• 지구물리와물리탐사
• /
• 제15권2호
• /
• pp.75-84
• /
• 2012

해양 전자탐사의 겉보기 비저항은 해수층으로 인해 지표탐사와 그 정의가 달라지게 되며, 이를 적절히 계산할 수 있는 알고리듬의 개발은 해양 전자탐사의 출발점이 될 수 있다. 이를 위해, 1차원 층서 가스 하이드레이트 수치모형과 해수층과 그 하부의 반 무한매질로 이루어진 수치모형에서 계산한 전자기적 반응을 비교분석하였다. 겉보기 비저항을 계산하기 위해서는 실수와 허수 성분보다는 진폭과 위상을 사용하는 것이 더 적합하였으며 해양 전자탐사 반응의 민감도를 정량적으로 분석하여, 근거리 영역에서는 위상이 원거리 영역에서는 진폭 성분이 더 안정적인 결과를 주는 것을 알았다. 또한 위상과 진폭의 선택기준으로써 유도상수의 값을 제안하였다. 이러한 분석을 토대로 격자 탐색법(grid search)을 사용하여 겉보기 비저항을 계산하는 수치알고리듬을 개발하였다. 개발된 알고리듬을 이용하여 1차원 층서 가스 하이드레이트 수치모형의 다양한 변수를 변화시켜가며 겉보기 비저항을 계산해봄으로써 알고리듬의 타당성을 검증하였다. 마지막으로, 계산한 겉보기 비저항 값을 이용한 가스 하이드레이트 부존양상 정보의 도출가능성을 살펴보았다. 동해 울릉분지의 가스 하이드레이트 부존양상을 모사한 2차원 가스 하이드레이트 수치모형에서 계산된 자료의 겉치레 단면도는 가스 하이드레이트 부존양상 정보 추출이 가능함을 보여주었다.

• 유통과학연구
• /
• 제13권5호
• /
• pp.91-102
• /
• 2015

Purpose - This study aims to build a systematic frame for effective marketing performances by prioritizing product type and pertinent channel that are appropriate for digital channel characteristics. FCB grid model was used to define a product type, and Internet communication satisfaction index was considered as a marketing performance measuring tool for digital channel. Research design, data, and methodology - As systematic understanding for Digital marketing is still unfamiliar to even professional marketer, the hypothesis was established based on preliminary research by conducting a qualitative survey of marketing experts who already experienced digital marketing in the fields as well as existing related study literature. Through a preliminary research, the degree for understanding for digital marketing, current digital marketing (including product/channel mix) execution status, and difficulties for marketers who had experienced digital marketing were figured out. Based on preliminary research, the main part of survey was designed to examine which type of product would be effective for digital marketing and which digital channel would be effective to achieve marketing performance in line with marketing objectives. To collect data, the questionnaire survey was conducted for professional marketers who had experienced digital marketing in 10 different fields including FMCG, cosmetics, distribution industry for one month (July, 10, 2014~Aug, 10, 2014). A total of 90 questionnaire were distributed and 66 questionnaires were used for the analysis, excluding the unanswered and insincere questionnaires. The data were analysed using SPSS ver.18.0. Results - The analysis for product type which is pertinent to digital marketing and prioritization for digital channel per digital marketing performance type could be summarized as followings. First, high involvement buying decision type of product and rational purchasing decision type of product in FCB grid are more effective for digital marketing in terms of marketing performance. Therefore, marketers in field would prioritize considering product type before executing digital marketing. Second, factor for sales increase, potential consumer creation and brand awareness was represented respectively 31.25%, 21.9%, and 20.8% as a result of factor analysis in terms of digital marketing channel performance. Third, effective major digital channel per digital marketing performance factor was differently identified as each digital channel has its own peculiarity. For instance, search engine is more effective for increasing sales while social media such as facebook and Kakaotalk is more effective for encouraging consumer participation. Conclusions - As a result of this study, product type and peculiarity which were pertinently fit to digital marketing were identified by using FCB grid model, and also suggested framework for decision making of digital channel selection in line with marketing objectives for effective marketing performance. It also provided insight to professional marketer which type of product could be effective for digital marketing execution as well as which factors should be measured for digital marketing performance.

• 한국산학기술학회논문지
• /
• 제17권1호
• /
• pp.9-14
• /
• 2016

본 논문에서는 인체 감지형 자기장 코일의 감지거리 13.4mm를 이용한 디지털 잠금장치 설계에 관한 연구를 하고자 한다. 현재 사용되는 디지털 잠금장치와는 다르게 실외 케이스는 기존의 고유번호 입력버튼, 조명, 보호 커버, 해당 pcb, 외곽 케이스, 데이터 전송 케이블 등이 삭제되고 구동전원 ON/OFF 스위치와 비상 단자로만 구성하였다. 실내 케이스는 내부에 설치 된 자기장 코일기판이 유리문 몸체에 밀착된 상태로 12mm 간격의 맞은편 실외에서 전송되는 전기적 저항 값을 감지하면 그에 대응하는 유도전류가 흐르게 된다. 이때, 해당 원형 코일의 주파수 변환이 이루어지면 자기장 코일은 센서의 역할을 수행하게 된다. 센서로서의 자기장 코일은 인체가 감지되기 전과 감지 후에 출력되는 발진 주파수의 크기 변화를 감지하고 2,000%이상 증폭시켜 디지털 신호로 변환 조합한 다음 전용 소프트웨어에 전송하여 내장된 고정 데이터와 비교하여 검색하는 역할을 한다. 연구결과 자기장 코일 $12.8{\emptyset}$ 기준으로 인체의 터치 면적에 따른 감지시간은 30% 대비 0.08sec, 80% 대비 0.03sec이며 감지거리는 13.4mm로 최고 수준으로 측정되었다.

• 로봇학회논문지
• /
• 제13권2호
• /
• pp.79-85
• /
• 2018

This study focuses on autonomous exploration based on map expansion for an underwater robot equipped with acoustic sonars. Map expansion is applicable to large-area mapping, but it may affect localization accuracy. Thus, as the key contribution of this paper, we propose a method for underwater autonomous exploration wherein the robot determines the trade-off between map expansion ratio and position accuracy, selects which of the two has higher priority, and then moves to a mission step. An occupancy grid map is synthesized by utilizing the measurements of an acoustic range sonar that determines the probability of occupancy. This information is then used to determine a path to the frontier, which becomes the new search point. During area searching and map building, the robot revisits artificial landmarks to improve its position accuracy as based on imaging sonar-based recognition and EKF-SLAM if the position accuracy is above the predetermined threshold. Additionally, real-time experiments were conducted by using an underwater robot, yShark, to validate the proposed method, and the analysis of the results is discussed herein.

• Structural Engineering and Mechanics
• /
• 제63권1호
• /
• pp.115-124
• /
• 2017

In this paper, a different technique to predict the effects of soil-structure interaction (SSI) on seismic response of building systems is investigated. The technique use a machine learning algorithm called Support Vector Regression (SVR) with technical and analytical results as input features. Normally, the effects of SSI on seismic response of existing building systems can be identified by different types of large data sets. Therefore, predicting and estimating the seismic response of building is a difficult task. It is possible to approximate a real valued function of the seismic response and make accurate investing choices regarding the design of building system and reduce the risk involved, by giving the right experimental and/or numerical data to a machine learning regression, such as SVR. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The results show that the performance of the technique can be predicted by reducing the number of real data input features. Further, performance enhancement was achieved by optimizing the RBF kernel and SVR parameters through grid search.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• 산업경영시스템학회지
• /
• 제47권2호
• /
• pp.1-9
• /
• 2024

New motor development requires high-speed load testing using dynamo equipment to calculate the efficiency of the motor. Abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft or looseness of the fixation, which may lead to safety accidents. In this study, three single-axis vibration sensors for X, Y, and Z axes were attached on the surface of the test motor to measure the vibration value of vibration. Analog data collected from these sensors was used in classification models for anomaly detection. Since the classification accuracy was around only 93%, commonly used hyperparameter optimization techniques such as Grid search, Random search, and Bayesian Optimization were applied to increase accuracy. In addition, Response Surface Method based on Design of Experiment was also used for hyperparameter optimization. However, it was found that there were limits to improving accuracy with these methods. The reason is that the sampling data from an analog signal does not reflect the patterns hidden in the signal. Therefore, in order to find pattern information of the sampling data, we obtained descriptive statistics such as mean, variance, skewness, kurtosis, and percentiles of the analog data, and applied them to the classification models. Classification models using descriptive statistics showed excellent performance improvement. The developed model can be used as a monitoring system that detects abnormal conditions of the motor test.

• 한국항공우주학회지
• /
• 제33권2호
• /
• pp.1-10
• /
• 2005

비정상 유동의 모사를 위한 병렬화된 비정렬 중첩격자기법을 개발하였다. 비정렬 격자계에서 효율적이고 강건하게 쓰일 수 있는 탐색방법과 병렬경계에서 유동적으로 변하는 데이터의 수를 처리할 수 있는 자료구조를 제안하였다. 격자계간의 정보전달을 위한 삽간경계면을 정의하였고, 공간상의 이차정확도를 유지하기 위한 삽간방법 및 물체내부에 위치하는 삽간점에 대한 처리방법을 제안하였다. 개발된 해석코드의 검증을 위해 Eglin/Pylon 형상에서 분리되는 스토어의 궤적을 해석하여 실험치와 비교하였고, 다 물체간의 상대운동이 있는 비정상유동의 적용을 위해 세 개의 스토어 분리에 대한 해석을 수행하였다.

• 전기학회논문지
• /
• 제64권4호
• /
• pp.515-522
• /
• 2015

Through the correspondence works with IEC in the smart grid fields and power IT fields, we set up the interpretation work procedure and defined the work rule for correspondence by analyzing the work results. In addition, we suggest cases for discussion of terms and definitions in the IEC and analyze them and then propose a matrix classification system for standardization to solve the cases for discussion. The matrix classification system with 3-axes of classification has been applied to newly emerging terminologies followed by smart gird. We drew the usefulness in search of terms in application fields and showed the cases of applying the matrix classification. The IEC Electropedia classification standard is unclear and the classification is mixed with principle, application and product areas. We proposed a new working group in IEC TC1 for research on the matrix classification system and then TC 1 decided to organize a new WG titled in the "IEV structure and supporting tools".

• Journal of the Korean Data and Information Science Society
• /
• 제27권4호
• /
• pp.911-923
• /
• 2016

빅데이터 시대에 머신러닝의 중요성은 더욱 부각되고 있고 로지스틱 회귀는 머신러닝에서 분류를 위한 방법으로 의료, 경제학, 마케팅 및 사회과학 전반에 걸쳐 널리 사용되고 있다. 지금까지 R과 Hadoop의 통합환경인 RHIPE 플랫폼은 설치 및 MapReduce 구현의 어려움으로 인해 거의 연구가 이루지 지지 않았다. 본 논문에서는 대용량 데이터에 대해 로지스틱 회귀 추정을 위한 두가지 알고리즘 즉, Gradient Descent 알고리즘과 Newton-Raphson 알고리즘에 대해 MapReduce로 구현하고, 실제 데이터와 모의실험 데이터를 가지고 이들 알고리즘 간의 성능을 비교하고자 한다. 알고리즘 성능 실험에서 Gradient Descent 알고리즘은 학습률에 크게 의존하고 또한 데이터에 따라 수렴하지 않는 문제를 갖고 있다. Newton-Raphson 알고리즘은 학습률이 불필요 할 뿐만 아니라 모든 실험 데이터에 대해 좋은 성능을 보였다.