• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.382-382
• /
• 2020

과거 많은 연구에서 다수의 모형의 결과를 이용한 앙상블 방법론은 인공지능 모형 (artificial neural network)의 예측 능력에 향상을 갖고 온다 논하였다. 본 연구에서는 미계측유역의 저수량(low flow)의 예측을 위하여 Jittering을 기반으로 한 인공지능 모형을 제시하고자 한다. 기본적인 방법론은 설명변수들에게 백색 잡음(white noise)를 삽입하여 훈련되는 자료를 증가시키는 것이다. Jittering을 기반으로 한 인공지능 모형에 대한 효과를 검증하기 위하여 본 연구에서는 Multi-output neural network model을 기반으로 모형을 구축하였다. 다음으로 Jittering을 기반으로 한 앙상블 모형을 variable importance measuring algorithm과 결합시켜서 유역특성치와 예측되는 저수량의 특성치들의 관계를 추론하였다. 본 연구에서 사용되는 방법론들의 효용성을 평가하기 위해서 미동북부에 위치하고 있는 총 207개의 유역을 사용하였다. 결과적으로 본 연구에서 제시한 Jittering을 기반으로 한 인공지능 앙상블 모형은 단일예측모형 (single modeling approach)을 정확도 측면에서 우수한 것으로 확인되었다. 또한, 적은 숫자의 앙상블 모형에서도 그 정확성이 단일예측모형보다 우수한 것을 확인하였다. 마지막으로 본 연구에서는 유역특성치들의 효과가 살펴보고자 하는 저수량의 특성치들에 따라서 일관적으로 영향을 미치거나 그 중요도가 변화하는 것을 확인하였다.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.1
• /
• pp.1-8
• /
• 2017

For popularization of virtual reality hardwares, VR sickness come from latency is huge problem. To reduce latency, most of the HMDs use cable for video transmission. However, cable causes spatial limitation that disturb user experience. For maximize user's immersion, wireless video transmission system is necessary. Unfortunately, wireless video transmission's latency is much longer than cable's latency. Prediction algorithms may reduce latency but cause jittering effect as a side effect. This paper experiment how jittering effect affects VR sickness. The result of experiment shows jittering effect make vr sickness worse. Future research about prediction algorithm should consider both prediction error and jittering effect.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.977-991
• /
• 2008

This study is about the k-nearest neighbor-based approach for the estimation of mutual information when the type of target variable is categorical and continuous. The results of Monte-Carlo simulation and experiments with real-world data show that k=1 is preferable. In practical application with real world data, our study shows that jittering and bootstrapping is needed.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.128-136
• /
• 2006

The stippling techniques, which represent objects with numerous points using pen and ink. The previous stippling techniques for Non-Photorsealistc Rendering(NPR) use single-colored points to represent the tone of gray image ur the material of surface. This paper presents a new stippling technique with various colored points based on the analysis of color information. By using the color information of the input image on HSV model, we define the color weight function that allows to determine automatically the number and size of points. The color jittering based on Munsell's color model can generate stippling drawings using various colored points to represent the image. Our color stippling method is expected to be used in many areas such as animation, digital art, video processing and CG tool.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.852-861
• /
• 2013

When users use medical volume rendering applications, selecting specific region of volume data and observing the region by magnification is a common process.As the wood-grain artifact is arise from the magnified image, the jittered sampling technique has been used to remove the problem. However, the jittered sampling leads to some noise along the volume edge. In this research, we reveal the reason of the noise, and present a solution. To remove the wood-grain artifact without the noise, we propose the empty space jittering and the sampling alignment method. Using these methods, we can produce high quality volume rendering images without noticeable time consuming.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.476-484
• /
• 2018

The high capacity audio watermarking algorithms are facing a main challenge in satisfying the robustness against attacks especially on de-synchronization attacks. In this paper, a robust and a high capacity algorithm is proposed using segment selection, Stationary Wavelet Transform (SWT) and the Quantization Index Modulation (QIM) techniques along with new synchronization mechanism. The proposed algorithm provides enhanced trade-off between robustness, imperceptibility, and capacity. The achieved watermarking improves the reliability of the available watermarking methods and shows high robustness towards signal processing (manipulating) attacks especially the de-synchronization attacks such as cropping, jittering, and zero inserting attacks. For imperceptibility evaluation, high signal to noise ratio values of above 22 dB has been achieved. Also subjective test with volunteer listeners shows that the proposed method has high imperceptibility with Subjective Difference Grade (SDG) of 4.76. Meanwhile, high rational capacity up to 176.4 bps is also achieved.

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.249-252
• /
• 2001

This paper focuses on the consideration of not only QoS parameters in wired network, but also QoS parameters in wireless network that supported for the Efficient QoS in the Al1 Service Levels. So, We supposed the "Efficient QoS Model" that guaranteed the QoS parameters "Loss Profile" , "Service Degradation" , "Latency and Jittering" , "Mobility of Mobile User" , "Probability of seamless communication" in wired-wireless networks. And the Method of Efficient QoS support that we supposed consists of "Multicast Routing-RSVP Protocol architecture based on Mobile IP" and "Protocols internetworking model ".

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.29-37
• /
• 1999

Murakami and Cavanagh (1998a,b, 1999) reported a jitter aftereffect in a static random noise after a period of adaptation to a patch of dynamic random noise. To a account for this phenomenon. they proposed the retinal slip caused by a small eye movements in the unadapted area, which is usually compensated by the visual system to stabilize images but is unsuppressed due to the adaptation. We tested this hypothesis with new experimental method and stimuli that were supposed to nullify or reduce the effect. However. the aftereffect was still observed even under these stimuls conditions More importantly, the perceived aftereffect was rather different from Murakami and Cavanagh's. After adaptation to a counterphase flickering cosine grating, the adjacent unadapted region seems to move away from the observer during the test period instead of jittering in the frontoparallel plane. We proposed a possible explanation for this new phenomenon noting the severe contrast reduction of the adapted region during flickering period. The aftereffect might be due to the flicker-inducing contrast reduction during adaptation that produces different depth planes for the adapted and unadapted region and its restoration during the test period.

• Journal of Broadcast Engineering
• /
• v.24 no.7
• /
• pp.1259-1265
• /
• 2019

Maintaining timing relationships among packets in a single media stream or between packets from different media streams is an essential criterion in MMT system. It is the function of the synchronization and de-jittering algorithms to re-adjust timing relationship between the MMT packets to assure synchronized playback. Thus, delivery of time constrained MPEG media on time, according to their temporal requirements, is an important goal of MMT. For this purpose MMT needs to specify syntax and semantics of a timing model to be used by the delivery functions. In this paper, we propose a proper timestamp-related header format for MMT delivery timing model to support media synchronization in various delivery scenarios including hybrid delivery.