Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2021 | Book

Active User Blind Detection Through Deep Learning Read chapter Read first chapter

Cognitive Radio-Oriented Wireless Networks

15th EAI International Conference, CrownCom 2020, Rome, Italy, November 25-26, 2020, Proceedings

Editors: Giuseppe Caso, Luca De Nardis, Prof. Dr. Liljana Gavrilovska

Publisher: Springer International Publishing

Book Series : Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book constitutes the refereed proceedings of the 15th International Conference on Cognitive Radio-Oriented Wireless Networks, CROWNCOM 2020, held in Rome, Italy, in November 2020. Due to COVID-19 pandemic the conference was held virtually.
The 13 revised full papers were selected from 28 submissions and present all major technical aspects related to cognitive radio and networks. The papers are organized in four sessions: spectrum sensing and environment awareness; resource sharing and optimization; verticals and applications; business models and spectrum management.

Table of Contents

Frontmatter

Spectrum Sensing and Environment Awareness

Frontmatter
Active User Blind Detection Through Deep Learning
Abstract
Active user detection is a standard problem that concerns many applications using random access channels in cellular or ad hoc networks. Despite being known for a long time, such a detection problem is complex, and standard algorithms for blind detection have to trade between high computational complexity and detection error probability. Traditional algorithms rely on various theoretical frameworks, including compressive sensing and bayesian detection, and lead to iterative algorithms, e.g. orthogonal matching pursuit (OMP). However, none of these algorithms have been proven to achieve optimal performance.
This paper proposes a deep learning based algorithm (NN-MAP) able to improve on the performance of state-of-the-art algorithm while reducing detection time, with a codebook known at training time.
Cyrille Morin, Diane Duchemin, Jean-Marie Gorce, Claire Goursaud, Leonardo S. Cardoso
Spectrum Sensing Based on Dynamic Primary User with Additive Laplacian Noise in Cognitive Radio
Abstract
In this paper, spectrum sensing techniques with dynamic primary user (PU) are considered in the environment of Laplacian noise. It means the PU may not be present or absent during the whole sensing time. However, PU arrives or departs randomly in the sensing time interval. We consider three different detection schemes such as energy detection, absolute value cumulation detection (AVCD) and improved AVCD (i-AVCD). We present the performance in terms of receiver operating characteristic (ROC) and detection probability versus average signal-to-noise ratio (SNR) using simulations. We conclude that the detection performance in the dynamic scenario is better than the performance in the static scenario, when the arrival/departure parameter (\(\theta _{A}T\)/\(\theta _{D}T\)) is beyond one, where \(\theta _A\) and \(\theta _D\) are corresponding to arrival rate and departure rate of the PU respectively, and T is the sampling interval. Furthermore, the i-AVCD scheme outperforms AVCD and energy detection in the considered scenario.
Khushboo Sinha, Yogesh N. Trivedi
Blind Source Separation for Wireless Networks: A Tool for Topology Sensing
(Invited Paper)
Abstract
In this work, a tool for topology sensing of a non-collaborative wireless network using power profiles captured by radio-frequency (RF) sensors is proposed. Assuming that the features of the network (i.e., the number of nodes, medium access control (MAC) and routing protocols) are unknown and that the sensors observe signal mixtures because of the wireless medium, blind source separation (BSS) is used to separate the traffic profiles. Successively, the topology of the network is inferred by detecting causal relationships between the separated streams. According to the numerical results, the proposed tool senses the topology with promising accuracy when operating in mild shadowing conditions, even with a relatively low number of radio-frequency (RF) sensors.
Enrico Testi, Elia Favarelli, Andrea Giorgetti

Resource Management and Optimization

Frontmatter
Efficient Clustering Schemes Towards Information Collection
Abstract
One of the challenges in cooperative spectrum sensing is to optimize the energy consumption of the network. Delivery of all measurements from all the nodes to the fusion centre is not the best solution from the perspective of energy-efficiency. Clustering of nodes with similar channel conditions may reduce the amount of transmitted data, and in consequence reduce the amount of consumed energy. In this paper we investigate the performance of selected algorithms known in the domain of artificial intelligence, applied to perform reliable yet energy-aware spectrum sensing.
Krzysztof Cichoń, Adrian Kliks
A Non-zero Sum Power Control Game with Uncertainty
Abstract
We consider the communication between a transmitter (user) and a receiver in the presence of a jammer where the jammer, in contrast to the user, has access to local information about jamming fading gain (reflecting distance of the jammer to the receiver) and jamming cost (reflecting its technical characteristics). The problem is modeled as a Bayesian game. Signal-to-interference-plus-noise ratio (SINR) is considered as user’s communication utility. Nash equilibrium as well as Stackelberg equilibrium are derived in closed form and compared.
Andrey Garnaev
Demonstrating Spectrally Efficient Asynchronous Coexistence for Machine Type Communication: A Software Defined Radio Approach
Abstract
A software defined radio (SDR) approach to demonstrate the coexistence in Machine Type Communication (MTC) scenarios is presented. MTC in recent years has gained significant attention with its inclusion in the 5G business model. Spectrally efficient asynchronous communication is a key enabler in situations involving MTC. Past research has shown that some modifications to baseline cyclic prefix orthogonal frequency division multiplexing (CP-OFDM) can achieve better out-of-band (OOB) suppression and enable asynchronous coexistence. Inspired by this research, we provide a real world example of coexistence using SDR. We demonstrate the ability to asynchronously transmitting waveforms in adjacent channels with very narrow guard bands in between, and still be able to receive and demodulate them with low error vector magnitude (EVM) and low bit error rate (BER) that are comparable to the baseline CP-OFDM that uses synchronous communication.
Suranga Handagala, Miriam Leeser

Verticals and Applications

Frontmatter
Distance Estimation for Database-Assisted Autonomous Platooning
Abstract
This paper presents the improved distance estimation for the purpose of Database-assisted Autonomous Platooning and V2V channel modelling. The proposed approach combines commonly used GPS-based measurements with UWB-based measurements to benefit from both solutions. While GPS allow for unlimited measurement range, the UWB improves accuracy for short range. The paper is based on real-word measurements.
Paweł Kryszkiewicz, Michał Sybis, Paweł Sroka, Adrian Kliks
A Priced-Deferred Acceptance (p-DA) Technique for D2D Communication in Factories of the Future
Abstract
The Deferred Acceptance (DA) algorithm has often been used to study spectrum sharing and to solve the assignment problem of Device-to-Device (D2D) links co-existing with traditional cellular users. We present a new reward-based DA algorithm denoted as priced-DA or (p-DA) to improve reuse gains in scenarios where there are variations in the number of cellular users and D2D links and when there are variations in the length of the preference lists. Interference coordination is implemented by jointly managing the power allocation and quality of service (QoS) admission control based on the inter-distances between devices. Simulation case studies demonstrate the advantages of the presented p-DA technique in comparison to other tested centralised approaches.
Idayat O. Sanusi, Karim M. Nasr, Klaus Moessner
Data-Driven Intelligent Management of Energy Constrained Autonomous Vehicles in Smart Cities
Abstract
Intelligent transportation is an important component of future smart cities, and electric autonomous vehicles (EAVs) are envisioned to be the main form of transportation because EAVs can save energy, protect the environment, and improve service efficiency. With limited vehicle-specific energy storage capacity and overall constraint in the smart grid’s electric load, we propose a novel intelligent management scheme to jointly schedule the travel and charging activities of the EAV fleet in one geographical area. This scheme not only schedules EAVs to meet the passengers’ requests but also explores the matching problem between the energy requirement of EAVs and the deployment of charging piles in smart cities. We minimize the total cruise energy consumption of EAVs under the condition of limited energy supply while guaranteeing the quality-of-service (QoS). Network Calculus (NC) is extended to model the electric traffic flow in this paper. With the real-world electric taxi data in Beijing, simulation results demonstrate that the proposed scheme can achieve substantial energy reduction and remarkable improvements in both the order completion rate and utilization rate of the charging stations.
Yingzhu Ren, Qimei Cui, Xiyu Zhao, Yingze Wang, Xueqing Huang, Wei Ni
A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting
Abstract
One of the beyond-5G developments that is often highlighted is the integration of wireless communication and radio sensing. This paper addresses the potential of communication-sensing integration of Large Intelligent Surfaces (LIS) in an exemplary Industry 4.0 scenario. Besides the potential for high throughput and efficient multiplexing of wireless links, an LIS can offer a high-resolution rendering of the propagation environment. This is because, in an indoor setting, it can be placed in proximity to the sensed phenomena, while the high resolution is offered by densely spaced tiny antennas deployed over a large area. By treating an LIS as a radio image of the environment, we develop sensing techniques that leverage the usage of computer vision combined with machine learning. We test these methods for a scenario where we need to detect whether an industrial robot deviates from a predefined route. The results show that the LIS-based sensing offers high precision and has a high application potential in indoor industrial environments.
Cristian J. Vaca-Rubio, Pablo Ramirez-Espinosa, Robin Jess Williams, Kimmo Kansanen, Zheng-Hua Tan, Elisabeth de Carvalho, Petar Popovski

Business Models and Spectrum Management

Frontmatter
Scalability and Replicability of Spectrum for Private 5G Network Business: Insights into Radio Authorization Policies
Abstract
New spectrum bands are being released to respond to the growing need for locally deployed industrial and private networks. This calls for new licensing schemes and spectrum sharing approaches. New challenges are faced from the ever-increasing variety of released spectrum bands with different technical and operational requirements and the increasing fragmentation of spectrum management approaches. While the standardization is progressing and technical solutions are developed for the new networks, less attention has been paid to the radio product related regulation, including equipment authorization frameworks. With roots in engineering, policy and economics, this paper looks through the lenses of business model framework at scenarios of wireless equipment authorization related to novel spectrum management approaches. This paper provides an overview of radio authorization for mobile communication networks and develops a conceptual framework to depict and analyze authorization policies. The results indicate the strong impact the authorization frameworks have on the scalability and replicability of the business. This calls for novel models of governance and regulation that highlight utilization of harmonized, widely employed frequency bands and the associated technical requirements.
Pekka Ojanen, Seppo Yrjölä
Novel Spectrum Administration and Management Approaches Transform 5G Towards Open Ecosystemic Business Models
Abstract
The ongoing 5G evolution transforming network from connectivity driven to service dominant logic will impact the stakeholder roles, ecosystem and business models. Systemic change will lower the barriers to entry and expand the ecosystem to new roles such as local operators, edge cloud services providers and resource aggregators and agents. Spectrum regulation has traditionally acted as a gate keeper of the mobile service provisioning, and lately national authorities have reacted via allocating new frequency bands and considering novel flexible spectrum administration and management methods and tools. This paper provides a comprehensive overview of the most recent spectrum regulation decisions for mobile communication networks and shows how local licensing, spectrum sharing, and unlicensed commons approaches work as novel business model antecedent. The study analyzes key spectrum antecedents for the open ecosystemic business model value configuration.
Seppo Yrjölä, Pekka Ojanen
Moving from 5G in Verticals to Sustainable 6G: Business, Regulatory and Technical Research Prospects
Abstract
Mobile communication research is increasingly addressing the use of 5G in verticals, which has led to the emergence of local and often private 5G networks. At the same time, research on 6G has started, with a bold goal of building a strong linkage between 6G and the United Nations Sustainable Development Goals (UN SDGs). Both of these developments call for a highly multi-disciplinary approach covering the inter-related perspectives of business, regulation and technology. This paper summarizes recent advances in using 5G to serve vertical sectors’ needs and describes a path towards sustainable 6G considering business, regulation and technology viewpoints. By focusing on key trends, the research summarizes four alternative scenarios for the futures business of 6G and considers related regulatory and technology aspects. Our findings highlight the importance of understanding the complex relations of business, regulation and technology perspectives and the role of ecosystems in both 5G in verticals and ultimately in the development of sustainable 6G to bring together stakeholders to solve long-term sustainability problems.
Marja Matinmikko-Blue, Seppo Yrjölä, Petri Ahokangas
Backmatter
Metadata
Title
Cognitive Radio-Oriented Wireless Networks
Editors
Giuseppe Caso
Luca De Nardis
Prof. Dr. Liljana Gavrilovska
Copyright Year
2021
Electronic ISBN
978-3-030-73423-7
Print ISBN
978-3-030-73422-0
DOI
https://doi.org/10.1007/978-3-030-73423-7

Premium Partner

    Image Credits