• 한국환경과학회지
• /
• 제19권1호
• /
• pp.47-59
• /
• 2010

This study was to examine the characteristics of wirdbirds habitat for improvement plan in green corridor. The target site, Gangseo-gu artificial green corridor was set up with the structure in which small scale of core green space with Goongsan and Yeomchang neighborhood parks in urbanized city was connected with the artificial green space with Gongamnaru, Hwanggeumnae neighborhood parks with 28~42.5 m in width. Wild birds six~eleven species; Dendrocopos spp, Paradoxornis webbiana, Parus major, Phasianus colchicus, etc. were observed in core green, but wild birds of two~five species: Columba livuia, Passer montanus, Pica pica, Hypsipetes amaurotis, etc. were observed in artificial green space. Thus wild birds of artificial and generalist species only moved in artificial green space. The artificial green space where vegetation structure was consisted of single-layer with poorness chose target species laying stress on generalist species and edge species of Parus major, P. palustris, Paradoxornis webbiana etc. for short-term and interior species of Dendrocopos major, Picus canus, etc. for long-term. The result suggested enhancement methods for target species's habitat in green corridor: to secure at least a corridor 30 meters in artificial corridor, to secure ecological pond, to offer the various shelterer and environment of prey-resources through the multi-layer structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권9호
• /
• pp.402-412
• /
• 2002

The navigation algorithms enable autonomous mobile robots to reach given target points without collision against obstacles. To achieve safe navigations in unknown environments, this paper presents an effective navigation algorithm for the autonomous mobile robots with ultrasonic sensors. The proposed navigation algorithm consists of an obstacle-avoidance behavior, a target-reaching behavior and a fuzzy-based decision maker. In the obstacle-avoidance behavior and the target-reaching behavior, artificial immune networks are used to select a proper steering angle, make the autonomous mobile robot avoid obstacles and approach a given target point. The fuzzy-based decision maker combines the steering angles from the target-reaching behavior and the obstacle-avoidance behavior in order to steer the autonomous mobile robot appropriately. Simulational and experimental results show that the proposed navigation algorithm is very effective in unknown environments.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.257-259
• /
• 2008

Acceleration time history (ATH) used in the seismic analysis should envelop a target power spectral density (PSD) function in addition to the design response spectrum in order to have sufficient energy at each frequency for the purpose of ensuring adequate load. Even though design regulations require the ATH used in seismic analysis to meet a target PSD function, the reason that ATHs meet to a target PSD function is not described. Thus, artificial ATHs for high PSD function and artificial ATHs for low PSD function are generated. And then elastic and inelastic single-degree-of-freedom (SDOF) systems are loaded with these artificial time histories as the earthquake load. As a result, linear response and inelastic response of SDOF systems are affected by PSD function.

• Structural Engineering and Mechanics
• /
• 제22권2호
• /
• pp.185-195
• /
• 2006

Nowadays it is very necessary to generate artificial accelerograms because of lack of adequate earthquake records and vast usage of time-history dynamic analysis to calculate responses of structures. According to the lack of natural records, the best choice is to use proper artificial earthquake records for the specified design zone. These records should be generated in a way that would contain seismic properties of a vast area and therefore could be applied as design records. The main objective of this paper is to present a new method based on wavelet theory to generate more artificial earthquake records, which are compatible with target spectrum. Wavelets are able to decompose time series to several levels that each level covers a specific range of frequencies. If an accelerogram is transformed by Fourier transform to frequency domain, then wavelets are considered as a transform in time-scale domain which frequency has been changed to scale in the recent domain. Since wavelet theory separates each signal, it is able to generate so many artificial records having the same target spectrum.

• 한국산학기술학회논문지
• /
• 제22권6호
• /
• pp.305-313
• /
• 2021

미래전의 양상은 네트워크 중심전으로 전체계의 연결을 통한 전장상황 정보획득 및 공유가 주를 이룰 것이다. 따라서 전장에서 생성되는 정보의 양은 많아지지만, 정보를 평가하여 전장을 효율적으로 지휘하는 기술은 부족한 것이 현실태이다. 이를 극복하기 위해 대두되는 기술이 전장 위협평가이다. 전장 위협평가는 획득된 정보를 사용하여 지휘관의 신속 결심을 지원하는 기술이지만 획득된 정보에는 표적의 불확실성이 많고 점차 지능화되는 전장상황에 적용하기에 현재 기술수준이 낮은 부분이 있다. 본 논문에서는 표적의 불확실성을 제거하고 고도화되는 전장상황에서도 적용 가능한 인공지능 기반의 전장 위협평가 기법에 대해 제안한다. 사용된 인공지능 시스템으로는 퍼지 추론 시스템과 다층 퍼셉트론을 사용하였다. 퍼지 추론 시스템에 표적의 고유특성을 입력시켜 표적을 분류해내었고 분류된 표적정보를 다른 표적 변수들과 함께 다층 퍼셉트론에 입력하여 해당 표적에 맞는 위협도 값을 산출하였다. 그 결과, 시뮬레이션을 통해 두 가지 시나리오상에서 무작위로 설정된 불확실 표적들을 인공신경망에 훈련시켰고, 훈련된 인공신경망에 시험용 표적을 입력하여 산출되는 위협도 값으로 제안한 기술의 타당성을 검증하였다.

• Structural Engineering and Mechanics
• /
• 제28권2호
• /
• pp.153-166
• /
• 2008

This paper suggests the use of wavelet multiresolution analysis (WMRA) and neural network for generation of artificial earthquake accelerograms from target spectrum. This procedure uses the learning capabilities of radial basis function (RBF) neural network to expand the knowledge of the inverse mapping from response spectrum to earthquake accelerogram. In the first step, WMRA is used to decompose earthquake accelerograms to several levels that each level covers a special range of frequencies, and then for every level a RBF neural network is trained to learn to relate the response spectrum to wavelet coefficients. Finally the generated accelerogram using inverse discrete wavelet transform is obtained. An example is presented to demonstrate the effectiveness of the method.

• 대한원격탐사학회지
• /
• 제27권5호
• /
• pp.587-599
• /
• 2011

NIIRS(National Imagery Interpretability Rating Scale)는 영상의 판독력을 설명하는 품질 지표로 고해상도 위성영상의 품질을 나타내는데 널리 사용되어 왔다. 이는 MTF(Modulation Transfer Function), SNR(Signal to Noise Ratio), 또는 GSD(Ground Sampling Distance)와는 달리 객관적이고, 직관적으로 영상의 전반적인 품질을 설명할 수 있다는 점에서, 그 활용도가 매우 크다고 할 수 있다. NIIRS는 전문 판독가에 의해 육안으로 직접 측정되거나, 영상의 에지 분석(Edge analysis)을 통해 정확하게 추정할 수 있다. 일반적으로 에지 분석에는 품질 측정을 위해 특별히 제작된 인공의 표적이 사용된다. 이 인공표적의 일례로 특정 크기의 반사율 차이를 가지는 흑백 패턴의 천막 형태가 있으며, 이러한 인공표적은 인공위성의 촬영경로 상에 설치되어 진다. 이 때문에 인공표적을 이용하는 방식은 표적의 설치와 관련하여 많은 비용이 지출될 뿐 아니라, 수시로 수행될 수 없다는 문제점을 가지게 된다. 이에 본 논문에서는 영상에서 쉽게 관측될 수 있는 자연표적들로부터 정확한 NIIRS 추정이 가능한 새로운 방식의 에지 분석법을 제안하였다. 이 방법은 임의의 성질을 가지는 자연표적의 특성을 반영하기 위해 알고리즘의 강인성이 강조되었으며, 다양한 실험들을 통해 성능이 평가되었다. 실험 결과는 제안 알고리즘이 기존 방식의 대안으로서 충분히 활용 가능함을 보여 주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.134.6-134
• /
• 2001

The purpose of navigation algorithm is to reach a given target point without collision with obstacles while an autonomous mobile robot is navigating. To achieve a safe navigation, this paper presents an effective navigation algorithm for the autonomous mobile robot equipped with ultrasonic sensors in unknown environments. The proposed navigation algorithm consists of an obstacle-avoidance behavior, a target-reaching behavior and a fuzzy-based decision maker. In the obstacle-avoidance behavior and the target-reaching behavior, artificial immune networks are used to select a proper steering angle, make the autonomous mobile robot avoid obstacles and approach a given target point. The decision maker using fuzzy inference systems weights the steering angles selected ...

• Structural Engineering and Mechanics
• /
• 제37권6호
• /
• pp.575-592
• /
• 2011

For seismic resistant design of critical structures, a dynamic analysis, either response spectrum or time history is frequently required. Owing to the lack of recorded data and the randomness of earthquake ground motion that may be experienced by structure in the future, usually it is difficult to obtain recorded data which fit the requirements (site type, epicenteral distance, etc.) well. Therefore, the artificial seismic records are widely used in seismic designs, verification of seismic capacity and seismic assessment of structures. The purpose of this paper is to develop a numerical method using Artificial Neural Network (ANN) and wavelet packet transform in best basis method which is presented for the decomposition of artificial earthquake records consistent with any arbitrarily specified target response spectra requirements. The ground motion has been modeled as a non-stationary process using wavelet packet. This study shows that the procedure using ANN-based models and wavelet packets in best-basis method are applicable to generate artificial earthquakes compatible with any response spectra. Several numerical examples are given to verify the developed model.