Deep ECGNet: An Optimal Deep Learning Framework for Monitoring Mental Stress Using Ultra Short-Term ECG Signals.

BACKGROUND: Stress recognition using electrocardiogram (ECG) signals requires the intractable long-term heart rate variability (HRV) parameter extraction process. This study proposes a novel deep learning framework to recognize the stressful states, the Deep ECGNet, using ultra short-term raw ECG signals without any feature engineering methods. METHODS: The Deep ECGNet was developed through various experiments and analysis of ECG waveforms. We proposed the optimal recurrent and convolutional neural networks architecture, and also the optimal convolution filter length (related to the P, Q, R, S, and T wave durations of ECG) and pooling length (related to the heart beat period) based on the optimization experiments and analysis on the waveform characteristics of ECG signals. The experiments were also conducted with conventional methods using HRV parameters and frequency features as a benchmark test. The data used in this study were obtained from Kwangwoon University in Korea (13 subjects, Case 1) and KU Leuven University in Belgium (9 subjects, Case 2). Experiments were designed according to various experimental protocols to elicit stressful conditions. RESULTS: The proposed framework to recognize stress conditions, the Deep ECGNet, outperformed the conventional approaches with the highest accuracy of 87.39% for Case 1 and 73.96% for Case 2, respectively, that is, 16.22% and 10.98% improvements compared with those of the conventional HRV method. CONCLUSIONS: We proposed an optimal deep learning architecture and its parameters for stress recognition, and the theoretical consideration on how to design the deep learning structure based on the periodic patterns of the raw ECG data. Experimental results in this study have proved that the proposed deep learning model, the Deep ECGNet, is an optimal structure to recognize the stress conditions using ultra short-term ECG data.

Deep Neural Network-based Empirical Mode Decomposition for Motor Imagery EEG Classification.

Motor imagery refers to the brain's response during the mental simulation of physical activities, which can be detected through electroencephalogram (EEG) signals. However, EEG signals exhibit a low signal-to-noise ratio (SNR) due to various artifacts originating from other physiological sources. To enhance the classification performance of motor imagery tasks by increasing the SNR of EEG signals, several signal decomposition approaches have been proposed. Empirical mode decomposition (EMD) has shown promising results in extracting EEG components associated with motor imagery tasks more effectively than traditional linear decomposition algorithms such as Fourier and wavelet methods. Nevertheless, the EMD-based algorithm suffers from a significant challenge known as mode mixing, where frequency components intertwine with the intrinsic mode functions obtained through EMD. This issue severely hampers the accuracy of motor imagery classification. Despite numerous algorithms proposed, mode mixing remains a persistent issue. In this paper, we propose the Deep-EMD algorithm, a deep neural network-based approach to mode mixing problem. We employ two datasets to compare the motor imagery classification and mode mixing improvement achieved by the conventional EMD algorithm. Our experimental results demonstrate that the Deep-EMD algorithm effectively mitigates the mode mixing problem in decomposed EEG components, leading to improved motor imagery classification performance.

Improved performance of stretchable piezoelectric energy harvester based on stress rearrangement.

With the development of wearable devices and soft electronics, the demand for stretchable piezoelectric energy harvesters (SPEHs) has increased. Energy harvesting can provide energy when large batteries or power sources cannot be employed, and stretchability provides a user-friendly experience. However, the performance of SPEHs remains low, which limits their application. In this study, a wearable SPEH is developed by adopting a kirigami structure on a polyvinylidene fluoride film. The performance of the SPEH is improved by rearranging the stress distribution throughout the film. This is conducted using two approaches: topological depolarization, which eliminates the opposite charge generation by thermal treatment, and optimization of the neutral axis, which maximizes the stress applied at the surface of the piezoelectric film. The SPEH performance is experimentally measured and compared with that of existing SPEHs. Using these two approaches, the stress was rearranged in both the x-y plane and z-direction, and the output voltage increased by 21.57% compared with that of the original film with the same stretching motion. The generated energy harvester was successfully applied to smart transmittance-changing contact lenses.

Unobtrusive measurement of indoor energy expenditure using an infrared sensor-based activity monitoring system.

The purpose of this study was to develop an unobtrusive energy expenditure (EE) measurement system using an infrared (IR) sensor-based activity monitoring system to measure indoor activities and to estimate individual quantitative EE. IR-sensor activation counts were measured with a Bluetooth-based monitoring system and the standard EE was calculated using an established regression equation. Ten male subjects participated in the experiment and three different EE measurement systems (gas analyzer, accelerometer, IR sensor) were used simultaneously in order to determine the regression equation and evaluate the performance. As a standard measurement, oxygen consumption was simultaneously measured by a portable metabolic system (Metamax 3X, Cortex, Germany). A single room experiment was performed to develop a regression model of the standard EE measurement from the proposed IR sensor-based measurement system. In addition, correlation and regression analyses were done to compare the performance of the IR system with that of the Actigraph system. We determined that our proposed IR-based EE measurement system shows a similar correlation to the Actigraph system with the standard measurement system.