• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.6
• /
• pp.280-298
• /
• 2008

For efficient content-based image retrieval, diverse visual features such as color, texture, and shape have been widely used. In the case of leaf images, further improvement can be achieved based on the following observations. Most plants have unique shape of leaves that consist of one or more blades. Hence, blade-based matching can be more efficient than whole shape-based matching since the number and shape of blades are very effective to filtering out dissimilar leaves. Guaranteeing rotational invariance is critical for matching accuracy. In this paper, we propose a new shape representation, indexing and matching scheme for leaf image retrieval. For leaf shape representation, we generated a distance curve that is a sequence of distances between the leaf’s center and all the contour points. For matching, we developed a blade-based matching algorithm called rotation invariant - partial dynamic time warping (RI-PDTW). To speed up the matching, we suggest two additional techniques: i) priority queue-based pruning of unnecessary blade sequences for rotational invariance, and ii) lower bound-based pruning of unnecessary partial dynamic time warping (PDTW) calculations. We implemented a prototype system on the GEMINI framework [1][2]. Using experimental results, we showed that our scheme achieves excellent performance compared to competitive schemes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.2
• /
• pp.155-161
• /
• 1991

In this paper, Fingerprint matching mathod which is able to confirm one's identify using position and direction data of minutiae (ending point & bifurcation). Using number of response data, quantity of transfer, quantity of position matching. We decided whether fingerprint identity is true of not.

• Journal of the Korean Statistical Society
• /
• v.36 no.1
• /
• pp.77-91
• /
• 2007

This paper considers development of noninformative priors for the familial data when the families have equal number of offspring. Several noninformative priors including the widely used Jeffreys' prior as well as the different reference priors are derived. Also, a simultaneously-marginally-probability-matching prior is considered and probability matching priors are derived when the parameter of interest is inter- or intra-class correlation coefficient. The simulation study implemented by Gibbs sampler shows that two-group reference prior is slightly edge over the others in terms of coverage probability.

• Journal of Labour Economics
• /
• v.43 no.2
• /
• pp.109-133
• /
• 2020

This paper estimates a matching function in Korea by using the method of Borowczyk-Martins et al. (2013) in order to mitigate endogeneity problems. The endogeneity was controlled through the GMM estimation by approximating the unobserved matching efficiency with the ARMA(p,q) process. The monthly data from the Economically Active Population Survey and Labor Force Survey at Establishments from June 2009 to December 2019 were used for the estimation. The matching elasticity that indicates the elasticity of new hires with respect to vacancies was estimated to be 0.859. When excluding 2019 samples, which had a large number of direct jobs provided by the government, the matching elasticity was lowered to 0.755, but still higher than that of other countries.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.2
• /
• pp.60-65
• /
• 2008

The matching preclusion set of a graph is a set of edges whose deletion results in a graph that has neither perfect matchings nor almost perfect matchings. The matching preclusion number is the minimum cardinality over all matching preclusion sets. We show in this paper that, for any $m{\geq}4$, the matching preclusion numbers of both m-dimensional restricted HL-graph and recursive circulant $G(2^m,4)$ are equal to degree m of the networks, and that every minimum matching preclusion set is the set of edges incident to a single vertex.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.3 s.246
• /
• pp.310-317
• /
• 2006

Currently most practical vibration and structural problems in automotive suspensions require the use of the finite element method to obtain their structural responses. When the finite element model has a very large number of degrees of freedom the harmonic and dynamic analyses are computationally too expensive to repeat within a feasible design process time. To alleviate the computational difficulty, this paper presents a moment-matching based model order reduction (MOR) which reduces the number of degrees of freedom of the original finite element model and speeds up the necessary simulations with the reduced-size models. The moment-matching model reduction via the Arnoldi process is performed directly to ANSYS finite element models by software mor4ansys. Among automotive suspension components, a knuckle is taken as an example to demonstrate the advantages of this approach for vibration simulation. The frequency and transient dynamic responses by the MOR are compared with those by the mode superposition method.

• Bulletin of the Korean Mathematical Society
• /
• v.37 no.1
• /
• pp.121-125
• /
• 2000

In this paper, we obtain an algorithm for finding a maximum matching in the line graph L(G) of a graph G. The complexity of our algorithm is O($$\mid$E$\mid$$), where is the edge set of G($$\mid$E$\mid$$ is equal to the number of vertices in L(G)).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.3
• /
• pp.395-404
• /
• 2013

A pattern matching algorithm plays an important role in traffic identification and classification based on predefined patterns for intrusion detection and prevention. As attacks become prevalent and complex, current patterns are written using regular expressions, called regexes, which are expressed into the deterministic finite automata(DFA) due to the guaranteed worst-case performance in pattern matching process. Currently, because of the increased complexity of regex patterns and their large number, memory-efficient DFA from states reduction have become the mainstay of pattern matching process. However, most of the previous works have focused on reducing only the number of states on a single automaton, and thus there still exists a state blowup problem under the large number of patterns. To solve the above problem, we propose a new state compression algorithm that merges states on multiple automata. We show that by merging states with the same input character on multiple automata, the proposed algorithm can lead to a significant reduction of the number of states in the original DFA by as much as 40.0% on average.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.761-767
• /
• 2005

The personal identification procedure through the fingerprints is divided as the classification process by the type of the fingerprints and the matching process to confirm oneself. Many existing researches for the classification and the matching of the fingerprint depend on the number of the minutiae of the fingerprints and the flow patterns by their direction information. In this paper, we focus on extracting the singular points by using the flow patterns of the direction information from identification. The extracted singular points are utilized as a standard point for the matching process by connecting with the extracted information from the singular point embodied. The orthogonal coordinates which is generated by the axises of the standard point can increase the accuracy of the fingerprints matching because of minimizing the effects on the location changes of the fingerprint images.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.89-99
• /
• 1995

One of the hardest problems that limit real application of production system is its slowness. One way to overcome this problem is to speed up the matching operation which occupies more than 90% of the total execution time. In this paper, we try to speed up the matching operation with parallel execution of a typical pattern matching algorithm, RETE, in a multiprocessor environment, This requires not only to make partitions of the rules but also to allocate the partitioned rules to processors, respectively. A partition strategy is proposed to make groups of similar rules by evaluating the similarity of rules according to the number of common conditions between rules. An allocation strategy is proposed to make the load of each processor even by assigning the different priority to the group of rules according to the expected amount of time required for matching operation. To compare with the existing methods, we perform simulation using OPS5 sample programs. The simulation results show that the proposed methods can improve the performance of production system.