• Journal of the Korean Mathematical Society
• /
• v.59 no.2
• /
• pp.217-233
• /
• 2022

Although machine learning shows state-of-the-art performance in a variety of fields, it is short a theoretical understanding of how machine learning works. Recently, theoretical approaches are actively being studied, and there are results for one of them, margin and its distribution. In this paper, especially we focused on the role of margin in the perturbations of inputs and parameters. We show a generalization bound for two cases, a linear model for binary classification and neural networks for multi-classification, when the inputs have normal distributed random noises. The additional generalization term caused by random noises is related to margin and exponentially inversely proportional to the noise level for binary classification. And in neural networks, the additional generalization term depends on (input dimension) × (norms of input and weights). For these results, we used the PAC-Bayesian framework. This paper is considering random noises and margin together, and it will be helpful to a better understanding of model sensitivity and the construction of robust generalization.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.297-299
• /
• 2021

Text classification is one of the popular tasks in Natural Language Processing (NLP) used to classify text or document applications such as sentiment analysis and email filtering. Nowadays, state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms are the core engine used to perform these classification tasks with high accuracy, and they show satisfying results. This paper conducts a benchmarking performance's analysis of multiple SOTA algorithms on the first known labeled Korean voice phishing dataset called KorCCVi. Experimental results reveal performed on a test set of 366 samples reveal which algorithm performs the best considering the training time and metrics such as accuracy and F1 score.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.628-631
• /
• 2023

We present a new approach to evaluate the generated texts by Large Language Models (LLMs) for meme classification. Analyzing an image with embedded texts, i.e. meme, is challenging, even for existing state-of-the-art computer vision models. By leveraging large image-to-text models, we can extract image descriptions that can be used in other tasks, such as classification. In our methodology, we first generate image captions using BLIP-2 models. Using these captions, we use GPT-4 to evaluate the relationship between the caption and the meme text. The results show that OPT_6.7B provides a better rating than other LLMs, suggesting that the proposed method has a potential for meme classification.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1517-1520
• /
• 2003

Generally, the environment we want to apply classifier system to is composed of several state spaces. So in this paper, we propose the layered classifier system having multifarious rule bases. From sensor's inputs, the lower layer of the layered classifier system learns strategies for each environmental state space. The higher layer learns how to allot each rule base of the strategy for environmental state space properly. To evaluate the proposed architecture of classifier system, we designed virtual environment having multifarious state spaces and from the analysis of the experimental results, we affirm that layered classifier system could find better strategies during a little time than other established classifier system's findings.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.3
• /
• pp.210-216
• /
• 2015

This paper proposes a method to determine vehicle driving state using the driving characteristics index. This index is a quantitative value to classify the driving state of a vehicle with its velocity and heading angle in that instant. It can classify driving state into straight driving, lane changing driving and curve driving in real time. In addition, the number of positional information is movably set up by designed region of interest. The proposed index is expressed on the stable driving states. Each driving state has characteristic tendency, and is compared with index distributional areas. The proposed method is verified by the actual driving experiment on the KATECH proving ground.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.07a
• /
• pp.645-650
• /
• 2000

The discrete wavelet transform is utilized as processing of neural network(NN) to identifying aging state of internal partial discharge in transformer. The discrete wavelet transform is used to produce wavelet coefficients which are used for classification. The mean values of the wavelet coefficients are input into an back-propagation neural network. The networks, after training, can decide if the test signals is aging early state or aging last state, or normal state.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.4 no.1
• /
• pp.23-28
• /
• 2002

Sets of weather variables for estimation of LWD were evaluated using CART(Classification And Regression Tree) models. Input variables were sets of hourly observations of air temperature at 0.3-m and 1.5-m height, relative humidity(RH), and wind speed that were obtained from May to September in 1997, 1998, and 1999 at 15 weather stations in iowa, Illinois, and Nebraska, USA. A model that included air temperature at 0.3-m height, RH, and wind speed showed the lowest misidentification rate for wetness. The model estimated presence or absence of wetness more accurately (85.5%) than the CART/SLD model (84.7%) proposed by Gleason et al. (1994). This slight improvement, however, was insufficient to justify the use of our model, which requires additional measurements, in preference to the CART/SLD model. This study demonstrated that the use of measurements of temperature, humidity, and wind from automated stations was sufficient to make LWD estimations of reasonable accuracy when the CART/SLD model was used. Therefore, implementation of crop disease-warning systems may be facilitated by application of the CART/SLD model that inputs readily obtainable weather observations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.3
• /
• pp.395-400
• /
• 2011

In this paper, we propose an study of the facial emotion recognition considering the dynamical variation of emotional state in facial image sequences. The proposed system consists of two main step: facial image based emotional feature extraction and emotional state classification/recognition. At first, we propose a method for extracting and analyzing the emotional feature region using a combination of Active Shape Model (ASM) and Facial Action Units (FAUs). And then, it is proposed that emotional state classification and recognition method based on Hidden Markov Model (HMM) type of dynamic Bayesian network. Also, we adopt a Harmony Search (HS) algorithm based heuristic optimization procedure in a parameter learning of HMM in order to classify the emotional state more accurately. By using all these methods, we construct the emotion recognition system based on variations of the dynamic facial image sequence and make an attempt at improvement of the recognition performance.