• Journal of Digital Convergence
• /
• v.13 no.6
• /
• pp.151-156
• /
• 2015

In this paper, we have proposed personal multimodal biometric authentication system based on face detection, recognition and speaker verification for smart-phone environment. Proposed system detect the face with Modified Census Transform algorithm then find the eye position in the face by using gabor filter and k-means algorithm. Perform preprocessing on the detected face and eye position, then we recognize with Linear Discriminant Analysis algorithm. Afterward in speaker verification process, we extract the feature from the end point of the speech data and Mel Frequency Cepstral Coefficient. We verified the speaker through Dynamic Time Warping algorithm because the speech feature changes in real-time. The proposed multimodal biometric system is to fuse the face and speech feature (to optimize the internal operation by integer representation) for smart-phone based real-time face detection, recognition and speaker verification. As mentioned the multimodal biometric system could form the reliable system by estimating the reasonable performance.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.4
• /
• pp.195-203
• /
• 2017

A 2U cube satellite called SNUGLITE has been developed by GNSS Research Laboratory in Seoul National University. Its main mission is to perform actual operation by mounting dual-frequency global positioning system (GPS) receivers. Its scientific mission aims to observe space environments and collect data. It is essential for a cube satellite to control an Earth-oriented attitude for reliable and successful data transmission and reception. To this end, an attitude estimation and control algorithm, Attitude Determination and Control System (ADCS), has been implemented in the on-board computer (OBC) processor in real time. In this paper, the Extended Kalman Filter (EKF) was employed as the attitude estimation algorithm. For the attitude control technique, the Linear Quadratic Gaussian (LQG) was utilized. The algorithm was verified through the processor in the loop simulation (PILS) procedure. To validate the ADCS algorithm in the ground, the experimental verification via a single axis Hardware-in-the-loop simulation (HILS) was used due to the simplicity and cost effectiveness, rather than using the 3-axis HILS verification (Schwartz et al. 2003) with complex air-bearing mechanism design and high cost.

• Journal of the Korean Physical Society
• /
• v.73 no.10
• /
• pp.1571-1576
• /
• 2018

We developed and evaluated an algorithm to calculate the target radiation dose in cancer patients by measuring the transmitted dose during 3D conformal radiation treatment (3D-CRT) treatment. The patient target doses were calculated from the transit dose, which was measured using a glass dosimeter positioned 150 cm from the source. The accuracy of the transit dose algorithm was evaluated using a solid water phantom for five patient treatment plans. We performed transit dose-based patient dose verification during the actual treatment of 34 patients who underwent 3D-CRT. These included 17 patients with breast cancer, 11 with pelvic cancer, and 6 with other cancers. In the solid water phantom study, the difference between the transit dosimetry algorithm with the treatment planning system (TPS) and the measurement was $-0.10{\pm}1.93%$. In the clinical study, this difference was $0.94{\pm}4.13%$ for the patients with 17 breast cancers, $-0.11{\pm}3.50%$ for the eight with rectal cancer, $0.51{\pm}5.10%$ for the four with bone cancer, and $0.91{\pm}3.69%$ for the other five. These results suggest that transit-dosimetry-based in-room patient dose verification is a useful application for 3D-CRT. We expect that this technique will be widely applicable for patient safety in the treatment room through improvements in the transit dosimetry algorithm for complicated treatment techniques (including intensity modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT).

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.7 no.3
• /
• pp.8-14
• /
• 2011

The clogging of the flow area at the tube support plates(TSPs), especially at the upper TSPs results in the water level oscillation of a steam generator during normal operation. A reduction of the TSP flow area causes to increase in pressure drop within the two-phase flow zone, which destabilizes the boiling flow through the tube bundle. This phenomenon was occasionally observed at a few domestic and foreign nuclear power plants. One of the methods for defining the flow area clogging is visual inspection, which is the most effective inspection method. The results of the visual inspection for TSPs' flow area are clogging images on TSPs' quartrefoil lobes. These images are complexly distorted due to lens aberration and external factors like the distance to a subject and angle etc. In this work, we developed the analysis algorithm for clogging image of the TSP flow area of steam generators. For this purpose, we designed an image verification device applicable to the camera employed in the field for visual inspection and then, we demonstrated the validity of image analysis algorithm by using this device and commercial autoCAD program.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9A
• /
• pp.874-881
• /
• 2008

This paper presents an automatic frequency control algorithm for RTLS DS-SS modem based on the standard of ISO/IEC 24730-2. The presented automatic frequency control algorithm consists of frequency acquisition mode and frequency tracking mode, and the frequency acquisition mode is divided into the angle estimation step for frequency offset estimation and the verification step for removing the angle ambiguity. In the angle estimation step, three different sub-bit angles are estimated according to the timing intervals, then the estimates are used to re move the angle ambiguity in the verification step. The theoretical analysis and the simulation results of the proposed frequency control algorithm are presented.

• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.6
• /
• pp.473-481
• /
• 2023

In this study, a simulation system was developed to verify autonomous navigation algorithm in complex maritime traffic areas. In particular, real-world maritime traffic scenario was applied by considering near real-time maritime traffic information provided by Korean e-Navigation service. For this, a navigation simulation system of Unmanned Surface Vehicle (USV) was integrated with an e-Navigation equipment, called Electronic Chart System (ECS). To verify autonomous navigation algorithm in the simulation system, initial conditions including initial position of an own ship and a set of paths for the ship to follow are assigned by an operator. Then, considering real-world maritime traffic information obtained from the service, the simulation is implemented in which the ship repeatedly travels by avoiding surrounding obstacles (e.g., approaching ships). In this paper, the developed simulation system and its application on verification of the autonomous navigation algorithm in complex maritime traffic areas are introduced.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.143-151
• /
• 2001

This paper investigates the development of a neural network based system for automated signature authentication that relies on an autoregressive characterization for the segments of a signature. The primary contributions of this work are tow-fold: a) the development of the neural network architecture and the modalities of training it, b) adaptation of the dynamic time warping algorithm to fomulate a new method for enabling consistent segmentation of multiple signatures from the same writer. The performance of the signature verification system has been tested using a sizable database that includes a comprehensive set of simulated and realistic forgeries. False Acceptance and False Rejection error rates of 0.78% and 1.6% respectively were obtained in tests conducted using 1920 skilled forgeries.

• Atmosphere
• /
• v.27 no.2
• /
• pp.235-249
• /
• 2017

This paper describes methodology verifying near-surface predictability of numerical weather prediction models against the surface synoptic weather station network (SYNOP) observation. As verification variables, temperature, wind, humidity-related variables, total cloud cover, and surface pressure are included in this tool. Quality controlled SYNOP observation through the pre-processing for data assimilation is used. To consider the difference of topographic height between observation and model grid points, vertical inter/extrapolation is applied for temperature, humidity, and surface pressure verification. This verification algorithm is applied for verifying medium-range forecasts by a global forecasting model developed by Korea Institute of Atmospheric Prediction Systems to measure the near-surface predictability of the model and to evaluate the capability of the developed verification tool. It is found that the verification of near-surface prediction against SYNOP observation shows consistency with verification of upper atmosphere against global radiosonde observation, suggesting reliability of those data and demonstrating importance of verification against in-situ measurement as well. Although verifying modeled total cloud cover with observation might have limitation due to the different definition between the model and observation, it is also capable to diagnose the relative bias of model predictability such as a regional reliability and diurnal evolution of the bias.

• MALSORI
• /
• no.52
• /
• pp.101-110
• /
• 2004

This paper proposes a new confidence measure for utterance verification with posterior probability approximation. The proposed method approximates probabilistic likelihoods by using Viterbi search characteristics and a clustered phoneme confusion matrix. Our measure consists of the weighted linear combination of acoustic and phonetic confidence scores. The proposed algorithm shows better performance even with the reduced computational complexity than those utilizing conventional confidence measures.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1255-1258
• /
• 1998

Hidden Markov Model (HMM) is the most widely used method in speech recognition. In general, HMM parameters are trained to have maximum likelihood (ML) for training data. This method doesn't take account of discrimination to other words. To complement this problem, this paper proposes a word verification method by re-recognition of the recognized word and its similar word using the discriminative function between two words. The similar word is selected by calculating the probability of other words to each HMM. The recognizer haveing discrimination to each word is realized using the weighting to each state and the weighting is calculated by genetic algorithm.