Keesam Jeong

Using Neural Network to Recognize Human Emotions from Heart Rate Variability and Skin Resistance

The purpose of this paper is to estimate emotions using neural network and the changes in activities of autonomic nervous system (ANS). Since ANS cannot be controlled artificially, we presumed that the changes in emotions would be reflected to the changes in ANS. In order to observe those changes, we provided the subjects with some video clips which can induce a variety of emotions and measured the changes in ANS, especially in heart rate variability (HRV) and in galvanic skin response (GSR). With those analyzed results from the experiments, we established an algorithm based on neural network, finally we could reach the estimating rate of 80.2%

Performance Evaluation of Textile-Based Electrodes and Motion Sensors for Smart Clothing

Development of textile-based electrodes and motion sensors is one of the main issues of recent smart textile research utilizing electronic textiles. Electrocardiogram (ECG) electrodes have been developed by various textile technologies such as sputtering or electroless-plating on the fabric surfaces, and embroidering or knitting with stainless steel yarns. In addition, two types of motion sensors have also been developed using piezo-resistive textiles. They were fabricated by knitting and braiding. To examine the usability of the ECG electrode, waveforms of the conventional AgCl electrode, and the new electrodes developed in our lab were compared. It was found that electrodes using metallic embroidering are more efficient when its substrate was a metal blended fabric. The electrolessly Cu/Ni plated fabrics obtained the best conductivity in textile-based electrodes. The first motion-measuring textile-based sensor was used to predict and measure the changes in electric resistances that accompany the angle changes in the elbow joint. An advanced piezo-resistive textile by braiding showed more accurate resistance changes and also better durability. Changes in its electrical resistance were mapped to changes in its length extension. From the relationship between the extension and the electrical resistance, movement or posture of human body was detected.

Exploring possibilities of ECG electrodes for bio-monitoring smartwear with cu sputtered fabrics

This article deals with a way of developing E-textiles using sputtering method and their possibilities as ECG electrodes for a bio-monitoring smartwear. As the market of smartwear is growing, researches toward E-textiles become more important. Among various ways of providing conductivity on textiles, we selected sputtering technology. Through the sputtering, we developed E-textiles deposited with thin Cu layer on the surface of the fabrics with thickness of about 2 micrometer. Then we measured the electrical resistances, examined their performances as ECG(electrocardiogram) electrodes and compared ECG signal measured with general AgCl electrodes. In result, ECG signals from Cu sputtered electrodes showed big potentials as textile-based electrodes by showing little difference in its signals compared with commonly used AgCl electrodes.

Design and evaluation of textile-based signal transmission lines and keypads for smart wear

The present paper was intended to prove the applications of surface-conductive fabrics as electronic textiles. First, we tested the electrical durability of a Cu/Ni electro-less plated fabric reinforced by PU(polyurethane) sealing. Using the fabric, we constructed textile-based signal transmission lines and textile-based keypads. For performance tests, we compared the output signals between the textile transmission lines and Cu cables and evaluated textile-based keypads by means of operation force and subjective operation feeling. PU sealing was effective to yield electrical durability for surface-conductive fabrics, thus the repeatedly-laundered fabric showed almost identical output signal with that of Cu, successfully operating an MP3 player. Subjective evaluation and operation force measurement identified that the rubber dome switch keypad was preferred due to a low operation force and less pressure on the skin when the keypad-mounted clothing is worn. The paper suggested specific applications and evaluation methods of electronic textiles as essential components for smart wear.

Tooth brushing Pattern Classification using Three-Axis Accelerometer and Magnetic Sensor for Smart Toothbrush

The concept of intelligent toothbrush, capable of monitoring brushing motion, orientation through the grip axis, during toothbrushing was suggested in our previous study. In this study, we describe a tooth brushing pattern classification algorithm using three-axis accelerometer and three-axis magnetic sensor. We have found that inappropriate tooth brushing pattern showed specific moving patterns. In order to trace the position and orientation of toothbrush in a mouth, we need to know absolute coordinate information of toothbrush. By applying tilt-compensated azimuth (heading) calculation algorithm, which is generally used in small telematics devices, we could find the inclination and orientation information of toothbrush. To assess the feasibility of the proposed algorithm, 8 brushing patterns were preformed by 6 individual healthy subjects. The proposed algorithm showed the detection ratio of 98%. This study showed that the proposed monitoring system was conceived to aid dental care personnel in patient education and instruction in oral hygiene regarding brushing style.

An exploration of electrolessly Cu/Ni plated polyester fabrics as e-textiles

Electrolessly Cu/Ni plated fabrics are favorable to be used as e-textiles owing to the excellent conductivity and the properties peculiar to fabrics. Nevertheless, durability is less ensured compared with Cu-based conductive lines. Therefore, we investigate the influence of abrasion and laundering on the electrical resistance of electrolessly Cu/Ni plated fabrics, and the effect of polyurethane sealing for the electrical durability.

Application of PU-sealing into Cu/Ni electroless plated polyester fabrics for e-textiles

Electroless metal plated fabrics are favorable to be used as e-textiles due to the excellent conductivity and peculiar properties of textiles such as flexibility. But, the electrical durability is not enough to be used as e-textiles. Therefore, we applied polyurethane(PU)-sealing (single-sealing vs. double-sealing) onto the electroless metal plated polyester fabrics (Ripstop vs. Mesh) to reinforce the electrical durability. We investigated the changes of electrical properties of the PU-sealed metal plated fabrics after laundering by a multi-meter, examined the surface changes using scanning electron microscope, and checked the metal existence using energy dispersive X-ray spectroscopy. And, we finally proved the possibility of the fabric strips as transmission lines by alternating conventional earphone lines. PU double-sealing showed higher performance on Ripstop polyester fabrics even after being laundered 10 times, which was almost the same as Cu-based typical conductive lines did.

Suggestion for optimal location of textile-based ECG electrodes on an elastic shirts considering clothing pressure of the shirt

For an effective design of ECG shirt, clothing pressure in each point with a shirt composed of 60% polyester, 33% cotton, and 7% Lycra was measured, and the qualities of ECG signals with the textile-based electrodes on the shirts according to contact capacity were compared. A clothing pressure measuring device developed for stationary state was used in the experiment to quantitatively analyze clothing pressure, and the ECG signal detection rates of the textile-based electrodes according to the regions where they were attached were calculated. Five subjects were participated in the experiments, and their clothing pressures were measured in 30 points in their upper body in 3 postures. The results showed a high degree of correlation between clothing pressure and ECG signal detection rate regardless of the subjects postures.

The Study on the Web-Based Clinical Database Management System of Oriental Pulse Waveform

There are many database-oriented sites on the web, which provide basic medical knowledge, hospital information, and medical counseling. However, there are only a few oriental pulse databases on the web. In this perspective, the goal of this study is to develop the Clinical Database Management System of Oriental Pulse Wave Form using the World Wide Web. Accordingly, this study has conducted researches in the Web-based diagnosis data management system of pulse waveform as well as the method of transmitting the data of pulse waveform. In order to set the standard for the documents of the pulse waveform of patients, the web-based clinical database management system has been developed.

Establishing a Measurement System for Human Motions Using a Textile-Based Motion Sensor

We developed a human motion measurement system using textile-based motion sensors whose electrical resistance changes with textile length. Eight body locations were marked and used for measurement, based on previous studies investigating the relationship between human muscles and activities. Five male subjects participated to the experiment, walking and running while the electrical resistance of each sensor was measured. Measuring and analyzing the variations in the electrical resistances of our sensors allowed us to successfully evaluate body postures and motions.