RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제
      • 좁혀본 항목 보기순서

        • 원문유무
        • 원문제공처
        • 등재정보
        • 학술지명
        • 주제분류
        • 발행연도
        • 작성언어
        • 저자
          펼치기

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • KCI등재

        A High-Precision Feature Extraction Network of Fatigue Speech from Air Traffic Controller Radiotelephony Based on Improved Deep Learning

        Zhiyuan Shen,Yitao Wei 한국통신학회 2021 ICT Express Vol.7 No.4

        Air traffic controller (ATC) fatigue is receiving considerable attention in recent studies because it represents a major cause of air traffic incidences. Research has revealed that the presence of fatigue can be detected by analysing speech utterances. However, constructing a complete labelled fatigue data set is very time-consuming. Moreover, a manually constructed speech collection will often contain only little key information to be used effectively in fatigue recognition, while multilevel deep models based on such speech materials often have overfitting problems due to an explosive increase of model parameters. To address these problems, a novel deep learning framework is proposed in this study to integrate active learning (AL) into complex speech features selected from a large set of unlabelled speech data in order to overcome the loss of information. A shallow feature set is first extracted using stacked sparse autoencoder networks, in which fatigue state challenge features from a manually selected speaker set of are exploited as the input vector. A densely connected convolutional autoencoder (DCAE) is then proposed to learn advanced features automatically from spectrograms of the selected data to supplement the fatigue features. The network can be effectively trained using a relatively small number of labelled samples with the help of AL sampling strategies, and the addition of a dense block to the convolutional automatic encoder can decrease the number of parameters and make the model easier to fit. Finally, the two above-mentioned features are combined using multiple kernel learning with a support-vector-machine classifier. A series of comparative experiments using the Civil Aviation Administration of China radiotelephony corpus demonstrates that the proposed method provides a significant improvement in the detection precision compared to current state-of-the-art approaches.

      • Novel High Speed Railway Uninterruptible Flexible Connector Based On Modular Multilevel Converter Structure

        Xu Tian,Qirong Jiang,Yingdong Wei,Junmin Zhang,Yitao Wei 전력전자학회 2015 ICPE(ISPE)논문집 Vol.2015 No.6

        Phase sequence commutating method among traction feeders results in a neutral section without power supply between two feeders in traction substation of electrified railway. Electric locomotives suffer from a nopower time of more than 100 millisecond when going through the neutral section, during which the power failure and restoration process causes serious over-voltage and over-current problems. A novel railway uninterruptible flexible connector based on two-phase modular multilevel converter structure(MMC-UFC) is proposed in this paper, which can completely eliminate power supply dead zone. System utilization and operational principle are analyzed. Mathematical model of MMC-UFC is built to derive the difference between MMC-UFC. Double close-loop control strategies are given and close-loop control of both upper arm current and lower arm current for MMC converter is proposed to ensure the quality of output current. PSCAD/EMTDC simulations and experiment are carried out to prove the effectiveness of proposed MMC-UFC and its control system.

      • KCI등재

        A comprehensive quality analysis of randomized controlled clinical trials of Asian ginseng and American ginseng based on the CONSORT guideline

        Weijie Chen,Xiuzhu Li,Zhejie Chen,Wei Hao,Peifen Yao,Meng Li,Kunmeng Liu,Hao Hu,Shengpeng Wang,Yitao Wang 고려인삼학회 2022 Journal of Ginseng Research Vol.46 No.1

        Ginseng is an international herb that has been used for thousands of years. Two species most commonly applied and investigated in the ginseng family are Asian ginseng and American ginseng. The number of randomized controlled clinical trials (RCTs) has conspicuously increased, driven by the rapid development of ginseng. However, the reporting of RCT items of ginseng is deficient because of different trial designs and reporting formats, which is a challenge for researchers who are looking for the data with high quality and reliability. Thus, this study focused on providing an extensive analysis of these two species and examined the quality of the RCTs, based on the Consolidated Standards of Reporting Trials (CONSORT) guideline. Ninety-one RCTs conducted from 1980 to 2019 that were related to Asian ginseng and American ginseng used singly met our inclusion criteria. We found that the reporting quality of the two species has improved during the past 40 years. Publication date and sample size were significantly associated with the reporting quality. Rigorous RCTs designed for the species of ginseng are warranted, which can shed light on product research and development of ginseng in the future.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼