• Geomechanics and Engineering
• /
• v.35 no.1
• /
• pp.67-80
• /
• 2023

Due to the nature of the conjunctive Cone Penetration Test(CPT), which does not verify the actual sample directly, geotechnical engineers commonly classify the underground geomaterials using CPT results with the classification diagrams proposed by various researchers. However, such classification diagrams may fail to reflect local geotechnical characteristics, potentially resulting in misclassification that does not align with the actual stratification in regions with strong local features. To address this, this paper presents an objective method for more accurate local CPT soil classification criteria, which utilizes C4.5 decision tree models trained with the CPT results from the clay-dominant southern coast of Korea and the sand-dominant region in South Carolina, USA. The results and analyses demonstrate that the C4.5 algorithm, in conjunction with oversampling, outlier removal, and pruning methods, can enhance and optimize the decision tree-based CPT soil classification model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.139-147
• /
• 2023

The metal bush assembling process is a process of inserting and compressing a metal bush that serves to reduce the occurrence of noise and stable compression in the rotating section. In the metal bush assembly process, the head diameter defect and placement defect of the metal bush occur due to metal bush omission, non-pressing, and poor press-fitting. Among these causes of defects, it is intended to prevent defects due to omission of the metal bush by using signals from sensors attached to the facility. In particular, a metal bush omission is predicted through various data mining techniques using left load cell value, right load cell value, current, and voltage as independent variables. In the case of metal bush omission defect, it is difficult to get defect data, resulting in data imbalance. Data imbalance refers to a case where there is a large difference in the number of data belonging to each class, which can be a problem when performing classification prediction. In order to solve the problem caused by data imbalance, oversampling and composite sampling techniques were applied in this study. In addition, simulated annealing was applied for optimization of parameters related to sampling and hyper-parameters of data mining techniques used for bush omission prediction. In this study, the metal bush omission was predicted using the actual data of M manufacturing company, and the classification performance was examined. All applied techniques showed excellent results, and in particular, the proposed methods, the method of mixing Random Forest and SA, and the method of mixing MLP and SA, showed better results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.505-508
• /
• 2024

금융산업의 디지털 전환은 사용자에게 편리함을 제공하지만 기존에 존재하지 않던 보안상 취약점을 유발했다. 이러한 문제를 해결하기 위해 기계학습 기술을 적용한 사기 거래 탐지 시스템에 대한 연구가 활발하게 이루어지고 있다. 하지만 모델 학습 과정에서 발생하는 데이터 불균형 문제로 인해 오랜 시간이 소요되고 탐지 성능이 저하되는 문제가 있다. 본 논문에서는 실시간 데이터 오버 샘플링을 통해 이상 거래 탐지 시 데이터 불균형 문제를 해결하고 모델 학습 시간을 개선한 새로운 이상 거래 탐지 시스템(Fraud Detection System, FDS)을 제안한다. 본 논문에서 제안하는 SMOTE(Synthetic Minority Oversampling Technique)를 적용한 LSTM(Long-Short Term Memory) 알고리즘 기반의 FDS 프레임워크는 종래의 LSTM 알고리즘 기반의 FDS 모델과 비교했을 때, 데이터 사이즈가 96.5% 감소했으며, 정밀도, 재현율, F1-Score 가 34.81%, 11.14%, 22.51% 개선되었다.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1720-1728
• /
• 2022

The industrial 4.0 era has been opened with the development of artificial intelligence technology, and the realization of smart farms incorporating ICT technology is receiving great attention in the livestock industry. Among them, the quality management technology of livestock products and livestock operations incorporating computer vision-based artificial intelligence technology represent key technologies. However, the insufficient number of livestock image data for artificial intelligence model training and the severely unbalanced ratio of labels for recognizing a specific defective state are major obstacles to the related research and technology development. To overcome these problems, in this study, combining oversampling and adversarial case generation techniques is proposed as a method necessary to effectively utilizing small data labels for successful defect detection. In addition, experiments comparing performance and time cost of the applicable techniques were conducted. Through experiments, we confirm the validity of the proposed methods and draw utilization strategies from the study results.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.173-198
• /
• 2016

Financial distress can damage stakeholders and even lead to significant social costs. Thus, financial distress prediction is an important issue in macroeconomics. However, most existing studies on building a financial distress prediction model have only considered idiosyncratic risk factors without considering systematic risk factors. In this study, we propose a prediction model that considers both the idiosyncratic risk based on a financial ratio and the systematic risk based on a business cycle. Ultimately, we build several IT artifacts associated with financial ratio and add them to the idiosyncratic risk factors as well as address the imbalanced data problem by using an oversampling technique and synthetic minority oversampling technique (SMOTE) to ensure good performance. When considering systematic risk, our study ensures that each data set consists of both financially distressed companies and financially sound companies in each business cycle phase. We conducted several experiments that change the initial imbalanced sample ratio between the two company groups into a 1:1 sample ratio using SMOTE and compared the prediction results from the individual data set. We also predicted data sets from the subsequent business cycle phase as a test set through a built prediction model that used business contraction phase data sets, and then we compared previous prediction performance and subsequent prediction performance. Thus, our findings can provide insights into making rational decisions for stakeholders that are experiencing an economic crisis.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.449-456
• /
• 2021

An intrusion detection system is a technology that detects abnormal behaviors that violate security, and detects abnormal operations and prevents system attacks. Existing intrusion detection systems have been designed using statistical analysis or anomaly detection techniques for traffic patterns, but modern systems generate a variety of traffic different from existing systems due to rapidly growing technologies, so the existing methods have limitations. In order to overcome this limitation, study on intrusion detection methods applying various machine learning techniques is being actively conducted. In this study, a comparative study was conducted on data preprocessing techniques that can improve the accuracy of anomaly detection using NGIDS-DS (Next Generation IDS Database) generated by simulation equipment for traffic in various network environments. Padding and sliding window were used as data preprocessing, and an oversampling technique with Adversarial Auto-Encoder (AAE) was applied to solve the problem of imbalance between the normal data rate and the abnormal data rate. In addition, the performance improvement of detection accuracy was confirmed by using Skip-gram among the Word2Vec techniques that can extract feature vectors of preprocessed sequence data. PCA-SVM and GRU were used as models for comparative experiments, and the experimental results showed better performance when sliding window, skip-gram, AAE, and GRU were applied.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.8
• /
• pp.1226-1237
• /
• 1993

For data transmission over strictly band-limited non-ideal channels, different types of filters with arbitrary responses are needed. In this paper. we proposed two efficient techniques for the design of such FIR filters whose response is specified in either the time or the frequency domain. In particular when a fractionally-spaced structure is used for the transceiver, these filters can be efficiently designed by making use of characteristics of oversampling. By using a minimum mean-squared error criterion, we design a fractionally-spaced FIR filter whose frequency response can be controlled without affecting the output error. With proper specification of the shape of the additive noise signals, for example, the design results in a receiver filter that can perform compromise equalization as well as phase splitting filtering for QAM demodulation. The second method ad-dresses the design of an FIR filter whose desired response can be arbitrarily specified in the frequency domain. For optimum design, we use an iterative optimization technique based on a weighted least mean square algorithm. A new adaptation algorithm for updating the weighting function is proposed for fast and stable convergence. It is shown that these two independent methods can be efficiently combined together for more complex applications.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.141-148
• /
• 2012

A design of a 32-bit fourth-stage decimation filter decimation filter used in sigma-delta analog-to-digital (A/D) converter is proposed in this work. A four-stage decimation filter with down-sampling factor of 512 and 32-bit output is developed. A multi-stage cascaded integrator-comb (CIC) filter, which reduces the sampling rate by 64, is used in the first stage. Three half-band FIR filters are used after the CIC filter, each of which reduces the sampling rate by two. The pipeline structure is applied in the CIC filter to reduce the power consumption of the CIC. The Canonic Signed Digit (CSD) arithmetic is used to optimize the multiplier structure of the FIR filter. This filter is implemented based on a semi-custom design flow and a 130nm CMOS standard cell library. This decimation filter operates at 98.304 MHz and provides 32-bit output data at an audio frequency of 192 kHz with power consumption of $697{\mu}W$. In comparison to the previous work, this design shows a higher performance in resolution, operation frequency and decimation factor with lower power consumption and small logic utilization.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2024

The introduction of Smart Factories has transformed manufacturing towards more objective and efficient line management. However, most companies are not effectively utilizing the vast amount of sensor data collected every second. This study aims to use this data to predict product quality and manage production processes efficiently. Due to security issues, specific sensor data could not be verified, so semiconductor process-related training data from the "SAMSUNG SDS Brightics AI" site was used. Data preprocessing, including removing missing values, outliers, scaling, and feature elimination, was crucial for optimal sensor data. Oversampling was used to balance the imbalanced training dataset. The SVM (rbf) model achieved high performance (Accuracy: 97.07%, GM: 96.61%), surpassing the MLP model implemented by "SAMSUNG SDS Brightics AI". This research can be applied to various topics, such as predicting component lifecycles and process conditions.