• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.11-25
• /
• 2012

We present the method to infer Context-Free Grammars by applying genetic algorithm to the Binary Third-order Recurrent Neural Networks(BTRNN). BTRNN is a multiple-layered architecture of recurrent neural networks, each of which is corresponding to an input symbol, and is combined with external stack. All parameters of BTRNN are represented as binary numbers and each state transition is performed with any stack operation simultaneously. We apply Genetic Algorithm to BTRNN chromosomes and obtain the optimal BTRNN inferring context-free grammar of positive and negative input patterns. This proposed method infers BTRNN, which includes the number of its states equal to or less than those of existing methods of Discrete Recurrent Neural Networks, with less examples and less learning trials. Also BTRNN is superior to the recent method of chromosomes representing grammars at recognition time complexity because of performing deterministic state transitions and stack operations at parsing process. If the number of non-terminals is p, the number of terminals q, the length of an input string k, and the max number of BTRNN states m, the parallel processing time is O(k) and the sequential processing time is O(km).

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.37-40
• /
• 2021

This paper presents a design of a speech to sign language converter for deaf and hard of hearing people. The device is low-cost, low-power consumption, and it can be able to work entirely offline. The speech recognition is implemented using an open-source API, Pocketsphinx library. In this work, we proposed a context-oriented language model, which measures the similarity between the recognized speech and the predefined speech to decide the output. The output speech is selected from the recommended speech stored in the database, which is the best match to the recognized speech. The proposed context-oriented language model can improve the speech recognition rate by 21% for working entirely offline. A decision module based on determining the similarity between the two texts using Levenshtein distance decides the output sign language. The output sign language corresponding to the recognized speech is generated as a set of sequential images. The speech to sign language converter is deployed on a Raspberry Pi Zero board for low-cost deaf assistive devices.

• School Mathematics
• /
• v.17 no.3
• /
• pp.493-513
• /
• 2015

This study is based on the perspective that tasks in local and global contexts are important to raise students' ability to mathematically analyze and solve diverse phenomena and social issues as members of future civil society. Therefore, this study analyzes 880 real world tasks from 13 types of 7th grade textbook based on 2009 revised Curriculum. As a result of analyzing tasks by using 3 types of context category and 9 types of ways as analysis framework and allowing repetitive coding, personal context was most frequent in the context of Younbokhap. In level of Integrated ways of Yungbokhap, sequential model in which other subjects' topics were not directly related to mathematics problem or presented in simple description is most frequent. The result shows that the textbooks are too limited to develop learner's competencies. Through such analysis result, we discuss about the necessity and methods of developing tasks which allow learners to study further in future society and global context and which connect other subjects' knowledge and social issue with mathematics in deeper level.

• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.619-627
• /
• 2002

It is unpractical for the optimal design theory based on the given model and assumption to be applied to the real-world experimentation. Particularly, when the experimenter feels it necessary to consider multiple objectives in experimentation, its modified version of optimality criteria is indeed desired. The constrained optimal design is one of many methods developed in this context. But when the number of constraints exceeds two, there always exists a problem in specifying the lower limit for the efficiencies of the constraints because the “infeasible solution” issue arises very quickly. In this paper, we developed a sequential approach to tackle this problem assuming that all the constraints can be ranked in terms of importance. This approach has been applied to the polynomial regression model.

• MALSORI
• /
• no.49
• /
• pp.159-174
• /
• 2004

The development of the durational component of prosody modelling was overviewed and discussed in text-to-speech conversion of spoken English and Korean, showing the strengths and weaknesses of each approach. The possibility of integrating linguistic feature effects into the duration modelling of TTS systems was also investigated. This paper claims that current approaches to language timing synthesis still require an understanding of how segmental duration is affected by context. Three modelling approaches were discussed: sequential rule systems, Classification and Regression Tree (CART) models and Sums-of-Products (SoP) models. The CART and SoP models show good performance results in predicting segment duration in English, while it is not the case in the SoP modelling of spoken Korean.

• Journal of environmental and Sanitary engineering
• /
• v.17 no.4
• /
• pp.10-18
• /
• 2002

The changes of conventional clarification processe and an increase in treatment cost are required to meet increasingly stringent regulations related to the treated water quality. Although many enhanced coagulations have introduced to improve organic matter removal, the results to remove color, nitrogen and phosphorus as well as organic material have not been very efficient yet. In this context as new flocculation using calcium hydroxide and magnesum sulfate was carried out. The removal of waste matters such as SS, organic matter, COD, nitrogen and phosphorus contained in stock wastewater was carried out by using the combination of calcium hydroxide and magnesium sulfate. The flocculation was investigated as a function of coagulant dose, pH, mixing time, settling time and coagulant addition modes such as the sequential addition of the two coagulants and the simultaneous addition of them. The flocculation by the combination of calcium hydroxide and magnesium sulfate was compared with that by aluminum sulfate. The mechanism of flocculation was investigated as well. About 60% of COD in stock watewater was removed by flocculation with combination of calcium hydroxide and magnesium sulfate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.301-303
• /
• 2002

Subspace analysis is a popular method for multivariate data analysis and is closely related to factor analysis and principal component analysis (PCA). In the context of image processing (especially positron emission tomography), all data points are nonnegative and it is expected that both basis images and factors are nonnegative in order to obtain reasonable result. In this paper We present a sequential EM algorithm for rectified subspace analysis (subspace in nonnegativity constraint) and apply it to dynamic PET image analysis. Experimental results show that our proposed method is useful in dynamic PET image analysis.

• The Korean Journal of Applied Statistics
• /
• v.33 no.1
• /
• pp.1-10
• /
• 2020

We propose a unified approach to variable selection, transformation and outliers in the linear model. The procedure includes a sequential method for outlier detection and a least trimmed squares estimator for variable transformation. It uses all possible subsets regressions for model selection. Some real data analyses and the simulation results are provided to show the efficiency of the methods in the context of the correct variable selection and the fitness of the estimated model.

• Journal of the Korea Safety Management & Science
• /
• v.7 no.5
• /
• pp.107-117
• /
• 2005

Zohar(1980) emphasized the influence of social, organizational, and psychological context in occupational safety and health study. With this research trend, Neal, Griffin, and Hart(2000) developed a sequential safety climate model. In this paper, author examined the usability of their model the relationships among safety climates, safety knowledge, safety motivation, and safety performance(safety compliance and safety participation). The author conducted a survey to 207 manufacturing workers, and the chief results of statistical analysis are as follows : 1) the leadership has positive effects on safety knowledge and motivation, 2) the precaution activities has only positive on safety knowledge, 3) the safety system has only on safety motivation, 4) the safety knowledge and motivation have positive effects on safety compliance and participation.

• Journal of the Korean Statistical Society
• /
• v.27 no.2
• /
• pp.237-249
• /
• 1998

Process adjustment has been widely used in production processes in order to set the output characteristic as close as to the target. Box and Kramer(1992) developed a feedback adjustment control procedure for process adjustment. We generalize their procedure by using a rational subgrouping of sequential observations. In this paper the feedback control rule of the rational subgrouping is proposed and the overall expected cost is evaluated. Also properties of the proposed control scheme are illustrated and compared to Box and Kramer's in the context of the expected cost.