• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1780-1783
• /
• 2002

A problem of signal transmitted and received in OFDM systems is considered. In particular, an efficient solution to the problem of blind channel estimation based on Maximum Likelihood (ML) principle has been investigated. The paper proposes a new upper-bound cost, used in conjunction with a standard branch and bound integer programming technique for solving the ML problem. The tighter upper-bound cost exploits a finite-alphabet property of the transmitted signal. The proposed upper-bound cost was found to greatly speed up the ML algorithm, thus reducing computational complexity. Experimental results and discussion are included.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.2
• /
• pp.87-93
• /
• 2002

A new approach of constructing a suffix tree $T_s$for the given string S is to construct recursively a suffix tree $ T_0$ for odd positions construct a suffix tree $T_e$ for even positions from $ T_o$ and then merge $ T_o$ and $T_e$ into $T_s$ To construct suffix trees for integer alphabets in linear time had been a major open problem on index data structures. Farach used this approach and gave the first linear-time algorithm for integer alphabets The hardest part of Farachs algorithm is the merging step. In this paper we present a new and simpler merging algorithm based on a coupled BFS (breadth-first search) Our merging algorithm is more intuitive than Farachs coupled DFS (depth-first search ) merging and thus it can be easily extended to other applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.11
• /
• pp.1735-1741
• /
• 1993

New family of frequency hopping patterns with long period and good Hamming autocorrelation and Hamming crosscorrelation properties which can be used for frequency hopped multiple access communication systems is introduced. Period of frequency hopping patterns is qk-1, the alphabet size of frequency hopping patterns is q, and the size of family of frequency hopping patterns is q, where k is arbitrary integer and q is power of prime number. The maximum value of out-of-Phase Hamming autocorrelation function of any frequency hopping pattern and Hamming crosscorrelation function of any two frequency hopping patterns in the family is qk-1, which corresponds to optima1 Hamming correlation properties. And the average number of hits per q*q square in one frequency hopping pattern and its time shifted version or two frequency hopping patterns in the frequency hopped multiple access communication systems is less than 1.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.8
• /
• pp.319-326
• /
• 2007

To perform fast searching in massive data such as DNA strings, the most efficient method is to construct full-text index data structures of given strings. The widely used full-text index structures are suffix trees and suffix arrays. Since the suffix may uses less space than the suffix tree, the suffix array is proper for DNA strings. Previously developed construction algorithms of suffix arrays are not suitable for DNA strings since those are designed for integer alphabets. We propose a fast algorithm to construct suffix arrays on DNA strings whose alphabet sizes are fixed by 4. We reduce the construction time by improving encoding and merging steps on Kim et al.[1]'s algorithm. Experimental results show that our algorithm constructs suffix arrays on DNA strings 1.3-1.6 times faster than Kim et al.'s algorithm, and also for other algorithms in most cases.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.9_10
• /
• pp.476-484
• /
• 2008

Most string problems and their solutions are relevant to diverse applications such as pattern matching, data compression, recently bioinformatics, and so on. However, there have been few works on the relations between string problems and cryptographic problems. In this paper, we consider the following string reconstruction problems and show how these problems can be applied to cryptography. Given a string x of length n over a constant-sized alphabet ${\sum}$ and a set W of strings of lengths at most an integer $k({\leq}n)$, the first problem is to find the sequence of strings in W that reconstruct x by the minimum number of concatenations. We propose an O(kn+L)-time algorithm for this problem, where L is the sum of all lengths of strings in a given set, using suffix trees and a shortest path algorithm for directed acyclic graphs. The other is a dynamic version of the first problem and we propose an $O(k^3n+L)$-time algorithm. Finally, we show that exponentiation problems that arise in cryptography can be successfully reduced to these problems and propose a new solution for exponentiation.