• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.37-46
• /
• 2021

In this paper, we designed and implemented a program to measure and to judge the accuracy of yoga postures using Azure Kinect. The program measures all joint positions of the user through Azure Kinect Camera and sensors. The measured values of joints are used as data to determine accuracy in two ways. The measured joint data are determined by trigonometry and Pythagoras theorem to determine the angle of the joint. In addition, the measured joint value is changed to relative position value. The calculated and obtained values are compared to the joint values and relative position values of the desired posture to determine the accuracy. Azure Kinect Camera organizes the screen so that users can check their posture and gives feedback on the user's posture accuracy to improve their posture.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.27-27
• /
• 2021

세굴은 유체와 유사의 상호작용으로 발생하는 중요한 자연 현상 중 하나로, 구조 및 지반 붕괴, 홍수, 생태계 파괴 등의 문제를 야기할 수 있다. 이러한 세굴 현상을 예측하기 위해 많은 수치적 연구가 진행되어왔지만, 대부분의 연구가 기존 격자기반방법인 유한체적법 (FVM)과 개별요소법 (DEM)이 연성된 모델을 이용하였고, 이는 격자 의존도로 인한 정확도와 효율성의 문제점을 보였다. 해결책으로 입자기반 유체해석 방법인 약압축성 SPH (WCSPH)와 개별요소법의 결합모델을 이용한 모의가 연구되어 왔지만, 단순 밀도차를 활용한 유체해석방법이 압력의 불안정성을 야기하여 유사의 운동에도 영향을 주는 결과를 보였다. 또한, 개별요소법의 특성상 모의 입자의 크기를 실제 실험 입자의 크기와 동일하게 설정하면서 입자수가 지나치게 증가해 계산의 효율성이 현저히 낮아지게 되었고, 이로 인해 실제 자연 지형에 적용하는데 어려움을 보여주었다. 본 연구에서는 향상된 세굴 수치모의해석을 위해 반복법을 통해 안정적인 유체 압력을 계산하는 비압축성 SPH (ISPH)와 개별요소법을 연성한 ISPH-DEM 모델을 사용하였다. 또한, 계산속도 향상을 위해 하나의 입자가 다수의 작은 입자의 움직임을 대표하는 Coarse-grained 방법을 적용하여 기존 모델을 개선하였다. 개선된 모델을 NFLOW ISPH PURPLE 소프트웨어를 이용하여 세굴 현상을 수치 모의하였고 실험 결과와 검증을 진행한 결과, 세굴의 깊이, 너비, 형상 등을 비교하였을 때 약 10% 이내의 오차를 보였고, Coarse-grained 방법을 통한 입자 수 감소로 최소 13배 증가된 해석 속도를 보였다. 이를 통해 본 연구에서 제시된 모델이 실제 자연 지형에서의 적용가능성을 확인할 수 있었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.51-55
• /
• 2021

In this paper, we propose the deep learning based interference cancellation scheme algorithm for visible light communication (VLC) systems in smart building. The proposed scheme estimates the channel noise information by applying a deep learning model. Then, the estimated channel noise is updated in database. In the modulator, the channel noise which reduces the VLC performance is effectively removed through interference cancellation technique. The performance is evaluated in terms of bit error rate (BER). From the simulation results, it is confirmed that the proposed scheme has better BER performance. Consequently, the proposed interference cancellation with deep learning improves the signal quality of VLC systems by effectively removing the channel noise. The results of the paper can be applied to VLC for smart building and general communication systems.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.32-40
• /
• 2019

Indoor location estimation studies are needed in various fields. The method of estimating the indoor position can be divided into a method using hardware and a method using no hardware. The use of hardware is more accurate, but has the disadvantage of hardware installation costs. Conversely, the non-hardware method is not costly, but it is less accurate. To estimate the location for AR game, you need to get the solution of the Perspective-N-Point (PnP). To obtain the PnP problem, we need three-dimensional coordinates of the space in which we want to estimate the position and images taken in that space. The position can be estimated through six pairs of two-dimensional coordinates matching the three-dimensional coordinates. To further increase the accuracy of the solution, we proposed the use of an additional non-coplanarity degree to determine which points would increase accuracy. As the non-coplanarity degree increases, the accuracy of the position estimation becomes higher. The advantage of the proposed method is that it can be applied to all existing location estimation methods and that it has higher accuracy than hardware estimation.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.13-21
• /
• 2009

This paper describes research of image enhancement for detection of face area. Typical face recognition algorithms used fixed parameter filtering algorithms to optimize face images for the recognition process. A fixed filtering scheme introduces errors when applied to face images captured in various different environmental conditions. For acquiring face image of good quality from the image including complex background and illumination, we propose a method for image enhancement using the categories based on the image intensity values. When an image is acquired average values of image from sub-window are computed and then compared to training values that were computed during preprocessing. The category is selected and the most suitable image filter method is applied to the image. We used histogram equalization, and gamma correction filters with two different parameters, and then used the most suitable filter among those three. An increase in enrollment of filtered images was observed compared to enrollment rates of the original images.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.329-337
• /
• 2017

This paper proposes a search method that explores parameters C and σ values of support vector machines (SVM) to improve performance while maintaining search accuracy. A traditional grid search method requires tremendous computational times because it searches all available combinations of C and σ values to find optimal combinations which provide the best performance of SVM. To address this issue, this paper proposes a deep search method that reduces computational time. In the first stage, it divides C-σ- accurate metrics into four regions, searches a median value of each region, and then selects a point of the highest accurate value as a start point. In the second stage, the selected start points are re-divided into four regions, and then the highest accurate point is assigned as a new search point. In the third stage, after eight points near the search point. are explored and the highest accurate value is assigned as a new search point, corresponding points are divided into four parts and it calculates an accurate value. In the last stage, it is continued until an accurate metric value is the highest compared to the neighborhood point values. If it is not satisfied, it is repeated from the second stage with the input level value. Experimental results using normal and defect bearings show that the proposed deep search algorithm outperforms the conventional algorithms in terms of performance and search time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.293-299
• /
• 2012

Electrical impedance tomography is an imaging modality for determining the electrical properties inside a domain. Small currents are injected and the resulting voltages are measured through the electrodes. The internal electrical properties are reconstructed based on these voltage and current data. In this paper, a novel on-line Landweber algorithm was developed to fast estimate the resistivity distribution in the inverse calculation. Additionally, to enhance the reconstruction performance, a step-length was computed from the eigenvalue of the weighting matrix. The numerical experiments have been performed to evaluate the reconstruction performance of the proposed method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.154-158
• /
• 2009

본 연구에서는 관측 기술의 향상과 지형자료들의 가용성 증가를 통해 유역 홍수 통합관리에서 많은 주목을 받고 있는 분포형 강우-유출 모형의 적용성 검토를 수행하였다. 본 연구에서 이용한 다방향 흐름분배 알고리듬은 고해상도 지형정보로부터 도출된 흐름정보를 상대적으로 저해상도 지형정보에 전달하여, 저해상도 지형정보의 이용을 통해 발생될 수 있는 흐름정보의 평활화 (smoothing)로 인한 흐름정보의 손실을 최소화하는 목적으로 개발되었다. 다방향 흐름분배 알고리듬 및 실시간 강우-유출 보정 알고리듬의 적용성 검토를 위해 평창강유역에 대하여 지점 강우량 자료를 이용하여 모의를 수행하였다. 모형 수행의 정확도 검토를 위해 다방향 흐름분배 알고리듬 및 실시간 강우-유출 보정 알고리듬을 적용한 경우와 그렇지 않은 경우를 비교해 본 결과 알고리듬을 적용한 경우가 적용하지 않은 경우보다, 유역 유출반응을 더 잘 묘사하고 있음을 알 수 있었다. 알고리듬을 적용하지 않은 경우도 수문곡선의 형태상 좀 더 향상된 관측의 묘사가 가능할 것으로 예상되었으나 합리적이지 못한 매개변수의 무리한 조정이 요구될 수도 있으며, 매개변수의 조정으로 인해 수문곡선의 패턴의 변화가 발생될 수 있을 것이다.

• Proceedings of the KIEE Conference
• /
• 2005.11a
• /
• pp.9-11
• /
• 2005

본 연구는 GIS 진단신뢰성 향상기술 개발을 목적으로, 16개의 인위적 결함을 이용하여 부분방전 신호를 발생시키고 검출하여 그 패턴인식 확률을 높이기 위하여 신경망에 Genetic Algorithm (GA) 을 적용하였다. 이를 위하여 다음과 같은 5가지 서로 다른 신경망 모델을 선택하였다: Back Propagation (BP), Jordan-Elman Network (JEN), Principal Component Analysis (PCA), Self-Organizing Feature Map (SOFM) 및 Support Vector Machine (SVM). 이와 같이 선택된 모델에 동일한 데이터를 학습 시키고 패턴인식 확률을 비교 및 분석하였다. 실험 결과에 의하면, BP의 인식률이 가장 높고 다음으로 JEN의 인식률이 높이 나타났으며, 후자의 경우 모든 결함에 대하여 정확한 패턴분류를 한 반면에 전자의 경우 1.8% 의 분류 오차가 발생하였다. 따라서 인식률이 높은 신경망이 더 정확한 패턴분류를 보장하지 못한다는 실험적 결과를 고려 할 때, 인식률이 높은 두 개의 모델을 선정하여 각각의 출력에 일정한 가중치를 주고 합산하여 새로운 출력을 얻는 방법을 제안한다.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.53-61
• /
• 2024

This paper presents a novel M-shaped encoder-decoder architecture for skin lesion segmentation, achieving better performance than existing approaches. The proposed architecture utilizes the left and right legs to enable multi-scale feature extraction and is further enhanced by integrating an attention module within the skip connection. The image is partitioned into four distinct patches, facilitating enhanced processing within the encoder-decoder framework. A pivotal aspect of the proposed method is to focus more on critical image features through an attention mechanism, leading to refined segmentation. Experimental results highlight the effectiveness of the proposed approach, demonstrating superior accuracy, precision, and Jaccard Index compared to existing methods