1,720,968 research outputs found
Forward Nonlinear Model for Deep Learning of EEG Auditory Attention Detection in Cocktail Party Problem
Full text linkIn a multi-speaker scenario, humans are able to focus on a target speaker, ignoring all other speakers and noise, thus solving the so-called cocktail-party problem. However, elderly people and people suffering for hearing loss struggle to listening under these conditions. Recent studies have confirmed that the listener’s selective attention to the attended speaker can be decoded using recording of brain activity such as electroencephalography, thus opening new opportunities in developing a new generation of neuro-steered hearing aids and hearing prostheses. To this end several algorithms have been developed for solving the so called auditory attention decoding problem from electroencephalography on the basis of neural entrainment mechanism. The most common approaches in development of auditory attention decoding algorithms are based on linear modeling of the neural entrainment. However, even though these algorithms have shown to be effective in solving cocktail-party problem, they have some inherent limitations. The main objective of this contribution is to show that nonlinear modeling of speech-electroencephalography system ensures the best performance in terms of higher correlation between stimulus and neural response, thus proving the limitations of linear approach. For this purpose the most common linear models for auditory attention decoding are reviewed and a new nonlinear model for auditory attention decoding is proposed. An extensive experimentation using a specific speech-electroencephalography dataset, confirms the superiority of nonlinear modeling in solving the auditory attention decoding problem
Synthetic image dataset of shaft junctions inside wind turbines in presence or absence of oil leaks
No full textThis paper presents a dataset of images generated via 3D graphics rendering. The dataset is composed by pictures of the junction between the high-speed shaft and the external bracket of the power generator inside a wind turbine cabin, in presence and absence of oil leaks. Oil leak occurrence is an anomaly that can verify in a zone of interest of the junction. Since the wind turbines industry is becoming more and more important, turbines maintenance is growing in importance accordingly. In this context a dataset, as we propose, can be used, for example, to design machine learning algorithms for predictive maintenance. The renderings have been produced, from various framings and various leaks shapes and colors, using the rendering engine Keyshot9. Subsequent preprocessing has been performed with Matlab, including images grayscale conversion and image binarization. Finally, data augmentation has been implemented in Python, and it can be easily extended/customized for realizing any further processing. The Matlab and Python source codes are also provided. To the authors’ knowledge, there are no other public available datasets on this topic
High-Accuracy Clock Synchronization in Low-Power Wireless sEMG Sensors
Full text linkWireless surface electromyography (sEMG) sensors are very practical in that they can be worn freely, but the radio link between them and the receiver might cause unpredictable latencies that hinder the accurate synchronization of time between multiple sensors, which is an important aspect to study, e.g., the correlation between signals sampled at different sites. Moreover, to minimize power consumption, it can be useful to design a sensor with multiple clock domains so that each subsystem only runs at the minimum frequency for correct operation, thus saving energy. This paper presents the design, implementation, and test results of an sEMG sensor that uses Bluetooth Low Energy (BLE) communication and operates in three different clock domains to save power. In particular, this work focuses on the synchronization problem that arises from these design choices. It was solved through a detailed study of the timings experimentally observed over the BLE connection, and through the use of a dual-stage filtering mechanism to remove timestamp measurement noise. Time synchronization through three different clock domains (receiver, microcontroller, and ADC) was thus achieved, with a resulting total jitter of just 47 mu s RMS for a 1.25 ms sampling period, while the dedicated ADC clock domain saved between 10% to 50% of power, depending on the selected data rate
Energy and Performance Analysis of Lossless Compression Algorithms for Wireless EMG Sensors
Full text linkElectromyography (EMG) sensors produce a stream of data at rates that can easily saturate a low-energy wireless link such as Bluetooth Low Energy (BLE), especially if more than a few EMG channels are being transmitted simultaneously. Compressing data can thus be seen as a nice feature that could allow both longer battery life and more simultaneous channels at the same time. A lot of research has been done in lossy compression algorithms for EMG data, but being lossy, artifacts are inevitably introduced in the signal. Some artifacts can usually be tolerable for current applications. Nevertheless, for some research purposes and to enable future research on the collected data, that might need to exploit various and currently unforseen features that had been discarded by lossy algorithms, lossless compression of data may be very important, as it guarantees no extra artifacts are introduced on the digitized signal. The present paper aims at demonstrating the effectiveness of such approaches, investigating the performance of several algorithms and their implementation on a real EMG BLE wireless sensor node. It is demonstrated that the required bandwidth can be more than halved, even reduced to 1/4 on an average case, and if the complexity of the compressor is kept low, it also ensures significant power savings
Recurrent neural network for human activity recognition in embedded systems using ppg and accelerometer data
Full text linkPhotoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging
Nonlinear Dynamic System Identification in the Spectral Domain Using Particle-Bernstein Polynomials
Full text linkSystem identification (SI) is the discipline of inferring mathematical models from unknown dynamic systems using the input/output observations of such systems with or without prior knowledge of some of the system parameters. Many valid algorithms are available in the literature, including Volterra series expansion, Hammerstein–Wiener models, nonlinear auto-regressive moving average model with exogenous inputs (NARMAX) and its derivatives (NARX, NARMA). Different nonlinear estimators can be used for those algorithms, such as polynomials, neural networks or wavelet networks. This paper uses a different approach, named particle-Bernstein polynomials, as an estimator for SI. Moreover, unlike the mentioned algorithms, this approach does not operate in the time domain but rather in the spectral components of the signals through the use of the discrete Karhunen–Loève transform (DKLT). Some experiments are performed to validate this approach using a publicly available dataset based on ground vibration tests recorded from a real F-16 aircraft. The experiments show better results when compared with some of the traditional algorithms, especially for large, heterogeneous datasets such as the one used. In particular, the absolute error obtained with the prosed method is 63% smaller with respect to NARX and from 42% to 62% smaller with respect to various artificial neural network-based approaches
A multi-channel electromyography, electrocardiography and inertial wireless sensor module using bluetooth low-energy
Full text linkThis paper proposes a wireless sensor device for the real-time acquisition of bioelectrical signals such as electromyography (EMG) and electrocardiography (ECG), coupled with an inertial sensor, to provide a comprehensive stream of data suitable for human activity detection, motion analysis, and technology-assisted nursing of persons with physical or cognitive impairments. The sensor is able to acquire up to three independent bioelectrical channels (six electrodes), each with 24 bits of resolution and a sampling rate up to 3.2 kHz, and has a 6-DoF inertial platform measuring linear acceleration and angular velocity. The bluetooth low-energy wireless link was chosen because it allows easy interfacing with many consumer electronics devices, such as smartphones or tablets, that can work as data aggregators, but also imposes data rate restrictions. These restrictions are investigated in this paper as well, together with the strategy we adopted to maximize the available bandwidth and reliability of the transmission within the limits imposed by the protocol
Photoplethysmography and Inertial Sensors in Wearable Devices for Healthcare: Multimodal Signal Processing for Increasing Accuracy
No full textMultimodal signal processing is a technique by which signals from different physical domains are processed together in order to aid or improve the detection or measurement of quantities of interest. In this chapter we review a few key techniques that combine photoplethysmography (PPG) signals, that is, a non-invasive, optical measure of the peripheral blood flow commonly employed to measure parameters such as blood oxygenation (SpO2), heart rate (HR), or heart rate variation (HRV), and movement data coming from inertial sensors. This combination of signals is often employed because movement, especially in the limbs, greatly affects blood flow, and hence the PPG signal. We show that a number of techniques can be applied so that the signal from the inertial sensors can be used to clean out the so-called motion artifacts (MA) from the PPG signal, enhancing the accuracy of the HR information that can be extracted from it. The two signals can also be used together to improve the classification accuracy of the activities being performed, and this can in turn be used again to improve e.g., MA rejection, or to just obtain better estimates of the amount and type of activity a person is doing, which can be helpful in healthcare and/or nursing environments
Surface Electromyography Sensors for Human Activity Recognition: Recent Advancements and Perspectives
No full textHuman activity monitoring technology is one of the most relevant technologies for ambient assisted living, surveillance-based security, sports and fitness activities, healthcare of elderly people. Activity monitoring takes place in two phases: acquisition of the body signals and identification of the activities that are performed. Among the body signals, the surface electromyography (sEMG) signal has recently been received a great interest for its ability to give useful information about the body movements that are performed and its ease to be acquired throughout the skin of the body using small wireless sensors. This chapter aims to investigate the state of the art of wearable sEMG circuits and systems and recent advances on systems and techniques based on multimodal signal processing for recognizing human activities from sEMG-based sensors
- …
