STRATUM is a Horizon Europe multi-partner project developing a clinically validated, real-time 3D decision support tool for brain tumour surgery. The system integrates Hyperspectral Imaging (HSI), AI-based multimodal data fusion, and heterogeneous High-Performance Computing (HPC) architectures combining Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Processing-In-Memory (PIM) technologies. A touchless augmented reality interface facilitates safe and intuitive intraoperative interaction. The distinguishing characteristic of STRATUM is its end-to-end co-designed approach, which integrates advanced computing, state-of-the-art imaging and clinical expertise into a unified Point-of-Care (PoC) platform. Utilising a structured co-creation methodology involving surgeons, engineers, and social scientists, the project ensures usability, safety and regulatory compliance from its early design stages to its clinical validation. The usability of STRATUM will be tested in three hospitals located in different European regions with diverse conditions and regulations. This will allow to collect advice and remarks from surgical staff in a continuous co-creation and co-tuning protocol. Beyond its clinical objectives, STRATUM contributes to the advancement of heterogeneous computing for real-time diagnostics, AI acceleration in critical medical environments and energy-efficient system integration. Furthermore, it delivers open datasets, validated AI pipelines, and performance benchmarks with a view to fostering future research and industrial innovation in digital surgery. The STRATUM project establishes a replicable model for intelligent, human-centred computing integrating microelectronics, AI and medicine.The paper presents an overview of the project in terms of aims, concepts and technologies and the description of the state of the work when approaching the end of the second of the five years planned. Specifically, the outcomes of the steps related to the collaboration with surgeons and medical staff (co-creation process) and the intelligent Graphical User Interface (GUI) development will be described. The latter allows for contactless interaction of the surgeon with several functions that have already been developed in the system.

Real-time phonocardiogram analysis on embedded devices is a key enabler for scalable and accessible cardiovascular diagnostics, particularly considering portable systems designed for low-income countries. This work introduces a combination of compressive sensing and deep learning to build portable, efficient and effective diagnostic tools for widespread cardiac screenings. The proposed classification framework is tailored for deployment on ultra-low power STM32 microcontrollers equipped with the novel Neural-ART accelerator. Experimental evaluation on the CirCor Digiscope Phonocardiogram dataset demonstrates that even with a compression ratio exceeding 100×, a classification model can achieve up to 97.3% F1-score. A similar level of performance was obtained on the PhysioNet 2016 dataset, which was used to assess the robustness and generalization capability of the developed architectures. Compared to the state-of-the-art, our final edge solution achieves 94.3% accuracy, an inference time of 18.7 ms and an energy requirement of just 1.51 mJ per input window of 4,096 samples, confirming its suitability for real-time, energy-constrained medical applications.

Integrated digital diagnostics can support complex surgical procedures in many anatomical sites, brain tumour surgery being the most complex. STRATUM is a 5-year Horizon Europe funded project with the goal of developing an innovative 3D decision support tool for brain tumour surgeries, based on real-time multimodal data processing using artificial intelligence algorithms. The proposed tool is envisioned as an energy-efficient Point-of-Care computing system to be integrated within neurosurgical workflows to aid surgeons to make informed, efficient, and accurate decisions during surgical procedures. The expected long-term impact of STRATUM is to reduce the duration of surgical procedures, thus decreasing patients' risks, but also optimising the resources of European health care systems.

Hyperspectral 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.

Cardiovascular Diseases (CVDs) stand as the leading cause of mortality worldwide. Detecting subtle heart sounds alterations in the early stages of CVDs can be crucial for an initial effective treatment. Accordingly, the analysis of Phonocardiograms (PCGs) through segmentation could be helpful for CVDs screening. A well-established algorithm for this task is based on a Convolutional Neural Network (CNN) with an encoding-decoding topology. Prior to the CNN processing., a computationally intensive input pre-processing., based on envelopes extraction, is needed. Thus., achieving real-time performance can be challenging. The main goal of this study is the hardware design., implementation, and evaluation of four PCG pre-processing circuits to be employed together in the design of a low-power point-of-care device for real-time Artificial Intelligence (AI)-based PCG segmentation. Results have shown that the approximations introduced by the fixed-point format and this innovative architecture have a negligible impact on the AI segmentation quality. Finally, the pre-processing chain is real-time compliant., achieving a maximum latency of 257 ms for an available processing window of 1.28 s., while dissipating only 61 mW of power.

Abstract Hyperspectral imaging is applied in the medical field for automated diagnosis of diseases, especially cancer. Among the various classification algorithms, the most suitable ones are machine and deep learning techniques. In particular, Vision Transformers represent an innovative deep architecture to classify skin cancers through hyperspectral images. However, such methodologies are computationally intensive, requiring parallel solutions to ensure fast classification. In this paper, a parallel Vision Transformer is evaluated exploiting technologies in the context of Edge and Cloud Computing, envisioning portable instruments’ development through the analysis of significant parameters, like processing times, power consumption and communication latency, where applicable. A low-power GPU, different models of desktop GPUs and a GPU for scientific computing were used. Cloud solutions show lower processing times, while Edge boards based on GPU feature the lowest energy consumption, thus resulting as the optimal choice regarding portable instrumentation with no compelling time constraints.

Cardiovascular diseases (CVDs) are currently one of the leading causes of death worldwide. Being able to detect their symptoms at early stages, even the most hidden ones, is crucial to shorten the diagnosis time and facilitate an early treatment. Currently, the use of continuous tracking systems, mainly based on wearable devices that analyze data using artificial intelligence (AI) algorithms, is being explored to automatically identify, in real time, CVDs symptoms. This could be especially relevant in lowincome countries where there is a shortage of specialized doctors. Therefore, this work focuses on analyzing the real-time execution of the state-of-the-art convolutional neural network (CNN) for heart sound segmentation (HSS) on platforms such as traditional CPU/GPU and the Fraunhofer IMS © AIRISC Core Complex (a RISC-V processor developed for AI). Results revealed that, while all implementations exploiting the CPU/GPU platform proved to be useful in real-time diagnosis from a fixed location, the AIRISC demonstrated its goodness, as a system on a chip (SoC) for a real-time wearable application, when executing a quantized version of the CNN.

Recently, several medical applications have relied on hyperspectral imaging. This technology enables both automated diagnosis and surgeon guidance. The employed algorithms adopt machine and deep learning methods to classify the images. In particular, Vision Transformers are a recent deep architecture that have been used to classify hyperspectral images of skin cancers achieving interesting results. However, deep architectures are computationally intensive and parallel architectures are mandatory to ensure a fast classification (depending on the application type even in real time). In this paper, we propose a parallel Vision Transformer architecture exploiting a low power GPU targeting the development of a portable diagnostic device. The classification time and power consumption of the low power board are compared with the performance of a desktop GPU. The results clearly highlight the suitability of the low power GPU to develop a portable diagnostic system based on hyperspectral imaging.

Among the different contactless techniques for medical diagnosis, hyperspectral imaging has gained relevance due to the high accuracy in tissues classification. Several techniques have been proposed to elaborate these images, ranging from traditional machine learning methods to deep learning algorithms. This paper evaluates three popular machine learning methods, namely Support Vector Machine (SVM), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) considering a dataset of hyperspectral skin cancer images. The study demonstrates that the proposed algorithms are suitable for medical hyperspectral data classification, particularly when considering a small dataset.

In recent years, hyperspectral imaging has been employed in several medical applications, targeting automatic diagnosis of different diseases. These images showed good performance in identifying different types of cancers. Among the methods used for classification, machine learning and deep learning techniques emerged as the most suitable algorithms to handle these data. In this paper, we propose a novel hyperspectral image classification architecture exploiting Vision Transformers. We validated the method on a real hyperspectral dataset containing 76 skin cancer images. Obtained results clearly highlight that the Vision Transforms are a suitable architecture for this task. Measured results outperform the state-of-the-art both in terms of false negative rates and of processing times. Finally, the attention mechanism is evaluated for the first time on medical hyperspectral images.

Automatic 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.

Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.

Raman imaging is a hyperspectral approach able to provide information on the spatial distribution of a particular biochemical feature without the use of any staining or sample processing. The extraction of the relevant information from the large dataset obtained however is a laborious and complex task that still requires the development of robust chemometric approaches. In this paper, we propose a general framework for analyzing data acquired by a commercial Raman spectrometers. This framework is based both on exploiting spectral information and unsupervised clustering, in order to clearly identify the borders and the compositions of different regions of interest. Finally, we describe an efficient GPU-based parallelization, which ensures a fast image classification.

High performance computing (HPC) is becoming mandatory for the simulation of complex and realistic neuronal models. The development of such realistic models will allow to discover innovative therapies and to study brain diseases without undertaking invasive experiments that are not always possible. However, the models complexity requires adopting suitable technologies in order to provide results in short times, hopefully in real-time. To address this issue, the authors decided to exploit Graphics Processing Units (GPUs) in order to develop a realistic and morphologically detailed Purkinje cell model. This paper describes the simulation of the Purkinje cell activity adopting both single and multi-GPU strategy, together with the exploitation of different NVIDIA architectures. Results shows that the simulation times of 10000 cells is reduced from 13 days and 18 hours to about 2 hours.

Unintentional falls are the leading cause of fatal injuries and nonfatal trauma among older adults. An automated monitoring system that detects occurring falls and issues remote notifications will prove very valuable for improving the level of care that could be provided to people at higher risk. The work presented focuses on the design of embedded software for wearable devices that are connected in wireless mode to a remote monitoring system. The work focuses on the implementation of recurrent neural networks (RNNs) architectures of micro controller units (MCU) for fall detection with tri-axial accelerometers. A few general formulas for determining memory, computing power and power consumption for such architectures are presented. These formulas have been validated with an actual implementation for the SensorTile device by STMicroelectronics.

This paper describes the challenge of real-time tumor tissue identification dealt with by the HypErspectraL Imaging Cancer Detection (HELICoiD) European project. This project was funded by the Research Executive Agency, through the Future and Emerging Technologies (FET-Open) programme, under the 7th Framework Programme of the European Union. It involved four universities, three industrial partners and two hospitals. In this paper, we focused on the activity performed by the University of Las Palmas de Gran Canaria, in collaboration with the University of Pavia, concerning the parallel implementation of Support Vector Machine (SVM) classification for tumor tissue identification during surgery. Obtained results show that this classification is real-time compliant when performed using Graphic Processing Units (GPUs).

The use of High Performance Computing (HPC) technologies is gaining interest in the field of neuronal activity simulations. In fact, scientists' main goal is to understand and reproduce cells behavior in a realistic way. This will allow undertaking in silico experiments, instead of in vivo ones, to test new medicines, to study cerebral pathologies and to discover innovative therapies. To this aim, two main requirements are necessary: neurons have to be described by realistic models and their simulation hopefully have to satisfy the real-time constraint. This last property is very hard to accommodate because models used in these works are very heavy from the computational point of view. For this reason, authors decide to exploit Graphic Processing Unit (GPU) technology to simulate the cellular activity of Golgi cells, which constitute the cerebellar cortex. This paper describes an efficient Golgi cell activity simulation performed using NVIDIA GPUs. Results show that simulation times are reduced from 41 hours to about 2 hours when simulating 400'000 different cells.

This paper presents an efficient parallelization of the Motion Estimation procedure, one of the core parts of Super Resolution techniques. The algorithm considered is the basic version of Block Matching Super Resolution, with a single low-resolution camera and fixed Macro Block dimensions. Two are the implementations provided, with OpenMP and in CUDA on an NVIDIA Kepler GPU. Tests have been conducted on five image sequences and the results show a considerable improvement of the CUDA solution in all cases. Consequently, it can be stated that GPUs can efficiently accelerate computational times assuring the same image quality.

This paper describes the challenge of understanding brain function through high performance computing dealt with by the Human Brain Project, the European Commission Future and Emerging Technologies Flagship involving a consortium of 112 partners spread in 24 European countries. In particular, we describe the activity, performed by one of the Italian units involved into the project, aiming at identifying very accurate models of cerebellum neurons. These models are processed through high end Graphic Processing Units (GPUs) during the tuning phase and later implemented on FPGA-based application specific processors for respecting real time requirements together with embedded implantability. Models and performance of granular neurons implementations are given in the results section.

This paper describes the procedure of design and development of a novel prototype matrix conceived to automatically and unobtrusively measure and monitor the interface pressure distribution and the centre of pressure of seated people in various fields, such as automotive, ergonomics and clinical environments. The work regards an innovative technology, that associates equal or better characteristics compared to commercial devices, with lower costs of construction (even for the prototype), better flexibility and robustness. The system is able to perform a continuous monitoring both in laboratory contexts and in more disruptive conditions, such as hospital beds.

Recently the demand dramatically grew up for portable biosensors, providing an on-site multi-parametric measurement. Present instruments, however, are limited by large size and consumption (which prevents portability) and costs (which prevents their usage in some Countries). In this paper, we propose a compact and portable device based on a nano-structured array biochip featuring the Surface Plasmonic Resonance, lighted by a suitable optics and equipped with an 830 nm irradiating LED. The reflected image is detected by an Aptina CMOS sensor and managed by an ARM9 processor which is responsible of the acquisition end processing, performed within 14 sec form the application of the assy. The processor evaluates the average grey level pixel ratio between suitable biochip areas so as to be independent on illumination fluctuations and external noise. Preliminary results indicate a sensitivity close to 10-4 RIU change in the refractive index and applicability of the device to different applications and fields (waste water and food pollution analysis, among the main ones).

In this letter, we present a new parallel implementation of the vertex component analysis (VCA) algorithm for spectral unmixing of remotely sensed hyperspectral data on commodity graphics processing units. We first developed a C serial version of the VCA algorithm and three parallel versions: one using NVIDIA's Compute Unified Device Architecture (CUDA), another using CUDA basic linear algebra subroutines library CUBLAS, and the last using the CUDA linear algebra library CULA. Experimental results, based on the analysis of hyperspectral images acquired by a variety of hyperspectral imaging sensors, show the effectiveness of our implementation, which satisfies the real-time constraints given by the data acquisition rate.

Understanding and emulating the brain behaviour is one of the most challenging topic in neuroscience but simulating such complicated models always requires a lot of computation and, as a consequence, a lot of time. In order to efficiently evaluate a model it could be very useful to speed up the simulation process by using software or hardware accelerators. This paper presents an FPGA based accelerator who speeds up the simulation of two different kinds of innovative cerebellar neurons model, such as the Golgi cell and the granular cell, developed by the Physiology department of the University of Pavia. Since the achieved performance is real time compliant, such a circuit could be used, in the future, to bypass some dysfunction of the cerebellum in the human being.

In this paper, we present the implementation of the Infomax algorithm on a computing unit featuring a typical embedded processor of the ARM family and a second partial execution on a custom CPU developed through the FPGA technology. The computational unit will be the "core" of an instrument which aims at allowing the pregnant mothers a real time monitoring of her and the fetus health state. The Infomax algorithm belongs to the Independent Component Analysis family and serves to separate the fetal ECG from the mother's one. Also the evaluation of the wide literature and the corresponding debate is illustrated together with the motivations for the choice. In terms of performance, both the implementations are suitable for the project's goal, but the FPGA overcomes the ARM processor (on a reduced portion of the algorithm) by an order of magnitude.

Economic globalization has scattered industrial production, promoting manufacturing models able to chase the most favorable conditions in the widened international scenario. Interorganizational communication becomes thus a critical element for production streamline, being the bridge that creates continuity among industrial districts. However, many sectors still lack proper communication standards, thus slowing the production and increasing its costs. The footwear manufacturing industry especially suffers from this condition, having chronically promoted a plethora of similar-but-incompatible dialects to supply partial data exchange. To regulate and rationalize part of the footwear industry interorganizational communication, in this paper, we present the Shoe PRocess INTeroperability Standard (SPRINTS), conceived and carried out within an industrial district, ranging from shoe design to mass production. SPRINTS is based on the XML standard language to define a data exchange protocol among systems and machines of the footwear production field. SPRINTS describes both "vertical" transfers (i.e., between different steps of the design/production chain), and "horizontal" transfers (e.g., to allow data exchange between CADs from different vendors). Moreover, it allows a smooth transaction from existing standards, and it has been tested in real-world scenarios. SPRINTS is designed in collaboration with ASSOMAC, an association of shoe machineries manufacturers, comprising the worldwide majority of footwear manufacturing companies (http://info.assomac.com). The standard has been validated and already adopted by a few companies, that contributed to its development. In this paper, we present the standard and a tool able to validate and graphically render a SPRINTS file.

Biometric identification systems exploit automated methods of recognition based on physiological or behavioural people characteristics. Among these, fingerprints are very affordable biometric identifiers. In order to build embedded systems performing real-time authentication, a fast computational unit for image processing is required. In this paper we propose a parallel architecture that efficiently implements the high computationally demanding core of a matching algorithm based on Band Limited Phase Only spatial Correlation (BLPOC), elaborated by two concurrent computational units implemented onto Stratix II family Altera FPGA. The realised device is competitive with those provided by similar hardware solutions described in literature and outperforms the elaboration capabilities of general purpose PC processors.

Biometric identification systems are defined as systems exploiting automated methods of personal recognition based on physiological or behavioural characteristics. Among these, fingerprints are very reliable biometric identifiers. Trying to fasten the image processing step makes the recognition process more efficient, especially concerning embedded systems for real-time authentication. In this paper we propose an FPGA-based architecture that efficiently implements the high computationally demanding core of a matching algorithm based on phase-only spatial correlation. Moreover, we show how it is possible to use COTS components to embed an entire AFIS on chip and so reducing cost, space and energy used.

One of the most critical performance factors for race car is tires management. In particular, the main factor which provides information about the workload of tires is the temperature. Until now, the race engineerpsilas knowledge of how the tires performed has traditionally been limited to temperature readings, manually taken when the car returns to the pits. It does not provide the engineer with any real idea about how the tires are working at a specific part of the track on any specific lap. Having a better knowledge about how the tires work could offer an important advantage that allows to get to extremely pointy setups. To optimize the tire use, a more accurate way of monitoring their temperatures is presented: in this paper we introduce a new approach to study the tire temperature that use an infrared camera to effectively know how it evolves.

In this paper we describe an accelerator based on FPGA technology and interfaced to an external host computing system through standard bus connections; it is conceived to accelerate double precision floating point operations, present in the energy calculation of Monte Carlo (MC) metropolis particle system simulations. The accelerator plays the role of coprocessor giving a speed-up factor equal to 4, with respect last generation PCs. The proposed solution is based on COTS components and shows good characteristics of scalability in terms of clock frequency, memory capability and number of computing units. Moreover, the accelerator can be also conceived as a part of a computing system made up by a cluster of accelerated workstations

Exploiting hardware devoted to a specific application requires a proper programming support, like libraries allowing a simple interface with the device. As a complementary design, a dedicated device language might be developed to make its programming easier. In previous works by G. Danese et al. (2002) and G. Danese et al. (2003) we presented the architecture of a floating point operations accelerator based on Field Programmable Gate Array (FPGA) technology. In this paper we describe the development environment which allows writing, translating and simulating instruction sequences written in a language specifically conceived and designed for that device.

An instrument with a DSP for measurements of pressures, temperatures and humidity in lower limb prosthesis is presented. It has got sixteen analog input channels. The signals from the transducers are linked to the input channels and feed the conditioning network which is made up by amplification stages and peak detectors. Input signals are converted into a digital form by a 10 bit analog to digital converter integrated into the DSP and information are pre-processed and then stored in a removable memory with high capacity. The instalment is also equipped with an LCD display to show the progress of the interesting parameters in real time. Now we are testing the instrument at the Prosthetic Center in Vigorso di Budrio (Italy). The aim of these tests is checking the correct operation of the instrument in different working ways and bringing constructive modifications to prosthesis to better locate the sensors.

Mathematical models are frequently used to evaluate the physical properties of matter; they involve intensive computation: processing times and loan costs soar, using general purpose computers. Remarkable improvements are promised by special purpose architectures, in particular for the parallel execution of the most time consuming routines; the Monte Carlo-Metropolis method has been examined, and parallelization approaches have been identified. A double ring architecture of processing elements (PE) has been conceived, which optimizes efficiency, yet saves the algorithm principles. A network of 16 purposely built PEs has been assembled, and modeling programs have been run on it. The main architectural choices, both for hardware and software are described; they refer to the computing system and to each PE as well; preliminary results are also given.>