• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.26 no.1
• /
• pp.65-75
• /
• 1990

There have been many methods for measuring the injection rate of diesel engines, but the results of them are not always identical and the reason for the discordance is not clear. Besides, a single shot injection equipment has been used for the fuel spray and the combustion research of diesel engines, but the results of experiment using the equipment don't apply to a volleyed shot injection of real engines. This paper investigates the merits and faults of the Bosch's method and the Zeuch's method, at the same, this paper also compares the injection rates of single shot inject rates of single shot injection and a volleyed shot injected by the Bosch's method. the results are summarized as follows: (1) The measurement error of the Bosch's method is about $\pm$1%, therefore, its accuracy is reliable. (2) By the Bosch's method, as the speed and the load of fuel pump increase, the injection rate becomes higher, on the contrary, the injection period(ms) shortens as the speed increases and the load decreases. (3) In this experiment, the injection rate of a single shot injection is lower than that of a volleyed shot injection under the same conditions. (4) The bulk modulus of elasticity using the Zeuch's method increases in proportion to the back pressure. (5) The Zeuch's method is less accurate than the Bosch's method.

• Journal of Applied Reliability
• /
• v.11 no.4
• /
• pp.399-407
• /
• 2011

Reliability evaluation of One-Shot system which flies at speed of Mach must be evaluated as the result of many firing tests. But many firing tests are impossible because of budget deficit. Consequently the reliability prediction which substitutes firing tests is used. The accuracy of reliability prediction is decided according to a quantity of accumulated test data. If the test data is insufficient, the direction of prediction can not be set. So we propose the reliability prediction method which applies MIL-HDBK-217 Plus. MIL-HDBK-217 Plus is described about reliability prediction method without sufficient test data. So we apply MIL-HDBK-217 Plus to the rocket motor system, and we accomplish a modeling and a reliability prediction about the system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.332-333
• /
• 2021

In this paper, we propose a new image classification method based on several trainings, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small data sets and to improve classification accuracy.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.794-802
• /
• 2022

Objective: To evaluate the feasibility of single-shot whole thoracic time-resolved MR angiography (TR-MRA) to identify the feeding arteries of pulmonary arteriovenous malformations (PAVMs) and reperfusion of the lesion after embolization in patients with multiple PAVMs. Materials and Methods: Nine patients (8 females and 1 male; age range, 23-65 years) with a total of 62 PAVMs who underwent percutaneous embolization for multiple PAVMs and were subsequently followed up using TR-MRA and CT obtained within 6 months from each other were retrospectively reviewed. All imaging analyses were performed by two independent readers blinded to clinical information. The visibility of the feeding arteries on maximum intensity projection (MIP) reconstruction and multiplanar reconstruction (MPR) TR-MRA images was evaluated by comparing them to CT as a reference. The accuracy of TR-MRA for diagnosing reperfusion of the PAVM after embolization was assessed in a subgroup with angiographic confirmation. The reliability between the readers in interpreting the TR-MRA results was analyzed using kappa (κ) statistics. Results: Feeding arteries were visible on the original MIP images of TR-MRA in 82.3% (51/62) and 85.5% (53/62) of readers 1 and 2, respectively. Using the MPR, the rates increased to 93.5% (58/62) and 95.2% (59/62), respectively (κ = 0.760 and 0.792, respectively). Factors for invisibility were the course of feeding arteries in the anteroposterior plane, proximity to large enhancing vessels, adjacency to the chest wall, pulsation of the heart, and small feeding arteries. Thirty-seven PAVMs in five patients had angiographic confirmation of reperfusion status after embolization (32 occlusions and 5 reperfusions). TR-MRA showed 100% (5/5) sensitivity and 100% (32/32, including three cases in which the feeding arteries were not visible on TR-MRA) specificity for both readers. Conclusion: Single-shot whole thoracic TR-MRA with MPR showed good visibility of the feeding arteries of PAVMs and high accuracy in diagnosing reperfusion after embolization. Single-shot whole thoracic TR-MRA may be a feasible method for the follow-up of patients with multiple PAVMs.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.4
• /
• pp.340-346
• /
• 2014

There are many factors that contribute to hit probability of the gun shot of ground combat vehicles. Aiming accuracy is mainly affected by the dynamic state of the vehicle. The stabilization error of the turret under system vibration is one of the major factors that affect the aiming accuracy. The vibration of the vehicle is affected by both the state of the road and the speed of the vehicle. This paper analyzes the aiming accuracy of the gun equipped on the GCV when the vehicle drives on the different roads and at different speed. The vertical displacement and the pitch angle of the gun are calculated and the impact points of the target are calculated. Distribution of the impact points on the target is greatly influenced by the pitch rotation rather than vertical displacement. And this aiming errors result in the errors of point of impacts on the target after the bullet flies through the air under trajectory equations. The GCV is modeled using a half-car model with 6 D.O.F. and the specifications of the M2 machine gun are used in trajectory calculation simulation and the target is located in 1000 m away from the gun.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.2
• /
• pp.74-81
• /
• 2005

As the multimedia data increases, various scene change detection algorithms for video indexing and sequence matching have been proposed to efficiently manage and utilize digital media. In this paper, we propose a robust scene change detection algorithm for video sequences with abrupt luminance variations. To improve the accuracy and to reduce the computational complexity of video indexing with abrupt luminance variations, the proposed algorithm utilizes edge features as well as color features, which yields a remarkably better performance than conventional algorithms. In the proposed algorithm first we extract the candidate shot boundaries using color histograms and then determine using edge matching and luminance compensation if they are shot boundaries or luminance changes. If the scene contains trivial brightness variations, the edge matching and luminance compensation are performed only for shot boundaries. In experimental results, the proposed method gives remarkably a high performance and efficiency than the conventional methods with the similar computational complexity.

• Physical Therapy Rehabilitation Science
• /
• v.6 no.4
• /
• pp.189-195
• /
• 2017

Objective: The purpose of this study was to examine the effects of real-time visual feedback weight shift training during golf swinging on golf performance. Design: Repeated-measures crossover design. Methods: Twenty-sixth amateur golfers were enrolled and randomly divided into two groups: The golf swing training with real-time feedback on weight shift (experimental group) swing training on the Wii balance board (WBB) by viewing the center of pressure (COP) trajectory on the WBB. All participants were assigned to the experimental group and the control group. The general golf swing training group (control group) performed on the ground. The golf performance was measured using a high-speed 3-dimensional camera sensor which analyses the shot distance, ball velocity, vertical launch angle, horizontal launch angle, back spin velocity and side spin velocity. The COP trajectory was assessed during 10 practice sessions and the mean was used. The golf performance measurement was repeated three times and its mean value was used. The assessment and training were performed at 24-hour intervals. Results: After training sessions, the change in shot distance, ball velocity, and horizontal launch angle pre- and post-training were significantly different when using the driver and iron clubs in the experimental group (p<0.05). The interaction time${\times}$group and time${\times}$club were not significant for all variables. Conclusions: In this study, real-time feedback training using real-time feedback on weight shifting improves golf shot distance and accuracy, which will be effective in increasing golf performance. In addition, it can be used as an index for golf player ability.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.35-44
• /
• 2004

With increase in digitalmedia data, various video indexing and video sequence matching algorithms have been proposed to efficiently manage and utilize digital media. In this paper, we propose a robust video indexing algorithm to detect scene changes for video sequences with abrupt luminance variations and an efficient video sequence matching algorithm for video sequence query. To improve the accuracy and to reduce the computational complexity for video indexing with abrupt luminance variations, the proposed algorithm utilizes edge features as well as color features, which yields a remarkably better performance than conventional algorithms. In the proposed algorithm first we extract the candidate shot boundaries using color histograms and then determine using edge matching and luminance compensation if they are shot boundaries or luminance changes. If the scene contains trivial brighness variations, the edge matching and luminance compensation are performed only for shot boundaries. In experimental results, the proposed method gives remarkably a high performance and efficiency than the conventional methods with the similar computational complexity.