Informatics Publishing Limited

B. Shaji ¹, K. L. Nisha ²

Affiliations
1 Marthandam College of Engineering and Technology MACET, IN
2 Arunachala College of Engineering, Velichanthai, IN

Abstract

Wireless sensor networks (WSN) consist of several sensor nodes which are used for transmitting the data with limited capacity. In WSN, it is necessary to optimize the resource for better transmission of data from source node to destination and maximize the coverage area of the network to augment the lifetime of the network. In optimizing the resource in WSN, energy plays a major role to sustain the sensor nodes active status in the network. For maximizing the sensor nodes coverage area, several paths are followed by the previous researchers in different set of methods. Among all the previous works, Changlei Liu et. Al., presented a centralized heuristic protocol for scheduling the activities of the sensors for maximizing the spatial temporal coverage. To resolve the optimization problem, parallel optimization protocol (POP) is presented. Even though the sensor nodes are energy constrained by POP, only the limited numbers of sensor nodes are made active simultaneously for better coverage by consuming more energy. To resolve the above said issue, in this work, we plan to resolve the energy-efficient wireless sensor network coverage using node constrained linear integer programming technique. With the technique, a node constrained energy efficient connected coverage algorithm is developed for enhancing the lifetime of the network by increasing the coverage area of the sensor nodes. For the better coverage area phase, an energy drain rate of each sensor node is determined and formulates the sensing structure of the information. Experimental evaluation is done with the sensor nodes for better coverage in network environment and its performance is evaluated with varied set of sensor nodes with measuring metrics such as energy efficiency, network lifetime, and coverage area.

Keywords

Wireless Sensor Networks, Intermittently Connections, Resource Optimization, Energy Efficient, Linear Programming Technique, Greedy Approach.

Full Text

     

B. Shaji ¹, S. Purushothaman ², R. Rajeswari ³

Affiliations
1 VELS University, Pallavaram, Chennai-600117, IN
2 PET Engineering College, Vallioor-627117, IN
3 Mother Teresa Women's University, Kodaikanal-624102, IN

Abstract

Wavelet decomposition has been applied to mammogram image to obtain four different coefficients for 5 levels of decompositions. The coefficients are: low frequency coefficients (A), vertical high frequency coefficients (V), horizontal high frequency coefficients (H), and diagonal high frequency coefficients (D). The features of the mammography image are obtained using the wavelet transform selecting the different levels of decompositions. The proposed method presents a new classification approach to microcalcification (MC) detection in mammograms using wavelet and back propagation algorithm (BPA) Neural Network. These features obtained from wavelet are representation of MC as well as other information of the image. Daubauchi wavelet has been used to decompose image to 5 levels. Statistical features are extracted from the wavelet coefficients. Training the BPA with features and testing the BPA to identify the presence of MC has been done. The percentage identification is above 96.2%. The performance of the proposed method based on the quality of the mammogram image.

Keywords

Mammogram, Microcalcification, Wavelet Transform, Back Propagation Neural Network.

Full Text