http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
건설 공정 지연 예측을 위한 인공지능 기반 경고 시스템 개발
정희찬,한기웅,이병훈,한예지,허경휘,최호창,한성원 대한산업공학회 2022 대한산업공학회지 Vol.48 No.4
In the construction industry, the construction process is managed based on the completed construction in comparison to the planned construction. With the current construction management system, it is difficult to respond to construction delays in advance, because the construction process rate cannot be estimated quantitatively. In this paper, we developed an AI-based warning system that proactively predicts the delay in construction based on the completed construction of the past and additional data such as budget, subcontractor, and weather data. We experimented on two types of construction sites and seven machine and deep learning models and evaluated the prediction performance of the models for the construction process rate of the future three months with MAE. We analyze the importance of each feature on the model prediction using SHAP values. Furthermore, we select the adequate target variable for construction process prediction based on the results of prediction and key delay factors.
정희찬,김관,이희철,김홍국,김재묵,Jeong, Hi-Chan,Kim, Kwan,Lee, Hee-Chul,Kim, Hong-Kook,Kim, Jae-Mook 대한전자공학회 1995 전자공학회논문지-A Vol.32 No.2
The structure of boron ion-implanted pn junctio in the vacancy-doped p-type HgCdTe was investigated with the differential Hall measurement. The as-implanted junction showed the electron concentration as high as 1${\times}10^{18}/cm^{3}$ and the junction depth of 0.6.mu.m. When the HgCdTe junction was heated in oven, the electron concentration near the junction decreased and the junction depth increased as the annealing temperature and time increased. The junction structure after the thermal annealing was n$^{+}$/n$^{-}$/p. For the 200.deg. C 20min annealed sample, the electron mobility was 10$^{4}cm^{2}/V{\cdot}$s near the surface(n$^{+}$), and was larger thatn 10$^{5}cm^{2}/V{\cdot}$s near the junction(n$^{+}$). The junction formation mechanism is conjectured as follows. When HgCdTe is ion-implanted, the ion energy generates crystal defecis and displaced Hg atoms HgCdTe is ion-implanted, the ion energy generates crystal defecis and displaced Hg atoms near the surface. The displaced Hg vacancies diffuse in easily by the thernal treatment and a fill the Hg vacancies in the p-HgCdTe substrate. With the Hg vacancies filled completely, the GfCdTe substrate becomes n-type because of the residual n-type impurity which was added during the wafer growing. Therefore, the n$^{+}$/n$^{-}$/p regions are formed by crystal defects, residual impurities, and Hg vacancies, respectively.
Co-Cr-Ti 합금으로 제작한 conical telescope 외관의 변연적합도와 유지력에 관한 연구
정희찬,정창모,전영찬,임장섭,Jung, Hi-Chan,Jeong, Chang-Mo,Jeon, Young-Chan,Lim, Jang-Seop 대한치과보철학회 2000 대한치과보철학회지 Vol.38 No.2
The purpose of this study was to investigate the effects of investing conditions on the marginal discrepancy of conical telescope outer crown with Co-Cr-Ti alloy(Dentitan) and to compare the marginal discrepancy and the retention force of outer crowns using different pattern materials(plastic foil, casting wax, pattern resin). To evaluate the effects of investing conditions on the marginal discrepancy, patterns with plastic foil were invested under three different liquid/powder ratio conditions using phosphate bonded investment(Univest-nonprecious): standard, 10% decreased and 10% increased. At each liquid/powder ratio condition, metal ring was lined with single or double layers of ceramic ring liner. The marginal discrepancy of outer crown at different investing conditions was measured by ${\times}100$ compact measuring microscope(STM5, Olympus, Japan). For measurement of the marginal discrepancy and the retention force of outer crown using different pattern materials, the investing condition of 10% decreased liquid/powder ratio and double layers of ring liner was selected because this investing condition resulted in the best fit of outer crown. Marginal discrepancy was measured in the same way above and retention force on universal testing machine. Under the conditions of this study, the following conclusions were drawn: 1. The thickness of ring liner had more influence on the marginal discrepancy of outer crown than the liquid/powder ratio, and the acceptable marginal fitness could not be expected at the investing condition directed by investment manufacturer 2. There were no differences in the marginal discrepancy of outer crown among three different pattern materials(P>0.05). 3. Casting wax showed the greatest retention force(1640g) of outer crown, followed by pattern resin(1110g), plastic foil(820g). However, there was no significant difference between plastic foil and pattern resin(P>0.05). 4. Plastic foil showed the least variation in marginal discrepancy and retention force.
Gene Regulatory Network Analysis for Triple-Negative Breast Neoplasms by Using Gene Expression Data
정희찬,김성환,이정훈,김주한,한성원 한국유방암학회 2017 Journal of breast cancer Vol.20 No.3
Purpose: To better identify the physiology of triple-negative breast neoplasm (TNBN), we analyzed the TNBN gene regulatory network using gene expression data. Methods: We collected TNBN gene expression data from The Cancer Genome Atlas to construct a TNBN gene regulatory network using least absolute shrinkage and selection operator regression. In addition, we constructed a triple-positive breast neoplasm (TPBN) network for comparison. Furthermore, survival analysis based on gene expression levels and differentially expressed gene (DEG) analysis were carried out to support and compare the network analysis results, respectively. Results: The TNBN gene regulatory network, which followed a power-law distribution, had 10,237 vertices and 17,773 edges, with an average vertex-to-vertex distance of 8.6. The genes ZDHHC20 and RAPGEF6 were identified by centrality analysis to be important vertices. However, in the DEG analysis, we could not find meaningful fold changes in ZDHHC20 and RAPGEF6 between the TPBN and TNBN gene expression data. In the multivariate survival analysis, the hazard ratio for ZDHHC20 and RAPGEF6 was 1.677 (1.192–2.357) and 1.676 (1.222–2.299), respectively. Conclusion: Our TNBN gene regulatory network was a scale-free one, which means that the network would be easily destroyed if the hub vertices were attacked. Thus, it is important to identify the hub vertices in the network analysis. In the TNBN gene regulatory network, ZDHHC20 and RAPGEF6 were found to be oncogenes. Further study of these genes could help to reveal a novel method for treating TNBN in the future.