Source author record

Andrea Giudici

Andrea Giudici appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

cond-mat.soft Machine Learning physics.ao-ph physics.flu-dyn physics.geo-ph

Catalog footprint

What is connected

5works

5topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices

Gesture recognition is a cornerstone of Human-Computer Interaction (HCI) for smart eyewear, enabling natural and device-free control in augmented reality environments. Traditional vision-based approaches face significant challenges regarding power consumption, computational latency, and user privacy. This paper proposes a lightweight, privacy-preserving gesture recognition system based on the fusion of low-resolution Time-of-Flight (ToF) and Infrared (IR) thermal sensors. We used an 8 times 8 multizone ToF sensor (VL53L8CH) and an 8 times 8 IR array (AMG8833) to capture complementary depth and thermal cues. A compact Convolutional Neural Network (CNN) with a specialized grouped-convolution architecture is designed to fuse these modalities efficiently on a microcontroller (MCU). Experimental results on a custom dataset of 7 static gestures, validated via k-fold cross-validation, demonstrate that the proposed fusion strategy significantly outperforms single-sensor baselines with an accuracy of 92.3% and a macro F1-score of 0.93. Finally, on-device benchmarks on STM32F4 and STM32H7 MCUs confirm the system's suitability for resource-constrained wearables, requiring only 6,343 parameters and achieving millisecond-level inference latency with a total system power of 50 mW.

preprint2026arXiv

Hardware-Aware Neural Feature Extraction for Resource-Constrained Devices

Visual SLAM is a core component of spatial computing systems, yet deploying learned local feature extractors on microcontroller-class hardware remains challenging due to memory, bandwidth, and quantization constraints. While modern neural descriptors provide strong robustness, their practical adoption is often hindered by system-level bottlenecks that are not captured by FLOP-based efficiency metrics. In this work, we introduce Gideon, a hardware-aware neural feature extractor explicitly designed for resource-constrained devices. Our approach combines relational knowledge distillation from a SuperPoint teacher with differentiable neural architecture search (DNAS) under strict memory and operator constraints. Unlike conventional design pipelines, we treat quantization stability and dynamic-range compactness as first-class objectives. We show that architectural choices such as replacing Batch Normalization with affine layers significantly improve INT8 robustness, and that descriptor dimensionality directly governs quantization resilience. Deployed on STM32N6, Gideon achieves 9.003 ms inference time (111 fps) while remaining below a 1.5 MB memory footprint. Remarkably, INT8 quantization induces negligible degradation and occasionally matches full-precision performance. These results demonstrate that robust learned feature extraction can be reconciled with embedded hardware constraints through holistic hardware-algorithm co-design.

preprint2022arXiv

Curvature-driven instabilities in thin active shells

Spontaneous material shape changes, such as swelling, growth or thermal expansion, can be used to trigger dramatic elastic instabilities in thin shells. These instabilities originate in geometric incompatibility between the preferred extrinsic and intrinsic curvature of the shell, which may be modified by active deformations through the thickness and in plane respectively. Here, we solve the simplest possible model of such instabilities, which assumes the shells are shallow, thin enough to bend but not stretch, and subject to homogeneous preferred curvatures. We consider separately the cases of zero, positive and negative Gaussian curvature. We identify two types of super-critical symmetry breaking instability, in which the shell's principal curvature spontaneously breaks discrete up-down symmetry and continuous planar isotropy respectively. These are then augmented by inversion instabilities, in which the shell jumps sub-critically between up/down broken symmetry states, and rotation instabilities, in which the curvatures rotate by 90 degrees between states of broken isotropy without release of energy. Each instability has a thickness independent threshold value for the preferred extrinsic curvature proportional to the square-root of Gauss curvature. Finally, we show that the threshold for the isotropy-breaking instability is the same for deep spherical caps, in good agreement with recently published data.

preprint2021arXiv

Tracking areas with increased likelihood of surface particle aggregation in the Gulf of Finland: A first look at persistent Lagrangian Coherent Structures (LCS)

We explore the possibility to identify areas of intense patch formation from floating items due to systematic convergence of surface velocity fields by means of a visual comparison of Lagrangian Coherent Structures (LCS) and estimates of areas prone to patch formation using the concept of Finite-Time Compressibility (FTC, a generalisation of the notion of time series of divergence). The LCSs are evaluated using the Finite Time Lyapunov Exponent (FTLE) method. The test area is the Gulf of Finland (GoF) in the Baltic Sea. A basin-wide spatial average of backward FTLE is calculated for the GoF for the first time. This measure of the mixing strength displays a clear seasonal pattern. The evaluated backward FTLE features are linked with potential patch formation regions with high FTC levels. It is shown that areas hosting frequent upwelling or downwelling have consistently stronger than average mixing intensity. The combination of both methods, FTC and LCS, has the potential of being a powerful tool to identify the formation of patches of pollution at the sea surface.

preprint2020arXiv

Giant deformations and soft-inflation in LCE balloons

We propose that ballooning can be controlled, enriched and amplified by using rubbery networks of aligned molecular rods known as liquid crystal elastomers (LCEs). Firstly, LCEs are promising artificial muscles, showing large spontaneous deformations in response to heat and light. In LCE balloons, spontaneous deformations can trigger classic ballooning, either as phase-separation (at constant volume) or a volume jump (at constant pressure), resulting in greatly magnified actuation strains. Secondly, even at constant temperature, LCEs have unusual mechanics augmented by soft-modes of deformation in which the nematic director rotates within the elastomer. These soft modes enrich the mechanics of LCE balloons, which can also "balloon" between rotated and unrotated states, either during the classic instability, or as a separate pre-cursor, leading to successive instabilities during inflation.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint