• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1281-1297
• /
• 2016

In recent years, personal videos have seen a tremendous growth due to the substantial increase in the use of smart devices and networking services in which users create and share video content easily without many restrictions. However, taking both into account would significantly improve event detection performance because videos generally have multiple modalities and the frame data in video varies at different time points. This paper proposes an event detection method. In this method, high-level features are first extracted from multiple modalities in the videos, and the features are rearranged according to time sequence. Then the association of the modalities is learned by means of DNN to produce a personal video event detector. In our proposed method, audio and image data are first synchronized and then extracted. Then, the result is input into GoogLeNet as well as Multi-Layer Perceptron (MLP) to extract high-level features. The results are then re-arranged in time sequence, and every video is processed to extract one feature each for training by means of DNN.

• Geomechanics and Engineering
• /
• v.11 no.4
• /
• pp.571-585
• /
• 2016

The crest of the Pubugou central core rockfill dam (CCRD) cracked in the first and second impounding periods. To evaluate the safety of the Pubugou CCRD, an inversion analysis of the constitutive model parameters for rockfill materials is performed based on the in situ deformation monitoring data. The aim of this work is to truly reflect the deformation state of the Pubugou CCRD and determine the causes of the dam crest cracks. A novel real-coded genetic algorithm based upon the differences in gene fragments (DGFX) is proposed. It is used in combination with the radial based function neural network (RBFNN) to perform the parameters back analysis. The simulated settlements show good agreements with the monitoring data, illustrating that the back analysis is reasonable and accurate. Furthermore, the deformation gradient of the dam crest has been analysed. The dam crest has a great possibility of cracking due to the uncoordinated deformation, which agrees well with the field investigation. The deformation gradient decreases to the value lower than the critical one and reaches a stable state after the second full reservoir.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.4
• /
• pp.52-58
• /
• 2007

The irregular fuel surface was observed by the visualization of hybrid rocket combustion. Even though the test condition maintained oxidizer rich environment, the irregular dark fuel surface was formed as the result of incomplete combustion. In order to investigate the correlation of the characteristics of oxidizer flow and the irregular fuel surface, various flow conditions were imposed such as swirl flow, induced swirl flow by helical fuel configuration and straight flow. Test results revealed no correlation was found between oxidizer flow condition and irregular fuel surface. And this can be a commonly observed phenomena in the tests with different fuel/oxidizer combination. Thus, the irregular fuel surface can be a result of the interaction of blowing flow of vaporized fuel and the boundary layer of oxidizer flow. A further study will be required to confirm the assumption for the formation of irregular fuel surface.

• Smart Structures and Systems
• /
• v.3 no.3
• /
• pp.341-356
• /
• 2007

A good understanding of normal modal variability of civil structures due to varying environmental conditions such as temperature and wind is important for reliable performance of vibration-based damage detection methods. This paper addresses the quantification of wind-induced modal variability of a cable-stayed bridge making use of one-year monitoring data. In order to discriminate the wind-induced modal variability from the temperature-induced modal variability, the one-year monitoring data are divided into two sets: the first set includes the data obtained under weak wind conditions (hourly-average wind speed less than 2 m/s) during all four seasons, and the second set includes the data obtained under both weak and strong (typhoon) wind conditions during the summer only. The measured modal frequencies and temperatures of the bridge obtained from the first set of data are used to formulate temperature-frequency correlation models by means of artificial neural network technique. Before the second set of data is utilized to quantify the wind-induced modal variability, the effect of temperature on the measured modal frequencies is first eliminated by normalizing these modal frequencies to a reference temperature with the use of the temperature-frequency correlation models. Then the wind-induced modal variability is quantitatively evaluated by correlating the normalized modal frequencies for each mode with the wind speed measurement data. It is revealed that in contrast to the dependence of modal frequencies on temperature, there is no explicit correlation between the modal frequencies and wind intensity. For most of the measured modes, the modal frequencies exhibit a slightly increasing trend with the increase of wind speed in statistical sense. The relative variation of the modal frequencies arising from wind effect (with the maximum hourly-average wind speed up to 17.6 m/s) is estimated to range from 1.61% to 7.87% for the measured 8 modes of the bridge, being notably less than the modal variability caused by temperature effect.

• The Korean Journal of Physiology and Pharmacology
• /
• v.7 no.6
• /
• pp.317-323
• /
• 2003

Interneuron diversity is one of the key factors to hinder understanding the mechanism of cortical neural network functions even with their important roles. We characterized inhibitory interneurons in layer II/III of the rat primary visual cortex, using patch-clamp recording and confocal reconstruction, and classified inhibitory interneurons into fast spiking (FS), late spiking (LS), burst spiking (BS), and regular spiking non-pyramidal (RSNP) neurons according to their electrophysiological characteristics. Global parameters to identify inhibitory interneurons were resting membrane potential (＞-70 mV) and action potential (AP) width (＜0.9 msec at half amplitude). FS could be differentiated from LS, based on smaller amplitude of the AP (＜∼50 mV) and shorter peak-to-trough time (P-T time) of the afterhyperpolarization (＜4 msec). In addition to the shorter AP width, RSNP had the higher input resistance (＞200 $M{Omega}$) and the shorter P-T time (＜20 msec) than those of regular spiking pyramidal neurons. Confocal reconstruction of recorded cells revealed characteristic morphology of each subtype of inhibitory interneurons. Thus, our results provide at least four subtypes of inhibitory interneurons in layer II/III of the rat primary visual cortex and a classification scheme of inhibitory interneurons.

• Journal of the Korean Society of Systems Engineering
• /
• v.11 no.2
• /
• pp.61-73
• /
• 2015

The early-phase naval ship design demands requirements synthesis rather than design synthesis, which conducts engineering design for several domains on a detailed level. Requirements synthesis focuses on creating a balanced set of required operational capabilities satisfying user's needs and concept of operations. Requirements are evolved from capability based languages to function based language by statistical exploration and engineering design which are derived in the following order: concept alternative, concept baseline, initial baseline and functional baseline. The early-phase naval ship design process can be divided into three passes: concept definition, concept exploration and concept development. Main activities and outcomes in each pass are shortly presented. Concept definition is the first important step that produces a concept baseline through extensive design space exploration promptly. Design space exploration applies a statistical approach to explore design trends of existing ships and produce feasible design range corresponding to concept alternative. It further helps naval systems engineers and operational researchers by inducing useful responses to user and stakeholders' questions at a sufficient degree of confidence and success in the very early ship design. The focus of this paper is on the flow of design space exploration, and its application to a high-speed patrol craft. The views expressed in this paper are those of the authors, and do not reflect the official policy or rule of the Navy.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.86-96
• /
• 2020

Based on the use cases of image recognition technology, this study looked at how artificial intelligence plays a role in image recognition technology. Through image recognition technology, satellite images can be analyzed with artificial intelligence to reveal the calculation of oil storage tanks in certain countries. And image recognition technology makes it possible for searching images or products similar to images taken or downloaded by users, as well as arranging fruit yields, or detecting plant diseases. Based on deep learning and neural network algorithms, we can recognize people's age, gender, and mood, confirming that image recognition technology is being applied in various industries. In this study, we can look at the use cases of domestic and overseas image recognition technology, as well as see which methods are being applied to the industry. In addition, through this study, the direction of future research was presented, focusing on various successful cases in which image recognition technology was implemented and applied in various industries. At the conclusion, it can be considered that the direction in which domestic image recognition technology should move forward in the future.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1347-1359
• /
• 2005

We propose an efficient block classification of the document images using the second-order statistical texture features computed from spatial gray level dependence matrix (SGLDM). We studied on the techniques that will improve the block speed of the segmentation and feature extraction speed and the accuracy of the detailed classification. In order to speedup the block segmentation, we binarize the gray level image and then segmented by applying smoothing method instead of using texture features of gray level images. We extracted seven texture features from the SGLDM of the gray image blocks and we applied these normalized features to the BP (backpropagation) neural network, and classified the segmented blocks into the six detailed block categories of small font, medium font, large font, graphic, table, and photo blocks. Unlike the conventional texture classification of the gray level image in aerial terrain photos, we improve the classification speed by a single application of the texture discrimination mask, the size of which Is the same as that of each block already segmented in obtaining the SGLDM.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.837-848
• /
• 2018

Monitoring technology of machining has a long history since unmanned machining was introduced. Despite the long history, many researchers have presented new approaches continuously in this area. Sound based machine fault diagnosis is the process consisting of detecting automatically the damages that affect the machines by analyzing the sounds they produce during their operating time. The collected sound is corrupted by the surrounding work environment. Therefore, the most important part of the diagnosis is to find hidden elements inside the data that can represent the error pattern. This paper presents a feature extraction methodology that combines various digital signal processing and pattern recognition methods for the analysis of the sounds produced by tools. The magnitude spectrum of the sound is extracted using the Fourier analysis and the band-pass filter is applied to further characterize the data. Statistical functions are also used as input to the nonlinear classifier for the final response. The results prove that the proposed feature extraction method accurately captures the hidden patterns of the sound generated by the tool, unlike the conventional features. Therefore, it is shown that the proposed method can be applied to a sound based automatic diagnosis system.

• Journal of Distribution Science
• /
• v.17 no.11
• /
• pp.93-101
• /
• 2019

Purpose: Blockchain technology suggests ways to solve the problems in the existing industry. Among them, Cryptocurrency system, which is an element of Blockchain technology, is a very important factor for operating Blockchain. While Blockchain cryptocurrency has attracted attention, studies on cryptocurrency prices have been mainly conducted, however previous studies mainly conducted on Bitcoin prices. On the other hand, in the context of the creation and trading of various cryptocurrencies based on the Blockchain system, little research has been done on cryptocurrencies other than Bitcoin. Hence, this study attempts to find variables related to the prices of Dash, Litecoin, and Monero cryptocurrencies using machine learning techniques. We also attempt to find differences in the variables related to the prices for each cryptocurrencies and to examine machine learning techniques that can provide better performance. Research design, data, and methodology: This study performed Dash, Litecoin, and Monero price prediction analysis of cryptocurrency using Blockchain information and machine learning techniques. We employed number of transactions in Blockchain, amount of generated cryptocurrency, transaction fees, number of activity accounts in Blockchain, Block creation difficulty, block size, umber of created blocks as independent variables. This study tried to ensure the reliability of the analysis results through 10-fold cross validation. Blockchain information was hierarchically added for price prediction, and the analysis result was measured as RMSE and MAPE. Results: The analysis shows that the prices of Dash, Litecoin and Monero cryptocurrency are related to Blockchain information. Also, we found that different Blockchain information improves the analysis results for each cryptocurrency. In addition, this study found that the neural network machine learning technique provides better analysis results than support-vector machine in predicting cryptocurrency prices. Conclusion: This study concludes that the information of Blockchain should be considered for the prediction of the price of Dash, Litecoin, and Monero cryptocurrency. It also suggests that Blockchain information related to the price of cryptocurrency differs depending on the type of cryptocurrency. We suggest that future research on various types of cryptocurrencies is needed. The findings of this study can provide a theoretical basis for future cryptocurrency research in distribution management.