http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Huan yu Hsu (검색결과 5 건)
- 무료
- 기관 내 무료
- 유료
-
-
Huan Chen,Jyh-Yih Hsu,Jia-You Hsieh,Hsin-Yao Hsu,Chia-Hao Chang,Yu-Ju Lin 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.12
The predictive maintenance of wind turbines has become a critical issue with the rapid development of wind power generation. The early detection of abnormal operation conditions can prevent failure status, which takes a long time to recover. Energy waste can also be reduced while maintenance efficiency can be improved by using a supervisory control and data acquisition (SCADA) system to monitor the operation status of wind turbines. Massive data are generated from different sensors during wind turbine operation, and SCADA can be used to gather reports about hundreds of possible abnormal conditions. The popular maintenance methods have been mostly designed on the basis of statistical analysis and data mining. However, such schemes need not only big data but also sophisticated processing techniques. This study addresses the aforementioned challenges by proposing a deep learning model with comprehensive data preprocessing and hyperparameter tuning on batch size to achieve abnormal early detection. The necessary data preprocessing is initially conducted besides the conventional data cleaning and normalization steps, and time-series data windowing and label settings are also performed. Then, the imbalanced classes in the records are addressed by adopting an augmentation scheme called the synthetic minority oversampling technique. Principal component analysis is also used to enhance the training. Finally, the proposed deep learning method with fine-tuning is compared with three machine learning models for early anomaly event detection. Experimental results show that the proposed scheme can identify potential faults 72 hours before they occur, and the precision rate exceeds 90 %.
-
Kun-Yu Tsai,Jeng-Fu You,Tzong-Yun Tsai,Yih Jong Chern,Yu-Jen Hsu,Shu-Huan Huang,Wen-Sy Tsai 대한장연구학회 2023 Intestinal Research Vol.21 No.1
Background/Aims: Exacerbating factors of ulcerative colitis (UC) are multiple and complex with individual influence. We aimed to evaluate the efficacy of disease control by searching and restricting inflammation trigger factors of UC relapse individually in daily clinical practice. Methods: Both patients with UC history or new diagnosis were asked to avoid dairy products at first doctor visit. Individual-reported potential trigger factors were restricted when UC flared up (Mayo endoscopy score ≥1) from remission status. The remission rate, duration to remission and medication were analyzed between the groups of factor restriction complete, incomplete and unknown. Results: The total remission rate was 91.7% of 108 patients with complete restriction of dairy product. The duration to remission of UC history group was significantly longer than that of new diagnosis group (88.5 days vs. 43.4 days, P=0.006) in patients with initial endoscopic score 2–3, but no difference in patients with score 1. After first remission, the inflammation trigger factors in 161 relapse episodes of 72 patients were multiple and personal. Milk/dairy products, herb medicine/Chinese tonic food and dietary supplement were the common factors, followed by psychological issues, non-dietary factors (smoking cessation, cosmetic products) and discontinuation of medication by patients themselves. Factor unknown accounted for 14.1% of patients. The benefits of factor complete restriction included shorter duration to remission (P<0.001), less steroid and biological agent use (P=0.022) when compared to incomplete restriction or factor unknown group. Conclusions: Restriction of dairy diet first then searching and restricting trigger factors personally if UC relapse can improve the disease control and downgrade the medication usage of UC patients in daily clinical practice.
-
Li‑Huan Hsu,Yi‑chao Wu,Chou‑Chun Chiang,Jung‑Lien Chu,Yi‑Chiang Yu,An‑Hsiang Wang,Ben Jong‑Dao Jou 한국기상학회 2023 Asia-Pacific Journal of Atmospheric Sciences Vol.59 No.2
This study sought to assess the interdecadal and interannual variability of autumn extreme rainfall (ER) in Taiwan from 1979to 2019. Three types of ER events were identified based on a clustering analysis augmented by a deep autoencoder-basedneural network model. This method outperforms other methods in obtaining the optimal number of clusters by extractingthe synoptic features in advance. The patterns associated with these three types include a tropical cyclone covering Taiwan(TC), a TC-like circulation in the South China Sea (SCS) accompanied by northeasterly near northern Taiwan (TC-NE), andnortheasterly near northern Taiwan (NE). The differences in the rainfall pattern caused by the three types were discernableover Taiwan. How the PDO or ENSO modulates the regional large-scale environment to favor the occurrence of these ERevents was investigated. The occurrence of TC-NE events was simultaneously correlated with the negative phases of PDO/ENSO in the interdecadal/interannual scale. In the negative phases of PDO/ENSO, a low-level anomalous cyclone overSCS accompanied by background northeasterly favored the regional TC activities and may cause more TC-NE events. Theoccurrence of NE events is simultaneously correlated with the cold phase of ENSO. An anomalous low-level anticyclone inNortheast Asia strengthened the northeasterly toward northern Taiwan, and with the seasonal background moisture, providedfavorable conditions for the occurrence of the NE events. Overall, the occurrence of the TC events did not correlate with thePDO or ENSO signals; the reasons for the lack of correlation were discussed herein.
-
Ching-Hua Huang,Po-Lin Kuo,Ya-Ling Hsu,Tai-Tsung Chang,Hsing-I Tseng,Yu-Te Chu,Chang-Hung Kuo,Huan-Nan Chen,Chih-Hsing Hung 한국식품영양과학회 2010 Journal of medicinal food Vol.13 No.2
Dietary flavonoids have various biological functions, and there is increasing evidence that reduced prevalence and severity of allergic reactions are associated with the intake of flavonoids. Among natural flavonoids, apigenin is a potent anti-inflammatory agent. However, the mechanisms of apigenin's effect remain uncertain. Monocyte-derived chemokine (MDC) plays a pivotal role in recruiting T-helper (Th) 2 cells in the allergic inflammation process. In the late phase of allergic inflammation, the Th1 chemokine interferon-inducible protein 10 (IP-10) has also been found in elevated levels in the bronchial alveolar fluid of asthmatic children. We used human THP-1 monocyte cells, pretreated with or without apigenin, prior to lipopolysaccharide stimulation. By means of enzyme-linked immunosorbent assay, we found that apigenin inhibited production of both MDC and IP-10 by THP-1 cells and that the suppressive effect of apigenin was not reversed by the estrogen receptor antagonist ICI182780. The p65 phosphorylation of nuclear factor κB remained unaffected, but the phosphorylation of p38, c-Jun N-terminal kinase, and extracellular signal-regulated kinase mitogen-activated protein kinase pathways were all blocked. We found that inhibition of c-raf phosphorylation might be the target of apigenin's anti-inflammation property.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
