• Journal of Information Technology Services
• /
• v.18 no.2
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.705-713
• /
• 2006

For the analysis of multiunit extracellular neural signals as multiple spike trains, neural spike sorting is essential. Existing algorithms for the spike sorting have been unsatisfactory when the signal-to-noise ratio(SNR) is low, especially for implementation of fully-automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare its performance with a recent method based on principal component analysis(PCA) and fuzzy c-means(FCM) clustering algorithm. Our system consists of a spike detector that shows high performance under low SNR, a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance compared to the PCA, and the proposed combination of spike detector, feature extraction, and unsupervised classification yields much better performance than the PCA-FCM, in that the realization of fully-automated unsupervised spike sorting becomes more feasible.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1819-1820
• /
• 2008

Steel slabs are marked with slab management numbers (SMNs). To increase efficiency, automated identification of SMNs from digital images is desirable. Automatic extraction of SMNs is a prerequisite for automatic character segmentation and recognition. The images include complex background, and the position of the text region of the slabs is variable. This paper describes an pre-processing algorithm for detection of slab information using robust feature points extraction. Using SIFT(Scale Invariant Feature Transform) algorithm, we can reduce the search region for extraction of SMNs from the slab image.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.859-861
• /
• 2003

In order to present a space in details, it is indispensable to acquire 3D shape and texture simultaneously from the same platform. 3D shape is acquired by Laser Scanner as point cloud data, and texture is acquired by CCD sensor. Positioning data is acquired by IMU (Inertial Measurement Unit). All the sensors and equipments are assembled on a hand-trolley. In this research, a method of integrating the 3D shape and texture for automated construction of Digital Surface Model is developed. This Digital Surface Model is applied for efficient feature extraction. More detailed extraction is possible , because 3D Digital Surface Model has both 3D shape and texture information.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10573-10576
• /
• 2015

Background: Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrieval was tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.525-527
• /
• 2003

Recently, the spatial resolution of earth observation satellites is significantly increased to a few meters. Such high spatial resolution images definitely will provide lots of information for detail-thirsty remote sensing users. However, it is more difficult to develop automated image algorithms for automated image feature extraction and pattern recognition. In this study, we propose a two-stage procedure to extract road information from high resolution satellite images. At first stage, a watershed segmentation technique is developed to classify the image into various regions. Then, a knowledge is built for road and used to extract the road regions. In this study, we use panchromatic and multi-spectral images of the IKONOS satellite as test dataset. The experiment result shows that the proposed technique can generate suitable and meaningful road objects from high spatial resolution satellite images. Apparently, misclassified regions such as parking lots are recognized as road needed further refinement in future research.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.4
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• Journal of Industrial Technology
• /
• v.20 no.B
• /
• pp.207-211
• /
• 2000

For efficient massive image retrieval, an image retrieval requires that several important objectives are satisfied, namely: automated extraction of features, efficient indexing and effective retrieval. In this work, we present a technique for extracting the 4-dimension directional feature. By directional detail, we imply strong directional activity in the horizontal, vertical and diagonal direction present in region of the image texture. This directional information also present smoothness of region. The 4-dimension feature is only indexed in the 4-D space so that complex high-dimensional indexing can be avoided.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.37-43
• /
• 2018

Most of fruit quality classification has been done by time consuming, inaccurate and intensive manual labor. This study proposed an automated fruit grading system based on appearances and internal flavors. In this study, image processing technique and a weight checker were used to measure the value of appearance features and the near infrared spectroscopy analysis method was used to estimate the value of internal flavors. Additionally, I suggested 8x8x5x5 ANN based fruit quality classifier model to grade fruits quality. The proposed automated fruit quality classification system is expected to be very beneficial for many farms where heavy manual labor is usually needed for fruit quality classification.