• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.10
• /
• pp.598-605
• /
• 2003

In this paper, we propose the method that separates PPG signal and motion artifact signal from two input signals using new independent component analysis algorithm in time domain. In order to eliminate the large level artifact efficiently, block interleaving. lowpass time filtering and innovation processing technique were applied in ICA preprocessing, and FastICA algorithm were applicable. Experiments are made with the numerical simulation and the real PPG signal including four kinds of motion artifact pattern. Our results show that ICA can effectively detect, separate and remove motion artifact in input signals. Then from the separated signals we restore the original PPG signal and propose a new method which computes SpO$_2$ using ICA mixing matrix.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.2
• /
• pp.234-242
• /
• 2008

The purpose of this paper is to verify the practical effectiveness of an interphalangeal coordination-based joint motion planning method for humanoid finger operations. For the purpose, several experiments have been performed and comparative experimental results are shown. Through the experimental works, it is confirmed that according to the employed joint motion planning method, the joint configurations for a finger's trajectory can be planned stably or not, and consequently the actual joint torque command for controlling the finger can be made moderately or not. Finally, this paper analyzes that the interphalangeal coordination-based joint motion planning method is practically useful for implementing a stable finger manipulation. It is remarkably noted that the torque pattern by the method is well-balanced. Therefore, it is expected that the control performance of humanoid or prosthetic fingers can be enhanced by the method.

• Korean Journal of Applied Biomechanics
• /
• v.34 no.2
• /
• pp.71-80
• /
• 2024

Objective: This study aimed to explore the brain connectivity between brain and biomechanical variables by exploring motion recognition through FFT (fast fourier transform) analysis and AI (artificial intelligence) focusing on quiet standing movement patterns. Method: Participants included 12 young adult males, comprising university students (n=6) and elite gymnasts (n=6). The first experiment involved FFT of biomechanical signals (f_CoP, f_AJtorque and f_EEG), and the second experiment explored the optimization of AI-based GRU (gated recurrent unit) using f_EEG data. Results: Significant differences (p<.05) were observed in frequency bands and maximum power based on group and posture types in the first experiment. The second study improved motion prediction accuracy through GRU performance metrics derived from brain signals. Conclusion: This study delved into the movement pattern of upright standing posture through the analysis of bio-signals linking the cerebral cortex to motor performance, culminating in the attainment of motion recognition prediction performance.

• Journal of Internet Computing and Services
• /
• v.11 no.4
• /
• pp.59-72
• /
• 2010

WIM(Weigh-In-Motion) is the system measuring the weight of the vehicle with a high-speed. In the existing WIM system, vehicle weight is measured based on the constant speed and the error ratio has 10%. However, because of measuring the driving pattern, that is abnormal driving pattern which is like the acceleration and down-shift of the drivers, it has the error ratio which is bigger than the real. In order to it reduces the error ratio of WIM system, the improved WIM system needs to find the abnormal driving pattern. In order to reducing the error ratio of these WIM systems, the improved WIM system can find abnormal driving patterns. In this paper, the improved WIM system which analyzes the abnormality driving pattern influencing on the error ratio of WIM system of an existing and minimizes the error span is designed. The improved WIM system has the multi step loop structure of adding the loop sensor to an existing system. In addition, the measure function defined as an intrinsic is improved and the weight measured by the abnormal driving pattern is amended. The analysis of experiment result improved WIM system can know the fact that the error span reduces by 8% less than in the existing the maximum average sampling error 22.98%.

• Korean Journal of Computational Design and Engineering
• /
• v.6 no.4
• /
• pp.263-270
• /
• 2001

In stamping-die manufacturing, the first step is to build die patterns for lost wax casting process. A recent industry trend is to manufacture the die pattern using 3-axis NC machining. This study identifies technical considerations of the pattern machining caused by the characteristics of Styrofoam material, and proposes technical methods related to establishing a process plan and generating tool paths for optimizing the pattern machining. In this paper, the process plan includes the fellowing three items: 1) deter-mining a global machining sequence-a sequence of profile, top, bottom machining and two set-ups, 2) extracting machining features from a pattern model and merging them, and 3) determining a machining sequence of machining features. To each machining feature, this study determines the machining start point, generates the approach tool path, and proposes a tool path linking method fur reducing the distance of the cutter rapid motion. Finally, a smooth tool path generation and an automatic feedrate adjustment (AFA) method are introduced far raising the machining efficiency.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.6
• /
• pp.417-422
• /
• 2005

This paper presents an EMG pattern classification method to identify motion commands for the control of the artificial arm by SOM-TVC(self organizing map - tracking Voronoi cell) based on neural network with a feature parameter. The eigenvalue is extracted as a feature parameter from the EMG signals and Voronoi cells is used to define each pattern boundary in the pattern recognition space. And a TVC algorithm is designed to track the movement of the Voronoi cell varying as the condition of additive noise. Results are presented to support the efficiency of the proposed SOM-TVC algorithm for EMG pattern recognition and compared with the conventional EDM and BPNN methods.

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.254-265
• /
• 2024

Pattern recognition for surface electromyogram (sEMG) suffers from its nonstationary and stochastic property. Although it can be relieved by acquiring new training data, it is not only time-consuming and burdensome process but also hard to set the standard when the data acquisition should be held. Therefore, we propose an adaptive sEMG pattern recognition algorithm using principal component analysis. The proposed algorithm finds the relationship between sEMG channels and extracts the optimal principal component. Based on the relative distance, the proposed algorithm determines whether to update the existing patterns or to register the new pattern. From the experimental result, it is shown that multiple patterns are generated from the sEMG data stream and they are highly related to the motion. Furthermore, the proposed algorithm has shown higher classification accuracy than k-nearest neighbor (k-NN) and support vector machine (SVM). We expect that the proposed algorithm is utilized for adaptive and long-lasting pattern recognition.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.33 no.7
• /
• pp.506-511
• /
• 2009

Insect flight is adapted to cope with each circumstance by controlling a variety of the parameters of wing motion in nature. Many researchers have struggled to solve the fundamental concept of insect flight, but it has not been solved yet clearly. In this study, to find the most effective flapping wing dynamics, we conducted to analyze CFD data on fixing some of the optimal parameters of wing motion such as stoke amplitude, flip duration and wing rotation type and then controlled the deviation angle by fabricating wing tip motion. Although all patterns have the similar value of lift coefficient and drag coefficient, pattern A(pear-shape type) indicates the highest lift coefficient and pattern H(pear-shape type) has the lowest lift coefficient among four wing tip motions and three deviation angles. This result suggest that the lift and drag coefficient depends on the angle of attack and the deviation angle combined, and it could be explained by delayed stall and wake capture effect.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.2
• /
• pp.247-256
• /
• 1986

An experimental investigation was conducted to study natural convection due to temperature and concentration differences between the two opposite end walls of a rectangular enclosure of aspect ratio 0.2. Flow motion in the enclosure appears as a uni-cell flow pattern for the relatively lower concentration and higher temperature differences and vice versa, while it appears as a multicell flow pattern for the comparable temperature and concentration differences. In the multi-cell flow regime, when the cellular flow motiion is very slow, vertical temperature differences within the cells are negligible while the vertical concentration differences are large. In addition, both the temperature and concentration differences are negligible across the interface between the slowly moving cells. For the fast moving cellular flow motion, on thel contrary, vertical temperature differences within the cells are large while the vertical concentration differences are negligible. In this case, temperature differences are negligible and the concentration differences are large across the interface between the fase moving cells.

• Fashion & Textile Research Journal
• /
• v.21 no.4
• /
• pp.420-431
• /
• 2019

This paper evaluates the potential of dynamic graphical patterns in future-driven fashion design using computer graphics that enables changes to the visual appearance of a textile for aesthetic, expressive or communicative purposes. In particular, it focuses on experimenting with the possibility of creating digitalized dynamic fashion garments that are illustrated digitally using motion graphics developed collaboratively in a virtual space. Three objectives were formed and addressed. First, a dynamic graphical pattern was defined that also investigated the cases of tangible and virtual dynamic patterns in textiles and garments to identify current situations and future prospects in terms of functional techniques and expressive effects. Ten digital fashion illustrations were then created in collaboration with a group of graphic designers and motion artists to visualize dynamic graphical patterns changing over time. Four types of dynamic fashion illustrations were also introduced in their methodological and expressive aspects. Last, some findings resulted from digital works that led to implications for future studies on tangible dynamic fashion designs. This study proposed that computer graphics and digital imaging technologies integrated into a virtual fashion that creates eye-catching and futuristic dynamic fashion designs that can customize colors and patterns according to the desires of wearers or users.