Shengkun Wang

Shengkun Wang

Auto-generated profile, based on publicly available information

Shengkun Wang

Virginia Tech, Alexandria, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 November 2023
Verified
Conference Paper
Open access
LWLinhan Wang
Linhan Wang
SLShuo Lei
Shuo Lei
JHJianfeng He
Jianfeng He
SWShengkun Wang
Shengkun Wang
MZMin Zhang
Min Zhang
CLChang-Tien Lu
Chang-Tien Lu
Remote sensing image semantic segmentation is an important problem for remote sensing image interpretation. Although remarkable progress has been achieved, existing deep neural network methods suffer from the reliance on massive training data. Few-shot remote sensing semantic segmentation aims at learning to segment target objects from a query image using only a few annotated support images of the target class. Most existing few-shot learning methods stem primarily from their sole focus on extracting information from support images, thereby failing to effectively address the large variance in appearance and scales of geographic objects. To tackle these challenges, we propose a Self-Correlation and Cross-Correlation Learning Network for the few-shot remote sensing image semantic segmentation. Our model enhances the generalization by considering both self-correlation and cross-correlation between support and query images to make segmentation predictions. To further explore the self-correlation with the query image, we propose to adopt a classical spectral method to produce a class-agnostic segmentation mask based on the basic visual information of the image. Extensive experiments on two remote sensing image datasets demonstrate the effectiveness and superiority of our model in few-shot remote sensing image semantic segmentation. The code is available at https://github.com/linhanwang/SCCNet.

22 November 2024
Verified
Conference Paper
Open access
MAMariam Almutairi
Mariam Almutairi
LALulwah AlKulaib
Lulwah AlKulaib
SWShengkun Wang
Shengkun Wang
Zhiqian ChenZhiqian Chen
Zhiqian Chen
YAYoussif Almutairi
Youssif Almutairi
CLChang-Tien Lu
Chang-Tien Lu
The shift to electronic health records (EHRs) has enhanced patient care and research, but data sharing and complex clinical terminology remain challenges. The Fast Healthcare Interoperability Resource (FHIR) addresses interoperability issues, though extracting insights from FHIR data is still difficult. Traditional analytics often miss critical clinical context, and managing FHIR data requires advanced skills that are in short supply. This study presents FHIRViz, a novel analytics tool that integrates FHIR data with a semantic layer via a knowledge graph. It employs a large language model (LLM) system to extract insights and visualize them effectively. A retrieval vector store improves performance by saving successful generations for fine-tuning. FHIRViz translates clinical queries into actionable insights with high accuracy. Results show FHIRViz with GPT-4 achieving 92.62% accuracy, while Gemini 1.5 Pro reaches 89.34%, demonstrating the tool's potential in overcoming healthcare data analytics challenges.

6 November 2023
Verified
Conference Paper
Open access
SWShengkun Wang
Shengkun Wang
YBYangxiao Bai
Yangxiao Bai
KFKaiqun Fu
Kaiqun Fu
LWLinhan Wang
Linhan Wang
CLChang-Tien Lu
Chang-Tien Lu
TJTaoran Ji
Taoran Ji
For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being. To this end, we harness the power of social media data, a rich source of public sentiment, to enhance the accuracy of stock market predictions. Diverging from conventional methods, we pioneer an approach that integrates sentiment analysis, macroeconomic indicators, search engine data, and historical prices within a multi-attention deep learning model, masterfully decoding the complex patterns inherent in the data. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.


1 October 2026 in Journal of Library Metadata
Verified
Journal Article
Closed access
SWShengkun Wang
Shengkun Wang
MSMeizi Song
Meizi Song
YCYinlin Chen
Yinlin Chen
Libraries, repositories, and cultural heritage aggregators manage growing volumes of digital records, and metadata creation often becomes the bottleneck between ingest and discovery. Controlled met...