• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.4
• /
• pp.55-62
• /
• 2004

In this paper, we have developed a portable acceleration measurement system to measure acceleration signals during walking and a gait analysis algorithm which can evaluate gait regularity and symmetry and estimate gait parameters automatically. Portable acceleration measurement system consists of a biaxial accelerometer, amplifiers, lowpass filter with cut-off frequency of 16Hz, one-chip microcontroller, EEPROM and RF(TX/RX) module. The algerian includes FFT analysis, filter processing and detection of main peaks. In order to develop the algorithm, eight hemiplegic patients for training set and the other eight hemiplegic patients for test set are participated in the experiment. Acceleration signals during 10m walking were measured at 60 samples/sec from a biaxial accelerometer mounted between L3 and L4 intervertebral area. The algorithm, detected foot contacts and classified right/left steps, and then calculated gait parameters based on these informations. Compared with video data and analysis by manual, algorithm showed good performance in detection of foot contacts and classification of right/left steps in test set perfectly. In the future, with improving the reliability and ability of the algerian so that calculate more gait Parameters accurately, this system and algerian could be used to evaluate improvement of walking ability in hemiplegic patients in clinical practice.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.65.2-65
• /
• 2002

This paper is concerned with the accurate position control of a rodless pneumatic cylinder using On/Off solenoid valve. A novel Intelligent Modified Pulse Width Modulation(MPWM) is newly proposed. The control performance of this pneumatic cylinder depends on the external loads. To overcome this problem , switching of control parameter using artificial neural network is newly proposed, which estimates external loads on rodless pneumatic cylinder using this training neural network. As an underlying controller, a state feedback controller using position, velocity and acceleration is applied in the switching control the system. The effectiveness of the proposed control algorithms are demonstrated...on/off solenoid valve, load estimation, MPWM, Artificial neural network.

• Proceedings of the KIEE Conference
• /
• 1997.07e
• /
• pp.1847-1849
• /
• 1997

This paper describes the analysis of vibration signals of distorted mold transformer. For experiment, the acceleration sensors were adhered on the surface of winding and on the core. The vibration signals measured as variation of control variables were analyzed using data acquisition system. It was shown that the vibration signals of distorted mold transformer were distinguished from those of normal mold transformer.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.343-350
• /
• 2020

This study was intended to use the Inertia Sensor Units(IMU) for the national women's handball team to quantify movements for a total of 16 domestic or international practice games over five months and to identify the efficiency of training and differences in movements by position. A total of 15 players were participated excluding goalkeepers. The results are as follows. Player Load came in order of Wing>Back>Pivot and high in international games. Change of Direction(CoD) were found to have the most Pivot at low intensity, while middle and high intensity were the most in the Back. There have been a lot of low and middle intensity CoD in International games. Low-intensity acceleration(ACC) and deceleration(DEC) were found to have the most Pivot, while middle & high intensity ACC and DEC had the most Back. There have been many low and middle intensity ACC and low, middle and high intensity DEC in international games. There were many middle and high intensity jumps in Back and Wing, but there were no differences in the types of games.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.51 no.1
• /
• pp.71-78
• /
• 2015

In order to deduce an objective evaluation method of motion seasickness incidence (MSI) by ship motions during underway in irregular waves and to present the fundamental data of passenger comfort on the yacht and the passenger ship according to the result, the MSI of the trainees by the questionnaires was analysed and compared with the rate of variation of salivary ${\alpha}$-amylase activity (VSAA) on the training ship "A-ra ho" of Jeju national university. Relationship between rate of variation (x) by salivary ${\alpha}$-amylase activity and motion seasickness incidence (y) was described by the equation, MSI(%) = 0.6073 x + 12.189 including the correlation coefficient ($R^2=0.9853$). The result obtained through the rate of variation of salivary ${\alpha}$-amylase activity which was the quantitative evaluation method for ship motions causing seasickness was most affected by z-vertical acceleration and occurred within the frequency range 0.1 to 0.3Hz centered on 0.2Hz, and the simulation result based on this finding showed the motion seasickness rate at approximately 4% lower than the rate obtained through the survey.

• Korean Journal of Applied Biomechanics
• /
• v.26 no.4
• /
• pp.433-441
• /
• 2016

Objective: The purpose of this study was to understand the injury mechanism and to provide quantitative data to use in prevention or posture correction training by conducting kinematic and kinetic analyses of risk factors of lower extremity joint injury depending on the change of direction at different angles after a landing motion. Method: This study included 11 men in their twenties (age: $24.6{\pm}1.7years$, height: $176.6{\pm}4.4cm$, weight: $71.3{\pm}8.0kg$) who were right-leg dominant. By using seven infrared cameras (Oqus 300, Qualisys, Sweden), one force platform (AMTI, USA), and an accelerometer (Noraxon, USA), single-leg drop landing was performed at a height of 30 cm. The joint range of motion (ROM) of the lower extremity, peak joint moment, peak joint power, peak vertical ground reaction force (GRF), and peak vertical acceleration were measured. For statistical analysis, one-way repeated-measures analysis of variance was conducted at a significance level of ${\alpha}$ <.05. Results: Ankle and knee joint ROM in the sagittal plane significantly differed, respectively (F = 3.145, p = .024; F = 14.183, p = .000), depending on the change of direction. However, no significant differences were observed in the ROM of ankle and knee joint in the transverse plane. Significant differences in peak joint moment were also observed but no statistically significant differences were found in negative joint power between the conditions. Peak vertical GRF was high in landing (LAD) and after landing, left $45^{\circ}$ cutting (LLC), with a significant difference (F = 9.363, p = .000). The peak vertical acceleration was relatively high in LAD and LLC compared with other conditions, but the difference was not significant. Conclusion: We conclude that moving in the left direction may expose athletes to greater injury risk in terms of joint kinetics than moving in the right direction. However, further investigation of joint injury mechanisms in sports would be required to confirm these findings.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.13-20
• /
• 2022

It's proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It's for the coefficient of determination (R²) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.414-419
• /
• 2020

An artificial intelligence-based cable tension estimation model was developed to expand the utilization of data obtained from cable accelerometers of cable-stayed bridges. The model was based on an algorithm for selecting the natural frequency in the tension estimation process based on the vibration method and an applied artificial neural network (ANN). The training data of the ANN was composed after converting the cable acceleration data into the frequency, and machine learning was carried out using the characteristics with a pattern on the natural frequency. When developing the training data, the frequencies with various amplitudes can be used to represent the frequencies of multiple shapes to improve the selection performance for natural frequencies. The performance of the model was estimated by comparing it with the control criteria of the tension estimated by an expert. As a result of the verification using 139 frequencies obtained from the cable accelerometer as the input, the natural frequency was determined to be similar to the real criteria and the estimated tension of the cable by the natural frequency was 96.4% of the criteria.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.271-277
• /
• 2017

The purpose of this study was to develop a balance chair for improving pelvic correction and postural balance through postural balance training using tactile feedback by a vibration motor provided in real time according to the user's attitude. We built a body frame using mono cast(MC) Nylon, Touch thin film transistor(TFT) for user interface, a main control module using Arduino, a 9-axis acceleration sensor for user's posture determination, and a vibration module for tactile feedback. The prototype of the Balance Chair which surrounds the outside was made with cushion for sitting conformability. In order to verify the effectiveness of the postural balance training system using the built prototype, the muscle activity (% MVIC) of the left and right iliocostalis lumborum those are the main muscles of the spinal movement was measured with ten female subjects. And the balance ability before and after training was measured using Spine Balance 3D, a posture balance ability evaluation device. The muscular activities of the left and right iliocostalis lumborum showed the balance activation according to vibration feedback during exercise protocol and postural balance improved after balance exercise training using balance chair. This study could be apply to use the fundamental research for developing the various postural balance product.