• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권4호
• /
• pp.121-128
• /
• 2018

Sequence-to-sequence(Seq2seq) 모델은 입력열과 출력열의 길이가 다를 경우에도 적용할 수 있는 모델로 한국어 형태소 분석에서 많이 사용되고 있다. 일반적으로 Seq2seq 모델을 이용한 한국어 형태소 분석에서는 원문을 음절 단위로 처리하고 형태소와 품사를 음절 단위로 출력한다. 음절 단위의 형태소 분석은 사전 미등록어 문제를 쉽게 처리할 수 있다는 장점이 있는 반면 형태소 단위의 사전 정보를 반영하지 못한다는 단점이 있다. 본 연구에서는 Seq2seq 모델의 후처리로 재순위화 모델을 추가하여 형태소 분석의 최종 성능을 향상시킬 수 있는 모델을 제안한다. Seq2seq 모델에 빔 서치를 적용하여 K개 형태소 분석 결과를 생성하고 이들 결과의 순위를 재조정하는 재순위화 모델을 적용한다. 재순위화 모델은 기존의 음절 단위 처리에서 반영하지 못했던 형태소 단위의 임베딩 정보와 n-gram 문맥 정보를 활용한다. 제안한 재순위화 모델은 기존 Seq2seq 모델에 비해 약 1.17%의 F1 점수가 향상되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1702-1721
• /
• 2019

A workflow process (or business process) management system helps to define, execute, monitor and manage workflow models deployed on a workflow-supported enterprise, and the system is compartmentalized into a modeling subsystem and an enacting subsystem, in general. The modeling subsystem's functionality is to discover and analyze workflow models via a theoretical modeling methodology like ICN, to graphically define them via a graphical representation notation like BPMN, and to systematically deploy those graphically defined models onto the enacting subsystem by transforming into their textual models represented by a standardized workflow process definition language like XPDL. Before deploying those defined workflow models, it is very important to inspect its syntactical correctness as well as its structural properness to minimize the loss of effectiveness and the depreciation of efficiency in managing the corresponding workflow models. In this paper, we are particularly interested in verifying very large-scale and massively parallel workflow models, and so we need a sophisticated analyzer to automatically analyze those specialized and complex styles of workflow models. One of the sophisticated analyzers devised in this paper is able to analyze not only the structural complexity but also the data-sequence complexity, especially. The structural complexity is based upon combinational usages of those control-structure constructs such as subprocesses, exclusive-OR, parallel-AND and iterative-LOOP primitives with preserving matched pairing and proper nesting properties, whereas the data-sequence complexity is based upon combinational usages of those relevant data repositories such as data definition sequences and data use sequences. Through the devised and implemented analyzer in this paper, we are able eventually to achieve the systematic verifications of the syntactical correctness as well as the effective validation of the structural properness on those complicate and large-scale styles of workflow models. As an experimental study, we apply the implemented analyzer to an exemplary large-scale and massively parallel workflow process model, the Large Bank Transaction Workflow Process Model, and show the structural complexity analysis results via a series of operational screens captured from the implemented analyzer.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2009년도 춘계학술대회 논문집
• /
• pp.545-546
• /
• 2009

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.211-214
• /
• 1996

This paper propose a method for pattern recogniton using spectrum analyzer and fuzzy ARTMAP. Contour sequences obtained from 2-D planar images represent the Euclidean distance between the centroid and all boundary pixels of the shape, and are related to the overall shape of the images. The Fourier transform of contour sequence and spectrum analyzer are used as a means of feature selection and data reduction. The three dimensional spectral feature vectors are extracted by spectrum analyzer from the FFT spectrum. These Spectral feature vectors are invariant to shape translation, rotation, and scale transformations. The fuzzy ARTMAP neural network which is combined with two fuzzy ART modules is trained and tested with these feature vectors. The experiments include 4 aircrafts and 4 industrial parts recognition process are presented to illustrate the high performance of this proposed method in the ion problems of noisv shapes.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권8호
• /
• pp.486-494
• /
• 2005

This paper presents a design experience of a supervisory control system. For effective programming of job commands, a petri net-type graphical language (PGL) is proposed applied to various tasks having concurrency and synchronization. Our PGL based supervisory control system is composed of PGL editor and PGL compiler; PGL editor is designed to help us to generate a job program using graphical symbols. PGL compiler includes analyzer, scheduler, and tranlator, PGL analyzer prevents a deadlock or resource allocation of unit cell, PGL scheduler generates a adequate job sequence of unit cell. and PGL translator translate the scheduled sequence into the iob program of each unit cell.

• 전자공학회논문지A
• /
• 제33A권5호
• /
• pp.165-171
• /
• 1996

A noncoherent full-digital PN(pseudo noise) code acquisition/tracking loop has been presetned and implemented in FPGA for the CDMA band-limited direct-sequence spread-spectrum (DS-SS) signals. It employs a simple decimator to control of local PN code phase to lower the hardware cost, and a second order loop to enable the more accurate tracking. The proposed acquisition/tracking loop has been designed in RTL-level VHDL, synthesized into logic gates using the design analyzer of synopsys software, implemented in an ALTERA FPGA chip, and tested. The number of logic gates used in the implemented FPGA chip is around 7000. The functionality has been verified using a PC interface circuitry and a logic analyzer.

• 한국정보통신학회논문지
• /
• 제13권10호
• /
• pp.2129-2139
• /
• 2009

본 논문에서는 셀룰라 오토마타를 이용하여 테스트되는 회로에 상관없이 마지막 테스트 압축치가 일정하게 되도록 조직함으로써 오류를 진단한다. 이 방법은 셀룰라 오토마타를 이용한 테스트 절차를 간결하고 명확하게 한다. 그리고 셀룰라 오토마타의 상태전이 행렬의 역행렬을 사용하여 오류가 있는 입력수열의 오류를 탐지한다.

• 전기의세계
• /
• 제22권6호
• /
• pp.8-18
• /
• 1973

This paper is a part from the series study on the 22.9KVY multiground destribution system and its is divided into three parts as follow. A.C. Network Analyzer study on the load current flow when one phase line of the feeder is out of seroice because of cutting. A.C. Network Analyzer study on the increasing zero sequence current in the good feeders when one feeder is under fault of single phase short. Field test report of the common use of open telephone line on same poles of 22.9KVY distribution system.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.972-975
• /
• 2013

This work developed a code analysis & extraction tool named Function Network Analyzer (FNA) to reduce the cost of software safety analysis. FNA analyzes functions and variables which a given function depends on, and extracts subset of code that can be compiled of automotive operating system, final resulting a well-ordered code sequence that can be compiled for model checking technique. And the experimental result illustrates that FNA can get 100% accurate rate and over 96% reduction rate by testing API functions from trampoline system.

• 스마트미디어저널
• /
• 제12권9호
• /
• pp.19-27
• /
• 2023

형태소는 한국어에서 의미를 가진 최소단위이기 때문에, 한국어 언어모델의 성능을 높이기 위해서는 정확한 형태소 분석기의 개발이 필요하다. 기존의 형태소 분석기는 대부분 어절 단위 토큰을 입력 값으로 학습하여 형태소 분석 결과를 제시한다. 하지만 한국어의 어절은 어근에 조사나 접사가 부착된 형태이기 때문에 어근이 같은 어절이어도 조사나 접사로 인해 의미가 달라지는 성향이 있다. 따라서 어절 단위 토큰을 사용하여 형태소를 학습하면 조사나 접사에 대한 오분류가 발생할 수 있다. 본 논문에서는 형태소 단위의 토큰을 사용하여 한국어 문장에 내재된 의미를 과악하고, Transformer를 사용한 시퀀스 생성 방식의 형태소 분석기를 제안한다. 또한, 미등록 단어 문제를 해결하기 위해 학습 말뭉치 데이터를 기반으로 사용자 사전을 구축하였다. 실험 과정에서 각 형태소 분석기가 출력 한 형태소와 품사 태그를 함께 정답 데이터와 비교하여 성능을 측정하였으며, 실험 결과 본 논문에서 제시한 형태소 분석기가 기존 형태소 분석기에 비해 성능이 높음을 증명하였다.