UB ScholarWorks

A Highly Accurate Deep Learning Based Approach For Developing Wireless Sensor Network Middleware

Show simple item record

dc.contributor.author Alshinina, Remah
dc.date.accessioned 2018-10-09T17:06:26Z
dc.date.available 2018-10-09T17:06:26Z
dc.date.issued 2018-09-22
dc.identifier.citation R.A. Alshinina, "A Highly Accurate Deep Learning Based Approach For Developing Wireless Sensor Network Middleware", Ph.D. dissertation, Dept. of Computer Science and Engineering, Univ. of Bridgeport, Bridgeport, CT, 2018. en_US
dc.identifier.uri https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2492
dc.description.abstract Despite the popularity of wireless sensor networks (WSNs) in a wide range of applications, the security problems associated with WSNs have not been completely resolved. Since these applications deal with the transfer of sensitive data, protection from various attacks and intrusions is essential. From the current literature, we observed that existing security algorithms are not suitable for large-scale WSNs due to limitations in energy consumption, throughput, and overhead. Middleware is generally introduced as an intermediate layer between WSNs and the end user to address security challenges. However, literature suggests that most existing middleware only cater to intrusions and malicious attacks at the application level rather than during data transmission. This results in loss of nodes during data transmission, increased energy consumption, and increased overhead. In this research, we introduce an intelligent middleware based on an unsupervised learning technique called the Generative Adversarial Networks (GANs) algorithm. GANs contain two networks: a generator (G) network and a discriminator (D) network. The G network generates fake data that is identical to the data from the sensor nodes; it combines fake and real data to confuse the adversary and stop them from differentiating between the two. This technique completely eliminates the need for fake sensor nodes, which consume more power and reduce both throughput and the lifetime of the network. The D network contains multiple layers that have the ability to differentiate between real and fake data. The output intended for this algorithm shows an actual interpretation of the data that is securely communicated through the WSN. The framework is implemented in Python with experiments performed using Keras. The results illustrate that the suggested algorithm not only improves the accuracy of the data but also enhances its security by protecting it from attacks. Data transmission from the WSN to the end user then becomes much more secure and accurate compared to conventional techniques. Simulation results show that the proposed technique provides higher throughput and increases successful data rates while keeping the energy consumption low. en_US
dc.language.iso en_US en_US
dc.subject Wireless sensor networks (WSN) en_US
dc.subject Machine learning en_US
dc.subject Security en_US
dc.subject Generative adversarial network en_US
dc.subject Discriminator en_US
dc.title A Highly Accurate Deep Learning Based Approach For Developing Wireless Sensor Network Middleware en_US
dc.type Thesis en_US
dc.institute.department School of Engineering en_US
dc.institute.name University of Bridgeport en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ScholarWorks

Advanced Search


My Account