• Journal of Korean Society for Quality Management
• /
• v.42 no.2
• /
• pp.221-234
• /
• 2014

Purpose: The Purpose of this study is to develop a model for predicting agent churn group in the cosmetics industry. We develope two models, pattern model and matrix model, which are compared regarding the prediction accuracy of churn agents. Finally, we try to conclude if there is statistically significant difference between two models by empirical study. Methods: We develop two models using the part of RFM(Recency, Frequency, Monetary) method which is one of customer segmentation method in traditional CRM study. In order to ensure which model can predict churn agents more precisely between two models, we used CRM data of cosmetics company A in China. Results: Pattern model and matrix model have been developed. we find out that there is statistically significant differences between two models regarding the prediction accuracy. Conclusion: Pattern model and matrix model predict churn agents. Although pattern model employed the trend of monetary mount for six months, matrix model that used the amount of sales per month and the duration of the employment is better than pattern model in prediction accuracy.

• Journal of Biomedical Engineering Research
• /
• v.24 no.2
• /
• pp.55-60
• /
• 2003

For quantitative analysis of the cardiac diseases. it is necessary to segment the left-ventricle (LY) in MR (Magnetic Resonance) cardiac images. Snake or active contour model has been used to segment LV boundary. However, the contour of the LV front these models may not converge to the desirable one because the contour may fall into local minimum value due to image artifact inside of the LY Therefore, in this paper, we Propose the Preprocessing method using k-means clustering and merging algorithms that can improve the performance of the active contour model. We verified that our proposed algorithm overcomes local minimum convergence problem by experiment results.

• The KIPS Transactions:PartD
• /
• v.10D no.1
• /
• pp.109-116
• /
• 2003

In this paper, a CORBA-based collaborative medical image analysis and visualization system, which provides high accessibility and usability of the system for the users on distributed environment is introduced. The system allows us to manage datasets and manipulates medical images such as segmentation and volume visualization of computed geometry from biomedical images in distributed environments. Using Bayesian classification technique and an active contour model the system provides classification results of medical images or boundary information of specific tissue. Based on such information, the system can create real time 3D volume model from medical imagery. Moreover, the developed system supports collaborative work among multiple users using broadcasting and synchronization mechanisms. Since the system is developed using Java and CORBA, which provide distributed programming, the remote clients can access server objects via method invocation, without knowing where the distributed objects reside or what operating system it executes on.

• Journal of Broadcast Engineering
• /
• v.20 no.4
• /
• pp.557-567
• /
• 2015

Over the past decades, a variety of spatial saliency methods have been introduced. Recently, motion saliency has gained much interests, where motion data estimated from an image sequence are utilized. In general, motion saliency requires reliable motion data as well as image segmentation for producing satisfactory saliency map which poses difficulty in most natural images. To overcome this, we propose a motion-based saliency generation that enhances the spatial saliency based on the combination of spatial and motion saliencies as well as motion complexity without the consideration of complex motion classification and image segmentation. Further, an affinity model is integrated for the purpose of connecting close-by pixels with different colors and obtaining a similar saliency. In experiment, we performed the proposed method on eleven test sets. From the objective performance evaluation, we validated that the proposed method produces better result than spatial saliency based on objective evaluation as well as ROC test.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.5D
• /
• pp.527-532
• /
• 2012

Terrestrial LiDAR emerges as a main mapping technology for indoor 3D cadastre, cultural heritage conservation and, building management in that it provides fast, accurate, and reliable 3D data. In this paper, a new 3D modeling method consisting of segmentation stage and outline extraction stage is proposed to develop indoor 3D model from the terrestrial LiDAR. In the segmentation process, RANSAC and a refinement grid is used to identify points that belong to identical planar planes. In the outline tracing process, a tracing grid and a data conversion method are used to extract outlines of indoor 3D models. However, despite of an improvement of productivity, the proposed approach requires an optimization process to adjust parameters such as a threshold of the RANSAC and sizes of the refinement and outline extraction grids. Furthermore, it is required to model curvilinear and rounded shape of the indoor structures.

• Industrial Engineering and Management Systems
• /
• v.15 no.3
• /
• pp.224-230
• /
• 2016

The use of new words, numerous spoken languages, and abbreviations on the Internet is extensive. As such, automatically acquiring words for the purpose of analyzing Internet content is very difficult. In a previous study, we proposed a method for Japanese word segmentation using character N-grams. The previously proposed method is based on a simple state-transition model that is established under the assumption that the input document is described based on four states (denoted as A, B, C, and D) specified beforehand: state A represents words (nouns, verbs, etc.); state B represents statement separators (punctuation marks, conjunctions, etc.); state C represents postpositions (namely, words that follow nouns); and state D represents prepositions (namely, words that precede nouns). According to this state-transition model, based on the states applied to each pseudo-word, we search the document from beginning to end for an accessible pattern. In other words, the process of this transition detects some words during the search. In the present paper, we perform experiments based on the proposed word acquisition algorithm using Japanese and Chinese newspaper articles. These articles were obtained from Japan's Kyoto University and the Chinese People's Daily. The proposed method does not depend on the language structure. If text documents are expressed in Unicode the proposed method can, using the same algorithm, obtain words in Japanese and Chinese, which do not contain spaces between words. Hence, we demonstrate that the proposed method is language independent.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.71-79
• /
• 2019

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.157-165
• /
• 2021

Recently, as the spatial resolution of satellite and aerial images has improved, various studies using remotely sensed data with high spatial resolution have been conducted. In particular, since the building extraction is essential for creating digital thematic maps, high accuracy of building extraction result is required. In this manuscript, building extraction models were generated using SegNet, U-Net, FC-DenseNet, and HRNetV2, which are representative semantic segmentation models in deep learning techniques, and then the evaluation of building extraction results was performed. Training dataset for building extraction were generated by using aerial orthophotos including various buildings, and evaluation was conducted in three areas. First, the model performance was evaluated through the region adjacent to the training dataset. In addition, the applicability of the model was evaluated through the region different from the training dataset. As a result, the f1-score of HRNetV2 represented the best values in terms of model performance and applicability. Through this study, the possibility of creating and modifying the building layer in the digital map was confirmed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1722-1725
• /
• 1997

This paper presents image analysis method using a Markov random field(MRF) model. Particulary, image esgmentation is to partition the given image into regions. This scheme is first segmented into regions, and the obtained domain knowledge is used to obtain the improved segmented image by a Markov random field model. The method is a maximum a posteriori(MAP) estimation with the MRF model and its associated Gibbs distribution. MAP estimation method is applied to capture the natural image by TMS320C80(MVP) and to realize the segmented image by a MRF model.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.332-338
• /
• 2013

We propose a method for target detection in Infrared images. In order to effectively detect a target region from an image with noises and clutters, spatial information of the target is first considered by analyzing pixel distributions of projections in horizontal and vertical directions. These distributions are represented as Gaussian distributions, and Gaussian Mixture Model is created from these distributions in order to find thresholding points of the target region. Through analyzing the calculated Gaussian Mixture Model, the target region is detected by eliminating various backgrounds such as noises and clutters. This is performed by using a novel thresholding method which can effectively detect the target region. As experimental results, the proposed method has achieved better performance than existing methods.