• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• Journal of Digital Contents Society
• /
• v.19 no.3
• /
• pp.435-443
• /
• 2018

Recently, with the explosive development of computing power, various methods such as RNN and CNN have been proposed under the name of Deep Learning, which solve many problems of Computer Vision have. The Generative Adversarial Network, released in 2014, showed that the problem of computer vision can be sufficiently solved in unsupervised learning, and the generation domain can also be studied using learned generators. GAN is being developed in various forms in combination with various models. Machine learning has difficulty in collecting data. If it is too large, it is difficult to refine the effective data set by removing the noise. If it is too small, the small difference becomes too big noise, and learning is not easy. In this paper, we apply a deep CNN model for extracting facial region in image frame to GAN model as a preprocessing filter, and propose a method to produce composite images of various facial expressions by stably learning with limited collection data of two persons.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.3
• /
• pp.346-355
• /
• 2016

In this paper, we propose a method to analyze the clusters of RF threats emitting electrical signals based on collected signal variables in integrated electronic warfare environments. We first analyze the signal variables collected by an electronic warfare receiver, and construct a model based on variables showing the properties of threats. To visualize the distribution of RF threats and reversely identify them, we use k-means clustering algorithm and self-organizing map (SOM) algorithm, which are belonging to unsupervised learning techniques. Through the resulting model compiled by k-means clustering and SOM algorithms, the RF threats can be classified into one of the distribution of RF threats. In an experiment, we measure the accuracy of classification results using the algorithms, and verify the resulting model that could be used to visually recognize the distribution of RF threats.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.2
• /
• pp.321-330
• /
• 2019

Prevention of corporate confidentiality leakage by insiders in enterprises is an essential task for the survival of enterprises. In order to prevent information leakage by insiders, companies have adopted security solutions, but there is a limit to effectively detect abnormal behavior of insiders with access privileges. In this study, we use the Unsupervised Learning algorithm of the machine learning technique to effectively and efficiently cluster the normal and abnormal access logs of the worker's work screen in the manufacturing information system, which includes the company's product manufacturing history and quality information. We propose an optimal feature selection model for anomaly detection by studying clustering methods.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2C
• /
• pp.208-218
• /
• 2006

In this paper, we introduce the creation methods of attack detection model using data mining technologies that can classify the latest attack types, and can detect the modification of existing attacks as well as the novel attacks. Also, we evaluate comparatively these attack detection models in the view of detection accuracy and detection time. As the important factors for creating detection models, there are data, attribute, and detection algorithm. Thus, we used NetFlow data gathered at the real network, and KDD Cup 1999 data for the experiment in large quantities. And for attribute selection, we used a heuristic method and a theoretical method using decision tree algorithm. We evaluate comparatively detection models using a single supervised/unsupervised data mining approach and a combined supervised data mining approach. As a result, although a combined supervised data mining approach required more modeling time, it had better detection rate. All models using data mining techniques could detect the attacks within 1 second, thus these approaches could prove the real-time detection. Also, our experimental results for anomaly detection showed that our approaches provided the detection possibility for novel attack, and especially SOM model provided the additional information about existing attack that is similar to novel attack.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.2
• /
• pp.102-110
• /
• 2017

Current word sense disambiguation techniques employ various machine learning-based methods. Various approaches have been proposed to address this problem, including the knowledge base approach. This approach defines the sense of an ambiguous word in accordance with knowledge base information with no training corpus. In unsupervised learning techniques that use a knowledge base approach, graph-based and similarity-based methods have been the main research areas. The graph-based method has the advantage of constructing a semantic graph that delineates all paths between different senses that an ambiguous word may have. However, unnecessary semantic paths may be introduced, thereby increasing the risk of errors. To solve this problem and construct a fine-grained graph, in this paper, we propose a model that iteratively constructs the graph while eliminating unnecessary nodes and edges, i.e., senses and semantic paths. The hybrid similarity estimation model was applied to estimate a more accurate sense in the constructed semantic graph. Because the proposed model uses BabelNet, a multilingual lexical knowledge base, the model is not limited to a specific language.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.482-482
• /
• 2022

하천의 합류부에서는 수질이 다른 유체가 혼합하여 합류 전과 다른 특성을 보인다. 하천의 합류부에서 수질을 효율적으로 관리하기 위해서는 수질의 공간적인 혼합 특성을 규명하는 것이 중요하다. 합류부에서 수질의 공간적인 혼합 특성을 분석하기 위해 본 연구에서는 토폴로지 데이터 분석(topological data analysis, TDA), 자기 조직화 지도(Self-Organizing Map, SOM), k-평균 알고리즘(K-means clustering algorithm) 세 가지 기법을 이용하였다. 세 가지 기법을 비교하여 어떤 알고리즘이 합류부의 수질 변화 특성을 더 뚜렷하게 나타내는지 분석하였다. 수질 변화 비교 인자들은 pH, chlorophyll, DO, Turbidity 등이 있고, 수질 인자들은 YSI를 활용해 측정하였다. 자료의 측정 지역은 낙동강과 황강이 합류하는 지역이며, 보트에 YSI 장비를 부착하고 횡단하여 측정하였다. 측정한 데이터를 R 프로그램을 통해 세 가지 기법을 적용시켜 수질 변화 비교를 분석한다. 토폴로지 데이터 분석(topological data analysis, TDA)은 거대하고 복잡한 데이터로부터 유의미한 정보를 추출하는 데 사용하고, 자기조직화지도(Self-Organizing Map, SOM) 기법은 차원 축소와 군집화를 동시에 수행한다. k-평균 알고리즘(K-means clustering algorithm) 기법은 주어진 데이터를 k개의 클러스터로 묶는 머신러닝 비지도학습에 속하는 알고리즘이다. 세 가지 방법들의 주목적은 클러스터링이다. 클러스터 분석(Cluster analysis)이란 주어진 데이터들의 특성을 고려해 동일한 성격을 가진 여러 개의 그룹으로 대상을 분류하는 데이터 마이닝의 한 방법이다. 군집화 방법들인 TDA, SOM, K-means를 이용해 합류 지역의 수질 특성들을 클러스터링하여 수질 패턴들을 분석해 하천 수질 오염을 방지할 수 있을 것이다. 본 연구에서는 토폴로지 데이터 분석(topological data analysis, TDA), 자기조직화지도(Self-Organizing Map, SOM), k-평균 알고리즘(K-means clustering algorithm) 세 가지 기법을 이용하여 합류부에서의 수질 특성을 비교하며 어떤 기법이 합류의 특성을 더욱 뚜렷하게 나타내는지 규명했다. 합류의 특성을 군집화 방법을 이용해 알게 된다면, 합류부의 수질 변화 패턴을 다른 합류 지역에서도 적용할 수 있을 것으로 기대된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.10
• /
• pp.465-472
• /
• 2017

In the past, researchers mainly used the supervised learning technique of machine learning to analyze power data and investigated the identification of patterns through the data mining technique. Data analysis research, however, faces its limitations with the old data classification and analysis techniques today when the size of electric power data has increased with the possible real-time provision of data. This study thus set out to propose a clustering architecture to analyze large-sized electric power data. The clustering process proposed in the study supplements the K-means algorithm, an unsupervised learning technique, for its problems and is capable of automating the entire process from the collection of electric power data to their analysis. In the present study, power data were categorized and analyzed in total three levels, which include the row data level, clustering level, and user interface level. In addition, the investigator identified K, the ideal number of clusters, based on principal component analysis and normal distribution and proposed an altered K-means algorithm to reduce data that would be categorized as ideal points in order to increase the efficiency of clustering.