• The Journal of Korean Medicine
• /
• v.41 no.3
• /
• pp.1-8
• /
• 2020

Objectives: This paper aims to investigate the Donguibogam-based pattern diagnosis by applying natural language processing and machine learning. Methods: A database has been constructed by gathering symptoms and pattern diagnosis from Donguibogam. The symptom sentences were tokenized with nouns, verbs, and adjectives with natural language processing tool. To apply symptom sentences into machine learning, Word2Vec model has been established for converting words into numeric vectors. Using the pair of symptom's vector and pattern diagnosis, a pattern prediction model has been trained through Logistic Regression. Results: The Word2Vec model's maximum performance was obtained by optimizing Word2Vec's primary parameters -the number of iterations, the vector's dimensions, and window size. The obtained pattern diagnosis regression model showed 75% (chance level 16.7%) accuracy for the prediction of Six-Qi pattern diagnosis. Conclusions: In this study, we developed pattern diagnosis prediction model based on the symptom and pattern diagnosis from Donguibogam. The prediction accuracy could be increased by the collection of data through future expansions of oriental medicine classics.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.10b
• /
• pp.26-30
• /
• 2003

Since the dimension of cold forged part is larger than the cavity size of forging die, the difference results from the various features, such as, the elastic characteristics of die and workpiece, thermal influences, and machine-elasticity. All of these factors should be considered to get more accurate prediction of the dimension of forged part. In this paper, severe FE techniques are proposed to improve the prediction accuracy of dimension for cold forged part. To validate the importance of the above mentioned factors, and the estimated results are compared with the experimental results. The used model is a closed die upsetting of cylindrical billet. The calculated dimensions are well coincided with .the measured values based on the proposed techniques. The proposed techniques have put two simple but important points into Fe simulation. One is the separation of forging stages into 3 steps, from a loading through punch retraction to ejecting stage. The other is the dimensional change, according to the temperature changes due to the deformation. The FE analysis could predict the dimension of cold forged part within the $10{\mu}m$, based on the more realistic consideration.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.3
• /
• pp.7-12
• /
• 2012

Ceramic core processing technology using 5-axis high-speed cutting machine is applied to make the glass molds for aspherical ophthalmic lenses. In the technology, optimum processing conditions for aspherical ceramic molds are based on minimal experimental data of surface roughness. Such surface roughness is influenced by fabricating tools, cutting speed, feed rate, and depth of cut, respectively. In this paper, we present that surface roughness and shape accuracy of aspheric ceramic mold obtained by optimum processing conditions are Pa $0.6184{\mu}m$ and Pt $5.0301{\mu}m$, respectively, and propose that these values are sufficiently possible to apply to making the glass molds for aspherical ophthalmic lenses.

• Journal of Applied Reliability
• /
• v.17 no.3
• /
• pp.264-271
• /
• 2017

Purpose: Field operation data contains missing values or outliers due to various causes of the data collection process, so caution is required when utilizing RAM analysis results by field operation data. The purpose of this study is to present a method to minimize the RAM analysis error of the field data to improve the accuracy. Methods: Statistical methods are presented for processing of the outliers and the missing values of the field operating data, and after analyzing the RAM, the differences between before and after applying the technique are discussed. Results: The availability is estimated to be lower by 6.8 to 23.5% than that before processing, and it is judged that the processing of the missing values and outliers greatly affect the RAM analysis result. Conclusion: RAM analysis of OO weapon system was performed and suggestions for improvement of RAM analysis were presented through comparison with the new and current method. Data analysis results without appropriate treatment of error values may result in incorrect conclusions leading to inappropriate decisions and actions.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.235-245
• /
• 2018

Recently panoramic image overcomes camera limited viewing angle and offers wide viewing angle by stitching plenty of images. In this paper, we propose pre-processing and post-processing algorithm which makes speed and accuracy improvements when making panoramic images. In pre-processing, we can get camera sensor information and use three-dimensional rotation angle to find RoI(Region of Interest) image. Finding RoI images can reduce time when extracting feature point. In post-processing, we propose weighted minimal error boundary cut blending algorithm to improve accuracy. This paper explains our algorithm and shows experimental results comparing with existing algorithms.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.12
• /
• pp.1-7
• /
• 2004

We have developed a 24GHz side-looking vehicle detection radar. A 24GHz front-end module and a novel signal processing algorithm have been developed for speed measurement and size classification of vehicles in multiple lanes. The system has a fixed antenna and FMCW processing module. This paper presents the background theory of operation and shows some measured data using the algorithm. The data shows that measured velocity of the passing vehicle is within the accuracy of 95% in single lane and the velocity of the vehicles in two lanes is within the accuracy of 90% by using variable threshold estimation. The classification of vehicle size as small, medium and large has been measured with 89% accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.1
• /
• pp.79-90
• /
• 2016

The study has purposed in evaluating experiences for achievable accuracy and precision of time series at 3-D coordinates. It has been estimated from the kinematic medium-range baseline processing of Continuously Operating Reference Stations (CORS) for the potential application of crustal displacement analysis during an earthquake event. To derive the absolute coordinates of local CORS, it is highly recommended to include some of oversea country references, since it should be compromised of an observation network of the medium-range baselines within the length range from tens of kilometers to about 1,000 kilometers. A data processing procedure has reflected the dynamics of target stations as the parameter estimation stages, which have been applied to a series of experimental analysis in this research at the end. From the analysis of results, we could be concluded in that the subcentimeters-level of positioning accuracy and precision can be achievable. Furthermore, the paper summarizes impacts of satellite ephemeris, data lengths and levels of initial coordinate constraint into the positioning performance.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.4
• /
• pp.31-39
• /
• 2010

In this study, the performance of the online GPS processing services provided by diverse institutions was compared so that domestic GPS users in geodesy and surveying can easily get precise coordinates using those services. In order to evaluate the accuracy of each online GPS processing service, we calculated coordinates of seven GPS permanent stations located in Korea and foreign countries using APPS, CSRS-PPP, AUSPOS and OPUS. And the results were compared with published coordinates by IERS and National Geographic Information Institute. In the cases of foreign stations, the mean value of the horizontal errors was 9.3 mm and the descending order of accuracies was APPS, AUSPOS, OPUS and CSRS-PPP. In the cases of Korean stations, the mean value of the horizontal errors was 37.6 mm, although the order of accuracy was similar to the foreign cases; AUSPOS, APPS, OPUS and CSRS-PPP. Also, the average value of 3-D errors in Korean cases was about 3 cm larger than that of foreign cases and a bias of 3 cm was observed in the north direction.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.655-660
• /
• 2009

The context prediction algorithms are not suitable to provide real-time personalized service for users in context-awareness environment. The algorithms have problems like time delay in training data processing and the difficulties of implementation in real-time environment. In this paper, we propose a prediction algorithm with user modeling to shorten of processing time and to improve the prediction accuracy in the context prediction algorithm. The algorithm uses moving path of user contexts for context prediction and generates user model by time-series analysis of user's moving path. And that predicts the user context with the user model by sequence matching method. We compared our algorithms with the prediction algorithms by processing time and prediction accuracy. As the result, the prediction accuracy of our algorithm is similar to the prediction algorithms, and processing time is reduced by 40% in real time service environment.

• Geomechanics and Engineering
• /
• v.30 no.3
• /
• pp.259-272
• /
• 2022

Rockburst is a dynamic, multivariate, and non-linear phenomenon that occurs in underground mining and civil engineering structures. Predicting rockburst is challenging since conventional models are not standardized. Hence, machine learning techniques would improve the prediction accuracies. This study describes decision based uncertainty models to predict rockburst in underground engineering structures using gradient boosting algorithms (GBM). The model input variables were uniaxial compressive strength (UCS), uniaxial tensile strength (UTS), maximum tangential stress (MTS), excavation depth (D), stress ratio (SR), and brittleness coefficient (BC). Several models were trained using different combinations of the input variables and a 3-fold cross-validation resampling procedure. The hyperparameters comprising learning rate, number of boosting iterations, tree depth, and number of minimum observations were tuned to attain the optimum models. The performance of the models was tested using classification accuracy, Cohen's kappa coefficient (k), sensitivity and specificity. The best-performing model showed a classification accuracy, k, sensitivity and specificity values of 98%, 93%, 1.00 and 0.957 respectively by optimizing model ROC metrics. The most and least influential input variables were MTS and BC, respectively. The partial dependence plots revealed the relationship between the changes in the input variables and model predictions. The findings reveal that GBM can be used to anticipate rockburst and guide decisions about support requirements before mining development.