• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.456-459
• /
• 2019

대화 행위는 단순한 발화 문장들의 교환을 넘어 발화자들의 다양한 주변 정보를 고려한 종합적인 판단의 결과로 볼 수 있다. 본 논문은 여섯 가지 유형의 외부 상황 정보를 기반으로 적응적 발언을 생성하는 딥러닝 기반 대화 모델을 소개한다. 직접 구축한 상황 정보들이 태깅된 대화 데이터를 바탕으로, 외부 상황 정보를 사용자 발화와 더불어 활용하는 다양한 구조의 신경망 구조를 가지는 모델과 더불어 외부 상황 정보를 사용하지 않는 모델과의 성능에 대해 비교한다. 실험 결과들은 대화 모델의 발화 생성에 있어서 상황 정보 활용의 중요성을 보여준다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.222-227
• /
• 2006

Recently the research for Traveling Salesman Problem (TSP) using DNA computing with massive parallelism has been. However, there were difficulties in real biological experiments because the conventional method didn't reflect the precise characteristics of DNA when it express graph. Therefore, we need DNA sequence generation algorithm which can reflect DNA features and reduce biological experiment error. In this paper we proposed a DNA sequence generation algorithm that applied DNA coding method of evolution model to DNA computing. The algorithm was applied to TSP, and compared with a simple genetic algorithm. As a result, the algorithm could generate good sequences which minimize error and reduce the biologic experiment error rate.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.183-187
• /
• 2017

Smart phone users prefer fast reading and texting. Hence, users frequently use abbreviated sequences of words and phrases. Nowadays, abbreviations are widely used from chat terms to technical terms. Therefore, gathering abbreviations would be helpful to many services, including information retrieval, recommendation system, and so on. However, manually gathering abbreviations needs to much effort and cost. This is because new abbreviations are continuously generated whenever a new material such as a TV program or a phenomenon is made. Thus it is required to generate of abbreviations automatically. To generate Korean abbreviations, the existing methods use the rule-based approach. The rule-based approach has limitations, in that it is unable to generate irregular abbreviations. Another problem is to decide the correct abbreviation among candidate abbreviations generated rules. To address the limitations, we propose a method of generating Korean abbreviations automatically using sequence-to-sequence learning in this paper. The sequence-to-sequence learning can generate irregular abbreviation and does not lead to the problem of deciding correct abbreviation among candidate abbreviations. Accordingly, it is suitable for generating Korean abbreviations. To evaluate the proposed method, we use dataset of two type. As experimental results, we prove that our method is effective for irregular abbreviations.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.5 s.311
• /
• pp.44-59
• /
• 2006

This paper describes the efficient implementation of DNA sequence generate system with genetic algorithm for reducing computation time of NACST. The proposed processor is based on genetic algerian with fitness functions which would suit the point of reference for generated sequences. In order to implement efficient hardware structure, we used the pipelined structure. In addition our design was applied the parallelism to achieve even better simulation time than the sequence generator system which is designed on software. In this paper, our hardware is implemented on the FPGA board with xc2v6000 devices. Through experiment, the proposed hardware achieves 467 times speed-up over software on a PC and sequence generate performance of hardware is same with software.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.443-450
• /
• 2009

In an earlier development phase, the simulation technique is one of the key analysis methods for checking the correctness of system's functional requirements. In general, simulation is manually or randomly performed by executing state machine diagrams according to the requirement scenarios. Therefore, simulation is one of the most effort-consuming tasks. In this paper, an automatic simulation technique of state machine diagrams is provided according to the scenarios of the sequence diagrams. It is not easy to generate detailed simulation traces from sequence diagrams due to different abstraction levels between sequence diagrams and state machine diagrams. In order to adjust for different abstraction levels, state machine diagrams and sequence diagrams are transformed into LTS models and compositional analysis and transition reduction are performed. After checking behavior conformance between them, detailed simulation traces for the state machine diagrams are generated. These simulation traces are used not only for performing automatic simulation but also for assisting analyzers to reach a specific system state in order to guide further efficient simulation.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1505-1514
• /
• 2004

Sequence matching in time-series databases is an operation that finds the data sequences whose changing patterns are similar to that of a query sequence. Typically, sequence matching hires a multi-dimensional index for its efficient processing. In order to alleviate the dimensionality curse problem of the multi-dimensional index in high-dimensional cases, the previous methods for sequence matching apply the Discrete Fourier Transform(DFT) to data sequences, and take only the first two or three DFT coefficients as organizing attributes of the multi-dimensional index. This paper first points out the problems in such simple methods taking the firs two or three coefficients, and proposes a novel solution to construct the optimal multi -dimensional index. The proposed method analyzes the characteristics of a target database, and identifies the organizing attributes having the best discrimination power based on the analysis. It also determines the optimal number of organizing attributes for efficient sequence matching by using a cost model. To show the effectiveness of the proposed method, we perform a series of experiments. The results show that the Proposed method outperforms the previous ones significantly.

• Journal of the Korea Convergence Society
• /
• v.9 no.3
• /
• pp.53-59
• /
• 2018

In this paper, we propose a sequence mining based manufacturing process using a decision model in cognitive factory. The proposed model is a method to increase the production efficiency by applying the sequence mining decision model in a small scale production process. The data appearing in the production process is composed of the input variables. And the output variable is composed the production rate and the defect rate per hour. We use the GSP algorithm and the REPTree algorithm to generate rules and models using the variables with high significance level through t-test. As a result, the defect rate are improved by 0.38% and the average hourly production rate was increased by 1.89. This has a meaning results for improving the production efficiency through data mining analysis in the small scale production of the cognitive factory.

• Korean Management Science Review
• /
• v.13 no.1
• /
• pp.13-27
• /
• 1996

This paper considers the sequencing problem in mixed model assembly lines with hybrid workstation types and sequence-dependent setup times. Computation time is often a critical factor in choosing a method of determining the sequence. We develop a mathematical formulation of the problem to minimize the overall length of a line, and present a tabu search technique which can provide a near optimal solution in real time. The proposed technique is compared with a genetic algorithm and a branch-and-bound method. Experimental results are reported to demonstrate the efficiency of the technique.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.10a
• /
• pp.157-160
• /
• 2000

This study is concerned with how to optimize the Input sequence of product models with sequence -dependent setup time in Mixed-Model Assembly Line (MMAL) using conveyor system. Usually MMAL consists of a number of stations linked by conveyor belt and each station has a work zone limited by upstream and downstream boundaries. To avoid improper interference between operators in the adjacent stations and excess of machine moving range, operators are forced to complete their operations within their predetermined work zone. In this study, our goal is to determine sequence of models for minimizing the total work unfinished within their work zone. A generalized formulation of the product sequencing problem in MMAL is presented and we developed an optimal procedure using Branch & Bound. Also we developed a heuristic procedure using local search.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.76-77
• /
• 2022

In this paper, we propose a method to stabilize the 3D pose estimation result of a 3D volumetric data sequence by matching the pose estimation results from multi-view. Draw a circle centered on the volumetric model and project the model from the viewpoint at regular intervals. After performing Openpose 2D pose estimation on the projected 2D image, the 2D joint is matched to localize the 3D joint position. The tremor of 3D joints sequence according to the angular spacing was quantified and expressed in graphs, and the minimum conditions for stable results are suggested.