Filip Lemic

Filip Lemic, Jakob Struye, Jeroen Famaey

Full-immersive multiuser Virtual Reality (VR) envisions supporting unconstrained mobility of the users in the virtual worlds, while at the same time constraining their physical movements inside VR setups through redirected walking. For enabling delivery of high data rate video content in real-time, the supporting wireless networks will leverage highly directional communication links that will "track" the users for maintaining the Line-of-Sight (LoS) connectivity. Recurrent Neural Networks (RNNs) and in particular Long Short-Term Memory (LSTM) networks have historically presented themselves as a suitable candidate for near-term movement trajectory prediction for natural human mobility, and have also recently been shown as applicable in predicting VR users' mobility under the constraints of redirected walking. In this work, we extend these initial findings by showing that Gated Recurrent Unit (GRU) networks, another candidate from the RNN family, generally outperform the traditionally utilized LSTMs. Second, we show that context from a virtual world can enhance the accuracy of the prediction if used as an additional input feature in comparison to the more traditional utilization of solely the historical physical movements of the VR users. Finally, we show that the prediction system trained on a static number of coexisting VR users be scaled to a multi-user system without significant accuracy degradation.

Gerard Calvo Bartra, Filip Lemic, Guillem Pascual et al.

Contemporary research advances in nanotechnology and material science are rooted in the emergence of nanodevices as a versatile tool that harmonizes sensing, computing, wireless communication, data storage, and energy harvesting. These devices offer novel pathways for disease diagnostics, treatment, and monitoring within the bloodstreams. Ensuring precise localization of events of diagnostic interest, which underpins the concept of flow-guided in-body nanoscale localization, would provide an added diagnostic value to the detected events. Raw data generated by the nanodevices is pivotal for this localization and consist of an event detection indicator and the time elapsed since the last passage of a nanodevice through the heart. The energy constraints of the nanodevices lead to intermittent operation and unreliable communication, intrinsically affecting this data. This posits a need for comprehensively modelling the features of this data. These imperfections also have profound implications for the viability of existing flow-guided localization approaches, which are ill-prepared to address the intricacies of the environment. Our first contribution lies in an analytical model of raw data for flow-guided localization, dissecting how communication and energy capabilities influence the nanodevices' data output. This model acts as a vital bridge, reconciling idealized assumptions with practical challenges of flow-guided localization. Toward addressing these practical challenges, we also present an integration of Graph Neural Networks (GNNs) into the flow-guided localization paradigm. GNNs excel in capturing complex dynamic interactions inherent to the localization of events sensed by the nanodevices. Our results highlight the potential of GNNs not only to enhance localization accuracy but also extend coverage to encompass the entire bloodstream.

Guillem Pascual, Filip Lemic, Carmen Delgado et al.

Advancements in nanotechnology and material science are paving the way toward nanoscale devices that combine sensing, computing, data and energy storage, and wireless communication. In precision medicine, these nanodevices show promise for disease diagnostics, treatment, and monitoring from within the patients' bloodstreams. Assigning the location of a sensed biological event with the event itself, which is the main proposition of flow-guided in-body nanoscale localization, would be immensely beneficial from the perspective of precision medicine. The nanoscale nature of the nanodevices and the challenging environment that the bloodstream represents, result in current flow-guided localization approaches being constrained in their communication and energy-related capabilities. The communication and energy constraints of the nanodevices result in different features of raw data for flow-guided localization, in turn affecting its performance. An analytical modeling of the effects of imperfect communication and constrained energy causing intermittent operation of the nanodevices on the raw data produced by the nanodevices would be beneficial. Hence, we propose an analytical model of raw data for flow-guided localization, where the raw data is modeled as a function of communication and energy-related capabilities of the nanodevice. We evaluate the model by comparing its output with the one obtained through the utilization of a simulator for objective evaluation of flow-guided localization, featuring comparably higher level of realism. Our results across a number of scenarios and heterogeneous performance metrics indicate high similarity between the model and simulator-generated raw datasets.

Filip Lemic, Jakob Struye, Thomas Van Onsem et al.

The advancement of Virtual Reality (VR) technology is focused on improving its immersiveness, supporting multiuser Virtual Experiences (VEs), and enabling users to move freely within their VEs while remaining confined to specialized VR setups through Redirected Walking (RDW). To meet their extreme data-rate and latency requirements, future VR systems will require supporting wireless networking infrastructures operating in millimeter Wave (mmWave) frequencies that leverage highly directional communication in both transmission and reception through beamforming and beamsteering. We propose the use of predictive context-awareness to optimize transmitter and receiver-side beamforming and beamsteering. By predicting users' short-term lateral movements in multiuser VR setups with Redirected Walking (RDW), transmitter-side beamforming and beamsteering can be optimized through Line-of-Sight (LoS) "tracking" in the users' directions. At the same time, predictions of short-term orientational movements can be utilized for receiver-side beamforming for coverage flexibility enhancements. We target two open problems in predicting these two context information instances: i) predicting lateral movements in multiuser VR settings with RDW, and ii) generating synthetic head rotation datasets for training orientational movements predictors. Our experimental results demonstrate that Long Short-Term Memory (LSTM) networks feature promising accuracy in predicting lateral movements, and context-awareness stemming from VEs further enhances this accuracy. Additionally, we show that a TimeGAN-based approach for orientational data generation can create synthetic samples that closely match experimentally obtained ones.

Pablo Galván, Filip Lemic, Gerard Calvo Bartra et al.

Flow-guided localization using in-body nanodevices in the bloodstream is expected to be beneficial for early disease detection, continuous monitoring of biological conditions, and targeted treatment. The nanodevices face size and power constraints that produce erroneous raw data for localization purposes. On-body anchors receive this data, and use it to derive the locations of diagnostic events of interest. Different Machine Learning (ML) approaches have been recently proposed for this task, yet they are currently restricted to a reference bloodstream of a resting patient. As such, they are unable to deal with the physical diversity of patients' bloodstreams and cannot provide continuous monitoring due to changes in individual patient's activities. Toward addressing these issues for the current State-of-the-Art (SotA) flow-guided localization approach based on Graph Neural Networks (GNNs), we propose a pipeline for GNN adaptation based on individual physiological indicators including height, weight, and heart rate. Our results indicate that the proposed adaptions are beneficial in reconciling the individual differences between bloodstreams and activities.

Laura Rayón Ropero, Jasper De Laet, Filip Lemic et al.

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.

Ida Kleger-Rudomin, Filip Lemic, Sergi Abadal et al.

Liquid biopsy can detect tumor-derived biomarkers such as circulating tumor DNA (ctDNA), but ultra-low-fraction assays remain costly, slow, and difficult to scale. This motivates interest in intravascular in vivo sensing in the context of intrabody nanonetworks, where nanosensors could support local biomarker monitoring. BioFET-based nanosensors are relevant here because they are label-free, highly miniaturizable, and have shown strong ctDNA sensitivity in controlled media. We examine whether this sensitivity still yields reliable ctDNA detection in whole blood using a reduced-order stochastic simulation model that links operating-point selection, Debye-screened charge transduction, stochastic finite-capacity binding, nonspecific adsorption, background fluctuations, and intrinsic electronic noise to blank-threshold detection. Monte Carlo evaluation with physiologically grounded parameters shows that short Debye length and several-nanometer charge-to-channel separation attenuate the current shift, while low-frequency noise and background fluctuations reduce the margin between target-present and blank responses. Under the tested quasi-static charge-gating regime, the simulated current shifts do not reliably exceed the blank-derived threshold at low ctDNA concentrations. The model therefore provides a whole-blood boundary analysis that identifies which interface configurations and operating conditions most strongly limit reliable BioFET-based intravascular ctDNA detection.

Abdollah Rezagholi, Sergi Abadal, Filip Lemic et al.

Early detection of cancer is essential for timely diagnosis and improved patient outcomes. Among emerging technologies, intra-body nanoscale communication offers an innovative solution to identify molecular cues within the human bloodstream. This study investigates a minimally invasive approach for early-stage cancer biomarker detection using nanomachines introduced into the bloodstream. To assess the feasibility of this approach, computational simulations are used to emulate the vascular environment and evaluate biomarker detection performance under different physiological conditions. Current modeling approaches often fail to capture essential vascular characteristics, including non-uniform flow structures, size-dependent particle mobility, and particle margination driven by red blood cell interactions. To address these limitations, our study incorporates these factors into the simulation framework and quantifies their individual and combined effects on biomarker detection efficiency. Baseline detection performance is first obtained under uniform flow assumptions, after which introducing realistic vascular transport mechanisms progressively reduces detection probability for all vessel types and nanomachine sizes. Among the considered vessels, capillary consistently achieves the highest detection probability across all nanomachine sizes.

Jakob Struye, Filip Lemic, Jeroen Famaey

Extended Reality is a revolutionary method of delivering multimedia content to users. A large contributor to its popularity is the sense of immersion and interactivity enabled by having real-world motion reflected in the virtual experience accurately and immediately. This user motion, mainly caused by head rotations, induces several technical challenges. For instance, which content is generated and transmitted depends heavily on where the user is looking. Seamless systems, taking user motion into account proactively, will therefore require accurate predictions of upcoming rotations. Training and evaluating such predictors requires vast amounts of orientational input data, which is expensive to gather, as it requires human test subjects. A more feasible approach is to gather a modest dataset through test subjects, and then extend it to a more sizeable set using synthetic data generation methods. In this work, we present a head rotation time series generator based on TimeGAN, an extension of the well-known Generative Adversarial Network, designed specifically for generating time series. This approach is able to extend a dataset of head rotations with new samples closely matching the distribution of the measured time series.

Genís Castillo Gómez-Raya, Álmos Veres-Vitályos, Filip Lemic et al.

The increasing miniaturization of Unmanned Aerial Vehicles (UAVs) has expanded their deployment potential to indoor and hard-to-reach areas. However, this trend introduces distinct challenges, particularly in terms of flight dynamics and power consumption, which limit the UAVs' autonomy and mission capabilities. This paper presents a novel approach to overcoming these limitations by integrating Neural 3D Reconstruction (N3DR) with small UAV systems for fine-grained 3-Dimensional (3D) digital reconstruction of small static objects. Specifically, we design, implement, and evaluate an N3DR-based pipeline that leverages advanced models, i.e., Instant-ngp, Nerfacto, and Splatfacto, to improve the quality of 3D reconstructions using images of the object captured by a fleet of small UAVs. We assess the performance of the considered models using various imagery and pointcloud metrics, comparing them against the baseline Structure from Motion (SfM) algorithm. The experimental results demonstrate that the N3DR-enhanced pipeline significantly improves reconstruction quality, making it feasible for small UAVs to support high-precision 3D mapping and anomaly detection in constrained environments. In more general terms, our results highlight the potential of N3DR in advancing the capabilities of miniaturized UAV systems.

Àlmos Veres-Vitàlyos, Genis Castillo Gomez-Raya, Filip Lemic et al.

Small Unmanned Aerial Vehicles (UAVs) exhibit immense potential for navigating indoor and hard-to-reach areas, yet their significant constraints in payload and autonomy have largely prevented their use for complex tasks like high-quality 3-Dimensional (3D) reconstruction. To overcome this challenge, we introduce a novel system architecture that enables fully autonomous, high-fidelity 3D scanning of static objects using UAVs weighing under 100 grams. Our core innovation lies in a dual-reconstruction pipeline that creates a real-time feedback loop between data capture and flight control. A near-real-time (near-RT) process uses Structure from Motion (SfM) to generate an instantaneous pointcloud of the object. The system analyzes the model quality on the fly and dynamically adapts the UAV's trajectory to intelligently capture new images of poorly covered areas. This ensures comprehensive data acquisition. For the final, detailed output, a non-real-time (non-RT) pipeline employs a Neural Radiance Fields (NeRF)-based Neural 3D Reconstruction (N3DR) approach, fusing SfM-derived camera poses with precise Ultra Wide-Band (UWB) location data to achieve superior accuracy. We implemented and validated this architecture using Crazyflie 2.1 UAVs. Our experiments, conducted in both single- and multi-UAV configurations, conclusively show that dynamic trajectory adaptation consistently improves reconstruction quality over static flight paths. This work demonstrates a scalable and autonomous solution that unlocks the potential of miniaturized UAVs for fine-grained 3D reconstruction in constrained environments, a capability previously limited to much larger platforms.

Mika Leo Hube, Filip Lemic, Ethungshan Shitiri et al.

Flow-guided Localization (FGL) enables the identification of spatial regions within the human body that contain an event of diagnostic interest. FGL does that by leveraging the passive movement of energy-constrained nanodevices circulating through the bloodstream. Existing FGL solutions rely on graph models with fixed topologies or handcrafted features, which limit their adaptability to anatomical variability and hinder scalability. In this work, we explore the use of Set Transformer architectures to address these limitations. Our formulation treats nanodevices' circulation time reports as unordered sets, enabling permutation-invariant, variable-length input processing without relying on spatial priors. To improve robustness under data scarcity and class imbalance, we integrate synthetic data generation via deep generative models, including CGAN, WGAN, WGAN-GP, and CVAE. These models are trained to replicate realistic circulation time distributions conditioned on vascular region labels, and are used to augment the training data. Our results show that the Set Transformer achieves comparable classification accuracy compared to Graph Neural Networks (GNN) baselines, while simultaneously providing by-design improved generalization to anatomical variability. The findings highlight the potential of permutation-invariant models and synthetic augmentation for robust and scalable nanoscale localization.

Filip Lemic, Gerard Calvo Bartra, Arnau Brosa López et al.

Nanodevices with Terahertz (THz)-based wireless communication capabilities are providing a primer for flow-guided localization within the human bloodstreams. Such localization is allowing for assigning the locations of sensed events with the events themselves, providing benefits along the lines of early and precise diagnostics, and reduced costs and invasiveness. Flow-guided localization is still in a rudimentary phase, with only a handful of works targeting the problem. Nonetheless, the performance assessments of the proposed solutions are already carried out in a non-standardized way, usually along a single performance metric, and ignoring various aspects that are relevant at such a scale (e.g., nanodevices' limited energy) and for such a challenging environment (e.g., extreme attenuation of in-body THz propagation). As such, these assessments feature low levels of realism and cannot be compared in an objective way. Toward addressing this issue, we account for the environmental and scale-related peculiarities of the scenario and assess the performance of two state-of-the-art flow-guided localization approaches along a set of heterogeneous performance metrics such as the accuracy and reliability of localization.

Ken Mendes, Filip Lemic, Jeroen Famaey

Radio Environmental Maps (REMs) are a powerful tool for enhancing the performance of various communication and networked agents. However, generating REMs is a laborious undertaking, especially in complex 3-Dimensional (3D) environments, such as indoors. To address this issue, we propose a system for autonomous generation of fine-grained REMs of indoor 3D spaces. In the system, multiple small indoor Unmanned Aerial Vehicles (UAVs) are sequentially used for 3D sampling of signal quality indicators. The collected readings are streamlined to a Machine Learning (ML) system for its training and, once trained, the system is able to predict the signal quality at unknown 3D locations. The system enables automated and autonomous REM generation, and can be straightforwardly deployed in new environments. In addition, the system supports REM sampling without self-interference and is technology-agnostic, as long as the REM-sampling receivers features suitable sizes and weights to be carried by the UAVs. In the demonstration, we instantiate the system design using two UAVs and show its capability of visiting 72 waypoints and gathering thousands of Wi-Fi data samples. Our results also include an instantiation of the ML system for predicting the Received Signal Strength (RSS) of known Wi-Fi Access Points (APs) at locations not visited by the UAVs.