• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.343-350
• /
• 2022

It is worth verifying the effectiveness of data integration between data with different features. This study investigated whether the data integration affects the accuracy of deep neural network (DNN), and which integration method shows the best improvement. This study used two different public datasets. One public dataset was taken in an actual farm in India. And another was taken in a laboratory environment in Korea. Leaf images were selected from two different public datasets to have five classes which includes normal and four different types of plant diseases. DNN used pre-trained VGG16 as a feature extractor and multi-layer perceptron as a classifier. Data were integrated into three different ways to be used for the training process. DNN was trained in a supervised manner via the integrated data. The trained DNN was evaluated by using a test dataset taken in an actual farm. DNN shows the best accuracy for the test dataset when DNN was first trained by images taken in the laboratory environment and then trained by images taken in the actual farm. The results show that data integration between plant images taken in a different environment helps improve the performance of deep neural networks. And the results also confirmed that independent use of plant images taken in different environments during the training process is more effective in improving the performance of DNN.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.2
• /
• pp.27-37
• /
• 2001

Using satellite image and GIS, spatial distribution characteristics of black locust forest as honey plant area was identified and analyzed. Upon the result, the most suitable area for black locust forest was selected through the integration analysis of transparent overlay. The variables used for spatial analysis such as topography(elevation, aspect, slope), soil, drainage, distance from urban area, land use, meteorological elements were considered. Based on the suitability analysis, it was clarified that the integration of linear and factor combination technique is greatly efficient method for the most suitable area. In addition, Gokung, Imgo, Chungtong, Hwanam area were shown to be suitable in Young-chun Area. As the result of suitability analysis for honey plant area of black locust in Young-chun using satellite image and GIS, the present portion of potential distribution area was produced about 42.53%. The portion of most suitable area for honey plant area of black locust was about 26.77%. Finally, the total area for honey plant area of black locust in Young-chun came up to $15.79km^2$. Additionally, satellite image and GIS were expected to be significant tools for suitability analysis of honey plant complex area.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.489-491
• /
• 2000

A DAS(Distribution Automation System) enhances the efficiency and productivity of a utility. It also provides intangible benefits such as improved public image and market adventages. This paper discusses an approach to the integration of NDIS(New Distribution Information System) and DAS that will allow benefits from both technologies to support a common database and distributed computing architecture, thereby improving the ability of many functions to justify implementation of integrated systems based on transferring' data comparisons.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.990-995
• /
• 1991

The integration of intelligent robots into manufacturing systems should positively impact the product quality and productivity. A new theory of object location and recognition using the supporting plane is presented. The unknown supporting points are determined by image coordinates, known camera parameters, and joint coordinates of the robot manipulators. This is developed by using the geometrical interpretation of perspective projection and the geometrical constraints of industrial environments. This can be applied to solve typical robot vision problems such as determination of position, orientation, and recognition of objects.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.10B
• /
• pp.1803-1812
• /
• 2000

A new motion compensation method for ISAR is presented in this paper. It employs amplitude limiting and integration of consecutive range profiles to improve the range and phase alignment accuracy and to alter the propagation properties of compensation errors. These allow the image quality to be significantly improved. It is shown from the imaging results that the new motion compensation algorithm can get images of targets in field situations with much better quality than the traditional cross-correlation algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.248-253
• /
• 2011

This paper proposes the robust matching algorithm for optical images obtained by WSI(White-light Scanning Interferometer) machine. The matching algorithms are divided by two part according to the matching points: algorithm whether the matching points between two images exist or not. Also, after matching the images, we propose the algorithm to smooth the matched image. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 1999.10a
• /
• pp.44-45
• /
• 1999

The term ′multimedia′ has been one of the most pervasively used terms for the last a few years. Dyrli and Kinnaman(1995) define multimedia as "the seamless digital integration of text, graphics, animation, audio, still image, and motion video in a way that provides individual users with high levels of control and interaction".(omitted)

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2007.11a
• /
• pp.173-174
• /
• 2007

Through Silicon Via ( TSV)는 향후3D integration devices (CMOS image sensors) 와 보다 더 직접화되고 진보된 memory stack에 기여 할 것이다. 이는 한층 더 진보된 microprocessors system 을 구축 하리라 본다. 해서 본문은 TSV plasma etching processing 소개와 특히 Bosch process에 대한 개선 방법을 제시하고자 한다.

• The Journal of Bigdata
• /
• v.4 no.1
• /
• pp.53-61
• /
• 2019

The extracellular matrix, which provides the structural and biochemical support of surrounding cells, is a cell physiological modulator that controls cell division and differentiation. In the bio sector, the company produces Scapold, a three-dimensional support for tissue engineering, and cultivates stem cells in the produced Scapold to be transplanted into animals to assess tissue regeneration. This depends on components such as collagen in the tissue. Therefore, it is very important to identify the inclusion rate and distribution of components in the tissue, and the data are obtained by analyzing the color of the dyed tissue image. The process from image collection to analysis is costly, and the data collected and analyzed are managed in different formats by different research institutions. Therefore, data integration management and analysis results search are not being performed. In this paper, we establish a database that can manage relevant bigdata in an integrated manner, and propose a bio-image integrated management and retrieval system that can be searched based on color, an important analytical measure in this field of study.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.4 no.3
• /
• pp.182-188
• /
• 2004

We demonstrate a $2.1\;{\times}\;1.0\;{\times}\;0.1cm^3$ sized compact transmitter using LTCC System-in-Package (SiP) technology for 60GHz-band wireless communication applications. For low-attenuation characteristics and resonance suppression of the SiP, we have proposed and demonstrated a coplanar double wire-bond transition and novel CPW-to-stripline transition integrating air-cavities as well as novel air-cavities embedded CPW line. The fabricated transmitter achieves an output of 13dBm at a RF frequency of 62GHz, an IF frequency of 2.4GHz, and a LO frequency of 59.6GHz. The up-conversion gain is 11dB, while the LO signal is suppressed with the image rejection mixer below -21.4dBc, and the image and spurious signals are also suppressed below -31dBc.