterogeneous WSN is one way to analyze the radio capability in a given area. We propose a Cognitive Radio based Heterogeneous Wireless Sensor Area Network (CoRHAN), where Cognitive radio enabled device is integrated into a Heterogeneous Wireless Sensor Network. CR device scans the radio capability of HWSNs at a given instant of time, analyze to decide which sensor node with radio capability has the maximum communication capability with reliable transmission so as to send the packet faster rather than forwarding packets to the nodes which have less radio capability. CR device analyzes radio resources collectively in-order to fully utilize the best of different wireless technologies thereby provide reliable radio services effectively and efficiently through optimal radio selection scheme. It observes radio resource utility, verify and update it‟s local detection statistics for dynamic decision making by thresholding its detection statistics. In such case, the CR becomes more efficient in data gathering and data collection. In addition, based on environmental conditions the CR is able to scan the radio parameters and collect as much as data possible avoiding multi-path congestion within the WSN. CoRHAN shares radio resources fairly and efficiently by integrating multiple networks together. CoRHAN‟s primary objective is to provide 1) Highly reliable communication whenever and wherever needed 2) Efficient utilization of the radio spectrum. Simulation and experimental analysis proves that CoRHAN improves the reliability of data transmission reducing the bit error rate and delay with optimized sensing time, maximizing spectrum utilization with minimum latency and guaranteed integrity. © Research India Publications.

Loading Anna UniversityTamil Nadu collaborators
Loading Anna UniversityTamil Nadu collaborators