• Speech Sciences
• /
• v.15 no.2
• /
• pp.79-88
• /
• 2008

Recently demands for the speech technology-based products targeted for the mobile terminals such as cellular phones and PDA are rapidly increasing. And voting-based speaker identification algorithm is known to have a good performance in the mobile environment, since it works well with small amount of speaker training data. In this paper, we proposed a method to improve the performance of this voting based speaker identification system by using the observation confidence value which is derived from the function of SNR each frame. The proposed method is evaluated with ETRI cellular phone DB which is made for the speaker recognition task. The experimental results show that the proposed method has better performance of 2-3% identification rate than the conventional GMM method.

• 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.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.163-168
• /
• 2002

The voting algorithm for action selection performs self-improvement by Reinforcement learning algorithm in the dynamic environment. The proposed voting algorithm improves the navigation of the robot by adapting the eligibility of the behaviors and determining the Command Set Generator (CGS). The Navigator that using a proposed voting algorithm corresponds to the CGS for giving the weight values and taking the reward values. It is necessary to decide which Command Set control the mobile robot at given time and to select among the candidate actions. The Command Set was learnt online by means as Q-learning. Action Selector compares Q-values of Navigator with Heterogeneous behaviors. Finally, real-world experimentation was carried out. Results show the good performance for the selection on command set as well as the convergence of Q-value.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.5
• /
• pp.1201-1216
• /
• 2017

Recently, many countries around the world including Korea (Rep. of) have actively introduced online voting using distributed ledger technology (e.g. blockchain). However, online voting using distributed ledger technology based on the widely deployed telecommunication/ICT infrastructure. There is insufficient analysis of potential security threats. In this paper, we suggest a model for online voting system using distributed ledger technology and propose countermeasures by analyzing the security threats that may occur in online voting process in terms of information security.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.394-402
• /
• 2021

Electronic voting systems have been widely used in many countries around the world since the mid-1990s. In recent years, studies have applied blockchain to existing electronic voting systems in order to provide reliability, fairness, and transparency for voters. This approach is highly useful as a technology that promotes decentralized citizen participation. However, the existing electronic voting systems using blockchain have not sufficiently considered anonymity. Lack of anonymity acts as an important constraint in cases of small- and medium-sized voting, which is often required in decentralized citizen participation. In this study, we propose a model that provides anonymity to a voting system using blockchain by applying the concept of the master node in Dash cryptocurrency. First, we define the differences in the requirements of the transfer and voting systems in blockchain. We propose a parallel and autonomous model and algorithm to provide anonymity in the blockchain-that is, a decentralized development environment. In addition, a discussion of security and the environment for the proposed model is described.

• Journal of Korea Technology Innovation Society
• /
• v.15 no.3
• /
• pp.604-626
• /
• 2012

As a society of knowledge and information has been developed rapidly, because of changing from web environment to ubiquitous environment, a lot of countries across the world as well as S. Korea for e-Government have come to use the internet electronic voting for a variety of elections. So this research focused on the strategy consulting of the internet electronic voting of S. Korea with spatial information system analysed by the application of 'scenario planning' as a foresight method. And as a consequence, the strategy formulation of the electronic voting for the future S. Korea is to use the biometrics technology system as vein recognition and face recognition, using a part of the human body like a password, with spatial information system.

• Journal of the Korea Society for Simulation
• /
• v.30 no.4
• /
• pp.9-19
• /
• 2021

Electronic voting has been recognized as an alternative to complement the limitations of existing paper voting. At the same time, security concerns are being raised. This paper presents a blockchain-based electronic voting and survey system that can guarantee reliability. Our smart contract was created using Solidity on Ethereum which is a blockchain-based distributed computing platform, and the system was implemented in connection with the Javascript based user interface. In addition, in order to protect the personal information of participants, the system is generating hash of the personal data and storing the hash of users for the contract data. Since we exploited different kinds of languages for the system, we derived items of functionality testing and presented the functionality testing result. Moreover, we made use of the Chrome's performance evaluation functionality to see the response time of the blockchain-based system. In addition, we compared the performance with the system which has the same functionality on database. The contribution of this research is design and implementation of blockchain-based electronic voting system and presentation of the functionality and performance simulation result.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.798-802
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper, the robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is to use different models (CAD model etc.) known a priori. Also fusion of multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Because voting is a very simple or no model is needed for fusion, voting-based fusion of cues is applied. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters, namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.779-787
• /
• 2018

As security problems of the paper ballot have been emerged on and on, electronic voting with enhanced security and convenience has been introduced in several countries. However, it has not been adopted most of countries because of the problems that come from interdependence and security flaws. Meanwhile, the blockchain technology has high reliability due to the mechanism of mining that miners verify and preserve blocks independently by using P2P formation which does not have a central authority. Furthermore, because each block refers to the hash of the previous block. if any one block is changed, it is very difficult to forge and modify the blockchain because all blocks must be changed. If this technology is applied to the E-voting, integrity, and transparency about the result of the ballot is guaranteed. In this paper, we propose and implement an electronic voting system based on blockchain that improves interdependence, the reliability of excessive TTP and single point of failure come from original electronic voting. Also, we analyze the security and advantage of the proposal system compared with the existing bitcoin-based electronic voting system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.7B
• /
• pp.744-750
• /
• 2009

In this paper, the unified Markov modeling of hardware and software for AVTMR(AlI Voting Triple Modular Redundancy) system is proposed and the dependability is analyzed. In hardware case, a failure rate is fixed to no time varying parameter. But, in software case, failure rate is applied with time varying parameter. Especially, the dependability(Reliability, Availability, Maintainability, Safety) of software is analyzed with G-O/NHPP for Markov modeling. The dependability of single and AVTMR system is analyzed and simulated with a unified Markov modeling method, and the characteristic of each system is compared accroding to failure rate. This kind of fault tolerat system can be applied to an airplane and life critical system to meet the requirement for a specific requirement.