• Journal of the Korea Society of Computer and Information
• /
• v.17 no.8
• /
• pp.61-69
• /
• 2012

BIRS is an intermediate representation for verifying Java program. Java program in the form of bytecode could be translated into BIRS code. Verification conditions are generated from the BIRS code to verify the program. We propose a method generating verification conditions for BIRS code. Generating verification conditions is composed of constructing control flow graph for BIRS code, depth first searching for the control flow graph to generate basic paths, and calculating weakest preconditions of the basic paths.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.2
• /
• pp.69-77
• /
• 2002

Speaker verification can be classified in two categories, text-dependent speaker verification and text-independent speaker verification. In this paper, we discuss text-dependent speaker verification. Text-dependent speaker verification system determines whether the sound characteristics of the speaker are equal to those of the specific person or not. In this paper we obtain the speaker data using a sound card in various noisy conditions, apply a new Hidden LMS (Least Mean Square) adaptive algorithm to it, and extract LPC (Linear Predictive Coding)-cepstrum coefficients as feature vectors. Finally, we use a competitive learning neural network for speaker verification. The proposed hidden LMS adaptive filter using a neural network reduces noise and enhances features in various noisy conditions. We construct a separate neural network for each speaker, which makes it unnecessary to train the whole network for a new added speaker and makes the system expansion easy. We experimentally prove that the proposed method improves the speaker verification performance.

• MALSORI
• /
• no.43
• /
• pp.45-55
• /
• 2002

High reliability of automatic speaker recognition regardless of voice conditions is necessary for forensic application. Audio recordings in real cases are not consistent in voice conditions, such as duration, time interval of recording, given text or conversational speech, transmission channel, etc. In this study the variation of verification error rate of ASR system with the voice conditions was investigated. As a result in order to decrease both false rejection rate and false acception rate, the various voices should be used for training and the duration of train voices should be longer than the test voices.

• Journal of Computing Science and Engineering
• /
• v.10 no.2
• /
• pp.39-50
• /
• 2016

In this paper, we present a comparative study of spatial domain features for writer identification and verification with different ink width conditions. The existing methods give high error rates, when comparing two handwritten images with different pen types. To the best of our knowledge, we are the first to design the feature with different ink width conditions. To address this problem, contour based features were extracted using a chain code method. To improve accuracy at higher levels, we considered histograms of chain code and variance in bins of histogram of chain code as features to discriminate handwriting samples. The system was trained and tested for 1,000 writers with two samples using different writing instruments. The feature performance is tested on our newly created dataset of 4,000 samples. The experimental results show that the histogram of chain code feature is good compared to other methods with false acceptance rate of 11.67%, false rejection rate of 36.70%, average error rates of 24.18%, and average verification accuracy of 75.89% on our new dataset. We also studied the effect of amount of text and dataset size on verification accuracy.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.2
• /
• pp.29-37
• /
• 2011

Java bytecode verification is a critical process to guarantee the safety of transmitted Java applet on the web or contemporary embedded devices. We propose a design of framework which enables to analyze and verify java bytecode. The designed framework translates from a java bytecode into the intermediate representation which can specify a properties of program without using an operand stack. Using the framework is able to produce automatically error specifications that could be occurred in a program and express specifications annotated in intermediate representation by a user. Furthermore we design a verification condition generator which converts from an intermediate representation to a verification condition, a verification engine which verifies verification conditions from verification condition generator, and a result reporter which displays results of verification.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1099-1104
• /
• 2013

This paper presents a learning-based visual inspection method that addresses the need for an improved adaptability of a visual inspection system for parts verification in panorama sunroof assembly lines. It is essential to ensure that the many parts required (bolts and nuts, etc.) are properly installed in the PLC sunroof manufacturing process. Instead of human inspectors, a visual inspection system can automatically perform parts verification tasks to assure that parts are properly installed while rejecting any that are improperly assembled. The proposed visual inspection method is able to adapt to changing inspection tasks and environmental conditions through an efficient learning process. The proposed system consists of two major modules: learning mode and test mode. The SVM (Support Vector Machine) learning algorithm is employed to implement part learning and verification. The proposed method is very robust for changing environmental conditions, and various experimental results show the effectiveness of the proposed method.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.6
• /
• pp.689-702
• /
• 2019

This paper deals with the verification of the functions about mining robot, which is the system for developing deep seabed resources by applying V&V(verification and validation). In order to overcome water pressure of 500 bar and to travel on soft ground, and to operate in deep sea environment with bad conditions, it is necessary to develop a robot that can satisfy various deepsea conditions. A mining robot has been developed based on simulation based design and Multidisciplinary design optimization. In order to verify the developed robot, lab test and real sea test should be performed for various marine environment conditions. There are too many requirements to consider, such as space, time, cost, personnel, and environment to do performance test. So it is costly and time consuming for developing robot. In order to solve this problems, V&V technique was applied to mining robot. The stages of mining robot design, fabrication and commission were verified.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.23-32
• /
• 2012

There is a method which identifies validity of program by transforming program to verification condition to verify program. If program is verified by generating verification condition, verification condition must have enough and accurate information for verifying program. However, verification condition is consisting of logical formulas, so the user cannot easily identify the verification condition. In this paper, we implemented program that visualize the poorly readable verification conditions. By the program, the users can easily identify information, such as the relationship between logical formulas that represent verification condition.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.05a
• /
• pp.443-444
• /
• 2012

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.1016-1023
• /
• 2022

In proton therapy, a highly conformal proton dose can be delivered to the tumor by means of the steep distal dose penumbra at the end of the beam range. The proton beam range, however, is highly sensitive to range uncertainty, which makes accurately locating the proton range in the patient difficult. In-vivo range verification is a method to manage range uncertainty, one of the promising techniques being prompt gamma imaging (PGI). In earlier studies, we proposed gamma electron vertex imaging (GEVI), and constructed a proof-of-principle system. The system successfully demonstrated the GEVI imaging principle for therapeutic proton pencil beams without scanning, but showed some limitations under clinical conditions, particularly for pencil beam scanning proton therapy. In the present study, we upgraded the GEVI system in several aspects and tested the performance improvements such as for range-shift verification in the context of line scanning proton treatment. Specifically, the system showed better performance in obtaining accurate prompt gamma (PG) distributions in the clinical environment. Furthermore, high shift-detection sensitivity and accuracy were shown under various range-shift conditions using line scanning proton beams.