http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Knowledge Transfer Using User-Generated Data within Real-Time Cloud Services
( Jing Zhang ),( Jianhan Pan ),( Zhicheng Cai ),( Min Li ),( Lin Cui ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.1
When automatic speech recognition (ASR) is provided as a cloud service, it is easy to collect voice and application domain data from users. Harnessing these data will facilitate the provision of more personalized services. In this paper, we demonstrate our transfer learning-based knowledge service that built with the user-generated data collected through our novel system that deliveries personalized ASR service. First, we discuss the motivation, challenges, and prospects of building up such a knowledge-based service-oriented system. Second, we present a Quadruple Transfer Learning (QTL) method that can learn a classification model from a source domain and transfer it to a target domain. Third, we provide an overview architecture of our novel system that collects voice data from mobile users, labels the data via crowdsourcing, utilises these collected user-generated data to train different machine learning models, and delivers the personalised real-time cloud services. Finally, we use the E-Book data collected from our system to train classification models and apply them in the smart TV domain, and the experimental results show that our QTL method is effective in two classification tasks, which confirms that the knowledge transfer provides a value-added service for the upper-layer mobile applications in different domains.
Occlusal deviations in adolescents with idiopathic and congenital scoliosis
Zhang Hao,Ma Jingbo,Zhang Zhicheng,Feng Yafei,Cai Chuan,Wang Chao 대한치과교정학회 2022 대한치과교정학회지 Vol.52 No.3
Objective: This cross-sectional study aimed to investigate the characteristics of malocclusions in scoliotic patients through clinical examinations. Methods: Fifty-eight patients with idiopathic scoliosis (IS) and 48 patients with congenital scoliosis (CS) participated in the study. A randomly selected group of 152 orthopedically healthy children served as the control group. Standardized orthodontic and orthopedic examination protocols were used to record the occlusal patterns and type of scoliosis. Assessments were made by three experienced orthodontists and a spinal surgery team. The differences in the frequency distribution of occlusal patterns were evaluated by the chi-squared test. Results: In comparison with patients showing IS, patients with CS showed a higher incidence of Cobb angle ≥ 45° (p = 0.020) and included a higher proportion of patients receiving surgical treatments (p < 0.001). The distribution of the Angle Class II subgroup was significantly higher in the IS (p < 0.001) and CS (p = 0.031) groups than in the control group. In comparison with the healthy controls, the CS and IS groups showed significantly higher (p < 0.05) frequencies of asymmetric molar and asymmetric canine relationships, upper and lower middle line deviations, anterior deep overbite, unilateral posterior crossbite, and canted occlusal plane, with the frequencies being especially higher in CS patients and to a lesser extent in IS patients. Conclusions: Patients with scoliosis showed a high frequency of malocclusions, which were most obvious in patients with CS.