• STI Policy Review
• /
• 제8권2호
• /
• pp.75-93
• /
• 2017

Recently, global competition in the manufacturing sector is driving firms in the manufacturing sector to conduct product innovation projects to maintain their competitive edge. The key points of product innovation projects are 1) what the purpose of the project is and 2) what expected results in the target market can be achieved by implementing the innovation. Therefore, this study focuses on the performance of innovation projects with a business viewpoint. In this respect, this study proposes the "achievement rate" of product innovation projects as a measurement of project performance. Then, this study finds the best strategies from various innovation activities to optimize the achievement rate of product innovation projects. There are three major innovation activities for the projects, including three types of R&D activities: Internal, joint and external R&D, and five types of non-R&D activities - acquisition of machines, equipment and software, purchasing external knowledge, job education and training, market research and design. This study applies decision tree modeling, a kind of data-mining methodology, to explore effective innovation activities. This study employs the data from the 'Korean Innovation Survey (KIS) 2014: Manufacturing Sector.' The KIS 2014 gathered information about innovation activities in the manufacturing sector over three years (2011-2013). This study gives some practical implication for managing the activities. First, innovation activities that increased the achievement rate of product diversification projects included a combination of market research, new product design, and job training. Second, our results show that a combination of internal R&D, job training and training, and market research increases the project achievement most for the replacement of outdated products. Third, new market creation or extension of market share indicates that launching replacement products and continuously upgrading products are most important.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.65-68
• /
• 2005

In this paper, an algorithm to extract bar-space area is suggested. In a section of bar-code space area the threshold value is computed, and bar and space are extracted according to threshold value. PDF417 is used everyday life and printed in many different materials. The printed PDF417 is especially influenced by various light source. The decision of bar and space is very hard under the change of illumination. The fixed threshold value to distinguish the bar and space can not be applied. in these cases, The proposed algorithm is developed to investigate variable threshold. The variable threshold can be obtained by simple calculation.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1994년도 추계학술대회
• /
• pp.9-13
• /
• 1994

The Heat Anisotropic Diffusion Method has shown very effective for the contour detection of 2-D echocardiogram. To implement this algorithm, we have to choose the parameter C, K, and the threshold level. The choice of C and K are not very sensitive for the good edge detection of the echocardiogram, however the choice of the threshold level is very critical. Until now the threshold level is chosen by the trial and error method. In this paper, we present an automatic threshold decision method from the histogram of the gradient of boundary-like pixels.

• 한국멀티미디어학회논문지
• /
• 제18권10호
• /
• pp.1172-1179
• /
• 2015

A wireless license plate region extracting module is proposed for LPR system controlling multiple gates. This module is cheaply implemented using Raspberry Pi which is open source and high performance. First, as the upper 1/3 of the captured image is discarded as it has no useful information on license plate. Using the OpenCV libraries the edge image is got by Canny algorithm after applying Gaussian filtering to gray image, and the labeling is conducted for 4 consecutive numbers in license plate. These numbers are located using various decision equations, and expanding the numbers region the final license plate region can be extracted. The result image is transferred to Server using wifi direct. Using the proposed module it becomes easy to set up and maintain the LPR system. The experimental results showed that the successful extracting rate was 98.4% using 500 car images with 640 × 480 resolution.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.381-381
• /
• 2000

This paper describes the path planning method in an unknown environment for an autonomous mobile robot equipped with CCD(Charge-Coupled Device) camera. The mobile robot moves along the guideline. The CCD camera is useful to detect the existence of a guideline. The wavelet transform is used to find the edge of guideline. Using wavelet transform, we can make an image processing more easily and rapidly. We make a fuzzy control rule using image data then make a decision the position and the navigation of the mobile robot. The center value that indicates the center of guideline is the input of fuzzy logic controller and the steering angle of the mobile robot is the fuzzy output. Some actual experiments for the mobile robot applied fuzzy control show that the mobile robot effectively moves to target position.

• 전자통신동향분석
• /
• 제32권6호
• /
• pp.57-65
• /
• 2017

Neural network based AI computing is a promising technology that reflects the recognition and decision operation of human beings. Early AI computing processors were composed of GPUs and CPUs; however, the dramatic increment of a floating point operation requires an energy efficient AI processor with a highly parallelized architecture. In this paper, we analyze the trends in processor architectures for AI computing. Some architectures are still composed using GPUs. However, they reduce the size of each processing unit by allowing a half precision operation, and raise the processing unit density. Other architectures concentrate on matrix multiplication, and require the construction of dedicated hardware for a fast vector operation. Finally, we propose our own inAB processor architecture and introduce domestic cutting-edge processor design capabilities.

• 센서학회지
• /
• 제24권6호
• /
• pp.368-372
• /
• 2015

In this paper, we proposed a post-processing technique for improving classification performance of electronic nose (E-Nose) system which may be occurred drift signals from sensor array. An adaptive radial basis function network using stochastic gradient (SG) and singular value decomposition (SVD) is applied to process signals from sensor array. Due to drift from sensor's aging and poisoning problems, the final classification results may be showed bias and fluctuations. The predicted classification results with drift are quantized to determine which identification level each class is on. To mitigate sharp fluctuations moving-averaging (MA) technique is applied to quantized identification results. Finally, quantization and some edge correction process are used to decide levels of the fluctuation-smoothed identification results. The proposed technique has been indicated that E-Nose system was shown correct odor identification results even if drift occurred in sensor array. It has been confirmed throughout the experimental works. The enhancements have produced a very robust odor identification capability which can compensate for decision errors induced from drift effects with sensor array in electronic nose system.

• 한국안전학회지
• /
• 제23권6호
• /
• pp.7-13
• /
• 2008

It is important to prevent roll failure in hot rolling process for reducing maintenance cost and production loss. The relationship between rolling pass schedule and the work roll wear profile will be presented. The roll wear pattern is related with roll catastrophic failure. The irregular and deep roll wear pattern should be removed by On-line Roll Grinder(ORG) for roll failure prevention. In this study, a computer roll wear prediction model under real process working condition is developed and evaluated with hot rolling pass schedule. The method of building wear calculation functions for center portion abrasion and marginal abrasion respectively was used to develop a work roll wear prediction mathematical model. The three type rolling schedule are evaluated by wear prediction model. The optimum roll grinding methods is suggested for schedule tree rolling technique.

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.277-283
• /
• 2021

This paper addresses the problem of vision-based mask filter inspection for mask production systems. Machine learning-based approaches can be considered to solve the problem, but they may not be applicable to mask filter inspection if normal and anomaly mask filter data are not sufficient. In such cases, handcrafted image processing methods have to be considered to solve the problem. In this paper, we propose a hierarchical correlation-based approach that combines handcrafted image processing methods to detect anomaly mask filters. The proposed approach combines image rotation, cropping and resizing, edge detection of mask filter parts, average blurring, and correlation-based decision. The proposed approach was tested and analyzed with real mask filters. The results showed that the proposed approach was able to successfully detect anomalies in mask filters.

• FOCUS: LIFE SCIENCE
• /
• 제1호
• /
• pp.9.1-9.5
• /
• 2024

Method development for complex low molecular mass (LMM) samples using reversed-phase (RP) separation conditions presents significant challenges due to the presence of many unknown analytes over wide concentration ranges. This guide aims to optimize method parameters-column length (L), temperature (T), flow rate (F), and final mobile phase conditions (Øfinal)-to maximize separation peak capacity. Validated by prior research, this protocol benefits laboratories dealing with metabolomics, natural products, and contaminant screening. This practical guide provides a structured approach to maximizing peak capacity for complex LMM separations. It complements computational optimization strategies and offers a step-by-step method development process. The Snyder-Dolan test is highlighted as essential for determining the need for gradient or isocratic elution and guiding column length decisions. The decision tree framework helps analysts prioritize variable optimization to develop effective separation methods for complex samples.