A5006018113- Advanced MIMO Systems Optimization
- Age of Information Optimization
- Vehicular Ad Hoc Networks (VANETs)
- Human Mobility and Location-Based Analysis
- Advanced Wireless Network Optimization
- IoT and Edge/Fog Computing
- IoT Networks and Protocols
- Wireless Communication Networks Research
- Human-Automation Interaction and Safety
- Privacy-Preserving Technologies in Data
- Air Quality Monitoring and Forecasting
- Distributed Sensor Networks and Detection Algorithms
- Embedded Systems and FPGA Design
- Anomaly Detection Techniques and Applications
- Speech and Audio Processing
- Advanced Wireless Communication Techniques
- Wireless Networks and Protocols
- Data Stream Mining Techniques
- Microwave Imaging and Scattering Analysis
- Advanced Wireless Communication Technologies
- Real-Time Systems Scheduling
- Geophysical Methods and Applications
- Millimeter-Wave Propagation and Modeling
BMW Group (Germany)
2020-2023
Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute
2022
BMW (Germany)
2020-2021
University of Kaiserslautern
2021
The evolution of wireless communications into 6G and beyond is expected to rely on new machine learning (ML)-based capabilities. These can enable proactive decisions actions from wireless-network components sustain quality-of-service (QoS) user experience. Moreover, use cases in the area vehicular industrial will emerge. Specifically vehicle communication, vehicle-to-everything (V2X) schemes benefit strongly such advances. With this mind, we have conducted a detailed measurement campaign...
In the future, mobility use cases will depend on precise predictions, with Quality of Service (QoS) prediction being a prominent example. This paper presents realistic measurements from today's vehicles to support robust QoS in future. Based dedicated and controlled measurement campaign, we highlight aspects wireless environment device characteristics, like sampling rates, that influence collected datasets. If not properly handled, such characteristics might hinder performance Artificial...
As cellular networks evolve towards the 6th generation, machine learning is seen as a key enabling technology to improve capabilities of network. Machine provides methodology for predictive systems, which, in turn, can make become proactive. This proactive behavior network be leveraged sustain, example, specific quality service requirement. With service, wide variety new use cases, both safety- and entertainment-related, are emerging, especially automotive sector. Therefore, this work, we...
The integration of functions into future communication systems that predict crucial Quality Service (QoS) parameters is expected to enable many new or enhanced use cases, for example, in vehicular networks and Industry 4.0. Especially with high user mobility, QoS prediction required an End-to-End (E2E) fashion guarantee uninterrupted connectivity provisioning real-time applications. In this paper, we present a concise list mobility both from automotive industrial production domains, benefit...
In autonomous driving, several applications like teleoperated back-end status verification, or online gaming for customer infotainment rely on low-latency communication. Ideally, we can select a route that best supports the applications' requirements before journey. Therefore, selection vehicles might require in-advance latency predictions. End-to-end (E2E) prediction is difficult task, especially when considering it needs to be achieved with limited active probing due cost constraints. We...
Recently, there have been many attempts to apply Machine Learning (ML)-based prediction mechanisms In wireless networks. One open question is how reliable such predictions can be, and well ML models learn from the radio environment. this paper, we present initial results on Quality of Service (QoS) using example throughput prediction. We focus suggesting new sets features that improve performance for different horizons. Thereby, identify important a large impact when environment data as...
The number of always-online vehicles continuously increases, and these will form an immense mobile sensor network. For example, cars can upload live temperature precipitation information to enhance weather forecasting, also transmit cellular network measurements the cloud. We leverage this vast amount data, particularly reference signal received power, estimate channel distribution (CDI) for vehicular environment. In particular, proposed CDI maps depict small-scale fading statistics...
Next-generation networks are envisioned to be empowered by artificial intelligence with predictive capabilities. Predicting handovers in high mobility scenarios enables and applications adapt ahead of time improve the Quality Service (QoS). In this paper, we present a two-step machine learning (ML) method, consisting classifier regressor, that can predict remaining until handover occurs. Our approach is validated on dataset was captured real cellular network. The results show upcoming...
Autonomous driving will rely on a multitude of connected applications with stringent quality service (QoS) requirements in terms low latency and high reliability. At the same time, passengers relieved steering duty have opportunity to enjoy infotainment services that are often associated data rates, e.g. video streaming. The simultaneous usage such safety-related leads diverse QoS which difficult satisfy current wireless networks. In an effort address this issue, we propose two-layer...
In autonomous driving, several safety-related connected applications will coexist with infotainment services for passenger entertainment. Serving the resulting set of diverse quality service (QoS) requirements poses a tremendous challenge future cellular networks. For example, require low latency, while are associated high throughput demands. To address coexistence challenge, we propose multi-cell anticipatory networking framework interference coordination based on channel distribution...
The evolution of wireless communications into 6G and beyond is expected to rely on new machine learning (ML)-based capabilities. These can enable proactive decisions actions from wireless-network components sustain quality-of-service (QoS) user experience. Moreover, use cases in the area vehicular industrial will emerge. Specifically vehicle communication, vehicle-to-everything (V2X) schemes benefit strongly such advances. With this mind, we have conducted a detailed measurement campaign...
As cellular networks evolve towards the 6th generation, machine learning is seen as a key enabling technology to improve capabilities of network. Machine provides methodology for predictive systems, which can make become proactive. This proactive behavior network be leveraged sustain, example, specific quality service requirement. With service, wide variety new use cases, both safety- and entertainment-related, are emerging, especially in automotive sector. Therefore, this work, we consider...
Machine learning (ML) equips next-generation networks with anticipatory capabilities. End-to-end predictive Quality of Service (pQoS) leverages ML models to estimate QoS indicators. In this paper, we present several that can the maximum achievable instantaneous throughput (link capacity) cellular networks. The do not only most likely value, but also quantify uncertainty their own by providing estimated quantile values as bounds. These estimates bounds enable network functions and user...
We consider the car key localization task using ultra-wideband (UWB) signal measurements. Given labeled data for a certain car, we train deep classifier to make prediction about new points. However, due differences in models and possible environmental effects that might alter propagation, collection requires considerable effort each car. In particular, situation where is collected only one environment, so have utilize measurements other environments from different propose framework based on...
Autonomous driving will rely on several safety-related connected applications that coexist with infotainment services for passenger entertainment. The simultaneous provisioning of resources to different quality service requirements poses an immense challenge future cellular networks. While most require low latencies, usually necessitate a high average throughput. We propose multi-cell, distributed predictive resource allocation framework interference coordination based channel distribution...