• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.12
• /
• pp.1278-1285
• /
• 2008

An optimization-based real-time joint angle extraction method of human elbow is proposed by processing the biomedical signal of surface EMG (electromyogram) measured at the center point of biceps brachii. The EMG signal is known as non-stationary (time-varying) signal, but we assume that it is quasi-stationary because a physical or physiological system has limitations in the rate at which it can change its characteristics. Based on the assumption, a pre-processing method to obtain pre-angle values from raw EMG signal is firstly suggested, and then an optimization method to minimize the error between the pre-angle and real joint angle is proposed in this paper. Finally, we suggest the experimental results showing the effectiveness of the proposed algorithm.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2014.11a
• /
• pp.293-293
• /
• 2014

The applicability of graphene has been demonstrated in the electronic fields. But, high performance of graphene is limited by the contact resistance (Rc) at the metal-graphene interface. Recently, Rc was found to be improved by forming edge-contacted graphene via theoretical simulation. Based on the differences between the surface and edge contacts at the M-G interface, we demonstrate "edge-contacted" graphene through the use of a controlled plasma processing technique that generates the edge structure of the bond and significantly reduces the contact resistance. The contact resistance attained by using pre-plasma processing was of $270{\Omega}{\cdot}{\mu}m$. Mechanisms of pre-plasma process leading to low Rc was revealed by SEM and Raman spectroscopy. In the end, controlled pre-plasma processing enabled to fabricate CVD-graphene field effect transistors with an enhanced adhesion and improved carrier mobility.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.282-291
• /
• 2022

This research applies a pre-trained bidirectional encoder representations from transformers (BERT) handwriting recognition model to predict foreign Korean-language learners' writing scores. A corpus of 586 answers to midterm and final exams written by foreign learners at the Intermediate 1 level was acquired and used for pre-training, resulting in consistent performance, even with small datasets. The test data were pre-processed and fine-tuned, and the results were calculated in the form of a score prediction. The difference between the prediction and actual score was then calculated. An accuracy of 95.8% was demonstrated, indicating that the prediction results were strong overall; hence, the tool is suitable for the automatic scoring of Korean written test answers, including grammatical errors, written by foreigners. These results are particularly meaningful in that the data included written language text produced by foreign learners, not native speakers.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.15-23
• /
• 2022

In the field of patents, as NLP(Natural Language Processing) is a challenging task due to the linguistic specificity of patent literature, there is an urgent need to research a language model optimized for Korean patent literature. Recently, in the field of NLP, there have been continuous attempts to establish a pre-trained language model for specific domains to improve performance in various tasks of related fields. Among them, ELECTRA is a pre-trained language model by Google using a new method called RTD(Replaced Token Detection), after BERT, for increasing training efficiency. The purpose of this paper is to propose KorPatELECTRA pre-trained on a large amount of Korean patent literature data. In addition, optimal pre-training was conducted by preprocessing the training corpus according to the characteristics of the patent literature and applying patent vocabulary and tokenizer. In order to confirm the performance, KorPatELECTRA was tested for NER(Named Entity Recognition), MRC(Machine Reading Comprehension), and patent classification tasks using actual patent data, and the most excellent performance was verified in all the three tasks compared to comparative general-purpose language models.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.1335-1336
• /
• 2010

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.70-73
• /
• 2000

The error diffusion is good for reproducing continuous image to binary image. However the reproduction of edge characteristics is weak in power spectrum analysis of display error. It is suggested for us an edge-enhanced error-diffusion method that is included pre-processing algorithm for edge characteristic enhancement. Pre-processing algorithm is organized horizontal and vertical directional 2nd order differential values and weighting function of pre-filter. The improved Error diffusion using pre-filter, presents a good results visually which edge characteristics is enhanced. The performance of the proposed algorithm is compared with that of the conventional edge-enhanced error diffusion by measuring the RAPSD of display error, the egde correlation and the local average accordance.

• Proceedings of the KSME Conference
• /
• 2002.08a
• /
• pp.67-70
• /
• 2002

In the present study a pre/post-processor program has been developed to be used with a general CFD code. This program is capable of performing the basic functions of the pre/post-processing, which include mesh generation and post processing plots. Also through perspective projection, this program can be used to check the quality of generated mesh by moving around inside the mesh. The smoke visualization can be also performed with the present program to visualize the smoke behavior in the case of fire simulation. The examples of the program execution are given in paper.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.3
• /
• pp.190-197
• /
• 2000

A graphic vehicle modeling pre-processing program and a visualization post-processing program have been developed for AutoDyn7, which is a special program for vehicle dynamics. The Rapid-App for GUI(Graphic User Interface) builder and the Open Inventor for 3D graphic library have been employed to develop these programs in Silicon Graphics workstation. A Graphic User Interface program integrates vehicle modeling pre-processor, AutoDyn7 analysis processor, and visualization post-processor. In vehicle modeling pre-processor, vehicle hard point data for a suspension model are automatically converted into multibody vehicle system data. An interactive graphics capabilities provides suspension modeling aides to verify user input data interactively. In visualization post-processor, vehicle virtual test simulation results are animated with virtual testing environments.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1289-1291
• /
• 1996

In this paper, we propose a new adaptive pre-processing technique for the linearization of a weakly nonlinear system which can be modeled by a Volterra series up to third order. To compensate the nonlinear effects of a given system, an update algorithm for the linear filter coefficients of the proposed adaptive pre-processor is introduced, and to compensate the linear distortion of the given system, the linear inverse filter is also utilized. For the performance test of the proposed adaptive pre-processor, computer simulation results obtained by analyzing an ANRSS loudspeaker model are provided.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.