• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.9
• /
• pp.21-28
• /
• 1998

In this paper, we propose an efficient linear ordering algorithm, called LIME, for netlist partitioning. LIME incrementally merges two segments which are selected based on the proposed cost function until only one segment remains. The final resultant segment then corresponds to the linear ordering. LIME also runs extremely fast, because it exploits sparsity of netlist. Compared to the earlier work, the proposed algorithm is eight times faster in producing linear ordering and yields an average of 17% improvement for the multi-way scaled cost partitioning.

• The Journal of Information Systems
• /
• v.29 no.3
• /
• pp.119-144
• /
• 2020

Purpose Real estate usually takes charge of the highest proportion of physical properties which individual, organizations, and government hold and instability of real estate market affects the economic condition seriously for each economic subject. Consequently, practices for predicting the real estate market have attention for various reasons, such as financial investment, administrative convenience, and wealth management. Additionally, development of machine learning algorithms and computing hardware enhances the expectation for more precise and useful prediction models in real estate market. Design/methodology/approach In response to the demand, this paper aims to provide a framework for forecasting the real estate market with machine learning algorithms. The framework consists of demonstrating the prediction efficiency of each machine learning algorithm, interpreting the interior feature effects of prediction model with a state-of-art algorithm, LIME(Local Interpretable Model-agnostic Explanation), and comparing the results in different cities. Findings This research could not only enhance the academic base for information system and real estate fields, but also resolve information asymmetry on real estate market among economic subjects. This research revealed that macroeconomic indicators, real estate-related indicators, and Google Trends search indexes can predict real-estate prices quite well.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.86-98
• /
• 2022

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

• Korean Journal of Computational Design and Engineering
• /
• v.8 no.1
• /
• pp.10-18
• /
• 2003

FEM (Finite Element Method) is a fundamental numerical analysis technique in wide spread use in engineering application. As the solving time occupies small portion of entire FEM analysis time because of development of hardware, the relative lime to the whole analysis time to make mesh mod-els is growing. In particular, in the case of stiffeners such as features attached to plate in ship structure, the line constraints are imposed on mesh model together with other constraints such as holes. To auto-matically generate two dimensional quadrilateral mesh with the line constraints, an algorithm is pro-posed based on the constrained Delaunay triangulation and Q-Morph algorithm in which the line constraints are not considered. The performance of the proposed algorithm is evaluated. And some numerical results of our proposed algorithm ate presented.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.163-165
• /
• 2002

In this paper a new numerical algorithm for fault distance calculation and arcing fault recognition based on one terminal data and derived in lime domain is presented. The algorithm is derived for the case of most frequent single-phase line to ground fault. The faulted phase voltage at the fault place is modeled as a serial connection of fault resistance and arc voltage. The fault distance and arc voltage amplitude are estimated using Least Error Squares Technique. The algorithm can be applied for distance protection, intelligent autoreclosure and for fault location. The results of algorithm tested through computer simulation are given.

• Journal of Internet Computing and Services
• /
• v.5 no.5
• /
• pp.119-127
• /
• 2004

As, the development of language-based programming environment, a study on incremental parsing has become an essential part. The purpose of this paper is to show the more efficient incremental parsing algorithm than earlier one that demands parsing speed and memorizing space too much. This paper suggests the threaded tree construction algorithm not using stack. In addition, to remove the reparsing process, it proposes the algorithm for creation node and construction incremental threaded tree not using stack.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.1
• /
• pp.1155-1161
• /
• 2001

We propose an adaptive nonlinear control algorithm for high precision tracking and stabilization of LOS(Line-of-Sight). The friction parameters of the LOS gimbal are estimated by off-line evolutionary strategy and the friction is compensated by estimated friction compensator. Especially, as the nonlinear control input in a small tracking error zone is enlarged by the nonlinear function, the steady state error is significantly reduced. The proposed algorithm is a direct adaptive control method based on the Lyapunov stability theory, and its convergence is guaranteed under the limited modeling error or torque disturbance. The performance of the pro-posed algorithm is verified by computer simulation on the LOS gimbal model of a moving vehicle.