A5100377114- Land Use and Ecosystem Services
- Ecology and Vegetation Dynamics Studies
- Imbalanced Data Classification Techniques
- Urban Green Space and Health
- Plant and animal studies
- Ferroelectric and Negative Capacitance Devices
- Advancements in Semiconductor Devices and Circuit Design
- Artificial Intelligence in Healthcare
- Electricity Theft Detection Techniques
- Urban Heat Island Mitigation
- Mycorrhizal Fungi and Plant Interactions
- Vehicle License Plate Recognition
- Acute Ischemic Stroke Management
- Semiconductor materials and devices
- Lichen and fungal ecology
Shanghai Jiao Tong University
2024
East China Normal University
2020-2022
Southeast University
2022
Early predicting heart attack out of stroke patients in a view data analysis is an approach to reduce high mortality rate. Stroke-patient Intensive Care Unit are imbalanced due that with the minority patients. How predict stroke-patient becomes challenge. For processing data, this paper designs algorithm by leveraging random undersampling, clustering and oversampling techniques, which called undersampling-clustering-oversampling (shortly, UCO algorithm). The generates nearly balanced...
Urbanization is one of the major causes for plant diversity loss at local and regional scale. However, how species distribute along urban–rural gradient what relationship between urbanization degree is, not very clear. In this paper, 134 sample sites two 18 km width transects that run across urban center Shanghai were investigated. We quantified spatial patterns measured degree, which was calculated using a land use cover map derived from high resolution aerial photos. recorded 526 vascular...
Abstract Urbanization alters the physicochemical environment on an unprecedented scale and strongly affects biodiversity. How urbanization biodiversity of soil microbial communities, especially in large cities, however, is poorly known. We investigated communities from 258 sites covering a variety environmental gradients megacity Shanghai, China, to determine impact Using distance city centre, urbanized land cover, road density as three proxies characterize levels urbanization, we revealed...
The spatial distribution of plant diversity in urban areas is fundamental to understanding the relationship between urbanization and biodiversity. Previous research has primarily focused on taxonomic levels assess species richness. In contrast, investigations into patterns phylogenetic plants remain limited. This study aims investigate along an urban–rural gradient quantify how degree are related. A survey vascular was conducted at 134 randomly selected sample plots four transects Shanghai,...
The impervious surface area (ISA) is a key indicator of urbanization, which brings out serious adverse environmental and ecological consequences. ISA often estimated from remotely sensed data via spectral mixture analysis (SMA). However, accurate extraction using SMA compromised by two major factors, endmember variability plant phenology. This study developed novel approach that incorporates phenology with Fisher transformation into conventional linear (PF-LSMA) to address these challenges....
ABSTRACT In recent years, feature engineering-based machine learning models have made significant progress in auto insurance fraud detection. However, most or systems focused only on structural data and did not utilize multi-modal to improve detection efficiency. To solve this problem, we adapt both natural language processing computer vision techniques our knowledge-based algorithm construct an Auto Insurance Multi-modal Learning (AIML) framework. We then apply AIML detect behavior cases...
In this article, an improved parasitic-aware design technology co-optimization (DTCO) for gate-all-around nanosheet field effect transistor (GAA-NSFET) at 3 nm node is proposed. The presented DTCO flow owns two distinct features. First, a novel de-embedding strategy designed to avoid the repeated calculation of gate–source/drain contact capacitance. Second, parasitic resistance middle-end-of-line (MEOL) and back-end-of-line (BEOL) accurately extracted, combing front-end-of-line (FEOL)...