- Indoor and Outdoor Localization Technologies
- Energy Efficient Wireless Sensor Networks
- Wireless Networks and Protocols
- Energy Harvesting in Wireless Networks
- IoT Networks and Protocols
- Ultra-Wideband Communications Technology
- Advanced MIMO Systems Optimization
- IoT and Edge/Fog Computing
- Wireless Body Area Networks
- Millimeter-Wave Propagation and Modeling
- Mobile Ad Hoc Networks
- Microwave Imaging and Scattering Analysis
- Cooperative Communication and Network Coding
- Wireless Signal Modulation Classification
- Speech and Audio Processing
- Underwater Vehicles and Communication Systems
- Bluetooth and Wireless Communication Technologies
- Context-Aware Activity Recognition Systems
- Software-Defined Networks and 5G
- Opportunistic and Delay-Tolerant Networks
- Animal Behavior and Welfare Studies
- Network Time Synchronization Technologies
- Cognitive Radio Networks and Spectrum Sensing
- Geophysical Methods and Applications
- Power Line Communications and Noise
Ghent University
2016-2025
Imec the Netherlands
2021-2025
Ghent University Hospital
2010-2024
IMEC
2019-2024
Research Institute for Fisheries and Aquaculture
2024
Princeton University
2023
Vlaamse Vereniging voor Obstetrie en Gynaecolo
2023
iMinds
2013-2016
Huazhong University of Science and Technology
2016
University of Technology Malaysia
2016
The increasing wireless data traffic demands have driven the need to explore suitable spectrum regions for meeting projected requirements. In light of this, millimeter wave (mmWave) communication has received considerable attention from research community. Typically, in fifth generation (5G) networks, mmWave massive multiple-input multipleoutput (MIMO) communications is realized by hybrid transceivers which combine high dimensional analog phase shifters and power amplifiers with...
This paper presents end-to-end learning from spectrum data-an umbrella term for new sophisticated wireless signal identification approaches in monitoring applications based on deep neural networks. End-to-end allows to: 1) automatically learn features directly simple representations, without requiring design of hand-crafted expert like higher order cyclic moments and 2) train classifiers one step which eliminates the need complex multi-stage machine processing pipelines. The purpose this is...
Smart embedded objects will become an important part of what is called the Internet Things. However, integration devices into introduces several challenges, since many existing technologies and protocols were not designed for this class devices. In past few years, there have been efforts to enable extension constrained Initially, resulted in proprietary architectures. Later, was embraced by IETF, moving towards standardized IP-based protocols. paper, we briefly review history integrating...
The increasing popularity of ultra-wideband (UWB) technology for location-based services, such as access control and real-time indoor track&tracing, well UWB support in new consumer devices smartphones, has resulted the availability multiple radio chips. However, due to this increase device availability, question which (industry) standards configuration factors impact interoperability compatibility becomes increasingly important. In paper, fundamentals are investigated by first giving...
ECG classification or heartbeat is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of signals assist human experts timely diagnosis cardiac diseases and help save precious lives. This research aims at digitizing a dataset images records into time series then applying deep learning (DL) on digitized dataset. State-of-the-art DL are proposed different classes. Multiple models, including convolutional neural network (CNN), long short-term memory (LSTM)...
The increasing complexity of wireless standards has shown that protocols cannot be designed once for all possible deployments, especially when unpredictable and mutating interference situations are present due to the coexistence heterogeneous technologies. As such, flexibility (re)programmability devices is crucial in emerging scenarios technology proliferation conditions. In this paper, we focus on possibility improve performance WiFi ZigBee networks by exploiting novel programmable...
Radio frequency (RF)-based indoor positioning systems (IPSs) use wireless technologies (including Wi-Fi, Zigbee, Bluetooth, and ultra-wide band (UWB)) to estimate the location of persons in areas where no Global Positioning System (GPS) reception is available, for example stadiums or sports halls. Of above-mentioned forms radio (RF) technology, UWB considered one most accurate approaches because it can provide estimates with centimeter-level accuracy. However, not yet known whether also...
The combination of an aging population and nursing staff shortages implies the need for more advanced systems in healthcare industry. Many key enablers optimization require provisioning location awareness patients (e.g. with dementia), nurses, doctors, assets, etc. Therefore, many Indoor Positioning Systems (IPSs) will be indispensable systems. However, although IPSs have been proposed literature, most these evaluated non-representative environments such as office buildings rather than a...
Radio frequency (RF) technologies are often used to track assets in indoor environments. Among others, ultra-wideband (UWB) has constantly gained interest thanks its capability obtain typical errors of 30 cm or lower, making it more accurate than other wireless such as WiFi, which normally can predict the location with several meters accuracy. However, mainly due technical requirements that part standard, conventional medium access strategies clear channel assessment, not straightforward...
Aside from vast deployment cost reduction, Industrial Wireless Sensor and Actuator Networks (IWSAN) introduce a new level of industrial connectivity. connection sensors actuators in environments not only enables wireless monitoring actuation, it also coordination production stages, connecting mobile robots autonomous transport vehicles, as well localization tracking assets. All these opportunities already inspired the development many technologies an effort to fully enable Industry 4.0....
Current inventory-taking methods (counting stocks and checking correct placements) in large vertical warehouses are mostly manual, resulting (i) personnel costs, (ii) human errors (iii) incidents due to working at heights. To remedy this, the use of autonomous indoor drones has been proposed. However, these require accurate localization solutions that easy (temporarily) install low costs warehouses. this end, we designed a Ultra-Wideband (UWB) solution uses infrastructure anchor nodes do not...
This paper presents a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering all layers protocol stack: PHY, MAC network. First, related work contributions are discussed, followed by providing necessary background data-driven approaches to help non-machine experts understand discussed techniques. Then, review is presented works employing ML-based optimize communication...
Non-Line-of-Sight (NLoS) propagation condition is a crucial factor affecting the precision of localization in Ultra-Wideband (UWB) Indoor Positioning System (IPS). Numerous supervised Machine Learning (ML) approaches have been applied for NLoS identification to improve accuracy IPS. However, it difficult existing ML maintain high classification when database contains small number signals and large Line-of-Sight (LoS) signals. The inaccurate target node caused by this can still be...
Monitoring animal welfare on farms and in research settings is attracting increasing interest, both for ethical reasons improving productivity through the early detection of stress or diseases. In contrast to video-based monitoring, which requires good light conditions has difficulty tracking specific animals, recent advances miniaturization wearable devices allow collection acceleration location data track individual behavior. However, broilers, there are several challenges address when...
Over the last few years, number of indoor localization solutions has grown exponentially, and a wide variety different technologies approaches are being explored. Unfortunately, there is currently no established standardized evaluation method for comparing their performance. As result, each solution evaluated in environment using proprietary metrics. Consequently, it extremely hard to objectively compare performance multiple with other. To address problem, we present EVARILOS Benchmarking...
So far, existing sub-GHz wireless communication technologies focused on low-bandwidth, long-range with large numbers of constrained devices. Although these characteristics are fine for many Internet Things (IoT) applications, more demanding application requirements could not be met and legacy such as Transmission Control Protocol/Internet Protocol (TCP/IP) used. This has changed the advent new IEEE 802.11ah Wi-Fi standard, which is much suitable reliable bidirectional high-throughput...
Data science or "data-driven research" is a research approach that uses real-life data to gain insight about the behavior of systems. It enables analysis small, simple as well large and more complex systems in order assess whether they function according intended design seen simulation. approaches have been successfully applied analyze networked interactions several areas such large-scale social networks, advanced business healthcare processes. Wireless networks can exhibit unpredictable...
Due to the fast pace at which IoT is evolving, there an increasing need support over-theair software updates for security updates, bug fixes, and extensions. To this end, multiple over-the-air techniques have been proposed, each covering a specific aspect of update process, such as (partial) code data dissemination, security. However, technique introduces overhead, especially in terms energy consumption, thereby impacting operational lifetime battery constrained devices. Until now,...
Radio frequency identification (RFID) technology brings tremendous advancements in the Industrial Internet of Things (IIoT), especially for smart inventory management, as it provides a fast and low-cost way counting or positioning items warehouse. In last decade, many novel solutions, including absolute relative methods, have been proposed this application. However, available methods are quite sensitive to minor changes deployment scenario, orientation tag antenna, materials contained inside...
Long-range sub-GHz technologies such as LoRaWAN, SigFox, IEEE 802.15.4, and DASH7 are increasingly popular for academic research daily life applications. However, especially in the European Union (EU), use of their corresponding frequency bands tightly regulated, since they must confirm to short-range device (SRD) regulations. Regulations standards SRDs exist on various levels, from global national, but often a source confusion. Not only multiple institutes responsible drafting legislation...
Indoor drone or Unmanned Aerial Vehicle (UAV) operations, automated with pilot control, are an upcoming and exciting subset of use cases. Automated indoor flights tighten the requirements stability localization accuracy in comparison classic outdoor cases which rely primarily on (RTK) GNSS for localization. In this paper effect multiple sensors 3D position is investigated using flexible sensor fusion platform OASE. This evaluation based real-life industrial lab mm-accurate ground truth...