Xiaohan Zhang

ORCID: 0000-0003-1522-4042
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Natural Language Processing Techniques
  • Ophthalmology and Visual Impairment Studies
  • Geochemistry and Geologic Mapping
  • Machine Learning and ELM
  • Corneal surgery and disorders
  • Linguistic Education and Pedagogy
  • Multimodal Machine Learning Applications
  • Sociology and Education Studies
  • Optical Imaging and Spectroscopy Techniques
  • Electricity Theft Detection Techniques
  • Imbalanced Data Classification Techniques
  • Fault Detection and Control Systems
  • Housing Market and Economics
  • Photoacoustic and Ultrasonic Imaging
  • Glaucoma and retinal disorders
  • Energy, Environment, Economic Growth
  • Retinal Diseases and Treatments
  • Neural Networks and Applications
  • Domain Adaptation and Few-Shot Learning
  • Retirement, Disability, and Employment
  • Anomaly Detection Techniques and Applications
  • Environmental Impact and Sustainability
  • Financial Literacy, Pension, Retirement Analysis
  • Education Methods and Technologies

Chinese Academy of Medical Sciences & Peking Union Medical College
2023-2025

Guang’anmen Hospital
2023-2025

Shandong First Medical University
2025

Shandong Provincial Hospital
2025

Dalian Maritime University
2022-2024

Heze University
2024

Tongji University
2022-2024

Zhejiang University
2019-2024

Dalian Polytechnic University
2023-2024

Federal Reserve Bank of Dallas
2022-2024

Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizon planning problems. By contrast, classical planners, once a problem is given formatted way, use efficient search algorithms quickly identify correct, or even optimal, plans. In an effort get the best of both worlds, this paper introduces...

10.48550/arxiv.2304.11477 preprint EN cc-by arXiv (Cornell University) 2023-01-01

An increasing number of consumer products include user interfaces that rely on touch input. While digital fabrication techniques such as 3D printing make it easier to prototype the shape custom devices, adding interactivity prototypes remains a challenge for many designers. We introduce Midas, software and hardware toolkit support design, fabrication, programming flexible capacitive sensors interactive objects. With designers first define desired shape, layout, type sensitive areas, well...

10.1145/2380116.2380189 article EN 2012-10-05

In order to improve the signal-to-noise ratio of hyperspectral sensors and exploit potential satellite data for predicting soil properties, we took MingShui County as study area, which area is approximately 1481 km2, selected Gaofen-5 (GF-5) image explore an applicable accurate denoising method that can effectively prediction accuracy organic matter (SOM) content. First, fractional-order derivative (FOD) processing performed on original reflectance (OR) evaluate optimal FOD. Second, singular...

10.3390/rs13122273 article EN cc-by Remote Sensing 2021-06-10

Advanced artificial intelligence (AI) technologies are now widely employed in China's medical and healthcare fields. Enormous amounts of personal data collected from various sources inserted into AI algorithms for purposes, producing challenges to patient's privacy. This is a comparative study Chinese, United States, European Union operational rules that then used functions, particularly focusing on legal differences deficiencies. The conceptual boundaries privacy information, the influence...

10.3390/healthcare10101878 article EN Healthcare 2022-09-27

Social media texts spontaneously produced and uploaded by the public contain a wealth of disaster information. As supplementary data source for remote sensing, they have played an important role in reduction emergency response recent years. However, social also has certain flaws, such as insufficient location information, etc. This affects efficiency combining these with sensing data. For flood disasters particular, extensively flooded areas limit distribution data, which makes it difficult...

10.3390/rs14051199 article EN cc-by Remote Sensing 2022-02-28

Since the safe and reliable behavior of a Railway Switch Machine (RSM) is definitely pivotal for rail transportation, scholars engineers have studied considerable number algorithms RSM fault diagnosis via many kinds sensor information. However, yet to consider impact sensors' states on classification, which cannot be ignored in practical railway applications. To fill gap, we propose an end-to-end deep learning architecture named Fault Diagnosis Considering Sensor Abnormality Network...

10.1109/itsc57777.2023.10422266 article EN 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) 2023-09-24

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

10.2139/ssrn.5090895 preprint EN 2025-01-01

Inflammation is among the known causes of cisplatin-induced hearing loss (CIHL), but its exact pathophysiological mechanisms remain unclear. Herein, we demonstrated that pyroptosis—a recently identified inflammatory type regulated cell death dependent on gasdermin D (GSDMD)—was activated in cochleae cisplatin-treated mice, causing CIHL. Meanwhile, treatment with GSDMD inhibitor necrosulfonamide alleviated CIHL these mice. To further examine role GSDMD-mediated pyroptosis CIHL, conducted...

10.1073/pnas.2415805122 article EN cc-by-nc-nd Proceedings of the National Academy of Sciences 2025-03-11

Developing a rapid and simple method for the detection of berberine chloride (BBC), one kind natural antibiotic, is significant to ensure reasonable control administration antibiotic residues in food other feed. In this report, sensitive selective fluorescent probe based on water-soluble perylene diimide derivative (PDI-Asp) has been screened (BBC). The sensing performance mechanism were systematically investigated by using UV–vis fluorescence spectroscopic techniques. Meanwhile, influencing...

10.1021/acssuschemeng.0c01177 article EN ACS Sustainable Chemistry & Engineering 2020-04-13

Incorporating expert knowledge at the time machine learning models are trained holds promise for producing that easier to interpret. The main objectives of this study were use a feature engineering approach incorporate clinical prior applying techniques, and assess impact on model complexity performance. Four predict mortality with severe asthma case study. Experiments select fewer input features based discriminative score showed low moderate precision discovering clinically meaningful...

10.1371/journal.pone.0231300 article EN cc-by PLoS ONE 2020-04-23

In the ongoing COVID-19 pandemic, digital technologies have played a vital role to minimize spread of COVID-19, and control its pitfalls for general public. Without such technologies, bringing pandemic under would been tricky slow. Consequently, exploration status, devising appropriate mitigation strategies also be difficult. this paper, we present comprehensive analysis community-beneficial that were employed fight pandemic. Specifically, demonstrate practical applications ten major...

10.3390/covid3010006 article EN cc-by COVID 2023-01-16
Coming Soon ...