• Journal of the Korea institute for structural maintenance and inspection
• /
• v.10 no.2
• /
• pp.111-123
• /
• 2006

In the design of bridges, exact evaluation of traffic loading is very important for the safety and maintenance of bridges. In general, traffic loading is represented by live load (including impact load) and fatigue load. For exact evaluation of traffic loading, it is important to get reliable and comprehensive truck data including the traffic and weight information. It requires the development of Bridge Weigh-In-Motion (BWIM), which measures the truck weights without stopping the traffic. Objectives of the study is (1) to develop the BWIM system, (2) to verified the system in bridges in Highways.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.51-56
• /
• 2011

This paper proposes an efficient moving picture compression for video sequences with luminance variations. In the proposed algorithm, the luminance variation parameters are estimated and local motions are compensated. To detect the frame required luminance compensation, we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than that of the conventional methods, with a low computational load, when the video scene contains large luminance variations.

• Journal of the Korean Society of Safety
• /
• v.15 no.4
• /
• pp.139-149
• /
• 2000

This study aims to review and assess the existing postural classification schemes used for evaluating postural loads in industry. The schemes can be classified into three categories: self-report, observational and instrument-based techniques depending upon how to record working postures. Of the three techniques, this study was mainly focused on the observational methods. The observational technique is most widely used in the industrial sites because it does not interfere with work, and is easy and simple to use and cost-effective without requiring the use of expensive equipment for estimating the angular deviation of a body segment from the neutral position. In spite of the usefulness and applicability, the techniques have some problems: 1) The existing observational techniques lack the consistency in the class limits of the motion categories in each body segment; 2) Most of them do not provide the post-analysis criteria needed to judge whether or not any posture is acceptable in view point of the postural load; and 3) They can not precisely evaluate the postural load for a given posture because the external loads and dynamic factors including acceleration, moment and force were not taken into consideration.

• Atmosphere
• /
• v.16 no.3
• /
• pp.235-246
• /
• 2006

Remote sensing techniques using satellites or the scanning weather radars depend mostly on the presence of clouds or precipitation, and leave the extensive regions of clear air unobserved. But wind profilers provide the most direct measurements of mesoscale vertical air motion in the troposphere, even in the context of heavy precipitation. In this paper, the precipitation events during the Changma period was classified into 4 precipitation types - stratiform, mixed stratiform/ convective, deep convective, and shallow convective. The parameters for the classification of analysis are the vertical structure of reflectivity, Doppler velocity, and spectral width measured with the wind profiler at Haenam for a three-year period (2003-2005). In addition, the synoptic fields and total amount of precipitation were analyzed using the Global Final Analyses (FNL) data and the Global Precipitation Climatology Project (GPCP) data. During the Changma period, the results show that the stratiform type was dominant under the moist-neutral atmosphere in 2003, whereas the deep convective type was under the moist unstable condition in 2004. The stratiform type was no less popular than the deep convective type among four seasons because the moist neutral layer was formed by the convergence between the upper-level jet and the low-level jet, and by the moisture transport along the western rim of the North Pacific subtropical anticyclone.

• Current Optics and Photonics
• /
• v.1 no.4
• /
• pp.402-411
• /
• 2017

Combined LIBS-Raman spectroscopy has been widely studied, due to its complementary capabilities as an elemental analyzer that can acquire signals of atoms, ions, and molecules. In this study, the classification of polymorphs was performed by laser-induced breakdown spectroscopy (LIBS) to overcome the limitation in molecular analysis; the results were verified by Raman spectroscopy. LIBS signals of the $CaCO_3$ polymorphs calcite and aragonite, and $CaSO_4{\cdot}2H_2O$ (gypsum) and $CaSO_4$ (anhydrite), were acquired using a Nd:YAG laser (532 nm, 6 ns). While the molecular study was performed using Raman spectroscopy, LIBS could also provide sufficient key data for classifying samples containing different molecular densities and structures, using the peculiar signal ratio of $5s{\rightarrow}4p$ for the orbital transition of two polymorphs that contain Ca. The basic principle was analyzed by electronic motion in plasma and electronic transition in atoms or ions. The key factors for the classification of polymorphs were the different electron quantities in the unit-cell volume of each sample, and the selection rule in electric-dipole transitions. The present work has extended the capabilities of LIBS in molecular analysis, as well as in atomic and ionic analysis.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.299-307
• /
• 2022

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classification of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into training, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.250-257
• /
• 2011

In this paper, we proposed the method detecting multiple pedestrians using motion information and SVM(Support Vector Machine) from a moving camera image. First, we detect moving pedestrians from both the difference image and the projection histogram which is compensated for the camera ego-motion using corresponding feature sets. The difference image is simple method but it is not detected motionless pedestrians. Thus, to fix up this problem, we detect motionless pedestrians using SVM The SVM works well particularly in binary classification problem such as pedestrian detection. However, it is not detected in case that the pedestrians are adjacent or they move arms and legs excessively in the image. Therefore, in this paper, we proposed the method detecting motionless and adjacent pedestrians as well as people who take excessive action in the image using motion information and SVM The experimental results on our various test video sequences demonstrated the high efficiency of our approach as it had shown an average detection ratio of 94% and False Positive of 2.8%.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.380-392
• /
• 2013

A method to classify a golf swing motion into 7 sections using a Kinect sensor and a fuzzy system is proposed. The inputs to the fuzzy logic are the positions of golf club and its head, which are extracted from the information of golfer's joint position and color information obtained by a Kinect sensor. The proposed method consists of three modules: one for extracting the joint's information, another for detecting and tracking of a golf club, and the other for classifying golf swing motions. The first module extracts the hand's position among the joint information provided by a Kinect sensor. The second module detects the golf club as well as its head with the Hough line transform based on the hand's coordinate. Using a fuzzy logic as a classification engine reduces recognition errors and, consequently, improves the performance of robust classification. From the experiments of real-time video clips, the proposed method shows the reliability of classification by 85.2%.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.365-374
• /
• 2011

Recently, malicious video classification and filtering techniques are of practical interest as ones can easily access to malicious multimedia contents through the Internet, IPTV, online social network, and etc. Considerable research efforts have been made to developing malicious video classification and filtering systems. However, the malicious video classification and filtering is not still being from mature in terms of reliable classification/filtering performance. In particular, the most of conventional approaches have been limited to using only the spatial features (such as a ratio of skin regions and bag of visual words) for the purpose of malicious image classification. Hence, previous approaches have been restricted to achieving acceptable classification and filtering performance. In order to overcome the aforementioned limitation, we propose new malicious video classification framework that takes advantage of using both the spatial and temporal features that are readily extracted from a sequence of video frames. In particular, we develop the effective temporal features based on the motion periodicity feature and temporal correlation. In addition, to exploit the best data fusion approach aiming to combine the spatial and temporal features, the representative data fusion approaches are applied to the proposed framework. To demonstrate the effectiveness of our method, we collect 200 sexual intercourse videos and 200 non-sexual intercourse videos. Experimental results show that the proposed method increases 3.75% (from 92.25% to 96%) for classification of sexual intercourse video in terms of accuracy. Further, based on our experimental results, feature-level fusion approach (for fusing spatial and temporal features) is found to achieve the best classification accuracy.

• Proceedings of the KAIS Fall Conference
• /
• 2002.05a
• /
• pp.109-111
• /
• 2002

모든 문화는 그 나름대로의 규칙과 분류와 표준이 존재한다. 게임문화에도 역시 그 발전속도와 규모에 부합되는, 정확한 분류와 표준안이 필요하다. 현재 여러 기관에서 게임 관련자들이 수긍할 수 있는 분류 안을 제시하고 있다. 그러나 기관별, 업체별, 그리고 게임 매체별로 게임 장르 분류에 대한 견해가 조금씩 차이를 보인다. 이에 본 논문에서는 대표적인 게임 장르를 살펴보고, 게임 장르 분류 방안을 제시하고자 한다.