• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제11B권2호
• /
• pp.40-50
• /
• 2001

This paper deals with the development of the simulation models Cheju - Haenam HVDC system and its dynamic performance study and verify the control characteristics of the HVDC system. It discusses the model development requirement and criteria. It provides guedelines for developing large-scale simulation models for detailed electromagnetic studies and presents the results of the modeling project.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.183-186
• /
• 2003

Speech recognition performance depends on various factors. One of the factors is the characteristic of a microphone which is used when speech data is collected. Thus, in the present experiment speech databases for tests are created through varying types of microphones. Then, acoustic models are built based on these databases, and each of the acoustic models is assessed by the data to determine recognition performance depending on various microphones.

• 한국지진공학회논문집
• /
• 제24권2호
• /
• pp.77-86
• /
• 2020

Nonlinear static analysis and preliminary evaluation were performed in this study to evaluate the seismic performance of unreinforced masonry buildings subjected to various soil conditions based on the revised Korean Building Code. Preliminary evaluation scores and nonlinear static analyses indicated that all buildings were susceptible to collapse and did not reach their target performance. Therefore, retrofit of those building models was carried out through a systematic procedure to determine areas to be strengthened. It was possible to make most building models satisfy performance objectives through the reinforcement alone of damaged external shear walls. However, the application of a preliminary evaluation procedure to retrofit design was found to be too conservative because all the retrofitted building models verified with nonlinear static analysis failed to satisfy performance objectives. Therefore, it is possible to economically retrofit unreinforced masonry buildings through the fortification of external walls if a simple evaluation procedure that can efficiently specify vulnerable parts is developed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1032-1032
• /
• 2001

Artificial Neural Network (ANN) calibration techniques have been used commercially for agricultural applications since the mid-nineties. Global models, based on transmission data from 850 to 1050 nm, are used routinely to measure protein and moisture in wheat and barley and also moisture in triticale, rye, and oats. These models are currently used commercially in approx. 15 countries throughout the world. Results concerning earlier European ANN models are being published elsewhere. Some of the findings from that study will be discussed here. ANN models have also been developed for coarsely ground samples of compound feed and feed ingredients, again measured in transmission mode from 850 to 1050 nm. The performance of models for pig- and poultry feed will be discussed briefly. These models were developed from a very large data set (more than 20,000 records), and cover a very broad range of finished products. The prediction curves are linear over the entire range for protein, fat moisture, fibre, and starch (measured only on poultry feed), and accuracy is in line with the performance of smaller models based on Partial Least Squares (PLS). A simple bias adjustment is sufficient for calibration transfer across instruments. Recently, we have investigated the possible use of ANN for a different type of NIR spectrometer, based on reflectance data from 1100 to 2500 nm. In one study, based on data for protein, fat, and moisture measured on unground compound feed samples, dedicated ANN models for specific product classes (cattle feed, pig feed, broiler feed, and layers feed) gave moderately better Standard Errors of Prediction (SEP) compared to modified PLS (MPLS). However, if the four product classes were combined into one general calibration model, the performance of the ANN model deteriorated only slightly compared to the class-specific models, while the SEP values for the MPLS predictions doubled. Brix value in molasses is a measure of sugar content. Even with a huge dataset, PLS models were not sufficiently accurate for commercial use. In contrast an ANN model based on the same data improved the accuracy considerably and straightened out non-linearity in the prediction plot. The work of Mr. David Funk (GIPSA, U. S. Department of Agriculture) who has studied the influence of various types of spectral distortions on ANN- and PLS models, thereby providing comparative information on the robustness of these models towards instrument differences, will be discussed. This study was based on data from different classes of North American wheat measured in transmission from 850 to 1050 nm. The distortions studied included the effect of absorbance offset pathlength variation, presence of stray light bandwidth, and wavelength stretch and offset (either individually or combined). It was shown that a global ANN model was much less sensitive to most perturbations than class-specific GIPSA PLS calibrations. It is concluded that ANN models based on large data sets offer substantial advantages over PLS models with respect to accuracy, range of materials that can be handled by a single calibration, stability, transferability, and sensitivity to perturbations.

• 방송공학회논문지
• /
• 제25권2호
• /
• pp.200-207
• /
• 2020

CNN 기반 인공신경망은 영상 분류, 객체 인식, 화질 개선 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 많은 응용에서 딥러닝(Deep Learning) 모델의 복잡도 및 연산량이 방대해짐에 따라 IoT 기기 및 모바일 환경에 적용하기에는 제한이 따른다. 따라서 기존 딥러닝 모델의 성능을 유지하면서 모델 크기를 줄이는 인공신경망 압축 기법이 연구되고 있다. 본 논문에서는 인공신경망 압축기법을 통하여 원본 CNN 모델을 압축하고, 압축된 모델을 임베디드 시스템 환경에서 그 성능을 검증한다. 성능 검증을 위해 인공지능 지원 맞춤형 칩인 QCS605를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축 CNN 모델의 분류성능과 추론시간을 비교 분석한다. 본 논문에서는 이미지 분류 CNN 모델인 MobileNetV2, ResNet50 및 VGG-16에 가지치기(pruning) 및 행렬분해의 인공신경망 압축 기법을 적용하였고, 실험결과에서 압축된 모델이 원본 모델 분류 성능 대비 2% 미만의 손실에서 모델의 크기를 1.3 ~ 11.2배로 압축했을 뿐만 아니라 보드에서 추론시간과 메모리 소모량을 각각 1.2 ~ 2.1배, 1.2 ~ 3.8배 감소함을 확인했다.

• 대한음성학회지:말소리
• /
• 제67호
• /
• pp.79-102
• /
• 2008

In this paper, we investigate the relation between Bayes factor and likelihood ratio test (LRT) approaches and apply the neighborhood information of Bayes factor to building an alternate hypothesis model of the LRT system. To consider the neighborhood approaches, we contemplate a distance measure between models and algorithms to be applied. We also evaluate several methods to improve performance of utterance verification using neighborhood information. Among these methods, the system which adopts anti-models built by collecting mixtures of neighborhood models obtains maximum error rate reduction of 17% compared to the baseline, linear and weighted combination of neighborhood models.

• 한국도서관정보학회지
• /
• 제36권2호
• /
• pp.49-68
• /
• 2005

본 연구의 목적은 정보검색 분야에서의 언어모델의 적용에 관한 연구동향을 개관하고 이 분야의 선행연구 결과들을 분석해 보는 것이다. 선행연구들은 (1)전통적인 모델 기반 정보검색과 언어모델링 정보검색의 성능 비교 실험에 초점을 두고 있는 1세대 언어모델링 정보검색(LMIR)과 (2)기본적인 언어모델링 정보검색과 확장된 언어모델링 정보검색의 성능 비교를 통해 보다 우수한 언어모델링 확장기법을 찾아내는 것에 초점을 두고 있는 2세대 LMIR로 구분하여 분석하였다. 선행연구들의 실험결과를 분석해 본 결과 첫째, 언어모델링 정보검색은 확률모델, 벡터모델 정보검색보다 그 성능이 뛰어나고 둘째 확장된 언어모델들은 기본적인 언어 모델 정보검색보다 그 성능이 우수한 것으로 나타났다.

• Structural Engineering and Mechanics
• /
• 제65권3호
• /
• pp.315-325
• /
• 2018

This paper predicts the flexural behaviour of reinforced concrete (RC) beams strengthened with a precast strip of ultra-high performance fiber-reinforced concrete (UHPFRC). In the first phase, ultimate load capacity of preloaded and strengthened RC beams by UHPFRC was predicted by using various analytical models available in the literature. RC beams were preloaded under static loading approximately to 70%, 80% and 90% of ultimate load of control beams. The models such as modified Kaar and sectional analysis predicted the ultimate load in close agreement to the corresponding experimental observations. In the second phase, the famous fatigue life models such as Papakonstantinou model and Ferrier model were employed to predict the number of cycles to failure and the corresponding deflection. The models were used to predict the life of the (i) strengthened RC beams after subjecting them to different pre-loadings (70%, 80% and 90% of ultimate load) under static loading and (ii) strengthened RC beams after subjecting them to different preloading cycles under fatigue loading. In both the cases precast UHPFRC strip of 10 mm thickness is attached on the tension face. It is found that both the models predicted the number of cycles to failure and the corresponding deflection very close to the experimental values. It can be concluded that the models are found to be robust and reliable for cement based strengthening systems also. Further, the Wang model which is based on Palmgren-Miner's rule is employed to predict the no. of cycles to failure and it is found that the predicted values are in very good agreement with the corresponding experimental observations.

• 대한간호학회지
• /
• 제49권5호
• /
• pp.575-585
• /
• 2019

Purpose: The purpose of this study was to develop predictive models for pressure ulcer incidence using electronic health record (EHR) data and to compare their predictive validity performance indicators with that of the Braden Scale used in the study hospital. Methods: A retrospective case-control study was conducted in a tertiary teaching hospital in Korea. Data of 202 pressure ulcer patients and 14,705 non-pressure ulcer patients admitted between January 2015 and May 2016 were extracted from the EHRs. Three predictive models for pressure ulcer incidence were developed using logistic regression, Cox proportional hazards regression, and decision tree modeling. The predictive validity performance indicators of the three models were compared with those of the Braden Scale. Results: The logistic regression model was most efficient with a high area under the receiver operating characteristics curve (AUC) estimate of 0.97, followed by the decision tree model (AUC 0.95), Cox proportional hazards regression model (AUC 0.95), and the Braden Scale (AUC 0.82). Decreased mobility was the most significant factor in the logistic regression and Cox proportional hazards models, and the endotracheal tube was the most important factor in the decision tree model. Conclusion: Predictive validity performance indicators of the Braden Scale were lower than those of the logistic regression, Cox proportional hazards regression, and decision tree models. The models developed in this study can be used to develop a clinical decision support system that automatically assesses risk for pressure ulcers to aid nurses.