The increasing demand for high-resolution hyperspectral images from nano and microsatellites conflicts with the strict bandwidth constraints for downlink transmission. A possible approach to mitigate this problem consists in reducing the amount of data to transmit to ground through on-board processing of hyperspectral images. In this paper, we propose a custom Convolutional Neural Network (CNN) deployed for a nanosatellite payload to select images eligible for transmission to ground, called CloudScout. The latter is installed on the Hyperscout-2, in the frame of the Phisat-1 ESA mission, which exploits a hyperspectral camera to classify cloud-covered images and clear ones. The images transmitted to ground are those that present less than 70% of cloudiness in a frame. We train and test the network against an extracted dataset from the Sentinel-2 mission, which was appropriately pre-processed to emulate the Hyperscout-2 hyperspectral sensor. On the test set we achieve 92% of accuracy with 1% of False Positives (FP). The Phisat-1 mission will start in 2020 and will operate for about 6 months. It represents the first in-orbit demonstration of Deep Neural Network (DNN) for data processing on the edge. The innovation aspect of our work concerns not only cloud detection but in general low power, low latency, and embedded applications. Our work should enable a new era of edge applications and enhance remote sensing applications directly on-board satellite.

Nowadays, chronic heart failure (CHF) affects an ever-growing segment of population, and it is among the major causes of hospitalization for elderly citizens. The actual out-of-hospital treatment model, based on periodic visits, has a low capability to detect signs of destabilization and leads to a high re-hospitalization rate. To this aim, in this paper, a complete and integrated Information and Communication Technology system is described enabling the CHF patients to daily collect vital signs at home and automatically send them to the Hospital Information System, allowing the physicians to monitor their patients at distance and take timely actions in case of necessity. A minimum set of vital parameters has been identified, consisting of electrocardiogram, SpO2, blood pressure, and weight, measured through a pool of wireless, non-invasive biomedical sensors. A multi-channel front-end IC for cardiac sensor interfacing has been also developed. Sensor data acquisition and signal processing are in charge of an additional device, the home gateway. All signals are processed upon acquisition in order to assert if both punctual values and extracted trends lay in a safety zone established by thresholds. Per-patient personalized thresholds, required measurements and transmission policy are allowed. As proved by first medical tests, the proposed telemedicine platform represents a valid support to early detect the alterations in vital signs that precede the acute syndromes, allowing early home interventions thus reducing the number of subsequent hospitalizations.

The management of the increasing number of patients affected by cardiovascular, pulmonary, and metabolic chronic diseases represents a major challenge for the National Health System (NHS) in any developed country. Chronic diseases are indeed the main cause of hospitalization, especially for elderly people, leading to sustainability problems due to the huge amount of resources required. In the last years, the adoption of the chronic care model (CCM) as assistive model improved the management of these patients and reduced the related healthcare costs. The diffusion of wireless sensors, portable devices and connectivity enables to implement new information and communication technology (ICT)-based innovative applications to further improve the outcomes of the CCM. This paper presents a telemedicine platform for data acquisition, distribution, processing, presentation, and storage, aimed to remotely monitor the clinical status of chronic patients. The proposed solution is based on monitoring kits, with wireless Bluetooth (BT)/ Bluetooth low energy (BLE) sensors and a gateway (i.e., smartphone or tablet) connected to a web-based cloud application that collects and makes available the clinical information to the medical staff. The platform allows clinicians and practitioners to monitor at distance their patients, according to personalized treatment plans, and to act promptly in case of aggravations, reducing hospitalizations and improving patients’ quality of life.

This paper presents a new remote healthcare model, which, exploiting wireless biomedical sensors, an embedded local unit (gateway) for sensor data acquisition-processing-communication, and a remote e-Health service center, can be scaled in different telemedicine scenarios. The aim is avoiding hospitalization cost and long waiting lists for patients affected by chronic illness who need continuous and long-term monitoring of some vital parameters. In the “1:1” scenario, the patient has a set of biomedical sensors and a gateway to exchange data and healthcare protocols with the remote service center. In the “1:N” scenario the use of gateway and sensors is managed by a professional caregiver, e.g., assigned by the Public Health System to a number N of different patients. In the “point of care” scenario the patient, instead of being hospitalized, can take the needed measurements at a specific health corner, which is then connected to the remote e-Health center. A mix of commercially available sensors and new custom-designed ones is presented. The new custom-designed sensors range from a single-lead electrocardiograph for easy measurements taken by the patients at their home, to a multi-channel biomedical integrated circuit for acquisition of multi-channel bio signals, to a new motion sensor for patient posture estimation and fall detection. Experimental trials in real-world telemedicine applications assess the proposed system in terms of easy usability from patients, specialist and family doctors, and caregivers, in terms of scalability in different scenarios, and in terms of suitability for implementation of needed care plans.

Covid-19 has brought many difficulties in the management of infected and high-risk patients. Telemedicine platforms can really help in this situation, since they allow remotely monitoring Covid-19 patients, reducing the risk for the doctors, without decreasing the efficiency of the therapies and while alleviating patients’ mental issues. In this paper, we present the entire architecture and the experience of using the Tel.Te.Covid19 telemedicine platform. Projected for the treatment of chronic diseases, it has been technologically updated for the management of Covid-19 patients with the support of a group of doctors in the territory when the pandemic arrived, introducing new sensors and functionalities (e.g., the familiar use and video calls). In Tuscany (Central Italy), during the first wave of outbreak, a model for enrolling patients was created and tested. Because of the positive results, the latter has been then adopted in the second current wave. The Tel.Te.Covid19 platform has been used by 40 among general practitioners and doctors of continuity care and about 180 symptomatic patients since March 2020. Both patients and doctors have good opinion of the platform, and no hospitalisations or deaths occurred for the monitored patients, reducing also the impact on the National Healthcare System.

Productivity and production quality have become primary goals for the success of companies in all industrial and manufacturing sectors. Performance in terms of productivity is influenced by several factors including machinery efficiency, work environment and safety conditions, production processes organization, and aspects related to workers’ behavior (human factors). In particular, work-related stress is among the human factors that are most impactful and difficult to capture. Thus, optimizing productivity and quality in an effective way requires considering all these factors simultaneously. The proposed system aims to detect workers’ stress and fatigue in real time using wearable sensors and machine learning techniques and also integrate all data regarding the monitoring of production processes and the work environment into a single platform. This allows comprehensive multidimensional data analysis and correlation research, enabling organizations to improve productivity through appropriate work environments and sustainable processes for workers. The on-field trial demonstrated the technical and operational feasibility of the system, its high degree of usability, and the ability to detect stress from ECG signals exploiting a 1D Convolutional Neural Network (accuracy 88.4%, F1-score 0.90).