• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Korean Chemical Engineering Research
• /
• v.59 no.1
• /
• pp.6-10
• /
• 2021

The shorting resistance (SR) of the PEMFC(Proton Exchange Membrane Fuel Cell) polymer membrane is an important indicator of the durability of the membrane. When SR decreases, shorting current (SC) increases, reducing durability and performance. When SR becomes less than about 0.1 kΩ·㎠, shorting occurs, the temperature rises rapidly, and MEA(Membrane Electrode Assembly) is burned to end stack operation. In order to prevent shorting, we need to control the SR, so the conditions affecting the SR were studied. There were differences in the SR measurement methods, and the SR measurement method, which improved the DOE(Department of Energy) and NEDO(New Energy and Industrial Technology Development Organization) method, was presented. It was confirmed that the SR decreases as the relative humidity, temperature and cell compression pressure increase. In the final stage of the accelerated durability evaluation process of the polymer membrane, SR rapidly decreased to less than 0.1 kΩ·㎠, and the hydrogen permeability became higher than 15 mA/㎠. After dismantling the MEA, SEM(Scanning Electron Microscope) analysis showed that a lot of platinum was distributed inside the membrane.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.2
• /
• pp.40-46
• /
• 2022

Hall thrusters are one of the electric propulsion, where ions are accelerated to generate thrust and are widely utilized in space missions due to their high specific impulses. Recently, as the utilization of small and micro satellites with the mass of similar or less than 100 kg is highly increasing, the importance of research and development of the low-power electric propulsion is also raised. In this study, we developed two sub-200 W or less class, laboratory model Hall thrusters and measured the thrust and analyzed the discharge characteristics. Consequently, we obtained 2.5-9.0 mN of thrust, 600-1,150 s of specific impulse, and 15-28% of anode efficiency at 50-175 W of anode power.

• Korean Chemical Engineering Research
• /
• v.60 no.3
• /
• pp.321-326
• /
• 2022

As the thickness of the polymer membrane of PEMFC(Proton Exchange Membrane Fuel Cells) is getting thinner for PEMFC performance and price reduction, research on improving durability has become more important. In the durability evaluation of membranes, the mechanical durability evaluation time is more than twice that of the chemical durability evaluation time, so it is necessary to select the durability evaluation conditions well. In this study, we tried to check how much the mechanical durability evaluation time changes when there is a difference in the inflow gas type and flow rate in the mechanical durability evaluation protocol (Wet/Dry). When nitrogen was used at a flow rate of 2,000 mL/min, the evaluation time increased by 1.25 times compared to when air was used. An increase in the degradation rate of the electrode Pt was the main factor when air was used. When the flow rate was reduced to 800 mL/min, the air and nitrogen evaluation times increased by 1.5 times and 1.2 times, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.23-31
• /
• 2022

Due to the recent outbreak of COVID-19 and an aging population and an increase in single-person households, the amount of time that household members spend doing various activities at home has increased significantly. In this study, we propose an algorithm for detecting anomalies in members of single-person households, including the elderly, based on the results of human movement and fall detection using an image sensor algorithm through home CCTV, an activity sensor algorithm using an acceleration sensor built into a smartphone, and a 2D LiDAR sensor-based LiDAR sensor algorithm. However, each single sensor-based algorithm has a disadvantage in that it is difficult to detect anomalies in a specific situation due to the limitations of the sensor. Accordingly, rather than using only a single sensor-based algorithm, we developed a fusion method that combines each algorithm to detect anomalies in various situations. We evaluated the performance of algorithms through the data collected by each sensor, and show that even in situations where only one algorithm cannot be used to detect accurate anomaly event through certain scenarios we can complement each other to efficiently detect accurate anomaly event.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1890-1897
• /
• 2022

In this paper, we design a navigation filter for an underwater glider. Underwater gliders are low-cost, reusable, and can be used for a long time. Two types of filters are designed considering characteristics such as small size, low cost, and low power. The navigation filter estimates the reference velocity of the underwater glider's body frame based on the minimum sensor output. The sensor configuration of the first filter consists of an accelerometer, a magnetometer, and a depth sensor. the second filter include extra a gyroscope in the same configuration. The estimated velocity is fused with the attitude, converted into the velocity of the navigation frame and finally the position is estimated. To analyze the performance of the proposed filter, analysis was performed using Monte Carlo numerical analysis method, and the results were analyzed with standard deviation (1σ). Standard deviations of each filter's position error are 334.34m, 125.91m.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.1
• /
• pp.177-186
• /
• 2017

Recently, Autonomous vehicles are getting hot attention. Amazon, the biggest online shopping service provider is developing a delivery system that uses drones. This kinds of platforms are need accurate attitude information for navigation. In this paper, a structure design of AHRS using low-cost inertia sensor is proposed. To estimate attitudes a Kalman filter which uses a quaternion based dynamic model, bias-removed measurements from MEMS Gyro, raw measurements from MEMS accelerometer and magnetometer, is designed. To remove bias from MEMS Gyro, an additional Kalman filter which uses raw Gyro measurements and attitude estimates, is designed. The performance of implemented AHRS is compared with high price off-the-shelf 3DM-GX3-25 AHRS from Microstrain. The Gyro bias was estimated within 0.0001[deg/s]. And from the estimated attitude, roll and pitch angle error is smaller than 0.2 and 0.3 degree. Yaw angle error is smaller than 6 degree.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1653-1659
• /
• 2022

Virtual reality content provides users with a high sense of immersion by using HMD devices. However, while wearing the HMD device, it is difficult to determine the user's location or distance from obstacles, resulting in injuries due to physical collisions. In this paper, we propose a reminder module to prevent accidents by notifying the risk of collision with obstacles while wearing the HMD device. The proposed module receives the user's state from the acceleration and gyro sensor and determines the motion that is likely to cause a collision. If there is an obstacle in the expected collision range, a buzzer sounds to the wearer. As a result of the experiment, the accuracy of obstacle detection in the state of wearing the HMD was 86.6% in the 1st stage and 83.3% in the 2nd stage, confirming the performance of the accident prevention reminder.