Search

Your search keyword '"Chai, Tingting"' showing total 28 results
Start Over Author "Chai, Tingting" Search Limiters Full Text
28 results on '"Chai, Tingting"'

1. Adaptive Prompt Learning-based Few-Shot Sentiment Analysis

Author

Zhang, Pengfei, Chai, Tingting, and Xu, Yongdong

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

In the field of natural language processing, sentiment analysis via deep learning has a excellent performance by using large labeled datasets. Meanwhile, labeled data are insufficient in many sentiment analysis, and obtaining these data is time-consuming and laborious. Prompt learning devotes to resolving the data deficiency by reformulating downstream tasks with the help of prompt. In this way, the appropriate prompt is very important for the performance of the model. This paper proposes an adaptive prompting(AP) construction strategy using seq2seq-attention structure to acquire the semantic information of the input sequence. Then dynamically construct adaptive prompt which can not only improve the quality of the prompt, but also can effectively generalize to other fields by pre-trained prompt which is constructed by existing public labeled data. The experimental results on FewCLUE datasets demonstrate that the proposed method AP can effectively construct appropriate adaptive prompt regardless of the quality of hand-crafted prompt and outperform the state-of-the-art baselines.

Published
2022

3. Palmprint Recognition in Uncontrolled and Uncooperative Environment

Author

Matkowski, Wojciech Michal, Chai, Tingting, and Kong, Adams Wai Kin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Online palmprint recognition and latent palmprint identification are two branches of palmprint studies. The former uses middle-resolution images collected by a digital camera in a well-controlled or contact-based environment with user cooperation for commercial applications and the latter uses high-resolution latent palmprints collected in crime scenes for forensic investigation. However, these two branches do not cover some palmprint images which have the potential for forensic investigation. Due to the prevalence of smartphone and consumer camera, more evidence is in the form of digital images taken in uncontrolled and uncooperative environment, e.g., child pornographic images and terrorist images, where the criminals commonly hide or cover their face. However, their palms can be observable. To study palmprint identification on images collected in uncontrolled and uncooperative environment, a new palmprint database is established and an end-to-end deep learning algorithm is proposed. The new database named NTU Palmprints from the Internet (NTU-PI-v1) contains 7881 images from 2035 palms collected from the Internet. The proposed algorithm consists of an alignment network and a feature extraction network and is end-to-end trainable. The proposed algorithm is compared with the state-of-the-art online palmprint recognition methods and evaluated on three public contactless palmprint databases, IITD, CASIA, and PolyU and two new databases, NTU-PI-v1 and NTU contactless palmprint database. The experimental results showed that the proposed algorithm outperforms the existing palmprint recognition methods., Comment: Accepted in the IEEE Transactions on Information Forensics and Security

Published
2019
Full Text
View/download PDF

4. Pelvic rotation correction combined with Schroth exercises for pelvic and spinal deformities in mild adolescent idiopathic scoliosis: A randomized controlled trial.

Author

Zhang, Yafei, Chai, Tingting, Weng, Hao, and Liu, Yang

Subjects
*ADOLESCENT idiopathic scoliosis, *SPINE abnormalities, *RANDOMIZED controlled trials, *EXPERIMENTAL groups, *ROTATIONAL motion, *KEGEL exercises
Abstract

Introduction: Individualized treatment of spinal deformity is needed for adolescent idiopathic scoliosis (AIS), and the integration of pelvic rotation correction based on proprioceptive neuromuscular facilitation (PNF) into regular physiotherapy may be a promising approach. However, few high-quality studies have investigated its effects. This study aimed to evaluate the efficacy of pelvic rotation correction combined with Schroth exercises in the treatment of mild AIS. Methods: This was a randomized controlled trial. Forty-two AIS patients were randomly divided into experimental and control groups. Both groups underwent 20 therapeutic sessions over 24 weeks. All patients (n = 42) performed Schroth exercises at each session. In addition, the experimental group (n = 21) also participated in a pelvic rotation correction program based on PNF at each session. The primary outcome was the concave/convex ratio of hipbone widths, and the secondary outcomes included the Cobb angle, trunk rotation angle, self-perception, apical vertebral translation, and apical vertebral rotation. Patients were evaluated before and after 24 weeks of intervention. Results: There was a significant between-group difference in the change from baseline between the experimental and control groups for the following parameters: concave/convex ratio 2.89% (95% confidence interval [CI], 1.58 to 4.20, P<0.001), trunk rotation angle −1.26° (95% CI, −2.20 to −0.32; P = 0.01), and apical vertebral rotation improved by at least one class from baseline in 3 patients (14.3%) in the control group and 9 patients (42.9%) in the experimental group (P = 0.04). While Cobb angle −1.60° (95% CI, −7.75 to 0.54; P = 0.14), self-image 0.149 (95% CI, 0.001 to 0.297; P = 0.049), apical vertebral translation −0.58 mm (95% CI, −3.83 to 2.67; P = 0.72), and pelvic obliquity 0.10° (95% CI, −0.21 to 0.41; P = 0.52) did not differ significantly. Conclusions: Pelvic rotation correction combined with Schroth exercises more effectively improved pelvic axial rotation and other spinal deformities, including trunk rotation and apical vertebral rotation, than Schroth exercises alone in the treatment of mild AIS. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

7. Health Risk Assessment of Antibiotic Pollutants in Large Yellow Croakers from Zhejiang Aquaculture Sites.

Author

Li, Zongjie, Jin, Yinyin, Wang, Xingyu, Xu, Liudong, Teng, Liyan, Fu, Kang, Li, Baoling, Li, Yulu, Huang, Ying, Ma, Ning, Cui, Feng, and Chai, Tingting

Subjects
LARIMICHTHYS, HEALTH risk assessment, POLLUTANTS, ANTIBIOTICS, FLUOROQUINOLONES
Abstract

Intensive aquaculture combatting the decline of large yellow croaker populations can trigger bacterial outbreaks, resulting in extensive antibiotic use. In this study, we screened 5 aquaculture sites in the coastal areas of Zhejiang and identified 17 antibiotics in large yellow croakers using UPLC-MS/MS. The distribution and occurrence of antibiotic pollutants were different in the different tissues of large yellow croakers, being primarily dominated by quinolones. Relatively higher average residue levels of enrofloxacin and ciprofloxacin were detected in the inedible parts, specifically the gills (37.29 μg/kg). Meanwhile, relatively high average residue levels of enrofloxacin and ciprofloxacin were also found in the edible parts, particularly in the muscle (23.18 μg/kg). We observed that the residue levels detected in the swim bladder exceeded the prescribed limit for fish muscle, but there is currently no specific regulatory limit established for this particular tissue. Despite the HI values of enrofloxacin and ciprofloxacin being below 0.01, the health risks should not be disregarded. The findings of this research provide significant practical implications for assessing antibiotic contamination and enhancing the risk management of coastal regions. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results