• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1186-1207
• /
• 2024

Bearings are one of the main components of mechanical equipment and one of the primary components prone to faults. Therefore, conducting fault diagnosis on bearings is a key issue in mechanical equipment research. Belief rule base (BRB) is essentially an expert system that effectively integrates qualitative and quantitative information, demonstrating excellent performance in fault diagnosis. However, class imbalance often occurs in the diagnosis task, which poses challenges to the diagnosis. Models with interpretability can enhance decision-makers' trust in the output results. However, the randomness in the optimization process can undermine interpretability, thereby reducing the level of trustworthiness in the results. Therefore, a hierarchical BRB model based on extreme gradient boosting (XGBoost) feature selection with interpretability (HFS-IBRB) is proposed in this paper. Utilizing a main BRB alongside multiple sub-BRBs allows for the conversion of a multi-classification challenge into several distinct binary classification tasks, thereby leading to enhanced accuracy. By incorporating interpretability constraints into the model, interpretability is effectively ensured. Finally, the case study of the actual dataset of bearing fault diagnosis demonstrates the ability of the HFS-IBRB model to perform accurate and interpretable diagnosis.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.83-88
• /
• 2024

In this research, we propose a Semi-Supervised learning based railroad surface defect detection method. The Resnet50 model, pretrained on ImageNet, was employed for the training. Data without labels are randomly selected, and then labeled to train the ResNet50 model. The trained model is used to predict the results of the remaining unlabeled training data. The predicted values exceeding a certain threshold are selected, sorted in descending order, and added to the training data. Pseudo-labeling is performed based on the class with the highest probability during this process. An experiment was conducted to assess the overall class classification performance based on the initial number of labeled data. The results showed an accuracy of 98% at best with less than 10% labeled training data compared to the overall training data.

• Journal of Digital Contents Society
• /
• v.14 no.3
• /
• pp.343-348
• /
• 2013

The purpose of this paper is to explore how effectively can learners improve their written skills in English language classrooms with the application of internet tools and software. First, the study compares and analyzes existing research on English writing and describes research background. Second, the study describes how internet tools can be used effectively in the English writing classrooms. For example, learners pick up vocabulary on the internet bulletin board and create sentences using the vocabulary. Third, the study analyzed changes in learners' in-class attitudes towards software and internet tools using comparative measures of performance. Unlike with offline instrumented classes, the in-class application of diverse software and internet tools such as websites and IRC (Internet Relay Chat) had a major impact on the improvement of learners' writing skills.

• Proceedings of the KSRS Conference
• /
• 2008.03a
• /
• pp.195-200
• /
• 2008

The accuracy of classifying pixels in HIRIS images is usually degraded by noisy bands since noisy bands may deform the typical shape of spectral reflectance. Proposed in this paper is a statistical method for noisy band removal which mainly makes use of the correlation coefficients between bands. Considering each band as a random variable, the correlation coefficient measures the strength and direction of a linear relationship between two random variables. While the correlation between two signal bands is high, existence of a noisy band will produce a low correlation due to ill-correlativeness and undirectedness. The application of the correlation coefficient as a measure for detecting noisy bands is under a two-pass screening scheme. This method is independent of the prior knowledge of the sensor or the cause resulted in the noise. The classification in this experiment uses the unsupervised k-nearest neighbor algorithm in accordance with the well-accepted Euclidean distance measure and the spectral angle mapper measure. This paper also proposes a hierarchical combination of these measures for spectral matching. Finally, a separability assessment based on the between-class and within-class scatter matrices is followed to evaluate the performance.

• Asia-Pacific Journal of Business
• /
• v.13 no.4
• /
• pp.45-59
• /
• 2022

Purpose - This study investigates the performance of investment strategies incorporating estimated stock market cycle based on a lead-lag relationship between business cycle and stock market cycle, thereby deriving empirical implications on risk management. Design/methodology/approach - The data period ranges from June 1953 to September 2022 and de-trended short rate, term spread, credit spread, stock market volatility are considered as major input variables to estimate business cycle and stock market cycle by applying probit model. Based on the estimated stock market cycle, two types of strategies are constructed and their performance relative to the benchmark is empirically examined. Findings Two types of strategies based on stock market cycle are considered: The first strategy is to long(short) on stocks when stock market stage is expected to be an expansion(a recession), and the second one is to long on stocks(bonds) when expecting an expansion(a recession). The empirical results show that the strategies based on stock market cycle outperforms a simple buy and hold strategy in both in-sample and out-of-sample investigation. Also the out-of-sample evidence suggests that the second strategy which is in line with asset allocation is more profitable than the first one. Research implications or Originality The strategies considered in this study are based on the estimated stock market cycle which only depends on a few easily available financial variables, thereby making easier to establish such a strategy. It implies that investors enhance investment performance by constructing a relatively simple trading strategies if they set their position on stocks or choose which asset class to buy conditioning on stock market cycle.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Structural Engineering and Mechanics
• /
• v.52 no.3
• /
• pp.613-632
• /
• 2014

In the early design stage of ships, the two most important structural analyses are performed to identify the structural capacity and safety. The first step is called global strength analysis (longitudinal strength analysis or hull girder strength analysis) and the second step is local buckling analysis (stiffened panel strength analysis). This paper deals with the ultimate strength performance of Arctic Sea Route-going commercial ships considering the effect of low temperature. In this study, two types of structural analyses are performed in Arctic sea conditions. Three types of ship namely oil tanker, bulk carrier and container ship with four different sizes (in total 12 vessels) are tested in four low temperatures (-20, -40, -60 and $-800^{\circ}C$), which are based on the Arctic environment and room temperature ($20^{\circ}C$). The ultimate strength performance is analysed with ALPS/HULL progressive hull collapse analysis code for ship hulls, then ALPS/ULSAP supersize finite element method for stiffened panels. The obtained results are summarised in terms of temperature, vessel type, vessel size, loading type and other effects. The important insights and outcomes are documented.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.11
• /
• pp.1602-1607
• /
• 2014

This paper deals with the design and property analysis of 7kW-class small-scaled superconducting Linear Synchronous Motor (LSM) and testing equipment for a number of performance pre-tests prior to the development of coreless-type superconducting LSM suitable for 600km/h very high speed train. First, the basic design and property analysis are conducted before developing a small-scaled superconducting LSM model with 2-pole superconducting electromagnets, and additionally the cost-down design of the superconducting electromagnets is conducted to use less high-Tc superconducting wire. Finally, the superconducting magnet coil span is selected at 120mm, and input ground armature current of 670Aturns is required to produce 44.7N of thrust based on research findings.

• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.119-129
• /
• 2023

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.