• International journal of advanced smart convergence
• /
• 제5권3호
• /
• pp.8-15
• /
• 2016

In recent years, one of deep learning models called Deep Belief Network (DBN) which formed by stacking restricted Boltzman machine in a greedy fashion has beed widely used for classification and recognition. With an ability to extracting features of high-level abstraction and deal with higher dimensional data structure, this model has ouperformed outstanding result on image and speech recognition. In this research, we assess the applicability of deep learning in dna classification level. Since the training phase of DBN is costly expensive, specially if deals with DNA sequence with thousand of variables, we introduce a new encoding method, using decimal-binary vector to represent the sequence as input to the model, thereafter compare with one-hot-vector encoding in two datasets. We evaluated our proposed model with different contrastive algorithms which achieved significant improvement for the training speed with comparable classification result. This result has shown a potential of using decimal-binary vector on DBN for DNA sequence to solve other sequence problem in bioinformatics.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.145-152
• /
• 2015

We consider an online selective-sample learning problem for sequence classification, where the goal is to learn a predictive model using a stream of data samples whose class labels can be selectively queried by the algorithm. Given that there is a limit to the total number of queries permitted, the key issue is choosing the most informative and salient samples for their class labels to be queried. Recently, several aggressive selective-sample algorithms have been proposed under a linear model for static (non-sequential) binary classification. We extend the idea to hidden Markov models for multi-class sequence classification by introducing reasonable measures for the novelty and prediction confidence of the incoming sample with respect to the current model, on which the query decision is based. For several sequence classification datasets/tasks in online learning setups, we demonstrate the effectiveness of the proposed approach.

• 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.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권5호
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.

• 한국산업정보학회논문지
• /
• 제17권6호
• /
• pp.59-72
• /
• 2012

단백질은 서열의 disorder 구역이 생물학적 반응을 일으켜 order로 변하는 과정에서 그 기능을 하게 되므로 서열 데이터에서 disorder 구역과 order 구역을 분리하는 것은 단백질의 3차 구조 및 특성을 예측하는데 반드시 필요하다. 따라서 이 논문에서는 효율적인 disorder와 order 구역 분류를 위해서 단백질의 특정 특징에 치우치지 않는 분류 결과를 얻으면서, 분류 속도를 향상 시킬 수 있도록 서열 데이터를 이용한 분류/예측 기법을 제안한다. 출현패턴 기반의 EPs-TFP 기법은 중복 출현패턴이 제거된 필수 출현패턴만을 이용하는 분류/예측 기법이다. 이 분류 기법은 disorder 구역의 서열 출현패턴들을 발견하며, 이러한 서열 출현패턴은 disorder 구역에서는 빈발하지만 order 구역에서는 상대적으로 빈발하지 않는 패턴들이다. 또한 제안 알고리즘의 성능 향상을 위해서 기존의 P-tree, T-tree 개념의 TFP 기법을 확장하여 분류/예측 기법으로 적용하였다. EPs-TFP 기법의 성능평가를 위해서 Disprot 4.9와 CASP 7 데이터를 활용하였고, disorder/order 구역을 분류한 결과, 민감도 73.6, 특이도 69.5, 정확도 74.2를 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제23권5호
• /
• pp.1-7
• /
• 2018

Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.231-235
• /
• 2004

According to revealing the DNA sequence of human and living things, it increases that a demand on a new computational processing method which utilizes DNA sequence information. In this paper we propose a classification algorithm based on negative selection of the immune system to classify DNA patterns. Negative selection is the process to determine an antigenic receptor that recognize antigens, nonself cells. The immune cells use this antigen receptor to judge whether a self or not. If one composes n group of antigenic receptor for n different patterns, they can classify into n patterns. In this paper we propose a pattern classification algorithm based on negative selection in nucleotide base level and amino acid level.

• 인지과학
• /
• 제18권1호
• /
• pp.1-14
• /
• 2007

목적 지향 대화에서 사용자의 의도는 화행과 개념열의 쌍으로 구성된 영역 행위로 표현될 수 있다. 그러므로 지능적인 대화 시스템을 구성하기 위해서는 영역 행위를 정확히 파악하는 것이 매우 중요하다. 본 논문에서는 CRFs (Conditional Random Fields)를 이용하여 화행과 개념열을 동시에 결정하는 통계 모델을 제안한다. 편향 학습 문제를 피하기 위하여 제안한 모델은 어휘와 품사 같은 낮은 수준의 언어 자질을 입력 자질로 사용하며, 카이 제곱 통계량을 이용하여 불필요한 자질들을 제거한다. 일정 관리 영역에서 실험을 수행한 결과, 제안한 모델은 화행 분류 정착률에서 93.0%, 개념열 분류 정확률에서 90.2%의 좋은 성능을 보였다.

• Journal of Microbiology
• /
• 제38권3호
• /
• pp.122-131
• /
• 2000

Phylogenetic classification of the Aphyllophorales was conducted based on the analysis of nuclear small subunit ribosomal RNA (nuc SSU rDNA) sequence. Based on phylogenetic groupings and taxonomic characters, 16 families were recognized and discussed. Although many of the characters had more or less homoplasies, miroscopic characters such ad the mitic system and clamp, spore amyloidity and rot type appeared to be important in the classification of the Aphyllophorales. Phylogenetically significant families were newly defined to improve the classification of the order Aphyllophorales.

• 천문학회보
• /
• 제38권2호
• /
• pp.49.1-49.1
• /
• 2013

We present a new galaxy classification scheme in the Wide-field Infrared Survey Explorer (WISE) [$3.4{\mu}m$]-[$12{\mu}m$] color versus $12{\mu}m$ luminosity diagram. In this diagram, galaxies can be classified into three groups in different evolutionary stages. Late-type galaxies are distributed linearly along "MIR star-forming sequence" identified by Hwang et al. (2012). Some early-type galaxies show another sequence at [3.4]-[12] $(AB){\simeq}-2.0$, and we call this 'MIR blue sequence'. They are quiescent systems with old stellar population older than 10 Gyr. Between the MIR star-forming sequence and the MIR blue sequence, some early- and late-type galaxies are sparsely distributed, and we call these galaxies 'MIR green cloud galaxies'. Interestingly, both MIR blue sequence galaxies and MIR green cloud ones lie on the red sequence in the optical color-magnitude diagram. However, MIR green cloud galaxies have lower stellar masses and younger stellar populations (smaller $D_n4000$) than MIR blue sequence galaxies, suggesting that MIR green cloud galaxies are in the transition stage from MIR star-forming sequence galaxies to MIR blue sequence ones. We present differences in various galaxy properties between the three MIR classes using a multi-wavelength data, combined with the WISE and Sloan Digital Sky Survey Data Release 10, of local (0.03 < z < 0.07) galaxies.