Compressive sensing with perceptron based routing for varying traffic intensity based on capsule networks. (October 2019)

• Record Type: Journal Article
• Authors: Alagirisamy, Mukil; Chow, Chee-Onn; Noordin, Kamarul Ariffin Bin
• Is Part Of: Computers & electrical engineering. Volume 79(2019)
• Publication Date: 2019-10
• Subjects: Compressive sensing -- Data forwarding -- Perceptron based optimal routing -- Perceptron based routing with moderate traffic intensity; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.08.008
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Compressive sensing with data acquisition at wireless sensor nodes has overcome the rigid sampling procedure to acquire sensor data. Transfer of network data efficiently is considerably reduced in congested links within the topology of sensor nodes. Hence, in this research, optimization is provided using compressive sensing with a discrete wavelet transform (DWT) for data acquisition, and data are transferred through perceptron-based forwarding. Two protocols are proposed, namely: Perceptron-based Optimal Routing (POR) and Perceptron-based Routing with Moderate Traffic Intensity (PRMTI). POR uses a bipolar logic with a target value at the relay node for forwarding. If the target response is not satisfactory, then weight update is performed iteratively, until the incoming data meets the target response. PRMTI forwards when the link capacity exceeds the defined data-forwarding threshold at the relay node. Simulation validation has been performed for both protocols.