• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.493-497
• /
• 2016

Infrared (IR) imaging is capable of detecting targets that are not visible at night, thus it has been widely used for the security and defense system. However, the quality of the IR image is often degraded by low resolution and noise corruption. This paper addresses target segmentation with the IR image. Multiple regions of interest (ROI) are extracted by the multi-level segmentation and targets are segmented from the individual ROI. Each level of the multi-level segmentation is composed of a k-means clustering algorithm an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering algorithm initializes the parameters of the Gaussian mixture model (GMM) and the EM algorithm iteratively estimates those parameters. Each pixel is assigned to one of clusters during the decision. This paper proposes the selection and the merging of the extracted ROIs. ROI regions are selectively merged in order to include the overlapped ROI windows. In the experiments, the proposed method is tested on an IR image capturing two pedestrians at night. The performance is compared with conventional methods showing that the proposed method outperforms others.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.4
• /
• pp.39-47
• /
• 2020

In this study, crash situations of representative bus crash types were elicited by analyzing a total of 1,416 bus repair record which were collected in 2018~2019. K-means clustering was used as a methodology for this study. Bus repair record contain the information of repair term, type of bus operation, responsibility of accident, weather condition, road surface condition, type of accident, other party, type of road and type of location for each data. Also, by checking collision parts of each bus repair record, each record was classified by types of collision regions. From this, 760 record are classified to frontal type, 363 record are classified to middle-frontal type, 374 record are classified to middle-rear type and 331 record are classified to rear type. As mentioned, k-means clustering was performed on each type of collision parts. As a result, this study analyzed the severity of bus crash based on actual bus accident data which are based on bus repair record not the crash data from the TAAS. Also, this study presented crash situation of representative bus crash types. It is expected that this study can be expanded to analyzing hydrogen bus crash and defining indicators of hydrogen bus safety.

• Journal of Internet Computing and Services
• /
• v.19 no.2
• /
• pp.17-26
• /
• 2018

Recently, through the emergence and convergence of Internet services, the unified Internet of thing(IoT) service platform have been researched. Currently, the IoT service is constructed as an independent system according to the purpose of the service provider, so information exchange and module reuse are impossible among similar services. In this paper, we propose a operation based service classification algorithm for various services in order to provide an environment of unfied Internet platform. In implementation, we classify and cluster more than 100 commercial IoT services. Based on this, we evaluated the performance of the proposed algorithm compared with the K-means algorithm. In order to prevent a single clustering due to the lack of sample groups, we re-cluster them using K-means algorithm. In future study, we will expand existing service sample groups and use the currently implemented classification system on Apache Spark for faster and more massive data processing.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.431-434
• /
• 2003

In this paper we introduce a modified objective function for fuzzy c-means clustering with logistic regression model in the presence of noise cluster. The logistic regression model is commonly used to describe the effect of one or several explanatory variables on a binary response variable. In real application there is very often no sharp boundary between clusters so that fuzzy clustering is often better suited for the data.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.619-624
• /
• 1998

This paper presents a new clustering algorithm called FCM algorithm for the design of fuzzy controller. FCM is an extended version of FCM(Fuzzy c-Means) algorithm and can estimate the number of clusters automatically and give membership grades $u_{ik}$ suitable for making fuzzy control rules. This paper also shows an example of its application to the line pursuit control of a car.

• IE interfaces
• /
• v.16 no.spc
• /
• pp.123-126
• /
• 2003

In this paper, we use three cluster algorithms (K-means, Self-Organizing Map, and Fuzzy K-means) to find proper graded stock market brokerage commission rates based on the cumulative transactions on both stock exchange market and HTS (Home Trading System). Stock trading investors for both modes are classified in terms of the total transaction as well as the corresponding mode of investment, respectively. Empirical analysis results indicated that fuzzy K-means cluster analysis is the best fit for the segmentation of customers of both transaction modes in terms of robustness. We then propose the rules for three grouping of customers based on decision tree and apply different brokerage commission to be 0.4%, 0.45%, and 0.5% for exchange market while 0.06%, 0.1%, 0.18% for HTS.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1230-1237
• /
• 2009

In this paper, we develop a design methodology of Granular-based Radial Basis Function Neural Networks(GRBFNN) by context-based clustering. In contrast with the plethora of existing approaches, here we promote a development strategy in which a topology of the network is predominantly based upon a collection of information granules formed on a basis of available experimental data. The output space is granulated making use of the K-Means clustering while the input space is clustered with the aid of a so-called context-based fuzzy clustering. The number of information granules produced for each context is adjusted so that we satisfy a certain reconstructability criterion that helps us minimize an error between the original data and the ones resulting from their reconstruction involving prototypes of the clusters and the corresponding membership values. In contrast to "standard" Radial Basis Function neural networks, the output neuron of the network exhibits a certain functional nature as its connections are realized as local linear whose location is determined by the values of the context and the prototypes in the input space. The other parameters of these local functions are subject to further parametric optimization. Numeric examples involve some low dimensional synthetic data and selected data coming from the Machine Learning repository.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.559-563
• /
• 2015

Identification of energy use patterns in buildings has a great opportunity for energy saving. To find what energy use patterns exist, clustering analysis has been commonly used such as K-means and hierarchical clustering method. In case of high dimensional data such as energy use time-series, data reduction should be considered to avoid the curse of dimensionality. Principle Component Analysis, Autocorrelation Function, Discrete Fourier Transform and Discrete Wavelet Transform have been widely used to map the original data into the lower dimensional spaces. However, there still remains an ongoing issue since the performance of clustering analysis is dependent on data type, purpose and application. Therefore, we need to understand which data reduction techniques are suitable for energy use management. This research aims find the best clustering method using energy use data obtained from Seoul National University campus. The results of this research show that most experiments with data reduction techniques have a better performance. Also, the results obtained helps facility managers optimally control energy systems such as HVAC to reduce energy use in buildings.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1132-1134
• /
• 2013

K-Means 클러스터링 기법은 데이터마이닝 분야 중 클러스터링 분야에서 가장 널리 쓰이는 방법 중 하나로 주어진 데이터 셋에서 k개의 클러스터를 중심으로 데이터를 분할하는 기법이다. 최근의 데이터는 여러개의 속성을 고려해야 한다. 따라서 본 논문에서는 K-Means 클러스터링 기법을 소개하고, 또 K-Means 클러스터링 기법을 여러 개의 속성을 고려하기 위하여 다차원 데이터에 적용한 실험을 소개한다.