• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.05a
• /
• pp.17-21
• /
• 2003

This paper presents a CAD interface system that imports CAD model data and exports input information to a CAPP(Compute Aided Process Planning) system to generate a sequence for block assembly operations. In developing this system we use an open architecture CAD kernel, OpenCASCASE. The functions of the system developed are visualization of the product, definition of relations between parts, and generation of relation graph and input file for CAPP. The functions are demonstrated with a simple example.

• Journal of Ocean Engineering and Technology
• /
• v.18 no.3
• /
• pp.26-31
• /
• 2004

This paper presents a process planning system that will generate and verify assembly sequences of block assemblies. It consists of a CAD interface system and an assembly sequence planning system. In developing this system, we used an open architecture CAD kernel for the CAD interface system, for visualizing the CAD model and the assembly sequences, and an expert system shell for the assembly sequence planning system. This paper also proposes a framework for the integration of all the steps required to automate the procedures, from design to production. The process planning system is demonstrated by a simple example.

• Annual Conference of KIPS
• /
• 2016.04a
• /
• pp.700-703
• /
• 2016

OpenCV(Open Computer Vision)에서 제공하는 얼굴 검출 알고리즘은 Haar-like feature와 Cascade 방식을 이용하여 얼굴의 패턴을 찾아내 얼굴을 검출한다. 그러나 우연히 얼굴이 아닌 곳이 얼굴과 유사한 패턴일 경우, 얼굴로 인식하는 오류를 범하게 된다. 따라서 본 논문은 MCT(Modified Census Transform)와 신경망을 이용하여 잘못된 얼굴 검출 영역을 감소시키는 알고리즘을 제안한다. MCT는 다양한 조명 조건에서도 강인한 얼굴 영상의 지역적 구조 특징을 추출하기 위하여 사용되고, 신경망 알고리즘은 Haar-Cascade 알고리즘의 얼굴 검출 방법으로 검출된 영역이 실제로 얼굴인지 아닌지를 판단하기 위하여 사용된다. 실험에서 사용된 6개의 데이터들은 인터넷에서 수집한 것으로서, Haar-Cascade 알고리즘의 얼굴 검출 방법으로 얼굴을 검출하였을 때 오검출된 영역이 1개 이상 존재한다. 본 논문에서 제안한 알고리즘으로 실험한 결과, Haar-Cascade 알고리즘의 얼굴 검출 방법에 비하여 오검출된 영역이 감소된 것을 확인할 수 있었다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.3
• /
• pp.151-158
• /
• 2002

Automotive engineers involved in a new car project use various CAD systems that are chosen based on work requirements. For example, engineers in Hyundai Motors are using Pro/Designer and Alias fur the style design, but they use CATIA to design parts and assemblies, ANSYS for FEM analysis, and Pro/Engineer to design engines. Because they use different CAD systems, they have difficulties in collaborative design. Data, which contains errors, is transferred between CAD systems. It is difficult to find out such errors in a large CAD model. An evaluation method for CAD models has been developed in this study. This diagnosis tool analyses a STEP or an IGES file generated from a CAD system, and produces a quantitative error report. The tool has been tested with actual data sets. This paper proposes an algorithm that produces mathematical error values of entities of IGES models that have geometrical data, and entities of STEP models that have topological data, and inspects every part off model. To develop this system, we have used the OpenCASCADE kernel, which is an open source kernel developed by Matra Datavision of France.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.27 no.2
• /
• pp.81-86
• /
• 2015

Performance of freezing and refrigeration systems in supermarket, which utilized $CO_2$ as a refrigerant, was investigated by using the Pack Calculation II. The configuration of simulated systems was basic parallel refrigeration system, cascade system, and two-stage system. The $CO_2$ cascade system showed higher COP than basic parallel R404A system by 13% for MT and 62% for LT, respectively. Among the $CO_2$ cascade systems, R717(MT)-$CO_2$(LT) showed the highest performance. Open-type intercooler method showed higher performance than liquid injection for the two-stage $CO_2$ systems.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.10
• /
• pp.190-196
• /
• 2014

This paper proposes a mobile-optimized pedestrian detection method using Cascade of HOG(Histograms of Oriented Gradients) for ADAS(Advanced Driver Assistance System) on smartphones. In order to use the limited resource of mobile platforms efficiently, the method is implemented by the OpenCL(Open Computing Language) library, and its processing time is reduced in the following two aspects. Firstly, the method sets a program build option specifically and adjusts work group sizes as variety of kernels in the host code. Secondly, it utilizes local memory and a LUT(Look-Up Table) in the kernel code to accelerate the program. For performance evaluation, the developed algorithm is compared with the mobile CPU-based OpenCV(Open Computer Vision) for Android function. The experimental results show that the processing speed is 25% faster than the OpenCV hogcascade.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.33-36
• /
• 2021

본 논문에서는 인간의 표정과 목소리를 기반으로 한 감정 분석기를 제안한다. 제안하는 분석기들은 수많은 인간의 표정 중 뚜렷한 특징을 가진 표정 7가지를 별도의 클래스로 구성하며, DNN 모델을 수정하여 사용하였다. 또한, 음성 데이터는 학습 데이터 증식을 위한 Data Augmentation을 하였으며, 학습 도중 과적합을 방지하기 위해 콜백 함수를 사용하여 가장 최적의 성능에 도달했을 때, Early-stop 되도록 설정했다. 제안하는 표정 감정 분석 모델의 학습 결과는 val loss값이 0.94, val accuracy 값은 0.66이고, 음성 감정 분석 모델의 학습 결과는 val loss 결과값이 0.89, val accuracy 값은 0.65로, OpenCV 라이브러리를 사용한 모델 테스트는 안정적인 결과를 도출하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.873-891
• /
• 2018

This paper suggests an automatic approach to extracting Java method implementation patterns associated with method identifiers using Cascade K-Medoids. Java method implementation patterns indicate recurring implementations for achieving the purpose described in the method identifier with the given parameters and return type. If the implementation is different from the purpose, readers of the code tend to take more time to comprehend the method, which eventually affects to the increment of software maintenance cost. In order to automatically identify implementation patterns and its representative sample code, we first propose three groups of feature vectors for characterizing the Java method signature, method body and their relation. Then, we apply Cascade K-Medoids by enhancing the K-Medoids algorithm with the Calinski and Harrabasez algorithm. As the evaluation of our approach, we identified 16,768 implementation patterns of 7,169 method identifiers from 50 open source projects. The implementation patterns have been validated by the 30 industrial practitioners with from 1 to 6 years industrial experience, resulting in 86% of the precision.

• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.51-57
• /
• 2017

Digital signage is becoming part of daily life across a wide range of visual advertisements segments market used in stations, hotels, retail stores, hotels, etc. The current digital signage system used in market is generally works on limited user interactivity with static contents. In this paper, a new approach is proposed using computer vision based dynamic audience adaptive cost-effective digital signage system. The proposed design uses the Camera attached Raspberry Pi Open source platform to employ the real-time audience interaction using computer vision algorithms to extract facial features of the audience. The real-time facial features are extracted using Haar Cascade algorithm which are used for audience gender specific rendering of dynamic digital signage content. The audience facial characterization using Haar Cascade is evaluated on the FERET database with 95% accuracy for gender classification. The proposed system, developed and evaluated with male and female audiences in real-life environments camera embedded raspberry pi with good level of accuracy.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.3
• /
• pp.145-153
• /
• 2004

A nonlinear adaptive speed observer is designed for the sensorless control of induction motors. In order to design the speed observer, the measurements of the stator currents and the estimates of the rotor fluxes are used. The sliding mode cascade observer is designed to estimate the time derivatives of the stator currents. The open-loop observer is designed to estimate the rotor fluxes and its time derivatives using the stator current derivatives. The adaptive observer is also designed to estimate the rotor resistance. Sequentially, the rotor speed is calculated using these estimated values. It is shown that the estimation errors of the corresponding states and the parameters converge to the specified residual set. It is also shown that the speed controller using these estimates is performed well. The simulation examples are represented to investigate the validity of the proposed observers for the sensorless control of induction motors.