• Journal of KIISE:Software and Applications
• /
• v.41 no.7
• /
• pp.523-532
• /
• 2014

In this paper, we propose a lattice-based discriminative approach for Korean morphological analysis and POS tagging. In our approach, for an input sentence, a morpheme lattice is first created from a lexicon where each node corresponds to a morpheme in the lexicon and each edge is formed between two consecutive morphemes. A candidate result of morphological analysis is then represented as a path in the morpheme lattice which is defined as the sequence of edges, starting in the initial state and ending with the final state. In this setting, the morphological analysis is simply considered as the process of finding the best path among all possible paths. Experiment results show that the proposed lattice-based method outperforms the first-order linear-chain CRF.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.3
• /
• pp.794-814
• /
• 2012

We propose a novel method for improving Wi-Fi positioning accuracy while reducing the energy consumption of mobile devices. Our method presents three contributions. First, we jointly and intelligently select the optimal subset of access points for positioning via maximum mutual information criterion. Second, we further propose local discriminant embedding algorithm for nonlinear discriminative feature extraction, a process that cannot be effectively handled by existing linear techniques. Third, to reduce complexity and make input signal space more compact, we incorporate clustering analysis to localize the positioning model. Experiments in realistic environments demonstrate that the proposed method can lower energy consumption while achieving higher accuracy compared with previous methods. The improvement can be attributed to the capability of our method to extract the most discriminative features for positioning as well as require smaller computation cost and shorter sensing time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.11
• /
• pp.9-16
• /
• 2015

We propose a hybrid pattern recognition method that effectively combines two different features for improving data classification. We first extract the PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) features, both of which are widely used in pattern recognition, to construct a set of basic features, and then evaluate the separability of each basic feature. According to the results of evaluation, we select only the basic features that contain a large amount of discriminative information for construction of the combined features. The experimental results for the various data sets in the UCI machine learning repository show that using the proposed combined features give better recognition rates than when solely using the PCA or LDA features.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.197-206
• /
• 2014

Motor imagery based Brain-computer Interface(BCI), which has recently attracted attention, is the technique for decoding the user's voluntary motor intention using Electroencephalography(EEG). For classifying the motor imagery, event-related desynchronization(ERD), which is the phenomenon of EEG voltage drop at sensorimotor area in ${\mu}$-band(8-13Hz), has been generally used but this method are not free from the performance degradation of the BCI system because EEG has low spatial resolution and shows different ERD-appearing band according to users. Common spatial pattern(CSP) was proposed to solve the low spatial resolution problem but it has a disadvantage of being very sensitive to frequency-band selection. Discriminative filter bank common spatial pattern(DFBCSP) tried to solve the frequency-band selection problem by using the Fisher ratio of the averaged EEG signal power and establishing discriminative filter bank(DFB) which only includes the feature frequency-band. However, we found that DFB might not include the proper filters showing the spatial pattern of ERD. To solve this problem, we apply a band-selection process using CSP feature vectors and linear discriminant analysis to DFBCSP instead of the averaged EEG signal power. The filter selection results and the classification accuracies of the existing and the proposed methods show that the CSP feature is more effective than signal power feature.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.3-8
• /
• 2013

본 논문에서는 래티스상의 구조적 분류에 기반한 한국어 형태소 분석 및 품사 태깅을 수행하는 방법을 제안한다. 제안하는 방법은 입력문이 주어질 때 어휘 사전을 참조하여, 형태소를 노드로 취하고 인접형태 소간의 에지를 갖도록 래티스를 구성하며, 구성된 래티스상 가장 점수가 높은 경로상에 있는 형태소들을 분석 결과로 제시하는 방법이다. 실험 결과, ETRI 품사 부착 코퍼스에서 기존의 1차 linear-chain CRF에 기반한 방법보다 높은 어절 정확률 그리고 문장 정확률을 얻었다.

• Journal of Life Science
• /
• v.32 no.10
• /
• pp.803-811
• /
• 2022

Despite the importance of traditional Korean fermented foods, little is known about the microbial communities and diversity of fermented soy products. To gain insight into the unexplored microbial communities of both Doenjang (DJ) and Ganjang (GJ) that may contribute to the fermentation in Korean traditional foods, we carried out next-generation sequencing (NGS) based on the V3-V4 region of 16S rDNA gene analysis. The alpha diversity analysis results revealed that both the Shannon and Simpson diversity indices were significantly different between the two groups, whereas the richness indices, including ACE, CHAO, and Jackknife, were not significant. Firmicutes were the most dominant phylum in both groups, but several taxa were found to be more abundant in DJ than in GJ. The proportions of Bacillus, Kroppenstedtia, Clostridium, and Pseudomonas and most halophiles and halotolerant bacteria, such as Tetragenococcus, Chromohalobacter, Lentibacillus, and Psychrobacter, were lower in DJ than in GJ. Linear discriminant effect size (LEfSe) analysis was carried out to discover discriminative functional biomarkers. Biomarker discovery results showed that Bacillus and Tetragenococcus were identified as the most important features for the classification of subjects to DJ and GJ. Paired-permutational multivariate analysis of variance (PERMANOVA) further revealed that the bacterial community structure between the two groups was statistically different (p=0.001).

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.663-673
• /
• 2005

An analysis model for the dynamics information of two-dimensional time-series patterns is described. In the proposed model, two novel transforms that visualize the dynamic characteristics are proposed. The first transform, referred to as speed equalization, reproduces a time-series pattern assuming a constant linear velocity to effectively model the temporal characteristics of the signing process. The second transform, referred to as velocity transform, maps the signal onto a horizontal vs. vertical velocity plane where the variation oi the velocities over time is represented as a visible shape. With the transforms, the dynamic characteristics in the original signing process are reflected in the shape of the transformed patterns. An analysis in the context of these shapes then naturally results in an effective analysis of the dynamic characteristics. The proposed transform technique is applied to an online signature verification problem for evaluation. Experimenting on a large signature database, the performance evaluated in EER(Equal Error Rate) was improved to 1.17$\%$ compared to 1.93$\%$ of the traditional signature verification algorithm in which no transformed patterns are utilized. In the case of skilled forgery experiments, the improvement was more outstanding; it was demonstrated that the parameter set extracted from the transformed patterns was more discriminative in rejecting forgeries

• Journal of Life Science
• /
• v.31 no.10
• /
• pp.922-928
• /
• 2021

To profile the microbial compositions of Korean traditional fermented paste made from whole soybeans, Doenjang and Cheonggukjang, and compare their taxonomic differences, we analyzed the V3-V4 region of 16S rRNA of naturally fermented foods by using next generation sequencing. α-Diversity results showed that values indicating bacterial community abundances (OTUs) and richness (ACE, Chao1) were statistically significant (p=0.0001) in Doenjang and Cheonggukjang. Firmicutes was the most common phylum in both groups, representing 97.02% and 99.67% in the Doenjang and Cheonggukjang groups, respectively. Bacillus was the most dominant genus, accounting for 71.70% and 59.87% in both groups. Linear discriminant (LDA) effect size (LEfSe) analysis was performed to reveal the significant ranking of abundant taxa in different fermented foods. A size-effect threshold of 2.0 on the logarithmic LDA score was used for discriminative functional biomarkers. On the species level, Bacillus subtilis, Tetragenococcus halophilus, and Clostridium arbusti were significantly more abundant in Doenjang than in Cheonggukjang, whereas Bacillus thermoamylovorans, Enterococcus faecium, and Lactobacillus sakei were significantly more abundant in Cheonggukjang than in Doenjang. Permutational multivariate analysis of variance (PERMANOVA) showed that the statistical difference in microbial clusters between the two groups was significant at the confidence level of p=0.001. This research could be used as basic research to identify the correlation between the biochemical characteristics of Korean fermented foods and the distribution of microbial communities.

• Radiation Oncology Journal
• /
• v.17 no.2
• /
• pp.120-129
• /
• 1999

Purpose : Serum squamous cell (SCC) antigen levels were examined in uterine cervix cancer undergoing radiation therapy, and authors analyzed the relationship between SCC antigen levels and treatment results. Materials and Methods :This is a retrospective study of 181 conical carcinoma patients who received radiotherapy and examined serial serum SCC antigen from 1991 to 1997 at Soonchunhyang University Hospital. One hundred and eighteen patients underwent SCC antigen evaluation at diagnosis The relationship between the serum tumor marker level and disease free survival, recurrence pattern, and other prognostic factors were analyzed according to various statistical methods. Results : The Positivity rate (initial serum value above 2.5 ng/ml) was increased with FIGO stage (IB-IIA 57% to IV 91%) and more discriminative than cutoff value of 1.5 ng/ml. Five year disease free survival rates for the stage IB-IIA, IIB, III and IV were 79.2%, 68.7%, 33.4% and 0%, respectively. The 5-year disease free survival rate for patients with serum SCC antigen levels above 5.0 ng/ml was 34% versus 55~62% for patients with normal range (>1.5 ng/ml) or mildly elevated levels (1.5~5.0 ng/ml). Rising SCC antigen levels preceded the clinical detection of disease by a mean of 4.8 months (range 1 ~13 months). Negative linear correlation was observed between initial SCC antigen levels and relapse free survival (r=-0.226), and by multivariate analysis, initial SCC antigen level had a large impact on the relapse free survival. Conclusion : SCC antigen assay is a useful aid to predict the prognosis of squamous cell carcinoma of the uterine cervix and to detect recurrence.