The main research motivation of this article is the fight against gender-based violence and achieving gender equality from a technological perspective. solution proposed in work goes beyond currently existing panic buttons, needing to be manually operated by victims under difficult circumstances. Instead, Bindi, our end-to-end autonomous multimodal system, relies on artificial intelligence methods automatically identify violent situations, based detecting fear-related emotions, trigger...

https://youtu.be/ltLSCUESeR0 INTRODUCTION Mobile technology and applications are now commonly used for neurocognitive testing. Adequate motor control is necessary to perform such assessments. This study assessed the perceived usability of three mobile among healthy individuals those with Parkinson’s Disease (PD). METHODS 25 adults (10 females, 15 males), aged 57 81 years, divided into two groups: (1) without PD (n= 11; m= 70.36 ± sd= 6.87yrs) (2) 14; 72.64 4.55yrs). Participants completed...

Cardiovascular diseases, a leading cause of noncommunicable disease-related deaths, require early and accurate detection to improve patient outcomes. Taking advantage advances in machine learning deep learning, multiple approaches have been proposed the literature address challenge detecting ECG anomalies. Typically, these methods are based on manual interpretation signals, which is time consuming depends expertise healthcare professionals. The objective this work propose system, FADE,...

Satellite observations provide indispensable data that is assimilated into numerical ocean models to correct errors and biases. Traditionally, sea surface height (SSH) from satellite altimeter tracks, temperature (SST), more recently, salinity (SSS), have been these models. Temperature are part of the governing equations dynamics, SSH directly derived state resolved ocean, making variables a first choice for assimilation. However, satellite-derived Chlorophyll-a (Chl-a) data, which offer...

Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than window length. However, it introduces additional computations. work explores potential optimize computational efficiency during inference by exploiting convolution's shift-invariance properties skip calculation of layer activations between successive Although convolutions are shift-invariant, zero-padding and pooling...

Continuous physiological monitoring integrated within current wearable devices is a hot topic nowadays. Despite that, measuring variables still challenging due to intrinsic and extrinsic personal factors. This results in the need for smart, adjustable, personalized sensing devices. Among different signals that can be measured, changes skin conductance are extensively used affective computing research. measurement presents an unequivocal relationship with sympathetic branch of autonomous...

Cyber-Physical Systems (CPSs) are systems designed as a network of different interacting elements, which integrate computational and physical capabilities. The human-machine interaction plays significant role in CPSs, especially applications where people an active element. In this context, emotion recognition is relevant aspect to achieve more efficient, collaborative, resilient machine performance collaboration with humans. On basis, paper proposes embedded learning approach for fully...

Emotion recognition is benefitting from the latest research into physiological monitoring and wireless communications, among other remarkable achievements. These technologies can indeed provide solutions to protect vulnerable people in scenarios such as personal assaults, abuse of children or elderly, gender violence sexual aggression. Cyberphysical systems using smart sensors, artificial intelligence wearable inconspicuous devices serve bodyguards detect these risky situations (through...

Coarse-Grain Reconfigurable Arrays (CGRAs) represent emerging low-power architectures designed to accelerate Compute-Intensive Loops (CILs). The effectiveness of CGRAs in providing acceleration relies on the quality mapping: how efficiently CIL is compiled onto platform. State-of-the-Art (SoA) compilation techniques utilize modulo scheduling minimize Iteration Interval (II) and use graph algorithms like Max-Clique Enumeration address mapping challenges. Our work approaches problem through a...

X-HEEP (eXtendable Heterogeneous Energy-Efficient Platform) is an open-source1, configurable, and extensible single-core RISC-V microcontroller developed at the Embedded Systems Laboratory (ESL) of EPFL for edge-computing platforms. can be used standalone as a low-cost microcontroller, or it integrated into existing platforms to act like peripheral subsystem, extended customized with external peripherals accelerators nimbly. The latter particularly appealing novel accelerators, memories,...

Microelectromechanical systems (MEMS) are revolutionizing a multitude of industries world wide, from consumer products to the scientific community. Rehabilitation robotics is robotic field specially interested in using advantages inertial sensors. The essential aspect this area intrinsic interaction between human and robot, which imposes several restrictions design sort robots. This paper addresses analysis application sensors as sensing technologies controlled orthotic devices with detailed...

Affective Internet of Things (AIoT) uses sensing technology empowered with the capability detecting or predicting emotional affective state person. Recently, personal area networks in wearable systems have received increasing attention regarding affect recognition research. The combination market-ready and smart integrated sensors makes wearable-based an essential building block. In this paper we present on-going PhD thesis work toward a fear detection system. A reduced set wearable-ready...

Accurate extraction of heart rate from photoplethysmography (PPG) signals remains challenging due to motion artifacts and signal degradation. Although deep learning methods trained as a data-driven inference problem offer promising solutions, they often underutilize existing knowledge the medical processing community. In this paper, we address three shortcomings models: artifact removal, degradation assessment, physiologically plausible analysis PPG signal. We propose KID-PPG,...

Exploring life conditions on the near-Earth planets and satellites before carrying out human missions is an important task for space agencies. For that purpose, scientific usually include instruments to measure climatological variables. Within this instrumentation measurement context, dust sensors (DSs) aim particles in suspension provide valuable information persons equipment conditions, while they must deal with low signal-to-noise ratios (SNRs). example, Exomars mission focused...

Informatics is becoming essential in our daily activities. The use of the human machine interface requires fine movements from user. When are distorted, for instance, by tremor, performance could be improved digitally filtering

This paper introduces the work developed by authors in study of tremor time series. First, it a novel technique for tremor. The presented is high-resolution that solves most limitations Fourier Analysis (the standard to series). was used tremorous movement joints upper limb. After, some conclusions about behaviour limb based on are presented. Furthermore, an algorithm able estimated real-time voluntary and validated two contexts with successful results. Finally, future

The combination of smart sensors and affective computing capabilities in wearable devices enables future technological integration horizons for high added value applications. Among the usual information considered field computing, those based on physiology have gained special attention recent years, since it is related to autonomic nervous system (ANS), which responsible physiological regulation stress relaxed situations. One metric heart rate variability (HRV), from ANS activation can be...

Nowadays, the integration of smart sensors in wearable affective computing systems aims to improve and create applications based on conventional sensing technology. The inclusion this type is key high sensing-demanding applications, such as those computing. This must be quantitatively supported by metrics that directly affect performance, processing time, memory usage, measurement accuracy. paper presents a comprehensive analysis specific sensor constrained device from an embedded...