• 전기학회논문지
• /
• 제67권9호
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1992년도 추계학술대회논문집
• /
• pp.113-120
• /
• 1992

In this paper, a mathematical model of learning curve is proposed to study the finger's reaction time. The model is a logarithmic linear type which represents a learning curve appropriately, and parameters are estimated by the linear. The learning coefficient and percentage of a reaction time can be easily computed in the mathematical model. This quantitative approach provides an important information to be used for the working capability qualification for re-employment as well as for the adaptability estimation of aged workers.

• 한국경제지리학회지
• /
• 제25권1호
• /
• pp.183-201
• /
• 2022

주택가격을 정확히 추정하기 위한 많은 연구가 진행되어 왔다. 선행연구들은 주택의 고유 특성과 인근 지역 특성을 통제하는 계량경제모형을 활용한 분석이 많았다. 본 연구에서는 인공신경망 모형(ANN)을 활용하여 주택가격을 추정하였다. 딥러닝 기술의 장점은 변수 간의 복잡하고 비선형적인 특성을 모델링하고 데이터의 패턴을 인식할 수 있다는 것이다. 본 연구에서는 부동산 시장에서 공간적 분포도 패턴으로 인식할 수 있다는 가정하에 지리좌표를 설명변수로 ANN에 투입하였다. 선형회귀분석과 ANN 모형 간 비교 결과, 선형 모형 대비 ANN 모형의 설명력이 높았으며, 특히 ANN 모형은 지리좌표를 투입하였을 때 더 높은 정확도를 보여주었다. 또한 ANN 모형의 경우 지리좌표를 통해 모형 잔차의 공간적 자기 상관성이 크게 감소하였다는 점을 확인하였다. 이를 통해 ANN 모형의 패턴인식 능력을 활용하면 공간적 패턴을 학습시킴으로써 주택가격을 정확히 추정할 수 있음을 밝혔다.

• 대한조선학회논문집
• /
• 제56권6호
• /
• pp.488-496
• /
• 2019

The estimation of block erection work time at a dock is one of the important factors when establishing or managing the total shipbuilding schedule. In order to predict the work time, it is a natural approach that the existing block erection data would be used to solve the problem. Generally the work time per unit is the product of coefficient value, quantity, and product value. Previously, the work time per unit is determined statistically by unit load data. However, we estimate the work time per unit through work time coefficient value from series ships using machine learning. In machine learning, the outcome depends mainly on how the training data is organized. Therefore, in this study, we use 'Feature Engineering' to determine which one should be used as features, and to check their influence on the result. In order to get the coefficient value of each block, we try to solve this problem through the Ensemble learning methods which is actively used nowadays. Among the many techniques of Ensemble learning, the final model is constructed by Stacking Ensemble techniques, consisting of the existing Ensemble models (Decision Tree, Random Forest, Gradient Boost, Square Loss Gradient Boost, XG Boost), and the accuracy is maximized by selecting three candidates among all models. Finally, the results of this study are verified by the predicted total work time for one ship among the same series.

• Journal of the Korean Data and Information Science Society
• /
• 제24권5호
• /
• pp.1077-1088
• /
• 2013

High-dimensional data analysis arises from almost all scientific areas, evolving with development of computing skills, and has encouraged penalized estimations that play important roles in statistical learning. For the past years, various penalized estimations have been developed, and the least absolute shrinkage and selection operator (LASSO) proposed by Tibshirani (1996) has shown outstanding ability, earning the first place on the development of penalized estimation. In this paper, we first introduce a number of recent advances in high-dimensional data analysis using the LASSO. The topics include various statistical problems such as variable selection and grouped or structured variable selection under sparse high-dimensional linear regression models. Several unsupervised learning methods including inverse covariance matrix estimation are presented. In addition, we address further studies on new applications which may establish a guideline on how to use the LASSO for statistical challenges of high-dimensional data analysis.

• 전기학회논문지P
• /
• 제60권4호
• /
• pp.181-185
• /
• 2011

Due to the increasing of nonlinear loads such as converters and inverters connected to the electric power distribution system, and extensive application of harmonic generation sources with power electronic devices, disturbance of the electric power system and its influences on industries have been continuously increasing. Thus, it is difficult to construct accurate load model for active and reactive power in environments with harmonics. In this research, we develop current harmonics estimation method based on Extreme Learning Machine (ELM) with fast learning procedure for residential loads. Using data sets acquired from various residential loads, the proposed method has been intensively tested. As the experimental results, we confirm that the proposed method makes it possible to effective estimate current harmonics for various input voltage.

• 한국정밀공학회지
• /
• 제31권10호
• /
• pp.947-954
• /
• 2014

Performance of next generation susceptor is affected by temperature uniformity in order to produce reliably large-sized flat panel display. In this paper, we propose a learning estimation model of susceptor to predict and appropriately assess the temperature uniformity. Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) are compared for the suitability of the learning estimation model. It is proved that SVMs provides more suitable verification of uniformity modeling than ANNs during each stage of temperature variations. Practical procedure for uniformity estimation of susceptor temperature was developed using the SVMs prediction algorithm.

• 전기학회논문지
• /
• 제66권4호
• /
• pp.672-681
• /
• 2017

This paper is concerned with the design methodology of face recognition system based on pose estimation. In 2-dimensional face recognition, the variations of facial pose cause the deterioration of recognition performance because object recognition is carried out by using brightness of each pixel on image. To alleviate such problem, the proposed face recognition system deals with Learning Vector Quantizatioin(LVQ) or K-Nearest Neighbor(K-NN) to estimate facial pose on image and then the images obtained from LVQ or K-NN are used as the inputs of networks such as Convolution Neural Networks(CNNs) and Radial Basis Function Neural Networks(RBFNNs). The effectiveness and efficiency of the post estimation using LVQ and K-NN as well as face recognition rate using CNNs and RBFNNs are discussed through experiments carried out by using ICPR and CMU PIE databases.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.314-321
• /
• 2022

Depth information used in SLAM and visual odometry is essential in robotics. Depth information often obtained from sensors or learned by networks. While learning-based methods have gained popularity, they are mostly limited to RGB images. However, the limitation of RGB images occurs in visually derailed environments. Thermal cameras are in the spotlight as a way to solve these problems. Unlike RGB images, thermal images reliably perceive the environment regardless of the illumination variance but show lacking contrast and texture. This low contrast in the thermal image prohibits an algorithm from effectively learning the underlying scene details. To tackle these challenges, we propose multi-channel remapping for contrast. Our method allows a learning-based depth prediction model to have an accurate depth prediction even in low light conditions. We validate the feasibility and show that our multi-channel remapping method outperforms the existing methods both visually and quantitatively over our dataset.

• 한국정보통신학회논문지
• /
• 제24권7호
• /
• pp.935-941
• /
• 2020

사람 수 추정 기술은 IoT 서비스를 제공하기 위해 중요하다. 대부분의 사람 수 추정 기술은 카메라 또는 센서 데이터를 활용한다. 하지만 기존 기술들은 사생활 침해 문제가 발생 가능하며 추가로 인프라를 구축해야한다는 단점이 있다. 본 논문은 Wi-Fi AP를 활용하여 사람 수를 추정하는 방법을 제안한다. 사람 수 추정을 위해서 Wi-Fi의 채널 상태 정보를 딥러닝 기술을 활용하여 분석한다. Wi-Fi AP 기반 사람 수 추정 기술은 사생활 침해 우려가 없으며, 기존 Wi-Fi AP 인프라를 활용하면 되기 때문에 추가 비용이 발생하지 않는다. 제안하는 알고리즘은 k-바인딩 데이터 전처리 과정과 1D-CNN 학습 모델을 사용한다. AP 2대를 설치하여 6명의 사람 수 추정 결과를 실험을 통해 분석하였다. 정확한 사람 수 판별에 관한 결과는 64.8%로 낮은 결과를 보였지만, 사람의 수를 클래스로 분류한 결과는 84.5%의 높은 결과를 보였다. 해당 알고리즘은 제한된 공간에 사람의 밀집도를 파악하는데 응용 가능할 것으로 기대된다.