http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
주조품 분류 정확도 향상을 위한 적대적 생성 네트워크(GAN) 이미지 데이터 확장
이준협 ( Junhyup Lee ),박기홍 ( Keehong Park ),은준엽 ( Joonyup Eun ) 한국로지스틱스학회 2021 로지스틱스연구 Vol.29 No.4
Casting is a method of making metal through molds by changing solid metal into liquid state, which has the advantage of being able to yield a large number of products with complex shapes. Owing to the advantage, it is widely used to manufacture jewelry, artwork, surgical implants, and impellers in automobiles and ships. However, low quality products can be produced due to pinholes, sand blows, shrinkage cavities, and cracks that are well-known issues in casting. Especially using a defective impeller, a rotating element of a centrifugal pump that accelerates fluid outside from the center and transfers the power of fluid kinetic energy, causes a significant damage to its pump and/or workers nearby due to its high pressure. Therefore, foundries endeavor to catch any defectives before sending them out to purchasers. However, foundries are usually small or medium-sized enterprises. It is difficult for them to hire additional experienced workers to catch more defectives or install photographing and imaging-storing devices to keep track of a large amount of product images for analyses. The foundries usually have a few inspectors to catch defective products and, due to a shortage of manpower and human inaccuracy, defective products are often classified as non-defective products. This study shows that a combination of classic augmentation and self-attention generative adversarial network improves the accuracy of classifying non-defective and defective impellers by augmenting a limited amount of image data that can be even manually photographed. Combining classic augmentation and self-attention generative adversarial network outperforms the sole use of classic augmentation in generating quality images for convolutional neural network.
QFD와 벤치마킹을 활용한 엔젤 교육 프로그램 설계 연구
이형주 ( Hyung Joo Lee ),황보윤 ( Yun Hwangbo ),은준엽 ( Joonyup Eun ) 한국생산성학회 2021 生産性論集 Vol.35 No.2
In order to vitalize angel investments, the Government of South Korea has recently promoted the general public investments, regional investments and network reinforcement, deregulation, and tax support. There is an urgent need of educational programs to discover potential angels and enhance their investment capabilities to promote the general public investments. This study attempts to present the design direction of consumer-centered angel educational programs using the quality function deployment(QFD) and benchmarking. The ameliorated programs are expected to discover potential angels and improve their investment capabilities. This study identifies the limitations of the existing job-oriented angel education through a literature review and confirms the necessity of consumer-oriented Kano-QFD-based educational programs. Subsequently, attractive quality factors are derived from Kano-based demand surveys of 19 angels, 25 startup representatives, and 20 education consultants. Customer needs priorities and quality importance are also determined using the QFD. In addition, the angel educational programs of 7 domestic and foreign institutions are benchmarked. Based on this empirical research, we identify the design direction of angel educational programs as follows. First, the program needs to be customized in depth. Second, the program needs to inspire self-esteem by conferring qualified angel investment certificates upon completion of the required education. Third, the program needs to invigorate the community of trainees and graduates. Fourth, the program needs to be designed to establish a refresher education system for angels. Fifth, the program needs to be a blended delivery of face-to-face and non-face-to-face education centering on online non-face-to-face education. Sixth, according to the target audience, the program should incorporate quality importance and customer needs priorities. This research proposes the direction to improve angel educational programs. It is expected to study the design of segmented educational programs that consider angel investment experience, gender, and region for future research.