• 센서학회지
• /
• 제20권6호
• /
• pp.382-387
• /
• 2011

Whether a person is feeling sleepy or reasonably awake is important safety information in many areas, such as humans operating in traffic or in heavy industry. The changes of body signals have been mostly researched by looking at electroencephalogram(EEG) signals but more and more other medical signals are being examined. In our study, an electrocardiogram(ECG) signal is measured at a sampling rate of 100 Hz and used to try to distinguish the possible differences in signal between the two states: awake and drowsy. Practical tests are conducted using a wireless sensor node connected to a wearable ECG sensor, and an ECG signal is transmitted wirelessly to a base station connected to a server PC. Through the QRS complex in the ECG analysis it is possible to obtain much information that is helpful for diagnosing different types of cardiovascular disease. A program is made with MATLAB for digital signal filtering and graphing as well as recognizing the parts of the QRS complex within the signal. Drowsiness detection is performed by evaluating the R peaks, R-R interval, interval between R and S peaks and the duration of the QRS complex..

• 융합신호처리학회논문지
• /
• 제20권1호
• /
• pp.24-30
• /
• 2019

현대인들은 불안정한 소득과 타인과의 갈등 등 다양한 요소로 인하여 정신건강 관리가 필요하다는 주장이 있다. 최근에는 웨어러블 장비에 심전도(Electrocardiogram, ECG)를 측정할 수 있는 장비가 보급되고 있으며, 해외의 경우 의학적 보조수단으로 활용된 사례를 볼 수 있다[14]. 이와 같은 기능을 활용하는 것으로 대표적인 감정(기쁨, 슬픔, 분노 등)을 객관적인 수치로 구별하는 연구들이 진행되고 있다. 그러나 대부분의 연구는 제한적인 환경에서 복합적인 생체 신호를 수집하는 것으로 정확도를 높이고 있다. 따라서 각각의 자극에 대한 생체 정보의 변화와 판별에 가장 많은 영향을 미친 요소를 살펴본다.

• 전기학회논문지
• /
• 제67권12호
• /
• pp.1690-1698
• /
• 2018

Recent advances in ICT technology have transformed many of our daily lives and attracted a lot of attention to personal health. Heart beat measurement that reflects cardiac activities has been used in various fields such as exercise evaluation and psychological state evaluation for a long time, but its utilization method is limited due to its differentiation from clinical electrocardiogram. Therefore, in this study, we could observe the change of the measured signal according to the change of the distance and the position of the measuring electrodes which are non-standard electrode configuration. Based on the electric dipole model of the heart, correlation with clinical electrocardiogram could be confirmed by synthesizing multiple surface potentials measured with a shorter electrode distance than standard one. From the electromagnetic point of view, the distance between the measuring electrodes corresponds to the distance that the electric potential by the cardiac electric dipole moves, and the electric potential measured at the body surface is proportional to the moving distance of the electric potential. Therefore, it is preferable to make the distance between electrodes as long as possible, and to position the measuring electrode close to the ventricle rather than the atrium. In addition, it was found that standard electrocardiographic waveforms could be synthesized by using arithmetic sum of multiple measuring electrodes due to the relationship of electrical dipole vectors, which is obtained by dividing and positioning a plurality of measuring electrodes on a reference electrode line, such as Lead-I, Lead-II direction. Also, we obtained a significant Pearson correlation coefficient ($r=0.9113{\pm}0.0169$) as a result of synthetic experiments on four subjects.

• 전기학회논문지
• /
• 제63권10호
• /
• pp.1448-1454
• /
• 2014

In this study, a new type of electrode device is implemented to measure the capacitance energy and interpret it as the ECG (Electrocardiogram) data. The main idea of this new electrode system is to estimate the capacitance on the skin by assembling a capacitive-coupled circuits and translate into the ECG signal. To measure the coupling energy and estimate the aquired data in terms of heart activity, the capacitive-coupled electrode is garmented with fabrics in the form of a chest band or a vest jacket. To compare the ECG data from the capacitive-coupled electrode with the conventional electrode(Ag-AgCl) system, the corelation coefficient between two signals is computed as 0.9517. Thus, we can conclude the fact that capacitive-coupled electrode system can measure a person's heart activity without any contact to his or her skin and can the interpreted as the ECG data.

• Korean Circulation Journal
• /
• 제54권3호
• /
• pp.140-153
• /
• 2024

Background and Objectives: Although a single-lead electrocardiogram (ECG) patch may provide advantages for detecting arrhythmias in outpatient settings owing to user convenience, its comparative effectiveness for real-time telemonitoring in inpatient settings remains unclear. We aimed to compare a novel telemonitoring system using a single-lead ECG patch with a conventional telemonitoring system in an inpatient setting. Methods: This was a single-center, prospective cohort study. Patients admitted to the cardiology unit for arrhythmia treatment who required a wireless ECG telemonitoring system were enrolled. A single-lead ECG patch and conventional telemetry were applied simultaneously in hospitalized patients for over 24 hours for real-time telemonitoring. The basic ECG parameters, arrhythmia episodes, and signal loss or noise were compared between the 2 systems. Results: Eighty participants (mean age 62±10 years, 76.3% male) were enrolled. The three most common indications for ECG telemonitoring were atrial fibrillation (66.3%), sick sinus syndrome (12.5%), and atrioventricular block (10.0%). The intra-class correlation coefficients for detecting the number of total beats, atrial and ventricular premature complexes, maximal, average, and minimal heart rates, and pauses were all over 0.9 with p values for reliability <0.001. Compared to a conventional system, a novel system demonstrated significantly lower signal noise (median 0.3% [0.1-1.6%] vs. 2.4% [1.4-3.7%], p<0.001) and fewer episodes of signal loss (median 22 [2-53] vs. 64 [22-112] episodes, p=0.002). Conclusions: The novel telemonitoring system using a single-lead ECG patch offers performance comparable to that of a conventional system while significantly reducing signal loss and noise.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권5호
• /
• pp.702-712
• /
• 2016

A wrist watch type wearable cardiovascular monitoring device is proposed for continuous and convenient monitoring of the patient's cardiovascular system. For comprehensive monitoring of the patient's cardiovascular system, the concurrent electrocardiogram (ECG) and arterial pulse wave (APW) sensor front-end are fabricated in $0.18{\mu}m$ CMOS technology. The ECG sensor frontend achieves 84.6-dB CMRR and $2.3-{\mu}Vrms$-input referred noise with $30-{\mu}W$ power consumption. The APW sensor front-end achieves $3.2-V/{\Omega}$ sensitivity with accurate bio-impedance measurement lesser than 1% error, consuming only $984-{\mu}W$. The ECG and APW sensor front-end is combined with power management unit, micro controller unit (MCU), display and Bluetooth transceiver so that concurrently measured ECG and APW can be transmitted into smartphone, showing patient's cardiovascular state in real time. In order to verify operation of the cardiovascular monitoring system, cardiovascular indicator is extracted from the healthy volunteer. As a result, 5.74 m/second-pulse wave velocity (PWV), 79.1 beats/minute-heart rate (HR) and positive slope of b-d peak-accelerated arterial pulse wave (AAPW) are achieved, showing the volunteer's healthy cardiovascular state.

• Journal of Communications and Networks
• /
• 제16권4호
• /
• pp.465-474
• /
• 2014

Wireless sensor network (WSN) is considered to be one of the most important research fields for ubiquitous healthcare (u-healthcare) applications. Healthcare systems combined with WSNs have only been introduced by several pioneering researchers. However, most researchers collect physiological data from medical nodes located at static locations and transmit them within a limited communication range between a base station and the medical nodes. In these healthcare systems, the network link can be easily broken owing to the movement of the object nodes. To overcome this issue, in this study, the fast link exchange minimum cost forwarding (FLE-MCF) routing protocol is proposed. This protocol allows real-time multi-hop communication in a healthcare system based on WSN. The protocol is designed for a multi-hop sensor network to rapidly restore the network link when it is broken. The performance of the proposed FLE-MCF protocol is compared with that of a modified minimum cost forwarding (MMCF) protocol. The FLE-MCF protocol shows a good packet delivery rate from/to a fast moving object in a WSN. The designed wearable platform utilizes an adaptive linear prediction filter to reduce the motion artifacts in the original electrocardiogram (ECG) signal. Two filter algorithms used for baseline drift removal are evaluated to check whether real-time execution is possible on our wearable platform. The experiment results shows that the ECG signal filtered by adaptive linear prediction filter recovers from the distorted ECG signal efficiently.

• 센서학회지
• /
• 제30권1호
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• 센서학회지
• /
• 제31권1호
• /
• pp.16-23
• /
• 2022

Cardiac disease is the most common cause of death worldwide. Therefore, detection and classification of electrocardiogram (ECG) signals are crucial to extend life expectancy. In this study, we aimed to implement an artificial intelligence signal recognition system in field programmable gate array (FPGA), which can recognize patterns of bio-signals such as ECG in edge devices that require batteries. Despite the increment in classification accuracy, deep learning models require exorbitant computational resources and power, which makes the mapping of deep neural networks slow and implementation on wearable devices challenging. To overcome these limitations, spiking neural networks (SNNs) have been applied. SNNs are biologically inspired, event-driven neural networks that compute and transfer information using discrete spikes, which require fewer operations and less complex hardware resources. Thus, they are more energy-efficient compared to other artificial neural networks algorithms.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.186-191
• /
• 2023

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.