• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.768-783
• /
• 2020

Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship's drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.229-237
• /
• 2022

Motion recognition is very useful for implementing an intuitive HMI (Human-Machine Interface). In particular, hands are the body parts that can move most precisely with relatively small portion of energy. Thus hand motion has been used as an efficient communication interface with other persons or machines. In this paper, we design and implement a light-weight ANN (Artificial Neural Network)-based hand motion recognition using a state-of-the-art flex sensor. The proposed design consists of data collection from a wearable flex sensor, preprocessing filters, and a light-weight NN (Neural Network) classifier. For verifying the performance and functionality of the proposed design, we implement it on a low-end embedded device. Finally, our experiments and prototype implementation demonstrate that the accuracy of the proposed hand motion recognition achieves up to 98.7%.

• Journal of Biomedical Engineering Research
• /
• v.29 no.4
• /
• pp.295-301
• /
• 2008

A wireless 3 channel ECG monitoring system was developed so that it could monitor the health and movement state during subject's daily life. The developed system consists of a wireless biomedical signal acquisition device, a personal healthcare server, and a remote medical server. Three experiments were performed to evaluate the accuracy, reliability and operability, applicability during daily life of the developed device. First, ECG signals were measured using the developed device and commercial reference device during sitting and marking time and compared to verify the accuracy of R-R intervals. Second, the reliable data transmission to remote server was verified on two types of simulated emergency event using patient simulator. Third, during five types of motion in daily life, the accuracy of data transmission to remote server using CDMA network was verified on two types of event occurring. By acquiring and comparing subject's biomedical signal and motion signal, the accuracy, reliability and operability, applicability during daily life of the developed device were verified. In addition, PDA-phone based wireless system enabled subject to be monitored without any constraints. Therefore, the developed system is expected to be applicable for monitoring the aged and chronic diseased people and giving first-aid in emergency.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.982-990
• /
• 2018

In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.1
• /
• pp.63-68
• /
• 2018

At present, ultra-precision cutting technology has been studied in Korean research institutes, focusing on development of ultra-precision cutting tool technology and ultra-precision control engineering. However, the developed technologies are still far behind advanced countries. It focuses on metals including aluminum, copper and nickel, and nonmetals including plastics, silicone and germanium which require high precision while using a lathe. It is hard to implement high precision by grinding the aforementioned materials. To address the issue, the ultra-precision cutting technology has been developing by using ultra-precision machine tools very accurate and strong, and diamond tools highly abrasion-resistant. To address this issue, this study aims to conduct ultra-precision cutting by using ECTS (Error Compensation Tool Servo) to improve motion precision of elements and components, and compensate for motion errors in real time. An IR camera is used for analyzing cutting accuracy differences depending on the heat generated in diamond tools in cutting to examine the heat generated in cutting to study cutting accuracy depending on generated heat.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Earthquakes and Structures
• /
• v.26 no.2
• /
• pp.117-130
• /
• 2024

Probabilistic model of seismic demand is the main tool used for seismic demand estimation, which is a fundamental component of the new performance-based design method. This model seeks to mathematically relate the seismic demand parameter and the ground motion intensity measure. This study is intended to use Bayesian analysis to evaluate the accuracy of the seismic demand estimation of Steel moment resisting frames (SMRFs) through a completely Bayesian method in statistical calculations. In this study, two types of intensity measures (earthquake intensity-related indices such as magnitude and distance and intensity indices related to ground motion and spectral response including peak ground acceleration (PGA) and spectral acceleration (SA)) have been used to form the models. In addition, an extensive database consisting of sixty accelerograms was used for time-series analysis, and the target structures included five SMRFs of three, six, nine, twelve and fifteen stories. The results of this study showed that for low-rise frames, first mode spectral acceleration index is sufficient to accurately estimate demand. However, for high-rise frames, two parameters should be used to increase the accuracy. In addition, adding the product of the square of earthquake magnitude multiplied by distance to the model can significantly increase the accuracy of seismic demand estimation.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.38
• /
• pp.13.1-13.12
• /
• 2016

Background: Mandibular motion tracking system (ManMoS) has been developed for orthognathic surgery. This article aimed to introduce the ManMoS and to examine the accuracy of this system. Methods: Skeletal and dental models are reconstructed in a virtual space from the DICOM data of three-dimensional computed tomography (3D-CT) recording and the STL data of 3D scanning, respectively. The ManMoS uniquely integrates the virtual dento-skeletal model with the real motion of the dental cast mounted on the simulator, using the reference splint. Positional change of the dental cast is tracked by using the 3D motion tracking equipment and reflects on the jaw position of the virtual model in real time, generating the mixed-reality surgical simulation. ManMoS was applied for two clinical cases having a facial asymmetry. In order to assess the accuracy of the ManMoS, the positional change of the lower dental arch was compared between the virtual and real models. Results: With the measurement data of the real lower dental cast as a reference, measurement error for the whole simulation system was less than 0.32 mm. In ManMoS, the skeletal and dental asymmetries were adequately diagnosed in three dimensions. Jaw repositioning was simulated with priority given to the skeletal correction rather than the occlusal correction. In two cases, facial asymmetry was successfully improved while a normal occlusal relationship was reconstructed. Positional change measured in the virtual model did not differ significantly from that in the real model. Conclusions: It was suggested that the accuracy of the ManMoS was good enough for a clinical use. This surgical simulation system appears to meet clinical demands well and is an important facilitator of communication between orthodontists and surgeons.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.67-80
• /
• 2020

High-speed weigh in motion (HS-WIM) is a real-time unmanned system for measuring the weight of a freight-carrying vehicle while it is in motion without controlling vehicle traffic flow or deceleration. In Korea, HS-WIM systems are installed on the national highways and general national ways for pre-selection by law enforcement. In this study, to improve the measurement accuracy of HS-WIM, we devise improvements to the existing integral and peak weight conversion algorithms, and we provide a new fusion algorithm that can be applied to the mat-type HS-WIM. As a result of analyzing vehicle driving tests at a real site, we confirmed the highest level of weight-measuring accuracy.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.6
• /
• pp.925-932
• /
• 2010

Most of the research on three-dimensional interaction field have showed different accuracy in terms of sensing, mode and method. Furthermore, implementation of interaction has been a lack of consistency in application field. Therefore, this study is to suggest research trends of three-dimensional interaction using meta-analysis. Searching relative keyword in database provided with 153 domestic papers and 188 international papers covering three-dimensional interaction. Analytical coding tables determined 18 domestic papers and 28 international papers for analysis. Frequency analysis was carried out on method of action, element, number, accuracy and then verified accuracy by effect size of the meta-analysis. As the results, the effect size of sensor-based was higher than vision-based, but the effect size was extracted to small as 0.02. The effect size of vision-based using hand motion was higher than sensor-based using hand motion. Therefore, implementation of three-dimensional sensor-based interaction and vision-based using hand motions more efficient. This study was significant to comprehensive analysis of three-dimensional motion recognition for interaction and suggest to application directions of three-dimensional interaction.