• The KIPS Transactions:PartA
• /
• v.10A no.2
• /
• pp.173-180
• /
• 2003

This paper proposes Remote Educating Communication Tool (RECT) that allows students and teachers to communicate using Web-based Bulletin Board System. The distance teaching using DCOM (Distributed Component Object Model) voice module is used to enhance academic accomplishments for students in computer class. The DCOM voice module to be used in distance learning is designed, implemented and applied to teachers and students in the computer class in order to measure and analyze academic results. The RECT server provides Q&A sessions between students and teachers in the BBS using recording and playback functions. The client RECT includes recording and playback functions. The client module of RECT receives and uses DCOM module. When recording, the client transmits voice files with the recorded content to the server.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.6 s.261
• /
• pp.718-724
• /
• 2007

Some of gas turbine model of 7F-Class has constructed and is operating with units domestically. Non-destructive testing (NDT) is one of the methods being used to inspect damage $1^{st}$ stage bucket and review damage trends. We also analyze damage configuration and microstructure according to material and compare with pape of electric power research institute (EPRI). The damaged mode could be determined by leveraging failure analysis. Especially, configuration uprate of bucket is not only to prevent damage during operation but also avoid domestic manufacturing by the competitors. Modifications were mainly concentrated on surfaces such as cooling hole and bucket tips. Analyzing of bucket damage, the earlier model of 7F-Class used with one cycle with equivalent operation hour (EOH), has various cracking of the bucket surface. Bucket damage of new model is centered on tip area (54%) as analyzed by EPRI research. We conclude that improving bucket configuration would increase repair rate on the bucket tip.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.103.2-103.2
• /
• 2012

NGC 2024 FIR 6 is a star formation site in Orion and may contain a hypercompact H II region, FIR 6c, and a low-mass protostar, FIR 6n. The FIR 6 region was observed in the water maser line at 22 GHz and the methanol class I maser lines at 44, 95, and 133 GHz, using KVN in the single-dish telescope mode. The water maser spectra displayed several velocity components and month-scale time variabilities. Most of the velocity components may be associated with FIR 6n while one component was associated with FIR 4, another young stellar object in the 22 GHz beam. A typical life time of the water-maser velocity-components is about 8 months. The components showed velocity fluctuations with a typical drift rate of about 0.01 km/s/day. The methanol class I masers were detected toward FIR 6. The methanol emission is confined within a narrow range around the systemic velocity of the FIR 6 cloud core. The methanol masers did not show a detectable time-variability. The methanol masers suggest the existence of shocks driven by either the expanding H II region of FIR 6c or the outflow of FIR 6n.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1160-1166
• /
• 2006

The information of vehicle is very important for maintaining traffic order under the present complex traffic environments. This paper proposes a new vehicle plate recognition mechanism that is essential to know the information of vehicle. The proposed method uses SVM which is excellent object classification compare to other methods. Two-class SVM is used to find the location of vehicle plate and multi-class SVM is used to recognize the characters in the plate. As a real-time processing system using multi-step image processing and recognition process this method recognizes several different vehicle plates. Through the experimental results of real environmental image and recognition using the proposed method, the performance is proven.

• Korean Journal of Remote Sensing
• /
• v.16 no.4
• /
• pp.367-373
• /
• 2000

Natural and artificial land features are very dynamic, changing somewhat repidly in our lifetime. It is important that such changes are inventoried accurately so that the physical and human processes at work can be more fully understood. Change detection is a technique used to determine the change between two or more time periods of a particular object of study. Change detection is an important process in monitoring and managing natural resources and urban development because it provides quantitative analysis of the spatial distribution in the population of interest. The purpose of this research is to detect environmental changes surrounding an area of Mountain Moscow, Idaho using Landsat Thematic Maper (TM) images of (July 8, 1990 and July 20, 1991). For accurate classification, the Image enhancement process was performed for improving the image quality of each image. A SPOT image (Aug. 14, 1992) was used for image merging in this research. Supervised classification was performed using the maximum likelihood method. Accuracy assessments were done for each classification. Two images were compared on a pixel-by-pixel basis using the post-classification comparison method that is used for detecting the changes of the study area in this research. The 'from-to' change class information can be detected by post classification comparison using this method and we could find which class change to another.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.67.1-67.1
• /
• 2019

We present 2-dimensional continuum radiative transfer modeling for EC53. EC 53 is a Class I YSO, which was brightened at $850{\mu}m$ by a factor of 1.5. This luminosity variation was revealed by the JCMT Transient Survey. The increase in brightness is likely related to the enhanced accretion. We aim to investigate how much increase of protostellar luminosity causes the observed brightness increase at $850{\mu}m$. Thus we modeled the SED of EC 53 both in the quiescence and (small scale) outburst phases, with and without the external heating from the interstellar radiation field (ISRF). We found that the internal protostellar luminosity should increase more to fit the observed flux enhancement if the ISRF is considered in the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.104-109
• /
• 2022

For autonomous driving research using AI, datasets collected from road environments play an important role. In other countries, various datasets such as CityScapes, A2D2, and BDD have already been released, but datasets suitable for the domestic road environment still need to be provided. This paper analyzed and verified the dataset reflecting the Korean driving environment. In order to verify the training dataset, the class imbalance was confirmed by comparing the number of pixels and instances of the dataset. A similar A2D2 dataset was trained with the same deep learning model, ConvNeXt, to compare and verify the constructed dataset. IoU was compared for the same class between two datasets with ConvNeXt and mIoU was compared. In this paper, it was confirmed that the collected dataset reflecting the driving environment of Korea is suitable for learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.