• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.446-448
• /
• 2021

In training a deep learning model, it is crucial to tune various hyperparameters and gain speed and accuracy. While hyperparameters that mathematically induce convergence impact training speed, system parameters that affect host-to-device transfer are also crucial. Therefore, it is important to properly tune and select parameters that influence the data loader as a system parameter in overall time acceleration. We propose an automated framework called Num Worker Tuner (NWT) to address this problem. This method finds the appropriate number of multi-processing subprocesses through the search space and accelerates the learning through the number of subprocesses. Furthermore, this method allows memory efficiency and speed-up by tuning the system-dependent parameter, the number of multi-process spawns.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.811-822
• /
• 2005

Automated text categorization is to classify free text documents into predefined categories automatically and whose main goals is to reduce considerable manual process required to the task. The researches to improving the text categorization performance(efficiency) in recent years, focused on enhancing existing classification models and algorithms itself, but, whose range had been limited by feature based statistical methodology. In this paper, we propose RTPost system of different style from i.ny traditional method, which takes fault tolerant system approach and data mining strategy. The 2 important parts of RTPost system are reinforcement training and post-processing part. First, the main point of training method deals with the problem of defining category to be classified before selecting training sample documents. And post-processing method deals with the problem of assigning category, not performance of classification algorithms. In experiments, we applied our system to documents getting low classification accuracy which were laid on a decision boundary nearby. Through the experiments, we shows that our system has high accuracy and stability in actual conditions. It wholly did not depend on some variables which are important influence to classification power such as number of training documents, selection problem and performance of classification algorithms. In addition, we can expect self learning effect which decrease the training cost and increase the training power with employing active learning advantage.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.5
• /
• pp.493-504
• /
• 2010

This study proposes a classification method based on an automated training extraction procedure that may be used with very high resolution (VHR) images of non-accessible areas. The proposed method overcomes the problem of scale difference between VHR images and geographic information system (GIS) data through filtering and use of a Landsat image. In order to automate maximum likelihood classification (MLC), GIS data were used as an input to the MLC of a Landsat image, and a binary edge and a normalized difference vegetation index (NDVI) were used to increase the purity of the training samples. We identified the thresholds of an NDVI and binary edge appropriate to obtain pure samples of each class. The proposed method was then applied to QuickBird and SPOT-5 images. In order to validate the method, visual interpretation and quantitative assessment of the results were compared with products of a manual method. The results showed that the proposed method could classify VHR images and efficiently update GIS data.

• Nuclear Engineering and Technology
• /
• v.51 no.7
• /
• pp.1784-1790
• /
• 2019

Accurate and consistent characterization of defects in steam generator tubes (SGT) in nuclear power plants is one of the key issues in the field of nondestructive testing since the large number of signals to be analyzed in a time-limited in-service inspection causes a serious problem in practice. This paper presents an effective approach to this difficult task of automated classification of motorized rotating pancake coil (MRPC) eddy current flaw acquired from tube specimens with deliberated defects using deep neural networks (DNN). This approach consists of five steps, namely, the data acquisition using the MRPC probe in the tube, the signal preprocessing to make data more suitable for training DNN, the data augmentation for boosting a training performance, the training of DNN, and finally demonstration of the trained DNN for discriminating the axial and circumferential defects. The high performance obtained in this study shows that DNN is useful for classification of defects in tubes from the MRPC eddy current signals even though the number of signals is very large.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1373-1382
• /
• 2011

In this study, we propose an automated smile analysis system for self smile training. The proposed system detects the face area from the input image with the AdaBoost algorithm, followed by identifying facial features based on the face shape model generated by using an ASM(active shpae model). Once facial features are identified, the lip line and teeth area necessary for smile analysis are detected. It is necessary to judge the relationship between the lip line and teeth for smiling degree analysis, and to this end, the second differentiation of the teeth image is carried out, and then individual the teeth areas are identified by means of histogram projection on the vertical axis and horizontal axis. An analysis of the lip line and individual the teeth areas allows for an automated analysis of smiling degree of users, enabling users to check their smiling degree on a real time basis. The developed system in this study exhibited an error of 8.6% or below, compared to previous smile analysis results released by dental clinics for smile training, and it is expected to be used directly by users for smile training.

• The KIPS Transactions:PartB
• /
• v.16B no.6
• /
• pp.479-488
• /
• 2009

This paper shows a reinforced construction scheme of training data for improvement of text classification by automatic search of boundary category. The documents laid on boundary area are usually misclassified as they are including multiple topics and features. which is the main factor that we focus on. In this paper, we propose an automated exploring methodology of optimal boundary category based on previous research. We consider the boundary area among target categories to new category to be required training, which are then added to the target category sementically. In experiments, we applied our method to complex documents by intentionally making errors in training process. The experimental results show that our system has high accuracy and reliability in noisy environment.

• Journal of Fisheries and Marine Sciences Education
• /
• v.4 no.2
• /
• pp.101-108
• /
• 1992

This study is some parts, the contents on "Course of Power Machinery and of Automated-Ship Operation", of the results of the sixth curriculum, revision study for the fisheries high schools and merchant marine high schools. In this study, it was suggested that the existing name "the Course of Marine Engine" is revised to "the Course of Power Machinery" and "the Course of Automated-Ship Operation" is newly established. The purpose of the revision of the name to "the Course of Power Machinery" is to give the course a more flexible curriculum which enables the course to bring up not only sea duty marine engineers but also shore duty power engineers. Also, the purpose of the new establishment of "the Course of Automated-Ship Operation" is to bring up automated-ship operators. The necessities for automated-ship operator is derived from the process of ship automation to reduce the number of crew to cut down the expenses. The revised parts of the organization of the professional subjects exclusively related to "the Course of Power Machinery" and "the Course of Automated-Ship Operation" are summarised as follows; (l) The Automated-Ship are newly added. (2) The Sea Training, the Fisheries Law are Disused. (3) The Introduction to Ship, the Introduction to Marine Engine and the Introduction to Marine Communication are merged into the Introduction to Ship. (4) The name of the Marine Engine, the Shipping Business are revised to the Heat Engine, the Introduction to Shipping respectively. (5) M compulsory professional subjects, the Introduction to Fisheries is suggested for the fisheries high schools and the Introduction to Shipping is suggested for the merchant marine high schools.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.45
• /
• pp.365-374
• /
• 1998

Control Chart is a powerful tool to detect that process is in control or out of control. CIM can have real effect when CIM involve automated quality control. A neural network approach is used for unnatural pattern detecting of control chart. The previous moving window method uses all unnatural pattern that is detected as moving time window. Therefore, It trains a large number of unnatural pattern and takes training time long. In this paper, the proposed method tests a small number of training unnatural pattern which modifies test data without repeating time. We shows that the proposed method has differences In training time and identification rate on the previous moving windows method. As results, we reduced training time and obtain the same identification rate.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.183-191
• /
• 2005

This paper describes the automated call routing for call center system based on speech recognition. We focus on the task of automatically routing telephone calls based on a users fluently spoken response instead of touch tone menus in an interactive voice response system. Vector based call routing algorithm is investigated and normalization method suggested. Call center database which was collected by KT is used for call routing experiment. Experimental results evaluating call-classification from transcribed speech are reported for that database. In case of small training data, an average call routing error reduction rate of 9% is observed when normalization method is used.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.13-20
• /
• 2023

This study explores the potential of automated speech recognition (ASR) in assessing English learners' pronunciation. We employed ASR technology, acknowledged for its impartiality and consistent results, to analyze speech audio files, including synthesized speech, both native-like English and Korean-accented English, and speech recordings from a native English speaker. Through this analysis, we establish baseline values for the word error rate (WER). These were then compared with those obtained for human raters in perception experiments that assessed the speech productions of 30 first-year college students before and after taking a pronunciation course. Our sub-group analyses revealed positive training effects for Whisper, an ASR tool, and human raters, and identified distinct human rater strategies in different assessment aspects, such as proficiency, intelligibility, accuracy, and comprehensibility, that were not observed in ASR. Despite such challenges as recognizing accented speech traits, our findings suggest that digital tools such as ASR can streamline the pronunciation assessment process. With ongoing advancements in ASR technology, its potential as not only an assessment aid but also a self-directed learning tool for pronunciation feedback merits further exploration.