• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.3
• /
• pp.210-220
• /
• 2003

This work presents a method of point to surface assignment fur 3D metrology of solder pastes on PCB. A bounding box enclosing the solder paste tightly on all sides is introduced to avoid incorrect assignment. The shape of bounding box fur solder paste brick is variable according to geometry of measured points. The surface geometry of bounding box is obtained by using five peaks selected in the histogram of normalized gradient vectors. By using the bounding box enclosing the solder pastes, the task of point-to-surface assignment has been successfully conducted, then geometrical features are obtained through the task of surface fitting.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.599-612
• /
• 2022

This study focuses on improving a word embedding model to enhance the performance of downstream tasks, such as those of dialog systems. To improve traditional word embedding models, such as skip-gram, it is critical to refine the word features and expand the context model. In this paper, we approach the word model from the perspective of subword embedding and attempt to extend the context model by integrating various sentence models. Our proposed sentence model is a subword-based skip-thought model that integrates self-attention and relative position encoding techniques. We also propose a clustering-based dialog model for downstream task verification and evaluate its relationship with the sentence-model-based subword embedding technique. The proposed subword embedding method produces better results than previous methods in evaluating word and sentence similarity. In addition, the downstream task verification, a clustering-based dialog system, demonstrates an improvement of up to 4.86% over the results of FastText in previous research.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.209-218
• /
• 2013

Early researches in human action recognition have focused on tracking and classifying articulated body motions. Such methods required accurate segmentation of body parts, which is a sticky task, particularly under realistic imaging conditions. Recent trends of work have become popular towards the use of more and low-level appearance features such as spatio-temporal interest points. Given the great progress in pose estimation over the past few years, redefined views about pose-based approach are needed. This paper addresses the issues of whether it is sufficient to train a classifier only on low-level appearance features in appearance approach and proposes effective pose-based approach with pose estimation for emotional action recognition. In order for these questions to be solved, we compare the performance of pose-based, appearance-based and its combination-based features respectively with respect to scenario of various emotional action recognition. The experiment results show that pose-based features outperform low-level appearance-based approach of features, even when heavily spoiled by noise, suggesting that pose-based approach with pose estimation is beneficial for the emotional action recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1610-1629
• /
• 2021

Failures frequently occurred in manufacturing machines due to complex and changeable manufacturing environments, increasing the downtime and maintenance costs. This manuscript develops a novel deep learning-based method named Multi-Domain Convolutional Neural Network (MDCNN) to deal with this challenging task with vibration signals. The proposed MDCNN consists of time-domain, frequency-domain, and statistical-domain feature channels. The Time-domain channel is to model the hidden patterns of signals in the time domain. The frequency-domain channel uses Discrete Wavelet Transformation (DWT) to obtain the rich feature representations of signals in the frequency domain. The statistic-domain channel contains six statistical variables, which is to reflect the signals' macro statistical-domain features, respectively. Firstly, in the proposed MDCNN, time-domain and frequency-domain channels are processed by CNN individually with various filters. Secondly, the CNN extracted features from time, and frequency domains are merged as time-frequency features. Lastly, time-frequency domain features are fused with six statistical variables as the comprehensive features for identifying the fault. Thereby, the proposed method could make full use of those three domain-features for fault diagnosis while keeping high distinguishability due to CNN's utilization. The authors designed massive experiments with 10-folder cross-validation technology to validate the proposed method's effectiveness on the CWRU bearing data set. The experimental results are calculated by ten-time averaged accuracy. They have confirmed that the proposed MDCNN could intelligently, accurately, and timely detect the fault under the complex manufacturing environments, whose accuracy is nearly 100%.

• Journal of the Korean School Mathematics Society
• /
• v.23 no.2
• /
• pp.179-201
• /
• 2020

The purpose of this study is to analyze tasks reflected in Korean and US textbooks according to the mathematical modeling perspectives, and then to compare the diversity of learning opportunities given to students from both countries. For this, we analyzed mathematical modeling tasks of textbooks based on three aspects: mathematical modeling process, data, and expression. Results are as follows. First, with respect to modeling process, Korean textbook provides a high percentage of the task at all stages of modeling than US textbook. Second, with respect to data, both countries' textbooks have the highest percentage of matching task. Korean textbooks have a large gap in data characteristics by textbook. Third, with respect to expression, both countries' textbooks have the highest percentage of text and picture. Korean textbooks have a large gap in the type of expression than US textbooks, and some textbooks have no other expression except for text and picture. Fourth, tasks were analyzed by integrating the three features. The three features were not combined in various ways. It is necessary to diversify the integration of the three features.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.1
• /
• pp.14-22
• /
• 2001

Off-line handwritten numeral recognition is a very difficult task and hard to achieve high recognition results using a single feature and a single classifier, since handwritten numerals contain many pattern variations which mostly depend upon individual writing styles. In this paper, we propose handwritten numeral recognition system using hybrid features and combined classifier. To improve recognition rate, we select mutually helpful features -directional features, crossing point feature and mesh features- and make throe new hybrid feature sets by using these features. These hybrid feature sets hold the local and global characteristics of input numeral images. And we implement combined classifier by combining three neural network classifiers to achieve high recognition rate, where fuzzy integral is used for multiple network fusion. In order to verify the performance of the proposed recognition system, experiments with the unconstrained handwritten numeral database of Concordia University, Canada were performed. As a result, our method has produced 97.85% of the recognition rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.524-527
• /
• 1997

Conventional target tracking algorithms based on the linear estimation techniques perform quite efficiently when the target motion does not involve maneuvers. Target maneuvers involving short term accelerations, however, cause a bias in the measurement sequence. Accurate compensation for the bias requires processing more samples of which adds to the computational complexity. The primary motivation for employing a neural network for this task comes from the efficiency with which more features can be as inputs for bias compensation. A system architecture that efficiently integrates the fusion capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described. The parallel processing capability of a properly trained neural network can permit fast processing of features to yield correct acceleration estimates and hence can take the burden off the primary Kalman filter which still provides the target position and velocity estimates.

• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.115-119
• /
• 2007

Huge amount of useful information is getting added to the academic digital world everyday, This digitalized information is heterogeneous and remained limited to a local domain only. How to integrate and share this scattered knowledge with simplicity remained a big challenge. In this paper, we propose a prototype of web application for accomplishing above task using web 2.0 features; it makes traditional academic digital libraries to form as a special case of collaborative environment. This application enables users to customize their own resources to form their own virtual digital library. Further users can utilize personalized information of other users working in similar research domain to form true collaborative environment. The model and framework for the new look of academic digital library is presented.

• International Journal of Contents
• /
• v.13 no.3
• /
• pp.38-42
• /
• 2017

Documents of the last few decades typically include more than one kind of language, so linguistic classification of each word is essential, especially in terms of English and Korean in handwritten documents. Traditional methods mostly use conventional features of structural or stroke features, but sometimes they fail to identify many characteristics of words because of complexity introduced by handwriting. Therefore, traditional methods lead to a considerably more-complicated task and naturally lead to possibly poor results. In this study, convolutional neural network (CNN) is used for classification of English and Korean handwritten words in text documents. Experimental results reveal that the proposed method works effectively compared to previous methods.