While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned tasks. This limitation presents a significant hurdle in deploying edge devices in real-world scenarios where information is presented in an inherently sequential manner. Active dendrites of pyramidal neurons play an important role in the brain's ability to learn new tasks incrementally. By exploiting key properties of time-to-first-spike (TTFS) encoding and leveraging its high sparsity, we present a novel spiking neural network (SNN) model enhanced with active dendrites. Our model can efficiently mitigate catastrophic forgetting in temporally-encoded SNNs, which we demonstrate with an end-of-training accuracy across tasks of 88.3% on the test set using the Split MNIST dataset. Furthermore, we provide a novel digital hardware architecture that paves the way for real-world deployment in edge devices. Using a Xilinx Zynq-7020 SoC FPGA, we demonstrate a 100-% match with our quantized software model, achieving an average inference time of 37.3 ms and an 80.0% accuracy.

@en

Robotic airships offer significant advantages in terms of safety, mobility, and extended flight times. However, their highly restrictive weight constraints pose a major challenge regarding the available computational resources to perform the required control tasks. Neuromorphic computing stands for a promising research direction for addressing such problem. By mimicking the biological process for transferring information between neurons using spikes or impulses, spiking neural networks (SNNs) allow for low power consumption and asynchronous event-driven processing. In this paper, we propose an evolved altitude controller based on an SNN for a robotic airship which relies solely on the sensory feedback provided by an airborne radar. Starting from the design of a lightweight, low-cost, open-source airship, we also present an SNN-based controller architecture, an evolutionary framework for training the network in a simulated environment, and a control strategy for ameliorating the gap with reality. The system's performance is evaluated through real-world experiments, demonstrating the advantages of our approach by comparing it with an artificial neural network and a linear controller. The results show an accurate tracking of the altitude command with an efficient control effort.@en

The advent of consumer and industrial Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, has opened business opportunities in many fields, including logistics, smart agriculture, inspection, surveillance, and construction. In addition, the autonomous operations of UAVs reduce risks by minimizing the time spent by human workers in harsh environments and lowering costs by automating tasks. For reliability and safety, the drones must sense and avoid potential obstacles and must be capable of safely navigating in unknown environments. UAVs' perception requires reliability in various settings, such as high dust levels, humidity, intense sun glare, dark, and fog that can severely obstruct many conventional sensing methods. Radar systems have unique strengths; they can reliably estimate how far an object is and measure its relative speed via the Doppler effect. In addition, because radars exploit radio waves to sense, they perform well in rain, fog, snow, or smoky environments. This stands in contrast to optical technologies, such as cameras or LIght Detection And Ranging (Lidars), which are more susceptible to the same challenges as the human eye. This survey paper aims to address the signal processing challenges for the exploitation of radar systems in unmanned aerial vehicles for advanced perception, considering recent integration trends and technology capabilities. The focus is on signal processing techniques for low-cost and power-efficient radar sensors, which operate onboard the UAVs in real-Time to ensure their needs in terms of perception, situational awareness, and navigation. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, safe, and autonomous way for UAVs to perceive and interact with the world.

@en

Cardiovascular diseases (CVD) are often characterized by their multifactorial complexity. This makes remote monitoring and ambulatory cardiac rehabilitation (CR) therapy challenging. Current wearable multimodal devices enable remote monitoring. Machine learning (ML) and artificial intelligence (AI) can help in tackling multifaceted datasets. However, for clinical acceptance, easy interpretability of the AI models is crucial. The goal of the present study was to investigate whether a multi-parameter sensor could be used during a standardized activity test to interpret functional capacity in the longitudinal follow-up of CR patients. A total of 129 patients were followed for 3 months during CR using 6-min walking tests (6MWT) equipped with a wearable ECG and accelerometer device. Functional capacity was assessed based on 6MWT distance (6MWD). Linear and nonlinear interpretable models were explored to predict 6MWD. The t-distributed stochastic neighboring embedding (t-SNE) technique was exploited to embed and visualize high dimensional data. The performance of support vector machine (SVM) models, combining different features and using different kernel types, to predict functional capacity was evaluated. The SVM model, using chronotropic response and effort as input features, showed a mean absolute error of 42.8 m (±36.8 m). The 3D-maps derived using the t-SNE technique visualized the relationship between sensor-derived biomarkers and functional capacity, which enables tracking of the evolution of patients throughout the CR program. The current study showed that wearable monitoring combined with interpretable ML can objectively track clinical progression in a CR population. These results pave the road towards ambulatory CR.

@en