• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2014

In this paper, we present an effective sound classification system for recognizing the real-time context of a smartphone user. Our system avoids unnecessary consumption of limited computational resource by filtering both silence and white noise out of input sound data in the pre-processing step. It also improves the classification performance on low energy-level sounds by amplifying them as pre-processing. Moreover, for efficient learning and application of HMM classification models, our system executes the dimension reduction and discretization on the feature vectors through k-means clustering. We collected a large amount of 8 different type sound data from daily life in a university research building and then conducted experiments using them. Through these experiments, our system showed high classification performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.969-976
• /
• 2019

A lightweight artificial intelligence hardware has made great strides in many application areas. In general, a lightweight artificial intelligence system consist of lightweight artificial intelligence engine and preprocessor including feature selection, generation, extraction, and normalization. In order to achieve optimal performance in broad range of applications, lightweight artificial intelligence system needs to choose a good preprocessing function and set their respective hyper-parameters. This paper proposes a unified framework for a lightweight artificial intelligence system and utilization method for finding models with optimal performance to use on a given dataset. The proposed unified framework can easily generate a model combined with preprocessing functions and lightweight artificial intelligence engine. In performance evaluation using handwritten image dataset and fall detection dataset measured with inertial sensor, the proposed unified framework showed building optimal artificial intelligence models with over 90% test accuracy.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.401-410
• /
• 2021

Popular in discriminant classification analysis, k-nearest neighbor classification methods have limitations that do not reflect the local characteristic of the data, considering only the number of fixed neighbors. Considering the local structure of the data, the adaptive nearest neighbor method has been developed to select the number of neighbors. In the analysis of high-dimensional data, it is common to perform dimension reduction such as random projection techniques before using k-nearest neighbor classification. Recently, an ensemble technique has been developed that carefully combines the results of such random classifiers and makes final assignments by voting. In this paper, we propose a novel discriminant classification technique that combines adaptive nearest neighbor methods with random projection ensemble techniques for analysis on high-dimensional data. Through simulation and real-world data analyses, we confirm that the proposed method outperforms in terms of classification accuracy compared to the previously developed methods.

• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.667-684
• /
• 2022

Gene expression data present the level of mRNA abundance of each gene, and analyses of gene expressions have provided key ideas for understanding the mechanism of diseases and developing new drugs and therapies. Nowadays high-throughput technologies such as DNA microarray and RNA-sequencing enabled the simultaneous measurement of thousands of gene expressions, giving rise to a characteristic of gene expression data known as high dimensionality. Due to the high-dimensionality, learning models to analyze gene expression data are prone to overfitting problems, and to solve this issue, dimension reduction or feature selection techniques are commonly used as a preprocessing step. In particular, we can remove irrelevant and redundant genes and identify important genes using gene selection methods in the preprocessing step. Various gene selection methods have been developed in the context of machine learning so far. In this paper, we intensively review recent works on gene selection methods using machine learning approaches. In addition, the underlying difficulties with current gene selection methods as well as future research directions are discussed.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.252-258
• /
• 2022

In this study, we propose a method for analyzing students' understanding of probability and statistics in small lectures at universities. A computer-based test for probability and statistics was performed on 95 science and engineering college students. After dividing the students' responses into 7 clusters using the Robust PCA and the Gaussian mixture model, the achievement of each subject was analyzed for each cluster. High-ranking clusters generally showed high achievement on most topics except for statistical estimation, and low-achieving clusters showed strengths and weaknesses on different topics. Compared to the widely used PCA-based dimension reduction followed by clustering analysis, the proposed method showed each group's characteristics more clearly. The characteristics of each cluster can be used to develop an individualized learning strategy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.257-257
• /
• 2022

댐 건설은 홍수 및 가뭄에 대응하기 위한 구조적 방법으로써 우리나라와 같이 지표수에 의존적인 지역에서는 가용 수자원을 확보하기 위한 확실한 수단으로 활용되어왔다. 신규 댐의 건설은 대상 하천의 수리학적 특성에 큰 변화를 야기할 수 있으며, 댐의 안정성 및 하천의 하도보호를 위해 댐 주변의 수리적 특성의 변화에 대해서도 사전에 인지하여 설계 시 반영할 필요가 있다. 수공구조물 신설에 따라 변화되는 수리학적 특성을 분석하는 방법으로는 그 수단에 따라 상사법칙을 적용한 수리모형실험과 수치기법을 활용한 수치모형실험으로 나눌 수 있다. 본 연구에서는 수리모형실험을 통한 실험적 방법을 이용하여 댐 상하류 구간의 수리학적 특성을 분석하였다. 해당 실험은 한국농어촌공사 농어촌연구원의 대형수리모형실험시설에서 수행되었다. 적용대상 댐의 제원은 높이 약 70m, 길이 약 230m이며, 폭 55m의 여수로를 포함하는 구조로 설정하였다. 수리모형은 Froude 상사법칙을 적용하여 1/30 규모로 축소하였으며, 콘크리트 및 아크릴 재료를 이용하여 제작되었다. 댐 모형이 설치되는 하천구간은 댐 구조물을 포함하여 실규모를 기준으로 흐름방향으로 약 800m, 하폭방향으로 약 450m의 범위를 포함하도록 설계되었으며, 하류구간에 사행하천이 존재하는 것이 특징이다. 본 실험에서 유량은 총 12개의 펌프를 이용하여 공급되었으며, 최대 4cms에 해당하는 유량공급이 가능하도록 설계하였다. 공급유량은 정교한 절차에 의해 보정된 전자식 유량계를 통해 통제되었으며, 사용된 유량계의 허용오차는 약 0.5% 수준인 것으로 나타났다. 수위 측정은 오차범위 0.05mm 수준의 초음파 수위측정기를 이용하였으며, 유속측정은 약 0.5cm/s의 정확도를 지닌 3차원 전자기 유속계를 이용한 접촉식 측정과 흐름구조 가시화를 위한 비접촉식 입자추적기법을 병행하였다. 실험조건은 실규모 기준으로 방류량 3,000~5,000cms에 대해 수행하였으며, 각 방류량별 댐 상하류의 흐름패턴에 대해 정량적으로 분석하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.25-31
• /
• 2011

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction. Although PCA has been applied in many areas successfully, it is sensitive to outliers due to the use of sum-square-error. Several variants of PCA have been proposed to resolve the noise sensitivity and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA2, however, still can fall into a local optimum due to equal initial membership values for all data points. Another reason comes from the fact that RF-PCA2 is based on sum-square-error although fuzzy memberships are incorporated. In this paper, a variant of RF-PCA2 called RF-PCA3 is proposed. The proposed algorithm is based on the objective function of RF-PCA2. RF-PCA3 augments RF-PCA2 with the objective function of PCA and initial membership calculation using data distribution, which make RF-PCA3 to have more chance to converge on a better solution than that of RF-PCA2. RF-PCA3 outperforms RF-PCA2, which is demonstrated by experimental results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.173-178
• /
• 2014

In this study, we introduce ASM-based face recognition classifier and its design methodology with the aid of 2-dimensional 2-directional hybird preprocessing algorithm. Since the image of face recognition is easily affected by external environments, ASM(active shape model) as image preprocessing algorithm is used to resolve such problem. In particular, ASM is used widely for the purpose of feature extraction for human face. After extracting face image area by using ASM, the dimensionality of the extracted face image data is reduced by using $(2D)^2$hybrid preprocessing algorithm based on LDA and PCA. Face image data through preprocessing algorithm is used as input data for the design of the proposed polynomials based radial basis function neural network. Unlike as the case in existing neural networks, the proposed pattern classifier has the characteristics of a robust neural network and it is also superior from the view point of predictive ability as well as ability to resolve the problem of multi-dimensionality. The essential design parameters (the number of row eigenvectors, column eigenvectors, and clusters, and fuzzification coefficient) of the classifier are optimized by means of ABC(artificial bee colony) algorithm. The performance of the proposed classifier is quantified through yale and AT&T dataset widely used in the face recognition.