arXiv subjects

Jeroen Famaey

Publications and source records attributed to Jeroen Famaey.

At least 19 recordsLinked to original sources

arXiv2026

Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.

cs.NI↗

arXiv2026

Managing Task Execution for Unknown Workloads in Batteryless IoT: A Hardware-Agnostic Evaluation

In recent years, the Internet of Things (IoT) paradigm has been shifting toward batteryless, energy-harvesting architectures. Sustaining reliable operation in these systems requires intelligent management of highly volatile stored energy. As edge applications grow in complexity, traditional energy-aware schedulers struggle with unpredictable workloads due to their reliance on static execution thresholds or pre-measured, hardware-specific task profiles. To overcome this, we propose two novel, hardware-agnostic dynamic scheduling strategies treating applications as a "black box," requiring no prior energy information: a model-free Reinforcement Learning (RL) agent and an on-the-fly Approximated Prediction (AP) method. We evaluate these methods against an adaptive task rate approach (AsTAR) and optimized static thresholds using a custom-built, physically accurate simulation framework driven by real-world solar data and dynamic LoRa transmission profiles. Rather than claiming universal superiority, our analysis exposes the distinct operational trade-offs of each method: the AP approach delivers lightweight, near-oracle task throughput; the RL agent provides tunable survival-execution balancing; and AsTAR excels at execution pacing across long energy gaps. Finally, we demonstrate that while these advanced strategies provide critical resilience for severely constrained systems with small capacitors, devices with larger energy buffers can efficiently rely on simpler, less computationally expensive static policies.

cs.LG↗

arXiv2026

Integrated Sensing and Communications for Real-time Avatar Control in XR over 5G

Extended Reality (XR) presents a challenging use case for 5G and 6G networks, requiring high data-rates and lowlatency communication to deliver a truly immersive experience. Moreover, in order to seamlessly translate physical actions to the virtual world, accurate gesture recognition and pose estimation are required. Current XR interaction solutions based on handheld controllers and cameras cannot easily capture full-body poses, inhibit the free use of hands, and require good visibility and a clear line of sight. In this work, we propose a multimodal sensing architecture for XR that combines 5G MillimeterWave (mmWave) Integrated sensing and communication (ISAC) and surface electromyography (sEMG) signals. 5G mmWave ISAC cannot only be used to deliver content wirelessly to the Head-mounted display (HMD), but also the same communication signals can be used to derive coarse body-level gestures and poses of the user, to support real-time avatar control. For fine-grained finger-level gestures, our architecture leverages lightweight sEMG sensors that capture forearm muscle activity. To illustrate the need of both modalities, we present evaluations of both sensing technologies. At the body level (5G), our architecture relies on power-per-beam-pair (PPBP), which can be computed from standard beam management or beam sweeping procedures of the 5G NR standard. PPBP-based sensing achieves 82.2$\pm$5.9% average accuracy when evaluated on users not seen during training. For fine-grained finger-level interactions, we show that surface electromyography (sEMG) carries strong discriminative information achieving consistent promising performance across different movement settings. Thus, combining the two modalities enables multi-scale gesture recognition, at the body level via existing 5G signals and finger level via lightweight sEMG sensors, forming a complete XR framework.

eess.SP↗

arXiv2026

Adaptive Contention-based Random Access for Uplink Reporting in 3GPP Ambient IoT Networks

Ambient Internet of Things (A-IoT) targets energy harvesting (EH), battery-less devices as a simple connectivity solution for extensive ultra-low-power deployments. These devices typically face intermittent energy availability, making uplink reports increasingly susceptible to access collisions and energy outages. In this paper, we build upon the cellular standardization of A-IoT and examine the paging-triggered contention-based random access (CBRA) framework for uplink reporting. We analyze the effects of energy availability and collisions on these systems and introduce an EH-aware access control mechanism. In this mechanism, the reader broadcasts an access probability in the paging message, which helps regulate the number of devices attempting random access. Results show that, unlike the baselines, the proposed method scales well under dense deployments by keeping collisions nearly constant, improving access efficiency, and substantially reducing the number of paging rounds required for successful reporting. These results highlight the importance of lightweight reader-side access control for reliable and resource-efficient reporting in A-IoT environments.

eess.SY↗

arXiv2026

Towards Emotion Recognition with 3D Pointclouds Obtained from Facial Expression Images

Facial Emotion Recognition is a critical research area within Affective Computing due to its wide-ranging applications in Human Computer Interaction, mental health assessment and fatigue monitoring. Current FER methods predominantly rely on Deep Learning techniques trained on 2D image data, which pose significant privacy concerns and are unsuitable for continuous, real-time monitoring. As an alternative, we propose High-Frequency Wireless Sensing (HFWS) as an enabler of continuous, privacy-aware FER, through the generation of detailed 3D facial pointclouds via on-person sensors embedded in wearables. We present arguments supporting the privacy advantages of HFWS over traditional 2D imaging, particularly under increasingly stringent data protection regulations. A major barrier to adopting HFWS for FER is the scarcity of labeled 3D FER datasets. Towards addressing this issue, we introduce a FLAME-based method to generate 3D facial pointclouds from existing public 2D datasets. Using this approach, we create AffectNet3D, a 3D version of the AffectNet database. To evaluate the quality and usability of the generated data, we design a pointcloud refinement pipeline focused on isolating the facial region, and train the popular PointNet++ model on the refined pointclouds. Fine-tuning the model on a small subset of the unseen 3D FER dataset BU-3DFE yields a classification accuracy exceeding 70%, comparable to oracle-level performance. To further investigate the potential of HFWS-based FER for continuous monitoring, we simulate wearable sensing conditions by masking portions of the generated pointclouds. Experimental results show that models trained on AffectNet3D and fine-tuned with just 25% of BU-3DFE outperform those trained solely on BU-3DFE. These findings highlight the viability of our pipeline and support the feasibility of continuous, privacy-aware FER via wearable HFWS systems.

cs.CV↗

arXiv2026

Symbol-Synchronous Communication for Ultra-Low-Power Multi-Hop Ambient IoT Networks

Ambient Internet of Things (A-IoT) devices, as a critical enabler of future green IoT networks, have attracted broad interest from both industry and academia due to their ability to operate without batteries and with low maintenance costs. To accommodate their dynamic and constrained energy budget, an ultra-low-power connectivity protocol is required. Due to the severely limited transmit power of A-IoT devices, multi-hop connectivity is an interesting paradigm to extend their range. However, commonly used protocols for multi-hop communication may not be suitable for A-IoT due to excessive overhead related to channel access procedures, coordinated routing, and tight time synchronization requirements. This paper presents a novel network connectivity protocol based on symbol-synchronous transmissions, which allows battery-less relay nodes to participate in the forwarding process in an ad-hoc manner, without the need for synchronization or coordination. This allows them to adapt their duty cycle to the available harvested energy. Simulation results show that the proposed protocol can ensure high reliability in data packet delivery while significantly reducing the energy consumption of each relay node. We also investigate the relationship between wake-up probability and network density. For example, a 400-node network in a 625 m2 area can achieve a packet error rate below 1 % with an average awake time of 6 % per node, achieving an energy consumption reduction of 88 % compared to the baseline approach.

cs.NI↗

arXiv2026

RF-Zero-Wire: Design and Analysis of Multi-Hop Low-latency Symbol-synchronous RF Communication

The latency gap between wired and wireless networks poses a challenge in the adoption of wireless technologies in latency-sensitive scenarios. The gap is especially notable in multi-hop communication typical for industrial sensor networks and robotic swarms. The main reason behind it is that commonly used wireless protocols rely on store-and-forward routing and costly overhead procedures to avoid interference. This article introduces RF-Zero-Wire, an RF-based symbol-synchronous communication protocol. Instead of relaying the whole frame per hop in a store-and-forward manner, nodes concurrently relay the frame symbol by symbol, without the need for tight time synchronization. Based on data collected in real-world experiments, we reveal that the inevitable carrier frequency offsets (CFOs) introduced by imperfect crystal oscillators cause a beating effect under concurrent symbol transmissions. This is characterized by periodic constructive and destructive interference, which significantly affects reliability. Subsequently, a thorough simulation study shows how the beating problem can be overcome with error correction codes. RF-Zero-Wire allows achieving an end-to-end latency of less than 1ms for a small 4-byte frame transmitted across 5 hops. Moreover, latency is shown to increase only by 0.16% per extra hop for 16-byte frames, which is negligible compared to the over 100% per-hop latency increase observed in store-and-forward protocols. The trade-offs between network reliability and CFO range, communication distance, node density, and achievable data rate are studied in large-scale experiments based on simulation.

cs.NI↗

arXiv2026

Energy-Aware Multi-Exit TinyML for Smart Zero-Energy Devices

The proliferation of smart and autonomous systems has motivated a shift toward executing intelligence directly on edge devices. This shift becomes particularly challenging for zero-energy devices (ZEDs), where severe constraints on memory, energy availability, and inference accuracy must be addressed simultaneously. In this paper, we present a unified approach to managing these constraints for smart ZEDs. Specifically, we design, train, and deploy a tiny machine learning (TinyML) model for person detection on a ZED. The proposed architecture stores a single model in memory while enabling adaptive inference through multiple exit points, allowing computational effort to scale with input difficulty. As a result, low-energy inference is performed for easy instances, while higher-precision inference is selectively employed for harder cases. This strategy significantly reduces energy consumption without sacrificing detection accuracy. Furthermore, to enhance device autonomy and prevent power failures, we introduce auxiliary energy-aware circuits that dynamically regulate system operation based on available energy. Compared with a state-of-the-art energy-aware single-exit TinyML approach, the proposed method achieves an energy consumption reduction of approximately $29.6\%$. Overall, the proposed framework is appealing for enabling accurate and energy-efficient intelligence on ZED platforms.

eess.SP↗

arXiv2026

Millimeter-Wave Gesture Recognition in ISAC: Does Reducing Sensing Airtime Hamper Accuracy?

Most Integrated Sensing and Communications (ISAC) systems require dividing airtime across their two modes. However, the specific impact of this decision on sensing performance remains unclear and underexplored. In this paper, we therefore investigate the impact on a gesture recognition system using a Millimeter-Wave (mmWave) ISAC system. With our dataset of power per beam pair gathered with two mmWave devices performing constant beam sweeps while test subjects performed distinct gestures, we train a gesture classifier using Convolutional Neural Networks. We then subsample these measurements, emulating reduced sensing airtime, showing that a sensing airtime of 25 % only reduces classification accuracy by 0.15 percentage points from full-time sensing. Alongside this high-quality sensing at low airtime, mmWave systems are known to provide extremely high data throughputs, making mmWave ISAC a prime enabler for applications such as truly wireless Extended Reality.

eess.SP↗

arXiv2025

Beyond Sub-6 GHz: Leveraging mmWave Wi-Fi for Gait-Based Person Identification

Person identification plays a vital role in enabling intelligent, personalized, and secure human-computer interaction. Recent research has demonstrated the feasibility of leveraging Wi-Fi signals for passive person identification using a person's unique gait pattern. Although most existing work focuses on sub-6 GHz frequencies, the emergence of mmWave offers new opportunities through its finer spatial resolution, though its comparative advantages for person identification remain unexplored. This work presents the first comparative study between sub-6 GHz and mmWave Wi-Fi signals for person identification with commercial off-the-shelf (COTS) Wi-Fi, using a novel dataset of synchronized measurements from the two frequency bands in an indoor environment. To ensure a fair comparison, we apply identical training pipelines and model configurations across both frequency bands. Leveraging end-to-end deep learning, we show that even at low sampling rates (10 Hz), mmWave Wi-Fi signals can achieve high identification accuracy (91.2% on 20 individuals) when combined with effective background subtraction.

cs.LG↗

arXiv2025

Evaluating UORA-Based Polling Mechanism for Latency-Sensitive Uplink Traffic in Wi-Fi Networks

IEEE 802.11ax (Wi-Fi 6) introduced Orthogonal Frequency Division Multiple Access (OFDMA), which enables simultaneous transmissions through centralized resource allocation. However, effective uplink scheduling requires the Access Point (AP) to identify which stations (STAs) have data to transmit. This typically necessitates polling for buffer status reports, a process that becomes increasingly inefficient and unscalable with growing device density. In this paper, we study how the Uplink OFDMA-based Random Access (UORA) feature improves the scalability and delay experienced by latency-sensitive data streams. We show that UORA enables efficient uplink scheduling while opportunistically identifying buffered traffic from unscheduled STAs, striking a balance between coordination and scalability. Performance evaluation of different polling strategies is done by means of simulation in ns-3. The results indicate that UORA-based polling outperforms alternative schemes in densely deployed network environments with heterogeneous uplink traffic patterns. Furthermore, under highly sparse and sporadic traffic conditions, UORA-based polling yields over 40% delay reduction compared to Scheduled Access (SA) OFDMA.

cs.NI↗

arXiv2025

mmHSense: Multi-Modal and Distributed mmWave ISAC Datasets for Human Sensing

This article presents mmHSense, a set of open labeled mmWave datasets to support human sensing research within Integrated Sensing and Communication (ISAC) systems. The datasets can be used to explore mmWave ISAC for various end applications such as gesture recognition, person identification, pose estimation, and localization. Moreover, the datasets can be used to develop and advance signal processing and deep learning research on mmWave ISAC. This article describes the testbed, experimental settings, and signal features for each dataset. Furthermore, the utility of the datasets is demonstrated through validation on a specific downstream task. In addition, we demonstrate the use of parameter-efficient fine-tuning to adapt ISAC models to different tasks, significantly reducing computational complexity while maintaining performance on prior tasks.

cs.CV↗

arXiv2025

Cross-layer Integrated Sensing and Communication: A Joint Industrial and Academic Perspective

Integrated sensing and communication (ISAC) enables radio systems to simultaneously sense and communicate with their environment. This paper, developed within the Hexa-X-II project funded by the European Union, presents a comprehensive cross-layer vision for ISAC in 6G networks, integrating insights from physical-layer design, hardware architectures, AI-driven intelligence, and protocol-level innovations. We begin by revisiting the foundational principles of ISAC, highlighting synergies and trade-offs between sensing and communication across different integration levels. Enabling technologies (such as multiband operation, massive and distributed MIMO, non-terrestrial networks, reconfigurable intelligent surfaces, and machine learning) are analyzed in conjunction with hardware considerations including waveform design, synchronization, and full-duplex operation. To bridge implementation and system-level evaluation, we introduce a quantitative cross-layer framework linking design parameters to key performance and value indicators. By synthesizing perspectives from both academia and industry, this paper outlines how deeply integrated ISAC can transform 6G into a programmable and context-aware platform supporting applications from reliable wireless access to autonomous mobility and digital twinning.

eess.SP↗

arXiv2025

Foundations for Energy-Aware Zero-Energy Devices: From Energy Sensing to Adaptive Protocols

Zero-energy devices (ZEDs) are key enablers of sustainable Internet of Things networks by operating solely on harvested ambient energy. Their limited and dynamic energy budget calls for protocols that are energy-aware and intelligently adaptive. However, designing effective energy-aware protocols for ZEDs requires theoretical models that realistically reflect device constraints. Indeed, existing approaches often oversimplify key aspects such as energy information (EI) acquisition, task-level variability, and energy storage dynamics, limiting their practical relevance and transferability. This article addresses this gap by offering a structured overview of the key modeling components, trade-offs, and limitations involved in energy-aware ZED protocol design. For this, we dissect EI acquisition methods and costs, characterize core operational tasks, analyze energy usage models and storage constraints, and review representative protocol strategies. Moreover, we offer design insights and guidelines on how ZED operation protocols can leverage EI, often illustrated through selected in-house examples. Finally, we outline key research directions to inspire more efficient and scalable protocol solutions for future ZEDs.

eess.SY↗

arXiv2025

Feasibility of Energy Neutral Wildlife Tracking using Multi-Source Energy Harvesting

Long-term wildlife tracking is crucial for biodiversity monitoring, but energy limitations pose challenges, especially for animal tags, where replacing batteries is impractical and stressful for the animal due to the need to locate, possibly sedate, and handle it. Energy harvesting offers a sustainable alternative, yet most existing systems rely on a single energy source and infrastructure-limited communication technologies. This paper presents an energy-neutral system that combines solar and kinetic energy harvesting to enable the tracking and monitoring of wild animals. Harvesting from multiple sources increases the total available energy. Uniquely, the kinetic harvester also serves as a motion proxy by sampling harvested current, enabling activity monitoring without dedicated sensors. Our approach also ensures compatibility with existing cellular infrastructure, using Narrowband Internet of Things (NB-IoT). We present a simulation framework that models energy harvesting, storage, and consumption at the component level. An energy-aware scheduler coordinates task execution based on real-time energy availability. We evaluate performance under realistically varying conditions, comparing task frequencies and capacitor sizes. Results show that our approach maintains energy-neutral operation while significantly increasing data yield and reliability compared to single-source systems, with the ability to consistently sample GPS location data and kinetic harvesting data every two minutes while transmitting these results over NB-IoT every hour. These findings demonstrate the potential for maintenance-free, environmentally friendly tracking in remote habitats, enabling more effective and scalable wildlife monitoring.

cs.NI↗

arXiv2025

Design and Evaluation of IEEE 802.11ax Uplink Orthogonal Frequency Division Multiple Random Access in ns-3

Wi-Fi networks have long relied on the Enhanced Distributed Channel Access (EDCA) mechanism, allowing stations to compete for transmission opportunities. However, as networks become denser and emerging applications demand lower latency and higher reliability, the limitations of EDCA such as overhead due to contention and collisions have become more pronounced. To address these challenges, Orthogonal Frequency Division Multiple Access (OFDMA) has been introduced in Wi-Fi, enabling more efficient channel utilization through scheduled resource allocation. Furthermore, Wi-Fi 6 defines Uplink Orthogonal Frequency Division Multiple Random Access (UORA), a hybrid mechanism that combines both scheduled and random access, balancing efficiency and responsiveness in resource allocation. Despite significant research on UORA, most studies rely on custom simulators that are not publicly available, limiting reproducibility and preventing validation of the presented results. The only known open-source UORA implementation in the ns-3 simulator exhibits key limitations, such as usage of the same trigger frame (TF) to schedule resources for buffer status reports and data transmissions, and lack of signaling for UORA configuration. In this paper, we present a fully standard-compliant and open source UORA implementation that is compatible with ns-3 version 3.38, addressing these limitations to improve resource allocation efficiency and adaptability. This implementation enables more accurate and flexible evaluation of UORA, fostering future research on Wi-Fi resource allocation strategies.

cs.NI↗

arXiv2025

A Primer on AP Power Save in Wi-Fi 8: Overview, Analysis, and Open Challenges

Wi-Fi facilitates the Internet connectivity of billions of devices worldwide, making it an indispensable technology for modern life. Wi-Fi networks are becoming significantly denser, making energy consumption and its effects on operational costs and environmental sustainability crucial considerations. Wi-Fi has already introduced several mechanisms to enhance the energy efficiency of non-Access Point (non-AP) stations (STAs). However, the reduction of energy consumption of APs has never been a priority. Always-on APs operating at their highest capabilities consume significant power, which affects the energy costs of the infrastructure owner, aggravates the environmental impact, and decreases the lifetime of battery-powered APs. IEEE 802.11bn, which will be the basis of Wi-Fi 8, makes a big leap forward by introducing the AP Power Save (PS) framework. In this article, we describe and analyze the main proposals discussed in the IEEE 802.11bn Task Group (TGbn), such as Scheduled Power Save, (Semi-)Dynamic Power Save, and Cross-Link Power Save. We also consider other proposals that are being discussed in TGbn, namely the integration of Wake-up Radios (WuRs) and STA offloading. We then showcase the potential benefits of AP PS in several scenarios, including a deployment of 470 real APs in a university campus. Our numerical analysis reveals that AP power consumption can be decreased on average by up to 28 percent, with further improvement potential. Finally, we outline the open challenges that need to be addressed to optimally integrate AP PS in Wi-Fi and ensure its compatibility with legacy devices.

cs.NI↗

arXiv2025

Multi-Stream Transmission in Cell-Free MIMO Networks with Coherent AP Clustering

This letter proposes a multi-stream selection framework for \ac{CF-MIMO} networks. Partially coherent transmission has been considered by clustering \acp{AP} into phase-aligned clusters to address the challenges of phase misalignment and inter-cluster interference. A novel stream selection algorithm is developed to dynamically allocate multiple streams to each multi-antenna \ac{UE}, ensuring that the system optimizes the sum rate while minimizing inter-cluster and inter-stream interference. Numerical results validate the effectiveness of the proposed method in enhancing spectral efficiency and fairness in distributed \ac{CF-MIMO} networks.

eess.SP↗