• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2015년도 추계학술대회
• /
• pp.53-54
• /
• 2015

The maritime industry is expanding at an alarming rate and as such there is a perpetual need to improve situation awareness in the maritime environment using new and emerging technology. Tracking is one of the numerous ways of enhancing situation awareness by providing information that may be useful to the operator. The tracking system described herein comprises determining existing states of own ship, state prediction and state compensation caused by random noise. The purpose of this paper is to analyze the process of tracking and develop a tracking algorithm by using ${\alpha}-{\beta}-{\gamma}$ tracking filter under a random noise or irregular motion for use in a warship. The algorithm involves initializing the input parameters of position, velocity and course. The actual positions are then computed for each time interval. In addition, a weighted difference of the observed and predicted position at the nth observation is added to the predicted position to obtain the smoothed position. This estimation is subsequently employed to determine the predicted position at (n+1). The smoothed values, predicted values and the observed values are used to compute the twice distance root mean square (2drms) error as a measure of accuracy of the tracking module.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3165-3181
• /
• 2019

Spherical videos, which are also called 360-degree videos, have become increasingly popular due to the rapid development of virtual reality technology. However, the large amount of data in such videos is a huge challenge for existing transmission system. To use the existing encode framework, it should be converted into a 2D image plane by using a specific projection format, e.g. the equi-rectangular projection (ERP) format. The existing high-efficiency video coding standard (HEVC) can effectively compress video content, but its enormous computational complexity makes the time spent on compressing high-frame-rate and high-resolution 360-degree videos disproportionate to the benefits of compression. Focusing on the ERP format characteristics of 360-degree videos, this work develops a fast decision algorithm for predicting the coding unit depth interval and adaptive mode decision for intra prediction mode. The algorithm makes full use of the video characteristics of the ERP format by dealing with pole and equatorial areas separately. It sets different reference blocks and determination conditions according to the degree of stretching, which can reduce the coding time while ensuring the quality. Compared with the original reference software HM-16.16, the proposed algorithm can reduce time consumption by 39.3% in the all-intra configuration, and the BD-rate increases by only 0.84%.

• 한국압력기기공학회 논문집
• /
• 제19권2호
• /
• pp.93-101
• /
• 2023

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

• 대한교통학회지
• /
• 제18권1호
• /
• pp.47-59
• /
• 2000

본 연구에서는 고속도로 교통관리시스템에서 VDS 교통정보 와 대상지역의 TCS로부터 여행시간을 수집하고, 이들 자료를 토대로 신경망 이론을 이용한 여행시간 추정(Estimation)모형을 구축하였다. 또한, 신경망 이론에 칼만필터기법(Kalman Filter Technique)을 연계하여 단위시간 동안의 여행시간을 예측(Prediction)하여, 고속도로 이용자에게 보다 향상된 실시간 여행시간정보를 제공할 수 있는 여행시간 추정 및 예측 알고리즘을 개발하였다. 신경망 모형의 여행시간 추정 방식과 현재 적용되고 있는 여행시간 산출 방식의 비교/분석을 위해 각 각의 여행시간 산출방식에 의한 평가지표별로 시행한 평가의 결과는 신경망 모형이 제시한 대부분의 지표에서 상대적으로 우수하게 나타났다.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Agricultural and Biosystems Engineering
• /
• 제7권1호
• /
• pp.1-7
• /
• 2006

A need exists to monitor and control the localized high temperatures often experienced in solar grain dryers, which result in grain cracking, reduced germination and loss of cooking quality. A verified finite element model would be a useful to monitor and control the drying process. This study examined the feasibility of the finite element method (FEM) to predict temperature distribution in solar grain dryers. To achieve this, an indirect solar grain dryer system was developed. It consisted of a solar collector, plenum and drying chambers, and an electric fan. The system was used to acquire the necessary input and output data for the finite element model. The input data comprised ambient and plenum chamber temperatures, prevailing wind velocities, thermal conductivities of air, grain and dryer wall, and node locations in the xy-plane. The outputs were temperature at the different nodes, and these were compared with measured values. The ${\pm}5%$ residual error interval employed in the analysis yielded an overall prediction performance level of 83.3% for temperature distribution in the dryer. Satisfactory prediction levels were also attained for the lateral (61.5-96.2%) and vertical (73.1-92.3%) directions of grain drying. These results demonstrate that it is feasible to use a two-dimensional (2-D) finite element model to predict temperature distribution in a grain solar dryer. Consequently, the method offers considerable advantage over experimental approaches as it reduces time requirements and the need for expensive measuring equipment, and it also yields relatively accurate results.

• 한국항해항만학회지
• /
• 제40권2호
• /
• pp.83-87
• /
• 2016

The maritime industry is expanding at an alarming rate hence there is a perpetual need to improve situation awareness in the maritime environment using new and emerging technology. Tracking is one of the numerous ways of enhancing situation awareness by providing information that may be useful to the operator. The tracking module designed herein comprises determining existing states of high dynamic target warship, state prediction and state compensation due to random noise. This is achieved by first analyzing the process of tracking followed by design of a tracking algorithm that uses ${\alpha}-{\beta}-{\gamma}$ tracking filter under a random noise. The algorithm involves initializing the state parameters which include position, velocity, acceleration and the course. This is then followed by state prediction at each time interval. A weighted difference of the observed and predicted state values at the $n^{th}$ observation is added to the predicted state to obtain the smoothed (filtered) state. This estimation is subsequently employed to determine the predicted state in the next radar scan. The filtering coefficients ${\alpha}$, ${\beta}$ and ${\gamma}$ are determined from a pre-determined value of the damping parameter, ${\xi}$. The smoothed, predicted and the observed positions are used to compute the twice distance root mean square (2drms) error as a measure of the ability of the tracking module to manage the noise to acceptable levels.

• Computers and Concrete
• /
• 제2권4호
• /
• pp.325-343
• /
• 2005

Chloride ingress is a common cause of deterioration of reinforced concrete located in coastal zone. Modeling the chloride ingress is an important basis for designing reinforced concrete structures and for assessing the reliability of an existing structure. The modeling is also needed for predicting the deterioration of a reinforced structure. The existing deterministic solution for prediction model of corrosion initiation cannot reflect uncertainties which input variables have. This paper presents an approach to the fuzzy arithmetic based modeling of the chloride-induced corrosion of reinforcement in concrete structures that takes into account the uncertainties in the physical models of chloride penetration into concrete and corrosion of steel reinforcement, as well as the uncertainties in the governing parameters, including concrete diffusivity, concrete cover depth, surface chloride concentration and critical chloride level for corrosion initiation. There are a lot of prediction model for predicting the time of reinforcement corrosion of structures exposed to chloride-induced corrosion environment. In this work, RILEM model formula and Crank's solution of Fick's second law of diffusion is used. The parameters of the models are regarded as fuzzy numbers with proper membership function adapted to statistical data of the governing parameters instead of random variables of probabilistic modeling of Monte Carlo Simulation and the fuzziness of the time to corrosion initiation is determined by the fuzzy arithmetic of interval arithmetic and extension principle. An analysis is implemented by comparing deterministic calculation with fuzzy arithmetic for above two prediction models.

• 응용통계연구
• /
• 제32권5호
• /
• pp.671-681
• /
• 2019

최근에 부정맥 환자가 증가하면서 머신러닝을 이용한 부정맥을 예측하는 연구가 활발하게 진행되고 있다. 기존의 많은 연구들은 특정한 시점의 RR 간격 데이터에서 추출한 특징변수 다변량 데이터에 기반하여 부정맥을 예측하였다. 본 연구에서는 심장 상태가 시간에 따라 변해가는 패턴도 부정맥 예측에 중요한 정보가 될 수 있다고 생각하여 일정한 시간 간격을 두고 특징변수의 다변량 벡터를 추출하여 쌓음으써 얻어지는 다변량 시계열 데이터로 부정맥을 예측하는 것의 유용성에 대해 살펴보았다. 1-Nearest Neighbor 방법과 그것을 앙상블(ensemble)한 learner를 중심으로 비교했을 경우 시계열의 특징을 고려한 적절한 시계열 거리함수를 선택하여 시계열 정보를 활용한 다변량 시계열 데이터 기반 방법의 분류 성능이 더 좋게 나오는 것을 확인하였다.

• 대한기계학회논문집A
• /
• 제34권4호
• /
• pp.467-474
• /
• 2010

용접이음부의 신뢰성 확보는 구조물의 건전성과 내구성에 직접적인 영향을 미치기 때문에 가스용접 이음재의 피로설계기준(fatigue design criterion)을 정하기 위해서는 피로시험을 수행하여 ${\Delta}P$-Nf 관계를 이용하는 것이 일반적이다. 그러나 피로데이터를 장시간 획득하는 과정에서 여러 가지 변동인자에 의해서 피로데이터가 영향을 받기 때문에 피로데이터의 신뢰도가 떨어진다. 또한, 이음재의 재질 및 접합형태가 달라질 때마다, 각각의 경우에 대해서 새로운 피로시험이 요구됨으로 많은 시간과 비용이 소모된다. 따라서 이러한 문제점들을 개선하고 신뢰성 있는 설계를 하기 위해서 필렛 가스용접 이음재를 적용, 반복피로시험을 통한 데이터를 통계적으로 분석하여, 다양한 가스용접 이음재의 피로수명을 예측함과 동시에 실제 피로시험데이터와 비교 분석하여 예측된 수명의 신뢰도(reliability)와 신뢰구간(confidence interval)을 추정함으로서 새로운 피로설계기준 방법을 제시하고자 하였다.