• Journal of Integrative Natural Science
• /
• v.7 no.1
• /
• pp.57-61
• /
• 2014

This study measured the stream data from the several sensors, and stores the database in MapReduce framework environment, and it aims to design system with the small performance and cluster analysis error rate through the KMSVM algorithm. Through the KM-SVM algorithm, the cluster analysis effective data was used for U-health system. In the results of experiment by using 2003 data sets obtained from 52 test subjects, the k-NN algorithm showed 79.29% cluster analysis accuracy, K-means algorithm showed 87.15 cluster analysis accuracy, and SVM algorithm showed 83.72%, KM-SVM showed 90.72%. As a result, the process speed and cluster analysis effective ratio of KM-SVM algorithm was better.

• Journal of Sensor Science and Technology
• /
• v.31 no.1
• /
• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.921-926
• /
• 2022

Sugar solutions (5%, 10%, 15% and 20%) were tested by seven sensors of Astree E-Tongue for selecting a sensor for sweetness. NMS sensor was chosen as a sensor for sweetness among two sensors (PKS and NMS sensors selected in first stage) by considering precision, linearity and accuracy. Sugar, fructose, glucose and xylitol (5%, 10% and 15%) were tested by E-tongue. The principal component analysis (PCA) result by E-Tongue with seven sensors at 5% concentration level of four sweetners was not satisfactory (Discrimination index was -0.1). On the other hand, the relative NMS sensor response values were derived as 1.08 (fructose), 0.99 (glucose) and 1.00 (xylitol) comparing to sugar. Only the E-Tongue relative glucose response 0.99 was different from 0.5~0.75 of the relative sweetness range reported as the human sensory test results. Considering the excellent precision (%RSD, 1.53~3.64%) of E-Tongue using NMS single sensor for three types of sweeteners compared to sugar in the concentration range of 5% to 15%, replacing sensory test of sweetened beverages by E-Tongue might be possible for new product development and quality control.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.627-636
• /
• 2011

The purpose of this study is to develop the multi-modal interaction system. This system provides realistic and an immersive experience through multi-modal interaction. The system recognizes user behavior, intention, and attention, which overcomes the limitations of uni-modal interaction. The multi-modal interaction system is based upon gesture interaction methods, intuitive gesture interaction and attention evaluation technology. The gesture interaction methods were based on the sensors that were selected to analyze the accuracy of the 3-D gesture recognition technology using meta-analysis. The elements of intuitive gesture interaction were reflected through the results of experiments. The attention evaluation technology was developed by the physiological signal analysis. This system is divided into 3 modules; a motion cognitive system, an eye gaze detecting system, and a bio-reaction sensing system. The first module is the motion cognitive system which uses the accelerator sensor and flexible sensors to recognize hand and finger movements of the user. The second module is an eye gaze detecting system that detects pupil movements and reactions. The final module consists of a bio-reaction sensing system or attention evaluating system which tracks cardiovascular and skin temperature reactions. This study will be used for the development of realistic digital entertainment technology.

• Science of Emotion and Sensibility
• /
• v.9 no.2
• /
• pp.141-150
• /
• 2006

Since the late 1990s, 'smart clothing' has been developed in a various way to meet the need of users and to help people more friendly interact with computers through its various designs. Recently, various applications of smart clothing concept have been presented by researchers. Among the various applications, smart clothing with a health care system is most likely to gain the highest demand rate in the market. Among them, smart clothing for check-up of health status with its sensors is expected to sell better than other types of smart clothing on the market. Under this circumstance, research and development for this field have been accelerated furthermore. This research institution has invented biometric sensors suitable for the smart clothing, and has developed a design to diagnose various diseases such as cardiac disorder and respiratory diseases. The newly developed smart clothing in this study looks similar to the previous inventions, but people can feel more comfortable in it with its fabric interaction built in it. When people wear it, the health status of the wearers is diagnosed and its signals are transmitted to the connected computer so the result can be easily monitored in real time. This smart clothing is a new kind of clothing as a supporting system for preventing various cardiac disorder and respiratory diseases using its biometric sensor built-in, and is also an archetype to show how smart clothing can work on the market.

• KSBB Journal
• /
• v.22 no.6
• /
• pp.409-413
• /
• 2007

Polydiacetylene(PDA)-based sensors possess a number of properties that can be successfully applied for label-free detection system. PDA is one of the most attractive color-generating materials, with growing applications as sensors. Here we introduce various PDA-based devices, used as biosensor, chemosensor, thermosensor, and optoelectronics sensor. In general, PDA liposomes and films are closely packed and properly designed for polymerization via 1,4-addition reaction to form an ene-yne alternating polymer chain. PDA-based two/three dimensional structures have been used for colorimetric or fluorescent devices, sensing biological as well as chemical components. This color-generating material also present a very high charge carrier mobility, allowing its application as field-effect transistor (FET). The immobilized PDA structures or films have distinct advantages for the detection of low concentration target molecules over the aqueous solution-based detection systems. In the present review, reported detection methods by using various PDA structures are summarized with updated references.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.438-443
• /
• 2022

In this study, the lateral loading test was performed to analyze structural performance of multi-span plastic greenhouse through full-scale experiment and numerical analysis. In order to analyze the lateral stiffness and stress, we installed 9 displacement sensors and 19 strain gauge sensors on the specimen, respectively, and load of l mm per minute was applied until the specimen failure. In the comparison between the full-scale experiment and the structural analysis results of a multi-span greenhouse with venlo-type roof according to bracing installation, there was a large difference in the lateral stiffness of the structure. By installing a brace system, the lateral stiffness measured near the side elevation of the specimen increased by up 44%. As the bracing joint used in the field did not secure sufficient rigidity, the external force could not be transmitted to the entire structure properly. Therefore, it is necessary to establish a bracing construction method and design standards in order for a greenhouse to which bracing applied to have sufficient performance.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.28-36
• /
• 2006

In this paper, an algorithm to classify the 4 motions of arm and a control system to position control the prosthesis are studied. To classify the 4 motions, we use flex sensors which is electrical resistance type sensor that can measure warp of muscle. The flex sensors are attached to the biceps brchii muscle and coracobrachialis muscle and the sensor signals are passed the sensing system. 4 motion of the forearm - flexion and extension, the pronation and supination are classified from this. Also position of forearm is measured from the classified signals. Finally, A two D.O.F prosthesis arm with RC servo-motor is designed to verify the validity of the algorithm. At this time, fuzzy controller is used to reduce the position error by rotary inertia and noise. From the experiment, the position error had occurred within about 5 degree.

• Analytical Science and Technology
• /
• v.29 no.1
• /
• pp.35-42
• /
• 2016

A new nano-composite carbon ink for the development of disposable dopamine (DA) biosensors based on screen-printed carbon electrodes (SPCEs) is introduced. The method developed uses SPCEs coupled with a tyrosinase modified nano-composite carbon ink. The ink was prepared by an “in-house” procedure with reduced graphene oxide (rGO), Pt nanoparticles (PtNP), and carbon materials such as carbon black and graphite. The rGO-PtNP carbon composite ink was used to print the working electrodes of the SPCEs and the reference counter electrodes were printed by using a commercial Ag/AgCl ink. After the construction of nano-composite SPCEs, tyrosinase was immobilized onto the working electrodes by using a biocompatible matrix, chitosan. The composite of nano-materials was characterized by X-ray photoelectron spectroscopy (XPS) and the performance characteristics of the sensors were evaluated by using voltammetric and amperometric techniques. The cyclic voltammetry results indicated that the sensors prepared with the rGO-PtNP-carbon composite ink revealed a significant improvement in electro-catalytic activity to DA compared with the results obtained from bare or only PtNP embedded carbon inks. Optimum experimental parameters such as pH and operating potential were evaluated and calibration curves for dopamine were constructed with the results obtained from a series of amperometric detections at −0.1 V vs. Ag/AgCl. The limit of detection was found to be 14 nM in a linear range of 10 nM to 100 µM of DA, and the sensor’s sensitivity was calculated to be 0.4 µAµM⁻¹cm⁻².

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1257-1264
• /
• 2019

The traditional cuff-based method for BP(Blood Pressure) measurement is not suitable for continuous real-time BP measurement techniques. For this reason, the previous studies estimated various blood pressures by fusion with the electrocardiography (ECG) and photoplethysmogram (PPG) sensor signals. However, conventional techniques based on PPG bio-sensing measurement face many challenging issues such as noisy supply fluctuation, small pulsation, and drifting non-pulsatile. This paper proposed a novel BP estimation methods using PPG and ECG sensors, which can be derived from the relationship between PPG and ECG using PTT(Pulse Transit Time) and PWV(Pulse Wave Velocity). Unlike conventional height ratio features, which are extracted on the basis of the peaks in the PPG and ECG waveform. The proposed method can be reliably obtained even if there are missing peaks among the sensed PPG signal. The increased reliability comes from periodical estimation of the peak-to-peak interval time using ECG and PPG. After 250,000 times trials of the blood pressure measurement, the proposed estimation technique was verified with the accuracy of ±28.5% error, compared to a commercialized BP device.