Cong Feng

ORCID: 0000-0003-4000-1895
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Face and Expression Recognition
  • Remote-Sensing Image Classification
  • Astrophysics and Cosmic Phenomena
  • Dark Matter and Cosmic Phenomena
  • Machine Learning and ELM
  • Text and Document Classification Technologies
  • Neutrino Physics Research
  • Image Retrieval and Classification Techniques
  • Domain Adaptation and Few-Shot Learning
  • Video Surveillance and Tracking Methods
  • Cellular and Composite Structures
  • Radiation Therapy and Dosimetry
  • Advanced Computing and Algorithms
  • Advanced Image and Video Retrieval Techniques
  • Bone Tissue Engineering Materials
  • Advanced Image Fusion Techniques
  • Medical Image Segmentation Techniques
  • Remote Sensing and Land Use

Shandong University
2008-2025

Harbin University of Science and Technology
2023-2024

Sichuan University
2024

Heilongjiang University of Science and Technology
2023

We present an updated all-particle energy spectrum of primary cosmic rays in a wide range from 1014 to 1017 eV using 5.5 × 107 events collected 2000 November through 2004 October by the Tibet-III air-shower array located 4300 m above sea level (an atmospheric depth 606 g cm−2). The size exhibits sharp knee at corresponding around 4 PeV. This work uses increased statistics and new simulation calculations for analysis. discuss our extensive Monte Carlo model dependencies involved final result,...

10.1086/529514 article EN The Astrophysical Journal 2008-04-30

We present the measurements of all-particle energy spectrum and mean logarithmic mass cosmic rays in range 0.3-30 PeV using data collected from LHAASO-KM2A between September 2021 December 2022, which is based on a nearly composition-independent reconstruction method, achieving unprecedented accuracy. Our analysis reveals position knee at 3.67±0.05±0.15 PeV. Below knee, spectral index found to be -2.7413±0.0004±0.0050, while above it -3.128±0.005±0.027, with sharpness transition measured...

10.1103/physrevlett.132.131002 article EN Physical Review Letters 2024-03-26

The diffuse Galactic gamma-ray emission is a very important tool used to study the propagation and interaction of cosmic rays in Milky Way. In this Letter, we report measurements from plane---covering longitudes 15\ifmmode^\circ\else\textdegree\fi{} 235\ifmmode^\circ\else\textdegree\fi{} latitudes $\ensuremath{-}5\ifmmode^\circ\else\textdegree\fi{}$ $+5\ifmmode^\circ\else\textdegree\fi{}$, an energy range 1 25 TeV---made with Water Cherenkov Detector Array (WCDA) Large High Altitude Air...

10.1103/physrevlett.134.081002 article EN Physical Review Letters 2025-02-28

10.1016/j.engappai.2025.110387 article EN Engineering Applications of Artificial Intelligence 2025-03-05

In recent years, graph convolutional networks (GCNs) have attracted increased attention in hyperspectral image (HSI) classification through the utilization of data and their connection graph. However, most existing GCN-based methods two main drawbacks. First, constructed with pixel-level nodes loses many useful spatial information while high computational cost is required due to large size. Second, joint spatial-spectral structure hidden HSI are not fully explored for better neighbor...

10.1117/1.jrs.18.014504 article EN Journal of Applied Remote Sensing 2024-01-17

Since the rapid progress in multimedia and sensor technologies, multiview clustering (MVC) has become a prominent research area within machine learning data mining, experiencing significant advancements over recent decades. MVC is distinguished from single-view by its ability to integrate complementary information multiple distinct perspectives enhance performance. However, efficacy of methods predicated on availability complete views for all samples-an assumption that frequently fails...

10.1109/tnnls.2024.3411294 article EN IEEE Transactions on Neural Networks and Learning Systems 2024-01-01

Domain adaptation (DA) offers an effective way to align feature distributions of the source domain (SD) and target (TD) without requiring any label samples. As a method DA, representation learning effectively realizes alignment in different domains by transferring knowledge. However, existing methods often focus on unilateral transfer, which potentially results transfer bias. Additionally, most ignore connection between discrimination during DA process, easily causes negative transfer. This...

10.1080/01431161.2024.2365817 article EN International Journal of Remote Sensing 2024-07-01

How to accurately design a personalized matching implant that can induce skull regeneration is the focus of current research.

10.1039/d4tb01104j article EN Journal of Materials Chemistry B 2024-01-01
Coming Soon ...