• Title/Summary/Keyword: Verification experiment

Search Result 784, Processing Time 0.054 seconds

Speaker Verification System Using Continuants and Multilayer Perceptrons (지속음 및 다층신경망을 이용한 화자증명 시스템)

  • Lee, Tae-Seung;Park, Sung-Won;Hwang, Byong-Won
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2003.10a
    • /
    • pp.1015-1020
    • /
    • 2003
  • Among the techniques to protect private information by adopting biometrics, speaker verification is expected to be widely used due to advantages in convenient usage and implementation cost. Speaker verification should achieve a high degree of the reliability in the verification score, the flexibility in speech text usage, and the efficiency in verification system complexity. Continuants have excellent speaker-discriminant power and the modest number of phonemes in the category, and multilayer perceptrons (MLPs) have superior recognition ability and fast operation speed. In consequence, the two provide viable ways for speaker verification system to obtain the above properties. This paper implements a system to which continuants and MLPs are applied, and evaluates the system using a Korean speech database. The results of the experiment prove that continuants and MLPs enable the system to acquire the three properties.

  • PDF

Improved Face Detection Algorithm Using Face Verification (얼굴 검증을 이용한 개선된 얼굴 검출)

  • Oh, Jeong-su
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.22 no.10
    • /
    • pp.1334-1339
    • /
    • 2018
  • Viola & Jones's face detection algorithm is a typical face detection algorithm and shows excellent face detection performance. However, the Viola & Jones's algorithm in images including many faces generates undetected faces and wrong detected faces, such as false faces and duplicate detected faces, due to face diversity. This paper proposes an improved face detection algorithm using a face verification algorithm that eliminates the false detected faces generated from the Viola & Jones's algorithm. The proposed face verification algorithm verifies whether the detected face is valid by evaluating its size, its skin color in the designated area, its edges generated from eyes and mouth, and its duplicate detection. In the face verification experiment of 658 face images detected by the Viola & Jones's algorithm, the proposed face verification algorithm shows that all the face images created in the real person are verified.

Formal Verification of Functional Properties of an SCR-style Software Requirements Specifications using PVS (PVS를 이용한 SCR 스타일의 소프트웨어 요구사항 명세에서 기능 요구 사항의 정형 검증)

  • Kim, Tae-Ho;Cha, Sung-Deok
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.8 no.1
    • /
    • pp.46-61
    • /
    • 2002
  • Among the many phases involved in software development, requirements analysis phase in generally considered to play a crucial role in determining the overall software quality. Therefore, many software development companies manages the phase as one of the important phase. Especially, safety assurance through requirements analysis for safety-critical systems is quite demanding, and national and international bodies routinely require safety demonstration. Among various approaches, inspection and formal methods are generally shown to be effective. In this paper, we propose a formal verification procedure for SCR(Software Cost Reduction)-style SRS(Software Requirements Specification) using the PVS specification and verification procedure and applied this procedure to an industrial system such that a shutdown system for Wolsung nuclear power plant. This system had been verified through inspection not formal verification. The application of formal methods is rare in Korea, so it is very important to experiment about formal verification to industrial systems.

INTEGRATION OF GPS AND PSEUDOLITE FOR SEAMLESS POSITIONING : Fundamental Verification Experiment and Results

  • Suh, Yong-Cheol;Konishi, Yusuke;Shibasaki, Ryosuke
    • Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
    • /
    • 2002.04a
    • /
    • pp.77-84
    • /
    • 2002
  • The Global Positioning System, GPS technology has been widely used in positioning and attitude determination. It is well known that the accuracy, availability and reliability of the positioning results are heavily dependent on the number and geometric distribution of tracked GPS satellites. Because of this limitation, in some situations, such as in urban canyons, underground space or inside of buildings, it is really hard to navigate with GPS receiver. Therefore, in order to improve the performance of satellite-based positioning, the integration of GPS with the pseudolite technology has been proposed. With this pseudolite technology, it is expected that seamless positioning service can be provided in wider area without replacing existing GPS receivers. On the other hand, to adopt pseudolites at larger scale, it is necessary to verify how the pseudolites can complement the existing GPS-based positioning. In this paper the authors present the detail of experimental investigations and the results of the fundamental verification for seamless positioning using integration of GPS and pseudolite. This paper shows that the accuracy and efficiency of integrating GPS and pseudolite through the dynamic and static positioning experiment and discuss about the influence on GPS receiver by pseudolite signal. The experimental results indicate that the accuracy of the height component can indeed be significantly improved, to approximately the same level as the horizontal component.

  • PDF

Enhanced mass balance Tafel slope model for computer based FEM computation of corrosion rate of steel reinforced concrete coupled with CO2 transport

  • Hussain, Raja Rizwan
    • Computers and Concrete
    • /
    • v.8 no.2
    • /
    • pp.177-192
    • /
    • 2011
  • This research paper aims at computer based modeling of carbonation induced corrosion under extreme conditions and its experimental verification by incorporating enhanced electrochemical and mass balance equations based on thermo-hygro physics with strong coupling of mass transport and equilibrium in micro-pore structure of carbonated concrete for which the previous research data is limited. In this paper the carbonation induced electrochemical corrosion model is developed and coupled with carbon dioxide transport computational model by the use of a concrete durability computer based model DuCOM developed by our research group at concrete laboratory in the University of Tokyo and its reliability is checked in the light of experiment results of carbonation induced corrosion mass loss obtained in this research. The comparison of model analysis and experiment results shows a fair agreement. The carbonation induced corrosion model computation reasonably predicts the quantitative behavior of corrosion rate for normal air dry relative humidity conditions. The computational model developed also shows fair qualitative corrosion rate simulation and analysis for various pH levels and coupled environmental actions of chloride and carbonation. Detailed verification of the model for the quantitative carbonation induced corrosion rate computation under varying relative conditions, different pH levels and combined effects of carbonation and chloride attack remain as scope for future research.

Correlation Analysis of Airline Customer Satisfaction using Random Forest with Deep Neural Network and Support Vector Machine Model

  • Hong, Sang Hoon;Kim, Bumsu;Jung, Yong Gyu
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.12 no.4
    • /
    • pp.26-32
    • /
    • 2020
  • There are many airline customer evaluation data, but they are insufficient in terms of predicting customer satisfaction in practice. In particular, they are generally insufficient in case of verification of data value and development of a customer satisfaction prediction model based on customer evaluation data. In this paper, airline customer satisfaction analysis is conducted through an experiment of correlation analysis between customer evaluation data provided by Google's Kaggle. The difference in accuracy varied according to the three types, which are the overall variables, the top 4 and top 8 variables with the highest correlation. To build an airline customer satisfaction prediction model, they are applied to three classification algorithms of Random Forest, SVM, DNN and conduct a classification experiment. They are divided into training data and verification data by 7:3. As a result, the DNN model showed the lowest accuracy at 86.4%, while the SVM model at 89% and the Random Forest model at 95.7% showed the highest accuracy and performance.

The Output Feedback Control of Inverted Pendulum Systems for The Verification of Practical Use of Linear State Observers (선형 상태 관측기의 실용화 검증을 위한 도립진자 시스템의 출력 피드백 제어 실험)

  • Lee, Jong-Yeon;Cho, Kyu-Jung;Hyun, Chang-Ho
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.21 no.2
    • /
    • pp.192-197
    • /
    • 2011
  • In this paper, the output feedback control of inverted pendulum systems is experimented for the practicality verification of the linear state observer. For the experiment, a pendulum system, CEM-IP-01 of Cemware Inc. is used and Lagrange equation and Jacobian linearization are adopted for the dynamic analysis of the pendulum system. In addition, the output responses of the state feedback control and the output feedback control of the pendulum system are compared before the experiment by Matlab. Finally, we directly verify the practical use of the linear state observer by recognizing and solving some real problem to control the inverted pendulum system in practice.