http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Simulation Study on The Behavior Analysis of The Degree of Membership in Fuzzy c-means Method
Okazaki, Takeo,Aibara, Ukyo,Setiyani, Lina The Institute of Electronics and Information Engin 2015 IEIE Transactions on Smart Processing & Computing Vol.4 No.4
Fuzzy c-means method is typical soft clustering, and requires a degree of membership that indicates the degree of belonging to each cluster at the time of clustering. Parameter values greater than 1 and less than 2 have been used by convention. According to the proposed data-generation scheme and the simulation results, some behaviors in the degree of "fuzziness" was derived.
A simulation study for the behavior analysis of the degree of membership in fuzzy c-means method
Takeo Okazaki,Ukyo Aibara,Lina Setiyani 대한전자공학회 2015 ITC-CSCC :International Technical Conference on Ci Vol.2015 No.6
Fuzzy c-means method is a typical soft clustering, and needs to give the degree of membership that indicates the degree of belonging to each cluster at the time of the clustering execution. The parameter values greater than 1 less than 2 have been used conventionally. According to the proposed data generation scheme and the simulation results, some behavior of the fuzzy degree was derived.
NSGA-III Performance in Multi-objective Tour Guide Assignment Problem
Lina Setiyani,Takeo Okazaki 대한전자공학회 2019 IEIE Transactions on Smart Processing & Computing Vol.8 No.3
Optimization of a multi-objective tour guide assignment problem considering total guiding time, total assignment cost, and service quality is conducted. Several multi-objective evolutionary algorithms (MOEAs), such as the Non-dominated Sorting Genetic Algorithm III (NSGA-III), ε -NSGA-II, the epsilon MOEA (ε -MOEA), NSGA-II, the Pareto archived evolution strategy (PAES), and the Pareto Envelope-based Selection Algorithm II (PESA-II), have been used to solve and evaluate the problem in the MOEA framework. Based on the results, we found that NSGA-III gives better performance than the other algorithms in terms of solution quality and running time.
Epsilon NSGAIII (Ɛ-NSGAIII) for Multi-objective Problems
Lina Setiyani,Takeo Okazaki 대한전자공학회 2020 IEIE Transactions on Smart Processing & Computing Vol.9 No.5
The Non-dominated Sorted Genetic Algorithm III (NSGAIII) is known as an optimization algorithm with good efficiency and reliability in solving multi-objective optimization problems. However, in some cases, NSGAIII has been reported to have difficulties in maintaining diversity in the solutions for multi-objective optimization. In this study, we apply epsilon dominance (Ɛ-dominance) archiving to NSGAIII to enhance the algorithm’s efficiency and reliability. Ɛ-dominance NSGAIII (Ɛ-NSGAIII) was tested on standard evolutionary multi-objective optimization test problems. The results show that introducing Ɛ-dominance archiving can enhance the performance of the algorithm. Furthermore, the performance of Ɛ-NSGAIII was also compared to the original NSGAIII, Ɛ-NSGAII, and Ɛ-MOEA for a multi-objective Tour Guide Assignment Problem (TGAP).
Phauk Sokkhey,Takeo Okazaki 대한전자공학회 2020 IEIE Transactions on Smart Processing & Computing Vol.9 No.4
Deep learning has recently attracted increasing interest for several applications, and great progress has been made. This paper introduces a novel application of a deep learning framework called deep belief networks (DBNs) that can be used to predict the predicting academic performance of larger datasets. First, unsupervised training is considered a so-called pre-training section. The stacked restricted Boltzmann machine (RBM) was trained to obtain the trained weights instead of random initial weights. Subsequently, supervised learning was adopted using backpropagation in the fine-tuning section to classify the student performance levels. An optimization approach for improving the classification performance of the proposed DBN was proposed. The optimization approach consisted of using a feature selection method to obtain the optimal feature subset, optimizing the DBN model with the optimal values of the hyperparameters, and applying the L2-regularization method for weight decay. The experiment was carried out with two phases. Phase1 was implemented with an actual dataset. Phase 2 was then implemented with four artificial datasets of increasing sizes. Many experiments were performed independently on each dataset. With a larger dataset, the improved DBN generated the highest accuracy and lowest root mean square error with more accuracy and effectiveness than the other proposed algorithms.
Comparative Study of Prediction Models for High School Student Performance in Mathematics
Phauk Sokkhey,Takeo Okazaki 대한전자공학회 2019 IEIE Transactions on Smart Processing & Computing Vol.8 No.5
Measuring students’ performance and observing their learning behaviors are challenging tasks that can assist students and teachers in keeping track of progress in academic performance. Predicting student performance in mathematics has gained considerable attention from many researchers. Because a single tool may not be easily scalable from one context to another, several learning algorithms have been observed and compared for selecting an optimized prediction model. In this paper, we proposed a comparative study of the statistical analysis (SA) technique, machines learning (ML) algorithms, and a deep learning architecture for predicting student performance in mathematics. A proposed predictive structural equation modeling of SA, five superior classifiers in ML, and a graphical model for deep learning were executed and compared. Three datasets named, DS1, DS2, and DS3 were used in this analysis. We applied two main evaluation metrics, accuracy and predictive mean square error (PMSE), to measure the performance of the proposed models. On the three datasets, random forest produced the highest accuracy and the smallest PMSE which shows its potential as the best prediction model for the problem.
3D Neighborhood Relationships of Cellular Genetic Algorithms for the Tour Guide Assignment Problem
Lina Setiyani,Takeo Okazaki 대한전자공학회 2017 IEIE Transactions on Smart Processing & Computing Vol.6 No.3
Management optimization is very important in tourism, especially when it is related to productivity. One of the problems in management optimization is tour guide assignment. Wellarranged tour guide assignment will increase productivity while maintaining service quality. A cellular genetic algorithm is one of the methods that can be used to solve this problem. Furthermore, previous study has shown that a cellular dimension increase can lead to promising benefits for certain problems. The objective of this research is to give a clear understanding of the advantages of increasing cellular dimensionality on the tour guide assignment problem by using a cellular genetic algorithm.
PageRank based Score Function for Orientation to Genetic Causal Network
Hitoshi AFUSO,Takeo OKAZAKI,Morikazu NAKAMURA 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
To estimate genetic network from gene expression profile data, many approaches have been done[1][2][3] traditionally. As another approach for estimation of genetic network, Afuso[4] proposed the method constructed from two parts. First, extraction of direct causal relations from DNA microarray data. And second, giving edge orientation to extracted causal relations such satisfies certain constraint. In this paper, we proposed score function for edge orientation. And also, to evaluate appropriateness of proposal score function, we experimented comparison of proposal with other traditional score functions.
Sonam TSHERING,Takeo OKAZAKI 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
This paper proposes a web-based analytical tool with functionality for real time data collection, accurate depiction, meaningful exploration and mapping GNH spatial data. A form-based graphical user interface with standard input validation for completeness and consistency is designed to collect data. One of the two core objectives is to facilitate interactive modeling and visualization. Three methods have been employed to achieve this goal, namely spatial data manipulation, multivariate exploratory data analysis and spatial regression analysis. Another objective is to enable socio-spatial mapping and for this a thematic mapping is employed. Finally, based on models and maps GNH indexes are constructed. However, these indexes are not final, and with change in time and space, these indexes can be remodeled and modified.