• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.809-819
• /
• 2020

Gender prediction accuracy increases as convolutional neural network (CNN) architecture evolves. This paper compares voting and ensemble schemes to utilize the already trained five CNN models to further improve gender prediction accuracy. The majority voting usually requires odd-numbered models while the proposed softmax-based voting can utilize any number of models to improve accuracy. The ensemble of CNN models combined with one more fully-connected layer requires further tuning or training of the models combined. With experiments, it is observed that the voting or ensemble of CNN models leads to further improvement of gender prediction accuracy and that especially softmax-based voters always show better gender prediction accuracy than majority voters. Also, compared with softmax-based voters, ensemble models show a slightly better or similar accuracy with added training of the combined CNN models. Softmax-based voting can be a fast and efficient way to get better accuracy without further training since the selection of the top accuracy models among available CNN pre-trained models usually leads to similar accuracy to that of the corresponding ensemble models.

• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.258-267
• /
• 2013

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.

• Asia-Pacific Journal of Business
• /
• v.14 no.1
• /
• pp.313-325
• /
• 2023

Purpose - The purpose of this study is to examine the process of determining control in a situation where investors hold less than a majority of the voting rights of the investee through case. Design/methodology/approach - In this study, the various and complex considerations presented in K-IFRS 1110 'Consolidated Financial Statements' were systematically classified and stratified. Findings - First, the agreement to delegate voting rights does not necessarily have to be documented, but it can be said to be substantive rights right only if it is not of the nature that one party can discontinue at any time. Second, if it is clear that investors do not have power due to the relative size of voting rights and the degree of stock dispersion, there is no need to review the past shareholders' meeting resolutions and additional facts and circumstances. Research implications or Originality - This study expects to minimize errors in applying the standards by classifying and stratifying the various considerations presented in K-IFRS 1110 into first and subsequent considerations. In addition, it is expected to contribute to reducing practical confusion in determining control by presenting a step-by-step review through case on whether or not to have power to judge control when holding voting rights of less than a majority.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2687-2689
• /
• 2005

In this paper, a novel algorithm for adaptive majority voting using additional information is described. The novel algorithm increases the reliability of adaptive majority's history. The novel algorithm assists adaptive majority voter to select the result of the most reliable module. The performance of the proposed voter is evaluated through a series of fault injection simulations. The results are compared with those of adaptive majority voter. The empirical results show that the proposed voter has higher safety and availability levels than the adaptive majority voter

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.1
• /
• pp.68-74
• /
• 2014

In a previous work, we proposed a novel approach of histogram equalization using a supplement set which is composed of centroids of Fuzzy C-Means of the background utterances. The performance of the proposed method is affected by the size of the supplement set, but it is difficult to find the best size at the point of recognition. In this paper, we propose a histogram equalization using a supplement set for majority voting based speaker identification. The proposed method identifies test utterances using a majority voting on the histogram equalization methods with various sizes of supplement sets. The proposed method is compared with the conventional feature normalization methods such as CMN(Cepstral Mean Normalization), MVN(Mean and Variance Normalization), and HEQ(Histogram Equalization) and the histogram equalization method using a supplement set.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.6
• /
• pp.10-21
• /
• 2013

This study suggested combined filtering model to eliminate outlier travel time data in transportation information system, and it was based on Median Absolute Deviation and Voting Rule. This model applied Median Absolute Deviation (MAD) method to follow normal distribution as first filtering process. After that, Voting rule is applied to eliminate remaining outlier travel time data after Median Absolute Deviation. In Voting Rule, travel time samples are judged as outliers according to travel-time difference between sample data and mean data. Elimination or not of outliers are determined using a majority rule. In case study of national highway No. 3, combined filtering model selectively eliminated outliers only and could improve accuracy of estimated travel time.

• Journal of Internet of Things and Convergence
• /
• v.5 no.2
• /
• pp.67-72
• /
• 2019

As Internet voting can take place regardless of a voter's location, the participation rate of the voters would be increased and economic costs will be reduced. But the drawback of it is that all participants have to trust the election management server. If the server colludes with the specific candidate, the other candidates cannot prove rigged election. In addition, majority of researches on Internet voting are mainly focused on the voting restricted by the region and the country. Thus, it's not appropriate for the election in Internet community such as YouTube channels. As the Internet community is composed of members from all around the world, the new type of voting model is needed. In this study, we propose the smart contract based Internet voting model applicable on the blockchain network. The proposed smart contract model consists of candidate registration, voter registration, voting and counting stages. In the proposed model, anonymity of the voter is assured in the voter registration and voting stages, and all candidates can confirm the fairness of the election in the counting stage.

• Korean Journal of Legislative Studies
• /
• v.15 no.2
• /
• pp.187-217
• /
• 2009

The purpose of this study is to analyze whether there is gender difference in Members' voting on women's issue bills, and to find out determinants of Members voting decisions on the same bills. The findings are as follows. First, there is no gender difference in women's issue voting, so women Members as a group were not significantly different from men Members in voting behavior. That's not because women Members were split in voting but because both men and women Members are very supportive of the bills. Secondly, Members' party and ideology play a significant role in Member' voting on women's issue. Compared to the majority party(Uri party)'s overwhelming support, minority parties are much less supportive on the issues. Member's ideology also proved to be important indicator of voting decision. The more ideologically liberal Members are, the more supportive of the bills.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.869-877
• /
• 2016

In this paper, we propose an automated segmentation method of femoral cartilage in knee MR images using multi-atlas-based locally-weighted voting. The proposed method involves two steps. First, to utilize the shape information to show that the femoral cartilage is attached to a femur, the femur is segmented via volume and object-based locally-weighted voting and narrow-band region growing. Second, the object-based affine transformation of the femur is applied to the registration of femoral cartilage, and the femoral cartilage is segmented via multi-atlas shape-based locally-weighted voting. To evaluate the performance of the proposed method, we compared the segmentation results of majority voting method, intensity-based locally-weighted voting method, and the proposed method with manual segmentation results defined by expert. In our experimental results, the newly proposed method avoids a leakage into the neighboring regions having similar intensity of femoral cartilage, and shows improved segmentation accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.543-548
• /
• 2002

It is well known that FCM is an indispensible tool for fuzzy clustering. The problems of using FCM are 1) it is sensitive to the initial random membership functions and 2) FCM inherently requires the number of clusters. Hence we need to run FCM algorithms with an appropriate validity measure until we find a suitable number of clusters. In this paper, we suggest the Majority-Voting FCM with implied validity measure. With this algorithm, we can solve the aforementioned problems. The working simulation results are provided. The contributions are 1) MV-FCM algorithm and 2) its definitive capability of being an excellent validity measure.