Shengjia Cui

ORCID: 0000-0001-8884-0167
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Persona Design and Applications
  • Technology Use by Older Adults
  • Privacy, Security, and Data Protection
  • Advanced Electrical Measurement Techniques
  • Natural Language Processing Techniques
  • Dental Radiography and Imaging
  • Sensor Technology and Measurement Systems
  • Remote Sensing and Land Use
  • Statistical Methods in Clinical Trials
  • Statistical Methods and Inference
  • Fault Detection and Control Systems
  • Data Visualization and Analytics
  • Advanced Statistical Process Monitoring
  • Topic Modeling
  • Speech and dialogue systems
  • Advanced Chemical Sensor Technologies
  • Oral and Maxillofacial Pathology
  • Remote-Sensing Image Classification
  • Medical Image Segmentation Techniques

Baidu (China)
2021-2023

With the development of big data, analyzing environmental benefits transportation systems by artificial intelligence has become a hot issue in recent years. The ground traffic changes can be overlooked from high-altitude perspective, using technology multi-temporal remote sensing change detection. We proposed novel unsupervised algorithm combining image transformation and deep learning method. new for images is named multi-attention slow feature analysis (ASFA). In this model, three parts...

10.3390/rs14122834 article EN cc-by Remote Sensing 2022-06-13

In this paper, we propose a novel method, an adaptive localizing region-based level set using convolutional neural network, for improving performance of maxillary sinus segmentation. The healthy without lesion inside is easy conventional algorithms. However, in practice, most the cases are filled with lesions great heterogeneity which lead to lower accuracy. Therefore, provide strategy avoid active contour from being trapped into nontarget area. First, features and studied network (CNN) two...

10.1155/2021/4824613 article EN cc-by Computational Intelligence and Neuroscience 2021-01-01

Representation of language is the first and critical task for Natural Language Understanding (NLU) in a dialogue system. Pretraining, embedding model, fine-tuning intent classification slot-filling are popular well-performing approaches but time consuming inefficient low-resource languages. Concretely, out-of-vocabulary transferring to different languages two tough challenges multilingual pretrained cross-lingual models. Furthermore, quality-proved parallel data necessary current frameworks....

10.1155/2022/8407713 article EN Mathematical Problems in Engineering 2022-09-16

10.1504/ijcat.2022.10054567 article EN International Journal of Computer Applications in Technology 2022-01-01

Determining the long-term causal effects as well making decisions in a timely fashion are most challenging and significant tasks A/B tests. The key challenge is that short-term may be different, especially an online controlled experiment low-qualified ads strategy with high revenue hurt users' service experience future. We propose 'Transformer for Long-Term Effect (TLTE)' method to encode latent features predict outcome of estimate effects. TLTE utilises transformer structure capture...

10.1504/ijcat.2022.129383 article EN International Journal of Computer Applications in Technology 2022-01-01

10.1504/ijcat.2022.10055203 article IT International Journal of Computer Applications in Technology 2022-01-01

10.1504/ijcat.2022.129882 article IT International Journal of Computer Applications in Technology 2022-01-01
Coming Soon ...