• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.624-626
• /
• 2023

Credit scoring is a technique used by financial institutions to assess the creditworthiness of potential borrowers. This involves evaluating a borrower's credit history to predict the likelihood of defaulting on a loan. This paper presents an ensemble of two Transformer based models within a framework for discriminating the default risk of loan applications in the field of credit scoring. The first model is FinBERT, a pretrained NLP model to analyze sentiment of financial text. The second model is FT-Transformer, a simple adaptation of the Transformer architecture for the tabular domain. Both models are trained on the same underlying data set, with the only difference being the representation of the data. This multi-modal approach allows us to leverage the unique capabilities of each model and potentially uncover insights that may not be apparent when using a single model alone. We compare our model with two famous ensemble-based models, Random Forest and Extreme Gradient Boosting.

• 한국지리정보학회지
• /
• 제27권1호
• /
• pp.115-127
• /
• 2024

본 연구는 Transformer 모듈을 기반으로 다양한 구조의 모델을 구성하고, 토지피복 분류를 수행하여 Transformer 모듈의 활용방안 검토를 목적으로 하였다. 토지피복 분류를 위한 딥러닝 모델은 CNN 구조를 가진 Unet 모델을 베이스 모델로 선정하였으며, 모델의 인코더 및 디코더 부분을 Transformer 모듈과 조합하여 총 4가지 딥러닝 모델을 구축하였다. 딥러닝 모델의 학습과정에서 일반화 성능 평가를 위해 같은 학습조건으로 10회 반복하여 학습을 진행하였다. 딥러닝 모델의 분류 정확도 평가결과, 모델의 인코더 및 디코더 구조 모두 Transformer 모듈을 활용한 D모델이 전체 정확도 평균 약 89.4%, Kappa 평균 약 73.2%로 가장 높은 정확도를 보였다. 학습 소요시간 측면에서는 CNN 기반의 모델이 가장 효율적이었으나 Transformer 기반의 모델을 활용할 경우, 분류 정확도가 Kappa 기준 평균 0.5% 개선되었다. 차후, CNN 모델과 Transformer의 결합과정에서 하이퍼파라미터 조절과 이미지 패치사이즈 조절 등 다양한 변수들을 고려하여 모델을 고도화 할 필요가 있다고 판단된다. 토지피복 분류과정에서 모든 모델이 공통적으로 발생한 문제점은 소규모 객체들의 탐지가 어려운 점이었다. 이러한 오분류 현상의 개선을 위해서는 고해상도 입력자료의 활용방안 검토와 함께 지형 정보 및 질감 정보를 포함한 다차원적 데이터 통합이 필요할 것으로 판단된다.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.17-25
• /
• 2023

본 논문에서는 매개변수가 더 적고, 빠르게 추정 가능한 MobileViT 기반 모델을 통해 사람 자세 추정 과업을 수행할 수 있는 모델을 제안한다. 기반 모델은 합성곱 신경망의 특징과 Vision Transformer의 특징이 결합한 구조를 통해 경량화된 성능을 입증한다. 본 연구에서 주요 매커니즘이 되는 Transformer는 그 기반의 모델들이 컴퓨터 비전 분야에서도 합성곱 신경망 기반의 모델들 대비 더 나은 성능을 보이며, 영향력이 커지게 되었다. 이는 사람 자세 추정 과업에서도 동일한 상황이며, Vision Transformer기반의 ViTPose가 COCO, OCHuman, MPII 등 사람 자세 추정 벤치마크에서 모두 최고 성능을 지키고 있는 것이 그 적절한 예시이다. 하지만 Vision Transformer는 매개변수의 수가 많고 상대적으로 많은 연산량을 요구하는 무거운 모델 구조를 가지고 있기 때문에, 학습에 있어 사용자에게 많은 비용을 야기시킨다. 이에 기반 모델은 Vision Transformer가 많은 계산량을 요구하는 부족한 Inductive Bias 계산 문제를 합성곱 신경망 구조를 통한 Local Representation으로 극복하였다. 최종적으로, 제안 모델은 MS COCO 사람 자세 추정 벤치마크에서 제공하는 Validation Set으로 ViTPose 대비 각각 5분의 1과 9분의 1만큼의 3.28GFLOPs, 972만 매개변수를 나타내었고, 69.4 Mean Average Precision을 달성하여 상대적으로 우수한 성능을 보였다.

• 설비공학논문집
• /
• 제22권8호
• /
• pp.515-522
• /
• 2010

In order to improve the efficiency of a transformer cooling system, the intelligent algorithm was developed. The intelligent algorithm is composed of a setpoint algorithm and a control algorithm. The setpoint algorithm was developed by the neural network, and the control algorithm was developed by the fuzzy logic. These algorithms were used for the control of a blower and an oil pump of the transformer cooling system. In order to analyse performances of these algorithms, the dynamic model of a transformer cooling system was used. Based on various performance tests, energy savings and stable controls of a transformer cooling system were observed. Therefore, control algorithms developed for this study may be effectively used for the control of a transformer cooling system.

• 대한전기학회논문지:전력기술부문A
• /
• 제51권12호
• /
• pp.624-629
• /
• 2002

This paper presents the first Simulation model using EMTDC program to analyze the electrified train voltage distribution characteristics in ac auto-transformer 1110 railroads. In general, all of the electrified train supply system has the characteristics that the train supply line is a naturally non-symmetrical and unbalanced system. Also, it is needed to model the Scott transformer which invert the balanced 3-phase quantity into 2-phase. Therefore, the general simulation methodology using previous simplified equivalent circuit or RMS based program can't obtain the accurate results to reflect the real-time operation because these methodology is basically assumed on completely 3-phase balanced system. To overcome these defects, in this paper, the EMTDC simulation model to analysis the completely electrified railroad system with Scott transformer and AC auto-transformer is presented. Also, the correctness of EMTDC modeling is confirmed by the old basic concepts and we think that this EMTDC model has the future powerful capability for application of railroad system analysis.

• 한국철도학회논문집
• /
• 제5권4호
• /
• pp.253-259
• /
• 2002

This paper presents the first simulation model using EMTDC program to analyze the electrified train voltage distribution characteristics in ac auto-transformer fed railroads. In general, all of the electrified train supply system has the characteristics that the train supply line is a naturally non-symmetrical and unbalanced system. Also, it is needed to model the Scott transformer which invert the balanced 3-phase quantity into 2-phase. Therefore, the general simulation methodology using previous simplified equivalent circuit or RMS based program can't obtain the accurate results to reflect the real-time operation because these methodology is basically assumed on completely 3-phase balanced system. To overcome these defects, in this paper, the EMTDC simulation model to analysis the completely electrified railroad system with Scott transformer and AC auto-transformer is presented. Also, the correctness of EMTDC modeling is confirmed by the old basic concepts and we think that this EMTDC model has the future powerful capability for application of railroad system analysis.

• 한국기계가공학회지
• /
• 제20권7호
• /
• pp.48-57
• /
• 2021

The main research content of this paper is to evaluate the structural integrity and the cooling performance of 4250 kVA power transformer with ONAN(Oil Natural and Air Natural) mode. The dynamic analysis is used to verify the structural safety of the transformer by seismic loading. The transformer structure is simplified and NX software is used to build a three-dimensional model, and ANSYS commercial software is used to calculate the stress and deformation by applying corresponding load. The analysis result was evaluated whether it satisfies the design requirements according to the IEEE Std 693 standard. In terms of thermal analysis to evaluate the cooling performance, the thermal physical model is used to calculate the heat exchange between the radiator and the tank in the steady state, and the result is input into the Fluent software to calculate the internal temperature field of the transformer tank, which reduces the calculation cost of thermal fluid. Comparing the simulated hot spot temperature and top oil temperature of the transformer with the calculation results of the IEC60076 classic model, it is found that the error is only 1.9%.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 B
• /
• pp.607-612
• /
• 2002

This paper presents the first domestic model product of hybrid Insulation low-loss type pole transformer, with increased overload ability, increased life, reduced loss, focusing improved short-circuit characteristics. The capacity of this transformer is 100 KVZ, rates first voltage 13200 V and secondary voltage 230/115 type. The volume of model transformer that was produced in high temperature using hybrid insulation can be reduced to 10-20% in comparison with that of present transformer with the same capacity. In this paper, we did short-circuit test and tested general characteristics of model transformer. In addition, we suggested design application new concept and methods thorough this experiment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 추계학술대회 논문집 전력기술부문
• /
• pp.151-153
• /
• 2006

This paper describes the transient phenomena considering transformer model in combined distribution systems with power cables. To evaluate the overvoltage, the change of transformer model and system structure are considered. Transformer parameters calculated by BCTRAN of EMTP are considered to evaluate surge generation in underground distribution systems when underground distribution system has various parameters. It is evaluated that overvoltage value increases and decreases according to the structure of system. However it is confirmed that there is not much effect to overvoltage as transformer is operated in distribution line.

• 스마트미디어저널
• /
• 제13권4호
• /
• pp.9-15
• /
• 2024

Tree-based algorithms have been the dominant methods used build a prediction model for tabular data. This also includes personal credit data. However, they are limited to compatibility with categorical and numerical data only, and also do not capture information of the relationship between other features. In this work, we proposed an ensemble model using the Transformer architecture that includes text features and harness the self-attention mechanism to tackle the feature relationships limitation. We describe a text formatter module, that converts the original tabular data into sentence data that is fed into FinBERT along with other text features. Furthermore, we employed FT-Transformer that train with the original tabular data. We evaluate this multi-modal approach with two popular tree-based algorithms known as, Random Forest and Extreme Gradient Boosting, XGBoost and TabTransformer. Our proposed method shows superior Default Recall, F1 score and AUC results across two public data sets. Our results are significant for financial institutions to reduce the risk of financial loss regarding defaulters.