Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices

The article “Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices” by our lab member Ramiro Utrilla has just been published in the IEEE Access, a high-impact open-access journal.

This work has been carried out in collaboration with researchers from the CONNECT – Centre for Future Networks and Communications in Dublin (Ireland), where Ramiro carried out a research stay of 3 months.

In this article, they focus on the Automatic Modulation Classification (AMC). AMC is essential to carry out multiple CR techniques, such as dynamic spectrum access, link adaptation and interference detection, aimed at improving communications throughput and reliability and, in turn, spectral efficiency. In recent years, multiple Deep Learning (DL) techniques have been proposed to address the AMC problem. These DL techniques have demonstrated better generalization, scalability and robustness capabilities compared to previous solutions. However, most of these techniques require high processing and storage capabilities that limit their applicability to energy- and computation-constrained end-devices.

In this work, they propose a new gated recurrent unit neural network solution for AMC that has been specifically designed for resource-constrained IoT devices.


The proposed GRU network model for AMC.

They trained and tested their solution with over-the-air measurements of real radio signals, which were acquired with the MIGOU platform.


Dataset generation scenario set up.


Comparison of signals recorded at (a) 1 and (b) 6 meters. The signals in the bottom row are the normalized version of those in the top row.

Their results show that the proposed solution has a memory footprint of 73.5 kBytes, 51.74% less than the reference model, and achieves a classification accuracy of 92.4%.

Increasing the training set can lead to improvements in the performance of a model without increasing its complexity. These improvements allow developers to reduce the complexity of the model and, therefore, the device resources it requires. However, longer training processes can lead to fitting and gradient problems. These tradeoffs should be explored when developing neural network-based solutions for resource-constrained end-devices.

A Methodology for Choosing Time Synchronization Strategies for Wireless IoT Networks

This summer we have published a new article about time synchronization for wireless sensor networks, applied to the field of IoT, in Sensors Open Access Journal. This journal has these statistics:

  • 2018 Impact Factor: 3.031
  • 5-year Impact Factor: 3.302
  • JCR category rank: 15/61 (Q1) in ‘Instruments & Instrumentation’

This article belongs to the Special Issue Topology Control and Protocols in Sensor Network and IoT Applications.

This article has a direct relationship with the thesis of our colleague Francisco Tirado-Andrés. This thesis investigates a methodology, and associated tools, to make it easier for all researchers to choose time synchronization protocols for specific WSNs.

For more information about this article please visit MDPI webpage.

A WSN-Based Intrusion Alarm System to Improve Safety in Road Work Zones

Title: A WSN-Based Intrusion Alarm System to Improve Safety in Road Work Zones
Authors: Jose Martin, Alba Rozas, and Alvaro Araujo
Published in: Journal of Sensors
Date of Publication: Jun 2016
Digital Object Identifier : 10.1155/2016/7048141
Web: https://www.hindawi.com/journals/js/2016/7048141/

Road traffic accidents are one of the main causes of death and disability worldwide. Workers responsible for maintaining and repairing roadways are especially prone to suffer these events, given their exceptional exposure to traffic. Since these actuations usually coexist with regular traffic, an errant driver can easily intrude the work area and provoke a collision. Some authors have proposed mechanisms aimed at detecting breaches in the work zone perimeter and alerting workers, which are collectively called intrusion alarm systems. However, they have several limitations and have not yet fulfilled the necessities of these scenarios. In this paper, we propose a new intrusion alarm system based on a Wireless Sensor Network (WSN). Our system is comprised of two main elements: vehicle detectors that form a virtual barrier and detect perimeter breaches by means of an ultrasonic beam and individual warning devices that transmit alerts to the workers. All these elements have a wireless communication interface and form a network that covers the whole work area. This network is in charge of transmitting and routing the alarms and coordinates the behavior of the system. We have tested our solution under real conditions with satisfactory results.

Cognitive Wireless Sensor Network Platform for Cooperative Communications

Title: Cognitive Wireless Sensor Network Platform for Cooperative Communications
Authors: Agustín Tena, Guillermo Jara, Juan Domingo, Elena Romero, Alvaro Araujo
Published in: International Journal of Distributed Sensor Networks
Date of Publication: January 2014
Digital Object Identifier : 10.1155/2014/473905
Web: http://www.hindawi.com/journals/ijdsn/2014/473905/

Nowadays, Wireless Ad-Hoc Sensor Networks (WAHSNs), specially limited in energy and resources, are subject to development constraints and difficulties such as the increasing Radio Frequency (RF) spectrum saturation at the unlicensed bands. Cognitive Wireless Sensor Networks (CWSNs), leaning on a cooperative communication model, develop new strategies to mitigate the inefficient use of the spectrum that WAHSNs face. However, few and poorly featured platforms allow their study due to their early research stage.

This paper presents a versatile platform that brings together cognitive properties into WAHSNs. It combines hardware and software modules as an entire instrument to investigate CWSNs. The hardware fits WAHSN requirements in terms of size, cost, features, and energy. It allows communication over three different RF bands, becoming the first cognitive platform for WAHSNs with this capability. In addition, its modular and scalable design is widely adaptable to almost any WAHSN application.

Significant features such as Radio Interface (RI) agility or energy consumption have been proved throughout different performance tests.

 

nodo

PUE Attack Detection in CWSN Using Collaboration and Learning Behavior

Title: PUE Attack Detection in CWSN Using Collaboration and Learning Behavior
Authors: Javier Blesa, Elena Romero, Alba Rozas, Alvaro Araujo and Octavio Nieto-Taladriz
Published in: International Journal of Distributed Sensor Networks
Date of Publication: June 2013
Digital Object Identifier : 10.1155/2013/815959
Web: http://www.hindawi.com/journals/ijdsn/2013/815959/

Cognitive Wireless Sensor Network (CWSN) is a new paradigm which integrates cognitive features in traditional Wireless Sensor Networks (WSNs) to mitigate important problems such as spectrum occupancy. Security in Cognitive Wireless Sensor Networks is an important problem because these kinds of networks manage critical applications and data. Moreover, the specific constraints of WSN make the problem even more critical. However, effective solutions have not been implemented yet. Among the specific attacks derived from new cognitive features, the one most studied is the Primary User Emulation (PUE) attack. This paper discusses a new approach, based on anomaly behavior detection and collaboration, to detect the PUE attack in CWSN scenarios. A nonparametric CUSUM algorithm, suitable for low resource networks like CWSN, has been used in this work. The algorithm has been tested using a cognitive simulator that brings important results in this area. For example, the result shows that the number of collaborative nodes is the most important parameter in order to improve the PUE attack detection rates. If the 20% of the nodes collaborates, the PUE detection reaches the 98% with less than 1% of false positives.

cognitive radio module