• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.139-148
• /
• 2022

In this paper, we implement a distributed FMCW MIMO radar system to obtain Micro Doppler signatures of target motions. In addition, we also develop federated learning based motion recognition algorithm based on the Micro-Doppler radar signature collected by the implemented FMCW MIMO radar system. Through the experiment, we have verified that the proposed federated learning based algorithm can improve the motion recognition accuracy up to 90%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1981-1995
• /
• 2021

When a person tries to conceal emotions, real emotions will manifest themselves in the form of micro-expressions. Research on facial micro-expression recognition is still extremely challenging in the field of pattern recognition. This is because it is difficult to implement the best feature extraction method to cope with micro-expressions with small changes and short duration. Most methods are based on hand-crafted features to extract subtle facial movements. In this study, we introduce a method that incorporates optical flow and deep learning. First, we take out the onset frame and the apex frame from each video sequence. Then, the motion features between these two frames are extracted using the optical flow method. Finally, the features are inputted into an improved MobileNetV2 model, where SVM is applied to classify expressions. In order to evaluate the effectiveness of the method, we conduct experiments on the public spontaneous micro-expression database CASME II. Under the condition of applying the leave-one-subject-out cross-validation method, the recognition accuracy rate reaches 53.01%, and the F-score reaches 0.5231. The results show that the proposed method can significantly improve the micro-expression recognition performance.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.6
• /
• pp.557-565
• /
• 2016

It is very difficult to intercept the missiles because of the small radar cross-section and the high maneuverability. In addition, due to the decoy with the similar motion parameters, additional features other than those of the translation motion parameters need to be developed. In this paper, for the successful recognition of missiles, we propose an efficient method to extract micro-motion parameters and scatterers of the missile engaged in the micro motion. The proposed method extracts motion parameters and scatterers by using the matching score between the modeled micro-Doppler function and the time-frequency binary image as a cost function. Simulation results using a target composed of the point scatterer show the parameters and the scatterers were accurately extracted.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.6
• /
• pp.487-497
• /
• 2019

It is very difficult to detect ballistic missiles because of small cross-sections of the radar and the high maneuverability of the missiles. In addition, it is very difficult to recognize and intercept warheads because of the existence of debris and decoy with similar motion parameters in each flight phase. Therefore, feature vectors based on the maneuver, the micro-motion according to flight phase are needed, and the two types of features must be fused for the efficient recognition of ballistic warhead regardless of the flight phase. In this paper, we introduce feature vectors appropriate for each flight phase and an effective method to fuse them at the feature vector-level and classifier-level. According to the classification simulations using the radar signals predicted by the CAD models, the closer the warhead was to the final destination, the more improved was the classification performance. This was achieved by the classifier-level fusion, regardless of the flight phase in a noisy environment.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.125-138
• /
• 2023

The development of AI systems for radiation therapy is important to improve the accuracy, effectiveness, and safety of cancer treatment. The current system has the disadvantage of monitoring patients using CCTV, which can cause errors and mistakes in the treatment process, which can lead to misalignment of radiation. Developed the PMRP system, an AI automation system that uses depth cameras to measure patient's fine movements, segment patient's body into parts, align Z values of depth cameras with Z values, and transmit measured feedback to positioning devices in real time, monitoring errors and treatments. The need for such a system began because the CCTV visual monitoring system could not detect fine movements, Z-direction movements, and body part movements, hindering improvement of radiation therapy performance and increasing the risk of side effects in normal tissues. This study could provide the development of a field of radiotherapy that lags in many parts of the world, along with the economic and social importance of developing an independent platform for radiotherapy devices. This study verified its effectiveness and efficiency with data through phantom experiments, and future studies aim to help improve treatment performance by improving the posture correction mechanism and correcting left and right up and down movements in real time.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5440-5445
• /
• 2014

Many studies have examined robot control using human bio signals but complicated signal processing and expensive hardware are necessary. This study proposes a method to recognize a human's hand motion using a low-cost EMG sensor and Flex sensor. The method to classify movement of the hand and finger is determined from the change in output voltage measured through MCU. The analog reference voltage is determined to be 3.3V to increase the resolution of movement identification through experiment. The robotic hand is designed to realize the identified movement. The hand has four fingers and a wrist that are controlled using pneumatic cylinders and a DC servo motor, respectively. The results show that the proposed simple method can realize human hand motion in a remote environment using the fabricated robotic hand.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.237-242
• /
• 2013

There are some limitations to use the fitness center frequently by various reasons, excessive business workload, geographic location and time limit. This research specially focuses on the developement of health care application tool for aerobic/anaerobic exercise in a house accompanied by training coach, simply for the purpose of preventing from a boredom moment by exercing alone. This study newly proposes the realization of program tool by using Microsoft Kinect hardware tool which can be seen easily in the internet stores and can recognize the user. In addition, this program are designed to take care of movement control, weight and calory by maping the perceived user implementing modeling of 3D model.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.331-338
• /
• 2016

In this paper, we propose a system for transmitting army hand signals using motion sensors. The proposed system consists of a squad commander device, squad member devices, and a server. The squad command device and squad member device have been implemented using a micro arduino, an accelerometer sensor, and a gyroscope sensor, and the server has been implemented using a Rasberry Pi 3. Because the devices are made in the form of band, they are lightweight and portable. The proposed system can transmit the hand signals through vibration in conditions of poor visibility. We have designed and implemented the squad member device to be able to recognize four military hand signals. Through experiments, the proposed system have shown 88.82% of correct recognition. In conclusion, we expect to increase effectiveness of army operations and survival rate of soldiers.