To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Reduce Energy Consumption and Send Secure Data Wireless Multimedia Sensor Networks Using A Combination of Techniques For Multi-Layer Watermark And Deep Learning |
|
Author |
Nasim Heydari, Behrouz Minaei ?Bidgoli |
| Citation |
Vol. 17 No. 2 pp. 98-105 |
|
Abstract |
As we know, wireless sensor networks are made up of a number of nodes that wirelessly communicate with each other and the sensor unit consists of several sensor nodes. Unlike earlier wireless sensor networks, wireless sensor networks are used to collect images and video multimedia. Since this type of network in both military applications and are used in applications civilian oversight, so their safety is of utmost importance. These networks, such as wireless sensor networks in each node with limited energy resources faced by the management of energy resources in them is important. In this paper, a new unsupervised algorithm for classification of multimedia messages and sliced them to move between nodes using machine learning is used. The proposed method consists of several steps that include: 1. the sensor node information in the image data using algorithms to securely add watermark resistant to attack .2- aggregate data are aggregated information. 3. In the main sensors, high-level features and deep learning algorithms provided by trained, then categorize images in the form of continuous pieces are sent over the network. As well as the segmentation of the images using deep learning algorithms have been proposed, the volume of multimedia packets at the network level has been reduced and data transfer speed is also increased. So in this article we have shown that the proposed method is a safe method for collecting data and in addition reduces the data volume transferred, and makes about 8.7% of energy consumption compared to other methods in wireless sensor networks, multimedia decrease. |
|
Keywords |
deep learning, watermarking method, wireless sensor networks, Huffman compression, and discrete cosine transform segmentation data |
|
URL |
