• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1144-1158
• /
• 2016

In this paper, delay-constrained data transmission is considered over error-prone networks. Network coding is deployed for efficient information exchange, and an approximate decoding approach is deployed to overcome potential all-or-nothing problems. Our focus is on determining the cluster size and its impact on approximate decoding performance. Decoding performance is quantified, and we show that performance is determined only by the number of packets. Moreover, the fundamental tradeoff between approximate decoding performance and data transfer rate improvement is analyzed; as the cluster size increases, the data transfer rate improves and decoding performance is degraded. This tradeoff can lead to an optimal cluster size of network coding-based networks that achieves the target decoding performance of applications. A set of experiment results confirms the analysis.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.285-292
• /
• 2000

In general, exploratory data analysis consists of three processes: i) assessment of clustering tendency, ii) cluster analysis, and iii) cluster validation. This analysis method requiring a number of iterations of step ii) and iii) to converge is computationally inefficient. In this paper, we propose a density function-based approximate fuzzy clustering method with a hierachical structure which consosts of two phases: Phase I is a features(i.e., number of clusters and cluster centers) extraction process based on the tendency assessment of a given data and Phase II is a standard FCM with the cluster centers intialized by the results of the Phase I. Numerical examples are presented to show the validity of the proposed clustering method.

• Journal of Information Processing Systems
• /
• v.6 no.1
• /
• pp.67-78
• /
• 2010

In this study, a clustering algorithm that uses DCT transformed data is presented. The algorithm is a grid density-based clustering algorithm that can identify clusters of arbitrary shape. Streaming data are transformed and reconstructed as needed for clustering. Experimental results show that DCT is able to approximate a data distribution efficiently using only a small number of coefficients and preserve the clusters well. The grid based clustering algorithm works well with DCT transformed data, demonstrating the viability of DCT for data stream clustering applications.

• The Pure and Applied Mathematics
• /
• v.29 no.4
• /
• pp.255-275
• /
• 2022

In this paper, we introduce a new system of set-valued variational inclusion problems in semi-inner product spaces. We use resolvent operator technique to propose an iterative algorithm for computing the approximate solution of the system of set-valued variational inclusion problems. The results presented in this paper generalize, improve and unify many previously known results in the literature.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.6
• /
• pp.215-218
• /
• 2014

In hashing-based methods for approximate nearest neighbors(ANN) search, by mapping data points to k-bit binary codes, nearest neighbors are searched in a binary embedding space. In this paper, we present a hashing method using a PCA-based clustering method, Principal Direction Divisive Partitioning(PDDP). PDDP is a clustering method which repeatedly partitions the cluster with the largest variance into two clusters by using the first principal direction. The proposed hashing method utilizes the first principal direction as a projective direction for binary coding. Experimental results demonstrate that the proposed method is competitive compared with other hashing methods.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.65-76
• /
• 2008

Biplots are the multivariate analogue of scatter plots. They approximate the multivariate distribution of a sample in a few dimensions, typically two, and they superimpose on this display representations of the variables on which the samples are measured(Gower and Hand, 1996, Chapter 1). And the relationships between the observations and variables can be easily seen. Thus, biplots are useful for giving a graphical description of the data. However, this method does not give some concise interpretations between variables and observations when the number of observations are large. Therefore, in this study, we will suggest to interpret the biplot analysis by applying the K-means clustering analysis. It shows that the relationships between the clusters and variables can be easily interpreted. So, this method is more useful for giving a graphical description of the data than using raw data.

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.846-856
• /
• 2016

Wireless sensor networks (WSNs) are widely applied in monitoring and control of environment parameters. It is sometimes necessary to disseminate data through wireless links after they are deployed in order to adjust configuration parameters of sensors or distribute management commands and queries to sensors. Several approaches have been proposed recently for data dissemination in WSNs. However, none of these approaches achieves both high efficiency and low complexity simultaneously. To address this problem, cluster-tree based network architecture, which divides a WSN into hierarchies and clusters is proposed. Upon this architecture, data is delivered from base station to all sensors in clusters hierarchy by hierarchy. In each cluster, father broadcasts data to all his children with instantly decodable network coding (IDNC), and a novel scheme targeting to maximize total transmission gain (MTTG) is proposed. This scheme employs a new packet scheduling algorithm to select IDNC packets, which uses weight status feedback matrix (WSFM) directly. Analysis and simulation results indicate that the transmission efficiency approximate to the best existing approach maximum weight clique, but with much lower computational overhead. Hence, the energy efficiency achieves both in data transmission and processing.

• Science of Emotion and Sensibility
• /
• v.8 no.4
• /
• pp.355-363
• /
• 2005

The adjectives for represnting emotions is important to evaluate and select the colors or color patterns. In this paper, we perform the MDS analysis, factor analysis, and cluster analysis to the Soen's experimental data obtained from the evaluation of random color patterns with 13 adjective pairs. As a result, those adjectives can be reduced 3 different factors representing emotions of weight, activity and temperature, which is approximately corresponds the results of previous researches on single colors. Also, we show that the adjectives for preference can be approximate4 by other primary adjectives for color patterns using regression analysis. This implies that one can construct a uniform emotion space for evaluating and selecting color patterns regardless of objects such as wall papers, carpets, and so on.

• Korean Journal of Microbiology
• /
• v.25 no.3
• /
• pp.229-237
• /
• 1987

To determine the characteristics of heterotrophic bacterial community in estuarine ecosystem, water and sediment samples were taden from Naktong estuary. All isolates were compared with 73 characters and described by cluster analysis. With same characters, 30 reference strains were able to divide into approximate species level at 80% similarity (S value). Diversity indices ($H^{1}$) of sediment column isolates were higher than water column isolates. The bacterial community commonly appeared in water and sediment column was reduced with going to downstream. Tolerance indices for temperature (Pt) and salinity (Ps) were also higher in sediment isolates than in water isolates. The bacterial community in sediment column is believed to be composed with diverse populations compared to water column and maintains its stability against various environmental changes with high physiological tolerances.

• Journal of Soil and Groundwater Environment
• /
• v.14 no.5
• /
• pp.18-28
• /
• 2009

Both feasibility and accuracy of lumped approach to group 12 organic compounds in mixtures into a fewer number of pseudocompounds in sorption processes were evaluated using mixtures containing organic compounds with various physicochemical properties and low-surface-area mineral sorbents. The lumped approach for sorption to simulated mineral sorbents was developed by cluster analysis from statistics. Using the lumped approach, the sorption estimated from both reduced number of pseudocompounds and their sorption parameters (i.e., $K_f$, n) can approximate sorption behavior of complex organic mixtures. Additionally, the pseudocompounds for various mixtures to different types of low-surface-area mineral sorbents can be estimated a priori from the physicochemical properties of organic compound (i.e., ${\gamma_w}^{sat}$). Therefore, the lumped approach may help to simplify the complex fate and transport model of organic contaminant mixtures, reduce experimental efforts, and yet provide results that are statistically identical for practical purposes. Further research is warranted to enhance the accuracy of lumped approach using the multiple regression analysis considering the H-bonding capacity, site concentrations, functional groups for mineral sorbents.