You are here: Home / People of WaveCoRE Arenberg / Sofie Pollin

Sofie Pollin

Sofie Pollin
TELEMIC
Kasteelpark Arenberg 10 - box 2444
3001 Leuven
Belgium
room: 02.21

tel: +32 16 32 10 51 or +32 16 37 40 85
contact

My research interests are: 

  • wireless communication 

  • software defined radio and cognitive radio
  • sensor networks
  • wireless standards: WLAN, WPAN, LTE
  • cross-layer optimization
  • learning in networks
  • aerial sensor networks
  •  

Leading Group

Publications

query=user:U0041938 year:[2003 TO 2023] &institution=lirias&from=1&step=20&sort=scdate
showing 1 to 20 of 459
Items per page 10 |20 |50
Sort newest first |author |title |popularity
Type all | articles | presentations | conferences | chapters | other | reports | phd theses | book reviews | books | outreach | edited books
1/23
  • thesis-dissertation
    Basak, Sanjoy; 2023. Drone Detection and Classification using Artificial Intelligence based RF Sensing.
    LIRIAS4117873
    description
    Recent technological advancements and the growing popularity of drones have brought about many beneficial applications across various industries. However, their widespread availability has resulted in a rise in illegal activities. Implementing effective Counter-UAS (C-UAS) is essential to protect critical infrastructure, enforce regulations, and prevent contraband deliveries. By promptly identifying unauthorized drones, authorities can take the necessary actions to ensure responsible use of drones and mitigate potential liabilities and risks associated with their misuse. Radio Frequency (RF)-based drone detection is of significant importance in countering the illegal use of drones due to its effectiveness and versatility. RF detection systems monitor the RF signals transmitted by a drone and its Ground Control Station (GCS) in order to detect and classify them. However, conventional classification algorithms face significant challenges in accurately classifying drone RF protocols due to the prevalence of widely used RF communication systems, such as Wi-Fi and Bluetooth, operating in the same frequency bands (2.4 GHz and 5 GHz ISM band) and utilizing similar modulation techniques like spread spectrum modulation. This study aims to address these challenges by utilizing Artificial Intelligence (AI)-based algorithms to automatically detect and classify drone RF protocols. We achieve our study objective with the following five key contributions: (1) First, a novel and detailed RF database is created using commercial drone RF and Wi-Fi communication signals. This database facilitates the development of a Deep Learning (DL)-based detection and classification framework, addressing the absence of an open-source drone RF database for training such frameworks. (2) Second, this thesis proposes RF signal detection, feature extraction, and classification simultaneously using the You Only Look Once (YOLO) framework. We develop a YOLO framework to detect and classify multiple signals simultaneously, even at low SNR conditions. (3) Third, following signal detection and feature extraction, novelty detection is performed to determine whether the detected signal is known to the classifier or novel. (4) Fourth, this thesis proposes a data-driven DL-based framework to classify the drone RF protocol. (5) Finally, we develop a spectrum prediction framework to predict the future time and frequency sequences for smart RF jamming.

    Accepted
  • thesis-dissertation
    Storrer, Laurent; 2023. Passive Radar Based on Wi-Fi Signals for Crowd Monitoring: From Multi-Target Tracking to Large-Scale Crowd Analysis.
    LIRIAS4123274
    description
    This thesis aims at performing crowd monitoring by exploiting signals of opportunity from existing Wi-Fi access points to build a passive radar. Radar processing will be applied on signals that bounced on people (targets) in an environment to obtain a so-called range-Doppler map (RDM) containing the distance and speed information of the targets, as well as an angle spectrum (from MUSIC method) containing the angle-of-arrival of the signals that bounced on targets. Experiments will be performed with human targets using Universal Software Radio Peripherals (USRPs) to assess the feasibility of using the latest Wi-Fi standards (802.11ac, 802.11ax) for passive radar application, and the feasibility of building a multi-antenna passive radar with high bandwidth. Target tracking algorithm will be applied on measurements from the USRPs setup to track the target movements over time in cartesian coordinates in the environment. Since the relation between the measurements and the target tracking state in cartesian coordinates involves non-linear equations, the Unscented Kalman Filter (UKF) will be investigated in particular to tackle those non-linearities. Single-target tracking will first be considered, and then extended to multi-target tracking and group tracking. For the group tracking, clustering algorithms such as Density-based spatial clustering of applications with noise (DBSCAN) will be applied to combine the signal responses of several targets being close from each other in one single centroid in order to track that centroid only. Data association techniques such as the Probabilistic Data Association Filter (PDAF), the Joint-PDAF and possibly Multiple Hypothesis Tracking (MHT) will be investigated to link targets signals response with current tracks of the UKF. Machine learning-based algorithms will also be developped to count the number of people in a group based on the radar RDM and angle spectrum, by exploiting the high bandwidth provided by the latest Wi-Fi standard as well as the signals from multiple antennas at the receiver. This will include the study of Bayes classifiers, Support Vector Machines (SVM) and Neural Networks. The output of those algorithms will then be combined with the group tracking algorithms in order to simultaneously track groups in space and know the number of people in those groups.

    Accepted
  • thesis-dissertation
    Colpaert, Achiel; 2023. Reliable Connectivity of UAVs in Multi-Antenna Cellular Communication Systems.
    LIRIAS4122219
    description
    Unmanned aerial vehicles (UAV) are becoming more common and important in everyday life. Recently, Morgan Stanley released a forecast stating that by 2050, the total market of Urban Air Mobility, including drone delivery, air taxi, and patrolling drones, etc., will reach up to 11% of the projected global Gross Domestic Product. Ensuring the expected safety, security, operation transparency, and airspace usage efficiency of such a large fleet of UAVs requires seeking UAV Traffic Management (UTM) solutions. The UTM framework formulated by the International Civil Aviation Organization includes cellular networks as a critical enabler of large-scale drone deployments. However, the research community has indicated problems when introducing UAVs in cellular networks. Most of these problems are related to high inter-cell interference levels due to the different propagation conditions for UAVs. Since cellular networks are designed for serving ground users, the aerial coverage does not meet the reliability requirements for UAV operation. Increasing the directivity of the signal using beamforming has been proposed to improve the aerial coverage. However, the performance of both analog and digital beamforming for UAVs remains to be seen. Also, questions remain surrounding the impact of UAV mobility on the operation of cellular networks; for example, the standard base station handover protocol might behave differently for an aerial user when compared to a ground user. Researchers have explored the topics of aerial coverage, beamforming, and mobility on a theoretical basis. However, more practical research is needed to deploy UAVs in an actual environment. This thesis aims to build and extend the knowledge in the UAV research community and fill the gap between theory and practice through extensive 3D coverage simulations and measurements. We develop a comprehensive 3D aerial coverage simulator to analyze beamforming and operator diversity. We also build measurement platforms to evaluate Air-to-Ground Massive MIMO (MaMIMO) channel characteristics and to investigate both analog and digital beamforming for UAVs in the 6-GHz and mmWave frequency range. In this regard, seven main contributions have been achieved. The first three contributions are primarily simulator-based, where we use the 3D aerial coverage simulator to research the performance of UAVs in a realistic cellular network. The first main contribution is analyzing the aerial coverage of the current existing cellular networks. Using our simulator, we show that the existing cellular networks fail to provide reliable aerial coverage in their current state. However, we can improve the aerial coverage significantly when introducing mmWave beamforming to the current infrastructure. The second main contribution is investigating this mmWave beamforming by extending the aerial coverage simulator. We introduce realistic antenna array radiation patterns and provide guidelines for antenna array design for beamforming. In an actual environment, we evaluate how the antenna array topology impacts the beamforming performance and reliability for aerial users by evaluating handovers and radio link failures. The third main contribution is to further improve a cellular-connected UAV's reliability by introducing operator diversity. Using the abovementioned simulator, we show that connecting to multiple cellular networks can significantly enhance the link's reliability for a cellular-connected UAV. Our results show that operator diversity can decrease the number of handovers and that it increases the covered operating airspace for UAVs. The following four contributions are primarily measurement-based as we investigate the actual performance of the analog and digital beamforming and the stationarity of the wireless channel of aerial users. As the fourth main contribution, we demonstrate the increase in spectral efficiency when adding digital precoding on top of analog beamforming using a MaMIMO prototype. We do this by first creating an analytical model. Then, we implement a working Multi-User Massive MIMO prototype to perform over-the-air measurements. The results show that hybrid beamforming outperforms analog beamforming when serving more than one user by enabling multiple users to be served simultaneously and increasing spectral efficiency. The fifth main contribution is designing and implementing an Air-to-Ground (A2G) MaMIMO channel measurement system. The measurement system is designed to obtain channel data between a flying UAV and a large antenna array on the ground. We can use this channel data to characterize the channel of a mobile UAV to deepen our knowledge of the A2G MaMIMO channel. The sixth main contribution is using this measurement platform to characterize the quasi-stationarity of the A2G MaMIMO channel using over-the-air measurement data. We perform the channel characterization in the time, frequency, and spatial domains and evaluate the quasi-stationarity region for each domain. We introduce the stationary angle as a new metric to be considered alongside the stationary distance for MaMIMO systems. The stationary angle should be regarded as a tool when designing beam-tracking systems, as it indicates the stationarity of the channel in the angular domain. The seventh and final contribution is capturing an extensive A2G MaMIMO channel data set of different types of trajectories and publishing it to the research community.

    Accepted
  • conference
    Grosheva, Nina; Hersyandika, Rizqi; Widmer, Joerg; Pollin, Sofie; 2023. In-Band Multi-Connectivity with Local Beamtraining for Improving mmWave Network Resilience. MSWiM '23: Proceedings of the Int'l ACM Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems; 2023; pp. 277 - 284 Publisher: Association for Computing Machinery
    LIRIAS4120874
    description


    Published
  • conference
    Hammoud, Khodr; Schreurs, Dominique; Pollin, Sofie; Cui, Zhuangzhuang; 2023. A Joint Opportunistic Energy Harvesting and Communication System Using VLC for Battery-Less PV-Equipped IoT. IEEE International Conference on Communications; 2023; pp. Publisher: Institute of Electrical and Electronics Engineers
    LIRIAS4120318
    description


    Published
  • conference
    Leeman, Brian; Claeys, Tim; Pollin, Sofie; Hallez, Hans; Pissoort, Davy; 2023. Novel Narrowband Interference Model to Analyze the Electromagnetic Resilience of OFDM Systems. 2023 International Symposium on Electromagnetic Compatibility – EMC Europe; 2023; pp. 1 - 6 Publisher: IEEE
    LIRIAS4116069
    description
    Orthogonal Frequency Division Multiplexing based protocols are increasing in popularity for use in applications where dependability under harsh Electromagnetic conditions are of major importance, for example Vehicle-to-Everything communication. Orthogonal Frequency Division Multiplexing is especially vulnerable to narrowband interferences and thus, evaluating the electromagnetic resilience of Orthogonal Frequency Division Multiplexing systems to narrowband interferences is particularly interesting and important. Current narrowband interference models either don’t take into account the bandwidth of the narrowband interference or are constructed in such a way that in depth analysis on short time scales is impossible. Therefore, this paper presents a novel narrowband interference model for electromagnetic resilience analysis without the aforementioned limitations. The model is mathematically defined, a mathematical derivation for the interference spectrum is given and simulations for the model are performed when it behaves as a QAM16 interferer.

    Published
  • conference
    Xiong, Haoqiu; Cui, Zhuangzhuang; Liu, Mingqing; Miao, yang; Pollin, Sofie; 2023. Multi-person Localization and Respiration Sensing under IEEE 802.11ay Standard. Proceedings of the 3rd ACM MobiCom Workshop on Integrated Sensing and Communications Systems; 2023; pp. 31 - 36 Publisher: Association for Computing Machinery New York, NY, United States
    LIRIAS4119365
    description


    Published
  • journal-article
    Van Leemput, Dries; Sabovic, Adnan; Hammoud, Khodr; Famaey, Jeroen; Pollin, Sofie; De Poorter, Eli; 2023. Energy Harvesting for Wireless IoT Use Cases: A Generic Feasibility Model and Tradeoff Study. Ieee Internet Of Things Journal; 2023; Vol. 10; iss. 17; pp. 15025 - 15043
    LIRIAS4120317
    description

    Publisher: Institute of Electrical and Electronics Engineers
    Published
  • dataset
    COLPAERT, Achiel; THYS, Cel; CUI, Zhuangzhuang; POLLIN, Sofie; MaMIMO-UAV 3D Channel State Information Dataset. Publisher: KU Leuven RDR
    LIRIAS4089571
    description
    A base station is placed on the parking lot in front of the ESAT building. It has a 8x8 rectangular patch antenna array pointing towards the sky. A drone flew several trajectories on the campus of KULeuven, see figure 'measurements_plot.png', while transmitting pilot sequences. The channel between the drone and a base station is estimated using the pilot sequences.

    Published online
  • journal-article
    Colpaert, Achiel; De Bast, Sibren; Guevara, Andrea; Cui, Zhuangzhuang; Pollin, Sofie; Beerten, roobert; 2023. Massive MIMO Channel Measurement Data Set for Localization and Communication. Ieee Communications Magazine; 2023; pp. 1 - 7
    LIRIAS3955776
    description

    Publisher: Institute of Electrical and Electronics Engineers
    Published
  • thesis-dissertation
    Perenda, Erma; 2023. Deep Learning Based Modulation Classification with Channel and Hardware Impairments.
    LIRIAS4084112
    description
    Automatic Modulation Classification (AMC) is significant for the practical support of various emerging spectrum applications ranging from spectrum enforcement to signal intelligence. Although AMC has received considerable research interest for more than 40 years, most developed methods have been designed under the unrealistic assumptions of prior knowledge of signal and channel parameters and an ideal RF front-end. This doctoral work provides a significant contribution towards the robust modulation classification under realistic conditions leveraging the recent advancements in Deep Learning (DL). We achieve the robust modulation classifier by answering the following research questions: (1) Which features do DL-based classifiers learn, and why are they sensitive to channel and hardware impairments? (2) What is the performance gain of DLB signal transformations to emulate channel and hardware impairments? (3) How can we automate optimizing the DNN architectures adopted for modulation classifiers? (4) How to develop simple mathematical operators to emulate the impact of channel and hardware impairments to avoid the exhaustive design of channel and signal models? These research questions are answered with the following four key contributions of this doctoral work: (1) Deep inspection of DLB classifiers' sensitivity to channel and hardware impairmentsm (2) design of novel DL models for more robust modulation classification, (3) development a handy tool to optimize DNN architectures adopted for modulation classification, and (4) design of simple mathematical operators to emulate the impact of channel and hardware impairments on the signal constellations. We showed that signal shape critically depends on the input conditions and explains the poor transferability of learned models to unseen channel and hardware impairments. DL models can significantly improve the modulation classifier's robustness to channel and hardware impairments. A carefully designed memetic algorithm can find a deep neural network architecture that outperforms all human-crafted architectures for a modulation classifier. Data augmentation is a handy tool to guarantee balance among data from different channels and hardware impairments, which is hard to achieve in unlabeled data collected in practice.

    Published
  • conference
    Schuhmacher, Luisa; Pollin, Sofie; Sallouha, Hazem; 2023. ecoBLE: A Low-Computation Energy Consumption Prediction Framework for Bluetooth Low Energy. EWSN '23: Proceedings of the 2023 Inernational Conference on Embedded Wireless Systems and Networks; 2023
    LIRIAS4100855
    description


    Accepted
  • conference
    Fernandez Landivar, Jimmy Xavier; Crombez, Pieter; Pollin, Sofie; Sallouha, Hazem; 2023. QualityBLE: A QoS Aware Implementation for BLE Mesh Networks. ACM Digital Library; 2023
    LIRIAS4096384
    description


    Accepted
  • thesis-dissertation
    Minucci, Franco; 2023. Reliable Communication and Accurate Sensing for UAV Traffic Management.
    LIRIAS4085576
    description
    In recent years, the number of Unmanned Aerial Vehicles (a.k.a. drones) in our skies increased dramatically. Drones are used in many civil and, sadly, military applications. Typical civil applications are environmental and structural monitoring of difficult-to-reach zones, filming for the TV and the Cinema, taking spectacular panoramic photos, and also surveillance and search and rescue operations by the police, the forest guard, and the fire brigade. Delivery companies and big online retail companies are also experimenting with the use of drones for package delivery, which can be very convenient in certain areas with sparse populations. It is also evident how drones can greatly impact conflicts, such as the horrendous war between Russia and Ukraine (2022). The higher the number of drones flying in our skies, the higher the probability of accidents. The Single European Sky ATM Research 3 Joint Undertaking, together with EASA, took into its hands the responsibility of developing a framework to safely integrate drone traffic into the standard air traffic management system. This framework is called U-Space, and it comprises a multitude of projects to develop the technology and the operational procedures to safely operate drones in civil airspace. This thesis work spans two distinct projects, PercEvite and Electrosense, and exposes our findings in the context of drone-to-drone communications for safety applications. In our vision, drones should be able to interact and coordinate with each other autonomously and reliably for U-Space to happen. Drone-to-drone communication is thus an essential component to flying safely, with total autonomy, and with minimal pilot intervention. After an introductory chapter which expands on the concepts of U-Space and drone communications, the thesis is split into two parts. The first part, covering the PercEvite project, is composed of Chapters 2 and 3. The second part, covering the Electrosense project, is composed of Chapters 4 and 5. Chapter 2 is about unifying the terminologies of air traffic control and communication engineering, especially concerning the definition of terms such as 'safe separation' and 'conflict management'. The chapter also explains the architecture of a drone traffic management system and how different communication systems can be adapted for different use cases in the context of traffic management. Chapter 3 illustrates the design, simulation and implementation of a communication system for drones. The system exploits the small embedded Wi-Fi modules present in many small commercial drones which allows its deployment on already existing hardware. Chapter 4 is about RF interference, and how it can affect aerial communications at different altitudes. The chapter presents the design of a probe for high altitude measurements, based on a software-defined radio and an embedded computer. It also shows simulation results to roughly quantify the impact of interference on conflict management algorithms. Chapter 5 explains in detail how to calibrate software-defined radios to accurately measure RF power which is crucial to quantify interference levels and spectrum occupancy. As a test case to show the potential and pitfalls of software-defined radios, a measurement of the electric field generated by a 5G base station is discussed. Finally, Chapter 6 summarises the most important findings of this thesis and proposes future lines of research and potential work to answer the new research questions and improve the findings obtained during my PhD program.

    Accepted
  • conference
    Saboor, Abdul; Vinogradov, Evgenii; Cui, Zhuangzhuang; Pollin, Sofie; 2023. Probability of Line of Sight Evaluation in Urban Environments using 3D Simulator. 2023 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom 2023); 2023
    LIRIAS4087364
    description


    Accepted
  • journal-article
    Li, Chenglong; De Bast, Sibren; Miao, Yang; Tanghe, Emmeric; Pollin, Sofie; Joseph, Wout; 2023. Contact-Free Multitarget Tracking Using Distributed Massive MIMO-OFDM Communication System: Prototype and Analysis. Ieee Internet Of Things Journal; 2023; Vol. 10; iss. 10; pp. 9220 - 9233
    LIRIAS4089039
    description

    Publisher: Institute of Electrical and Electronics Engineers
    Published
  • journal-article
    Cui, Zhuangzhuang; Pollin, Sofie; 2023. Impact of Reconfigurable Intelligent Surface Geometry on Communication Performance. Ieee Wireless Communications Letters; 2023; Vol. 12; iss. 5; pp. 898 - 902
    LIRIAS4091349
    description

    Publisher: Institute of Electrical and Electronics Engineers
    Published
  • conference
    Liu, Mingqing; Gao, Fei; Cui, Zhuangzhuang; Pollin, sofie; Liu, Qingwen; 2023. Sensing with OFDM Waveform at mmWave Band based on Micro-Doppler Analysis. WORKSHOP ON SYNERGIES OF COMMUNICATION, LOCALIZATION, AND SENSING TOWARDS 6G; 2023
    LIRIAS4111699
    description


    Accepted
  • conference
    Hersyandika, Rizqi; Rossanese, Marco; Lutu, Andra; Miao, Yang; Wang, Qing; Pollin, Sofie; 2023. Coverage and Capacity Analysis for Football Player's Bodycam with Cell-Free Massive MIMO. IEEE; 2023
    LIRIAS4079825
    description


    Accepted
  • dataset
    Zare, Amin; van Berlo, Bram; HERSYANDIKA, Rizqi; MIAO, Yang; POLLIN, Sofie; Meratnia, Nirvana; 26 GHz Communication Channel Dataset for Domain Shift Invariant Blockage Prediction. Publisher: KU Leuven RDR
    LIRIAS4064813
    description
    The dataset contains the channel state information samples of 26 GHz OFDM communication channel for various human blockage activities measured using the KU Leuven mmWave and Massive MIMO testbed.

    Published online

1/23