The Automated External Defibrillator (AED) is a medical device that analyzes a patient's electrocardiogram in order to establish whether he/she is suffering from the fatal condition of Sudden Cardiac Arrest (SCA), and subsequently allows the release of a therapeutic dose of electrical energy (i.e. defibrillation). SCA is responsible for over 300,000 deaths per year both in Europe and in USA, and immediate clinical assistance through defibrillation is fundamental for recovery. In this context, an open-source approach can easily lead in improvements to the distribution and efficiency of AEDs. The proposed Open-Source AED (OAED) is composed of two separate electric boards: a high voltage board (HV-B), which contains the circuitry required to perform defibrillation and a control board (C-B), which detects SCA in the patient and controls the HV-B. Computer simulations and preliminary tests show that the OAED can release a 200 J biphasic defibrillation in about 12 s and detects SCA with sensitivity higher than 90% and specificity of about 99%. The OAED was also conceived as a template and teaching tool in the framework of UBORA, a platform for design and sharing medical devices compliant to international standards

Accurate gear defect detection in induction machine-based systems is a fundamental issue in several industrial applications. At this aim, shallow neural networks, i.e. architectures with only one hidden layer, have been used after a feature extraction step from vibration, torque, acoustic pressure and electrical signals. Their additional complexity is justified by their ability in extracting its own features and in the very high-test classification rates. These signals are here analyzed, both geometrically and topologically, in order to estimate the class manifolds and their reciprocal positioning. At this aim, the different states of the gears are studied by using linear (Pareto charts, biplots, principal angles) and nonlinear (curvilinear component analysis) techniques, while the class clusters are visualized by using the parallel coordinates. It is deduced that the class manifolds are compact and well separated. This result justifies the use of a shallow neural network, instead of a deep one, as already remarked in the literature, but with no theoretical justification. The experimental section confirms this assertion, and also compares the shallow neural network results with the other machine learning techniques used in the literature.

Every year cardiovascular diseases kill the highest number of people worldwide. Among these, pathologies characterized by sporadic symptoms, such as atrial fibrillation, are difficult to be detected as state-of-the-art solutions, e.g., 12-leads electrocardiogram (ECG) or Holter devices, often fail to tackle these kinds of pathologies. Many portable devices have already been proposed, both in literature and in the market. Unfortunately, they all miss relevant features: they are either not wearable or wireless and their usage over a long-term period is often unsuitable. In addition, the quality of recordings is another key factor to perform reliable diagnosis. The ECG WATCH is a device designed for targeting all these issues. It is inexpensive, wearable (size of a watch), and can be used without the need for any medical expertise about positioning or usage. It is non-invasive, it records single-lead ECG in just 10 s, anytime, anywhere, without the need to physically travel to hospitals or cardiologists. It can acquire any of the three peripheral leads; results can be shared with physicians by simply tapping a smartphone app. The ECG WATCH quality has been tested on 30 people and has successfully compared with an electrocardiograph and an ECG simulator, both certified. The app embeds an algorithm for automatically detecting atrial fibrillation, which has been successfully tested with an official ECG simulator on different severity of atrial fibrillation. In this sense, the ECG WATCH is a promising device for anytime cardiac health monitoring.