1,720,991 research outputs found
High speed wireless optical system for motorsport data loggers
No full textTelemetry allows to monitor the behavior of a system and it is applied to many different and popular fields such as motorsport. In this case, a data-logger collects all the data coming from different automobile sensors providing a very reliable image of the car status and a better vehicle setup. This paper is focused on the development of a new data-logging system for motorsport application, which meets several process constraints, such as high throughput and low power consumption that, to the best of the authors’ knowledge, the available devices on the market were not able to satisfy. The new data-logger consists of a fixed and a removable part, which exchanges data through a transceiver exploiting the visible light communication (VLC) technology. In this way, every physical contact between the two parts of the system is avoided. All the communication procedures are managed by a micro-controller mounted on each part of the system. The transceiver consists of the AFBR-1634Z and AFBR-2634Z (Broadcom Limited, San Jose, CA, USA) components, the optical fiber transmitter and the receiver, respectively, produced by Broadcom Inc. By keeping the distance short between them, they can assure a real wireless communication, even without using a high throughput technology like optical fiber. The entire system is powered by an inductive coupling system. In order to test the transceiver, it is connected to a micro-controller reaching a data rate of 8 Mbit/s. But even better performance is achieved by upgrading the micro-controller and changing the transmission technique, connecting the transceiver to the serial peripheral interface (SPI) port of the micro-controller: in this case, a data rate of 21 Mbit/s is reached, perfectly suitable with the application requirements and even furthe
Guest Editorial: Special Section on New Trends in Parallel and Distributed Computing for Human Sensible Applications
No full textProceedings - 11th EUROMICRO Conference on Digital System Design Architectures, Methods and Tools, DSD 2008: Message from the general and organizing chairs
No full textGPU-based key-frame selection of pulmonary ultrasound images to detect COVID-19
No full textIn the last decades, technological advances have led to a considerable increase in computing power constraints to simulate complex phenomena in various application fields, among which are climate, physics, genomics and medical diagnosis. Often, accurate results in real time, or quasi real time, are needed, especially if related to a process requiring rapid interventions. To deal with such demands, more sophisticated approaches have been designed, including GPUs, multicore processors and hardware accelerators. Supercomputers manage high amounts of data at a very high speed; however, despite their considerable performance, their limitations are due to maintenance costs, rapid obsolescence and notable energy consumption. New processing architectures and GPUs in the medical field can provide diagnostic and therapeutic support whenever the patient is subject to risk. In this context, image processing as an aid to diagnosis, in particular pulmonary ultrasound to detect COVID-19, represents a promising diagnostic tool with the ability to discriminate between different degrees of disease. This technique has several advantages, such as no radiation exposure, low costs, the availability of follow-up tests and the ease of use even with limited resources. This work aims to identify the best approach to optimize and parallelize the selection of the most significant frames of a video which is given as the input to the classification network that will differentiate between healthy and COVID patients. Three approaches have been evaluated: histogram, entropy and ResNet-50, followed by a K-means clustering. Results highlight the third approach as the most accurate, simultaneously showing GPUs significantly lowering all processing times
Guest Editorial: Special Section on New Trends in Parallel and Distributed Computing for Human Sensible Applications
No full textThe papers in this special section focus on collecting high-quality scientific contributions from the research community working in the fields of parallel and distributed computing, data analytics algorithms and big data frameworks, application specific processing. Specifically, the main focus is on emerging new computing trends that affect the concrete human life, the so-called "Human Sensible Applications". Problems in parallel computing related to implement precision medicine and novel therapeutical targets, real-time architectures for biomedical IoT, computational biology and chemical compounds simulations, realistic modelling of human body organs, bioimaging processing, but even emerging computing systems for Human Sustainability, including weather and climate changes monitoring/prediction, resources management, safety, disaster prediction and prevention, belong to this scenario
HS2RGB: an Encoder Approach to Transform Hyper-Spectral Images to Enriched RGB Images
No full textHyperspectral imaging (HSI) captures detailed spectral information across numerous wavelengths, providing superior object characterization to conventional RGB imaging. Despite these advantages, training deep learning models on HSI data is challenging due to the limited availability of extensive datasets, unlike the more familiar RGB images. To address this issue, we propose an encoder model that transforms hyperspectral images into enriched RGB images. These new enriched images represent a graphical depiction of HSI and become a new dataset to use as input for well-known models pre-trained on RGB images. In this work, we introduce HS2RGB, an encoder model based on the Vision Transformer (ViT) architecture, which condenses hyperspectral data into a three-element vector interpreted as RGB channels. The results demonstrate the effectiveness of the new images generated by the encoder, showing better visual differentiation of features compared to traditional RGB images. Morover, results highlighted greater consistency in latent vectors of the same type of tissue across different samples compared to images generated with feature selection and transformation techniques like PCA and t-SNE. Finally, we tested the enriched RGB images using Meta's SAM model for instance segmentation, revealing that our model's images provided more precise identification of regions of interest, such as tumours in medical images
An Hardware Recurrent Neural Network for Wearable Devices
No full textAutomatic classification of time series signals acquired by wearable or portable devices covers a central role in many critical healthcare applications, such as heart rate monitoring [1], sleep apnea study [2], gait analysis [3] and fall detection [4]. In recent years, many approaches have been adopted, including a wide range of methods ranging from threshold-based algorithms to Deep Learning techniques. The threshold-based methods have the advantage of being simple and not heavy from a computational point of view, but at the cost of low accuracy. Deep Learning approaches ensure a higher precision, but the computational complexity is increased. This is a critical issue for wearable devices because a high computational complexity strongly affects the processing time and the battery life. In this paper, we propose a hardware architecture for time series analysis using Recurrent Neural Networks (RNNs) exploiting FPGA technology. The architecture is validated with three-Axial accelerometer data acquired by a wearable device used for automatic fall detection. The experimental results show that the proposed architecture outperforms state of the art solutions both in terms of processing time and power consumption
- …
