• Wind and Structures
• /
• v.21 no.1
• /
• pp.25-40
• /
• 2015

Oscillating motions of flexible cylinders are associated to some extent with the aerodynamic response of plants. Tandem motions of reeds with flexible stems in a colony are experimentally investigated using an array of flexible cylinders made of polydimethylsiloxane (PDMS). Consecutive images of flexible cylinders subjected to oncoming wind are recorded with a high-speed camera. To quantify oscillating motions, the average bending angle and displacement of flexible cylinders are evaluated using point-tracking method and spectral analysis. The tandem motions of flexible cylinders are closely related to the flow characteristics around the cylinders. Thus, the dynamic motions of a tandem arrangement of flexible cylinders are investigated with varying numbers of cylinders arranged in-line, numbers of cylinders in a group (behaving like a single body), and Reynolds numbers (Re). When the number of cylinders in a group increases, the damping effect caused by the support of downstream cylinders is pronounced. These results would be provide useful information on the tandem-arranged design of complex structures and energy harvesting devices.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2748-2760
• /
• 2018

This paper proposes an audio event classification method based on convolutional neural networks (CNNs). CNN has great advantages of distinguishing complex shapes of image. Proposed system uses the features of audio sound as an input image of CNN. Mel scale filter bank features are extracted from each frame, then the features are concatenated over 40 consecutive frames and as a result, the concatenated frames are regarded as an input image. The output layer of CNN generates probabilities of audio event (e.g. dogs bark, siren, forest). The event probabilities for all images in an audio segment are accumulated, then the audio event having the highest accumulated probability is determined to be the classification result. This proposed method classified thirty audio events with the accuracy of 81.5% for the UrbanSound8K, BBC Sound FX, DCASE2016, and FREESOUND dataset.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.361-371
• /
• 1999

This paper is concerned with designing and implementing the Internet shopping mall by using virtual reality-driven avatar and web decision support system. Traditionally, the Internet shopping mall has been designed based on the combination of several hyperlinks, images, and tents. However, this sort of approach results in a lower performance because possible customers cannot make more accurate shopping decisions. To overcome this kind of pitfalls facing the current Internet shopping malls, we propose using a combination of virtual reality and web DSS. The main virtues of our proposed approach to designing the Internet shopping mall are as follows: First, the virtual reality technique is emerging as one of alternatives guaranteeing a sense of reality for customers' part and facilitating the complex process of shopping decision makings. Especially, the avatar, which is an artificially designed man working on the Internet, can make easy and absorbing the Internet shopping-related decision making processes. Second, the web DSS approach can provide an effective decision support mechanism for customers. Especially, we design a set of intelligent agents for the proposed web DSS. Experimental results with an illustrative example showed that our proposed approach can yield a new Internet shopping mall paradigm with which customers can benefit from a high level of decision support functions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.461-468
• /
• 2003

In a sequence of images obtained by surveillance cameras, facial regions appear very small and their colors change abruptly by lighting condition. This paper proposes a new face detection scheme, robust on complex background, small size, and lighting conditions. The proposed method is consisted of three processes. In the first step, the candidates for the face regions are selected using face color distribution and motion information. In the second stage, the non-face regions are removed using face color ratio, boundary ratio, and average of column-wise intensity variation in the candidates. The face regions containing eyes and mouth are segmented and classified, and then they are scored using their topological relations in the last step. To speed up and improve a performance the above process, a block based image segmentation technique is used. The experiments have shown that the proposed algorithm detects faced regions with more than 91% of accuracy and less than 4.3% of false alarm rate.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.8
• /
• pp.1145-1152
• /
• 2002

A non-intrusive Planar Laser-Induced Fluorescence(PLIF) technique was applied to study the turbulent mixing process in a Rushton turbine reactor. Instantaneous and ensemble averaged concentration fields was obtained by measuring the fluorescence intensity of Rhodamine B tracer excited by a thin Nd:Yag laser sheet illuminating the whole center plane of the stirred tank. The gray level images captured by a 14-bit cooled CCD camera could be transformed to the local concentration values using a calibration matrix. The dye injection point was selected at the tank wall with three quarter. height (3/4H) from the tank bottom to observe the mixing characteristics in upper bulk flow region. There exist distinct two time scales: the rapid decay of mean concentration after the dye infusion reflects the large scale turbulent mixing while the fellowed slow decay reveals the small scale molecular mixing. The temporal change of concentration variance field conjectures the two sequential processes for the batch type mixing. An inactive column of water is existed above the impeller disk, in which the fluid rotates with the shaft but is isolated from the mean bulk flow.

• Journal of Korean Neurosurgical Society
• /
• v.48 no.2
• /
• pp.173-176
• /
• 2010

In this report, we introduce an undetermined fibrous tumor with calcification occurring in the cerebellopontine angle (CPA). A 51-year-old woman was admitted with a short history of dizziness. Computed tomography and magnetic resonance images revealed a $2{\times}2{\times}2\;cm$ sized mass at the left CPA which was round and calcified. There was no dura or internal auditory canal involvement. At surgery, the tumor was located at the exit of 7th and 8th cranial nerve complex. It was very firm, bright yellow and well encapsulated. Histologic findings revealed that the tumor was predominantly composed of fibrous component, scant spindle cells and dystrophic calcification. Immunohistochemical staining demonstrated positive for vimentin and negative for epithelial membrane antigen (EMA), S-100 protein, CD34, factor XIIIa and smooth muscle actin. The diagnosis was not compatible with meningioma, schwannoma, metastatic brain tumors, and other fibrous tumors. Although the tumor was resected in total, long term follow-up monitoring is necessary due to the possibility of recurrence.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.27-33
• /
• 2009

We propose an efficient method for single image motion deblurring using edge prediction. Previous methods for motion deblurring from a single image have been based on total variation or natural image statistics. In contrast, our method predicts sharp edges by applying bilateral and shock filters and manipulating image gradients directly, and estimates motion blur using the predicted sharp edges. Sharp edge prediction makes our method possible to deblur efficiently with less computation. Results show that our method can effectively and efficiently restore images degraded by large complex motion blur.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.337-342
• /
• 2002

This paper proposes a new adaptive image labeling algorithm fur object analysis of the binary images. The proposed labeling algorithm need not merge/order of complex equivalent labels like classical labeling algorithm and the processing is done during only 1 Pass. In addition, this algorithm can be extended for gray-level image easily. Experiment result with HIPR image library shows that the proposed algorithm process more than 2 times laster than compared algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.6
• /
• pp.1170-1177
• /
• 1997

Morphology is a shape preseving filter. Several morphology filter can be made by the combination of morphological basic operation. If we use morphology filter in decimation process for a hierarchical encoder, there are some advantagesin reduction aliasing effects. In this paper, we propose a new hierarchical coder with morphological filtering and vector quantization. And then, firstly, we confirm that CO filtering is the best one among the 4 kinds of morphology filters to reduce aliasing effects in Laplacian pyramid transmission proposed by Burt. Secondly, the those two coders was compared. The results of our simulation show that our new coder surpasser the Laplacian pyramid especially in complex images.