• 정보과학회 논문지
• /
• 제42권2호
• /
• pp.220-226
• /
• 2015

의미역 결정은 자연어 문장의 서술어와 그 서술어에 속하는 논항들 사이의 의미관계를 결정하는 문제이다. 일반적으로 의미역 결정을 위해서는 서술어 인식(Predicate Identification, PI), 서술어 분류(Predicate Classification, PC), 논항 인식(Argument Identification, AI) 논항 분류(Argument Classification, AC) 단계가 수행된다. 본 논문에서는 한국어 의미역 결정 문제를 위해 Korean Propbank를 의미역 결정 학습 말뭉치로 사용하고, 의미역 결정 문제를 Sequence Labeling 문제로 바꾸어 이 문제에서 좋은 성능을 보이는 Structural SVM을 이용하였다. 실험결과 서술어 인식/분류(Predicate Identification and Classification, PIC)에서는 97.13%(F1)의 성능을 보였고, 논항 인식/분류(Argument Identification and Classification, AIC)에서는 76.96%(F1)의 성능을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1994년도 Proceedings of the Korea Automatic Control Conference, 9th (KACC) ; Taejeon, Korea; 17-20 Oct. 1994
• /
• pp.7-12
• /
• 1994

This paper describes an outline of pseudorandom M-sequence and its applications to measurement and control engineering. At first, generation and properties of M-sequence is briefly described and then its applications to delay time measurement, information transmission by use of M-array, two dimensional positioning, fault detection of logical circuit, fault detection of RAM, linear and nonlinear system identification.

• International Journal of Contents
• /
• 제6권3호
• /
• pp.5-9
• /
• 2010

To manage large database system with video, effective video indexing and retrieval are required. A large number of video retrieval algorithms have been presented for frame-wise user query or video content query, whereas a few video identification algorithms have been proposed for video sequence query. In this paper, we propose an effective video identification algorithm for video sequence query that employs the Cauchy function of histograms between successive frames and the modified Hausdorff distance. To effectively match the video sequences with a low computational load, we make use of the key frames extracted by the cumulative Cauchy function and compare the set of key frames using the modified Hausdorff distance. Experimental results with several color video sequences show that the proposed algorithm for video identification yields remarkably higher performance than conventional algorithms such as Euclidean metric, and directed divergence methods.

• Asian-Australasian Journal of Animal Sciences
• /
• 제16권12호
• /
• pp.1816-1821
• /
• 2003

Reliable PCR based identification of lactobacilli has been described utilizing the sequence of 16S-23S rRNA intergenic spacer region. Those sequence comparisons showed a high degree of difference in homology among the strains of L. rhamnosus, L. casei, L. acidophilus and L. helveticus whose 16S-23S rRNA intergenic small SR's sizes were 222 bp, 222 bp, 206 bp and 216 bp respectively. The sequence of 16S-23S rRNA intergenic spacer region of L. rhamnosus ATCC 53103 revealed the close relatedness to those of L. casei strains by the homology ranges from 95.4% to 97.2%. 16S-23S rRNA intergenic spacer region nucleotide sequence of L. acidophilus showed some distant relatedness with L. rhamnosus ATCC 53103 with the homology ranges from 40.3% to 41.8% and that with L. helveticus was shown to be 30% of homology, which exists at the most distant phylogenetic relatedness. The identification of species and strain of lactobacilli was possible on the basis of these results. The common sequences among the 17 strains were CTAAGGAA located in the initiating position of the DNA and some discrepancies were found between the same strains based on these results.

• 대한미생물학회지
• /
• 제34권6호
• /
• pp.561-571
• /
• 1999

Diagnosis of mycobacterial infection is dependent upon the isolation and identification of causative agents. The procedures involved are time consuming and technically demanding. To improve the laborious identification process mycobacterial systematics supported by gene analysis is feasible, being particularly useful for slowly growing or uncultivable mycobacteria. To complement genetic analysis for the differentiation and identification of mycobacterial species, an alternative marker gene, rpoB encoding the ${\beta}$ subunit of RNA polymerase, was investigated. rpoB DNAs (342 bp) were amplified from 52 reference strains of mycobacteria including Mycobacterium tuberculosis H37Rv (ATCC 27294) and clinical isolates by the PCR. The nucleotide sequences were directly determined (306 bp) and aligned using the multiple alignment algorithm in the MegAlign package (DNASTAR) and MEGA program. A phylogenetic tree was constructed with a neighborhood joining method. Comparative sequence analysis of rpoB DNA provided the basis for species differentiation. By being grouped into species-specific clusters with low sequence divergence among strains belonging to same species, all the clinical isolates could be easily identified. Furthermore RFLP analysis enabled rapid identification of clinical isolates.

• Journal of Microbiology and Biotechnology
• /
• 제24권10호
• /
• pp.1301-1307
• /
• 2014

White-rot fungi of the genus Bjerkandera are cosmopolitan and have shown potential for industrial application and bioremediation. When distinguishing morphological characters are no longer present (e.g., cultures or dried specimen fragments), characterizing true sequences of Bjerkandera is crucial for accurate identification and application of the species. To build a framework for molecular identification of Bjerkandera, we carefully identified specimens of B. adusta and B. fumosa from Korea based on morphological characters, followed by sequencing the internal transcribed spacer region and 28S nuclear ribosomal large subunit. The phylogenetic analysis of Korean Bjerkandera specimens showed clear genetic differentiation between the two species. Using this phylogeny as a framework, we examined the identification accuracy of sequences available in GenBank. Analyses revealed that many Bjerkandera sequences in the database are either misidentified or unidentified. This study provides robust reference sequences for sequence-based identification of Bjerkandera, and further demonstrates the presence and dangers of incorrect sequences in GenBank.

• 한국멀티미디어학회논문지
• /
• 제22권6호
• /
• pp.655-664
• /
• 2019

In this paper, we propose a novel way of combining multiple deep convolutional neural network (DCNN) architectures which work well for accurate video face identification by adopting a serial combination of 3D and 2D DCNNs. The proposed method first divides an input video sequence (to be recognized) into a number of sub-video sequences. The resulting sub-video sequences are used as input to the 3D DCNN so as to obtain the class-confidence scores for a given input video sequence by considering both temporal and spatial face feature characteristics of input video sequence. The class-confidence scores obtained from corresponding sub-video sequences is combined by forming our proposed class-confidence matrix. The resulting class-confidence matrix is then used as an input for learning 2D DCNN learning which is serially linked to 3D DCNN. Finally, fine-tuned, serially combined DCNN framework is applied for recognizing the identity present in a given test video sequence. To verify the effectiveness of our proposed method, extensive and comparative experiments have been conducted to evaluate our method on COX face databases with their standard face identification protocols. Experimental results showed that our method can achieve better or comparable identification rate compared to other state-of-the-art video FR methods.

• Transactions on Control, Automation and Systems Engineering
• /
• 제4권2호
• /
• pp.109-113
• /
• 2002

Van de Vusse reactor is known as a highly nonlinear chemical process and has been considered by a number of researchers as a benchmark problem for nonlinear chemical process. Various identification methods for nonlinear system are also verified by applying these methods to Van de Vusse reactor. From the point of view of identification, only the Volterra kernel of second order has been obtained until now. In this paper, the authors show that Volterra kernels of nonlinear Van de Vusse reactor of up to 3rd order are obtained by use of M-sequence correlation method. A pseudo-random M-sequence is applied to Van de Vusse reactor as an input and its output is measured. Taking the crosscorrelation function between the input and the output, we obtain up to 3rd order Volterra kernels, which is the highest order Volterra kernel obtained until now for Van de Vusse reactor. Computer simulations show that when Van de Vusse chemical process is identified by use of up to 3rd order Volterra kernels, a good agreement is observed between the calculated output and the actual output.

• 한국수산과학회지
• /
• 제50권4호
• /
• pp.447-452
• /
• 2017

In this study, we tried to identify a sea anemone collected from the coast of Gijang, Busan. The anemone was morphologically similar to species belonging to the genus Anthopleura, but its morphological characteristics did not allow for confirmed identification to species level. Multiple genes from mitochondrial cytochrome oxidase III, 12S and 16S rRNA, and nuclear 18S and 28S rRNA, were amplified for multilocus sequence typing (MLST) analysis using genomic DNA extracted from the sampled anemone and a different primer set. Based on the MLST analysis, the anemone obtained in this study was identified as Anthopleura artemisia. Also, the sequence of internal transcribed spacer-2 was most closely related to A. artemisia, indicating that this single region might be useful for anemone identification. This study shows significance of molecular identification for sea anemones, and will be helpful in studies of sea anemone identification using genotyping-by-sequencing.

• 말소리와 음성과학
• /
• 제1권1호
• /
• pp.63-67
• /
• 2009

In this paper, in order to protect music copyrights, we propose a music identification system which is scalable to the number of pieces of registered music and robust to signal-level variations of registered music. For its implementation, we define the new concepts of 'music word' and 'music phoneme' as recognition units to construct 'music acoustic models'. Then, with these concepts, we apply the HMM-based framework used in continuous speech recognition to identify the music. Each music file is transformed to a sequence of 39-dimensional vectors. This sequence of vectors is represented as ordered states with Gaussian mixtures. These ordered states are trained using Baum-Welch re-estimation method. Music files with a suspicious copyright are also transformed to a sequence of vectors. Then, the most probable music file is identified using Viterbi algorithm through the music identification network. We implemented a music identification system for 1,000 MP3 music files and tested this system with variations in terms of MP3 bit rate and music speed rate. Our proposed music identification system demonstrates robust performance to signal variations. In addition, scalability of this system is independent of the number of registered music files, since our system is based on HMM method.