Skip to Content
You are currently on the new version of our website. Access the old version .

14 Results Found

  • Article
  • Open Access
366 Views
34 Pages

Continuous and complete meteorological observations are essential for reliable climate analysis and environmental assessment. However, missing values caused by sensor malfunctions and transmission failures can introduce systematic biases and increase...

  • Communication
  • Open Access
31 Citations
4,451 Views
11 Pages

Regularized CNN Feature Hierarchy for Hyperspectral Image Classification

  • Muhammad Ahmad,
  • Manuel Mazzara and
  • Salvatore Distefano

10 June 2021

Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and lea...

(This article belongs to the Special Issue Hyperspectral Remote Sensing: Current Situation and New Challenges)
  • Article
  • Open Access
368 Views
27 Pages

16 September 2026

Unsupervised feature selection is essential for high-dimensional data analysis, where irrelevant and redundant variables may obscure the intrinsic data structure, reduce interpretability, and degrade downstream learning performance. The key challenge...

(This article belongs to the Section Signal and Data Analysis)
  • Article
  • Open Access
11 Citations
3,919 Views
24 Pages

Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification

  • Kavitha Munishamaiaha,
  • Gayathri Rajagopal,
  • Dhilip Kumar Venkatesan,
  • Muhammad Arif and ,
  • Dragos Vicoveanu,
  • Iuliana Chiuchisan,
  • Diana Izdrui and
  • Oana Geman
  • + 3 authors+ 0 author

22 April 2022

Increasing importance in the field of artificial intelligence has led to huge progress in remote sensing. Deep learning approaches have made tremendous progress in hyperspectral image (HSI) classification. However, the complexity in classifying the H...

(This article belongs to the Section Sensing and Imaging)
  • Feature Paper
  • Article
  • Open Access
1 Citations
1,336 Views
22 Pages

Uncovering Neural Learning Dynamics Through Latent Mutual Information

  • Arianna Issitt,
  • Alex Merino,
  • Lamine Deen,
  • Ryan T. White and
  • Mackenzie J. Meni

19 January 2026

We study how convolutional neural networks reorganize information during learning in natural image classification tasks by tracking mutual information (MI) between inputs, intermediate representations, and labels. Across VGG-16, ResNet-18, and ResNet...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
911 Views
24 Pages

11 August 2026

Hyperspectral image classification (HSIC) remains challenging because high-dimensional spectral signatures must be interpreted together with spatially coherent land-cover structures, particularly when labeled samples are limited. This paper presents...

(This article belongs to the Special Issue Recent Advances in Hyperspectral Remote Sensing: Theories, Technologies and Applications)
  • Article
  • Open Access
579 Views
22 Pages

PDAM: Prototype-Guided Dynamic and Attention-Aware Masking for Hyperspectral Classification with Noisy Labels

  • Yunmin Zhang,
  • Youqiang Zhang,
  • Boshan Shi,
  • Bisheng Wang and ,
  • Qiqiong Yu and
  • Haitao Zhao
  • + 1 author+ 0 author

3 June 2026

Existing noisy-label hyperspectral image classification (HSIC) methods usually address clean sample selection and representation regularization as separate problems, although the reliability of observed labels varies substantially across samples in h...

(This article belongs to the Special Issue AI-Driven Hyperspectral Image Classification and Processing in Remote Sensing)
  • Article
  • Open Access
1 Citations
1,156 Views
25 Pages

Research on Diamond Nano-Grinding of 4H-SiC Crystals and Wear of Abrasives with Different Sharpness

  • Lijie Wu,
  • Song Fan,
  • Hanxiao Li,
  • Zijuan Han and ,
  • Ping Yang,
  • Xiuting Zhao and
  • Jisheng Pan
  • + 2 authors+ 0 author

1 April 2026

Single-crystal 4H-SiC, as a wide-bandgap semiconductor material, has become a key substrate for high-power electronics and radio frequency devices due to its outstanding characteristics such as high-voltage tolerance, high-temperature stability, high...

(This article belongs to the Special Issue Diamond Micro-Machining and Its Applications)
  • Article
  • Open Access
3 Citations
3,205 Views
8 Pages

Forward Voltage Drop Induced by an Abnormal Threading Dislocation Aggregation in 4H-SiC GTO Devices

  • Yingxin Cui,
  • Peng Dong,
  • Zhe Chen,
  • Zhiqiang Li and ,
  • Lianghui Li and
  • Juntao Li
  • + 1 author+ 0 author

5 December 2019

An abnormal star-like defect was found on the failed SiC gate turn-off thyristor (GTO) devices after metal removal and KOH etching at 450 °C in this work. It is of extraordinary larger size of 210–580 µm, even much larger than the etc...

  • Article
  • Open Access
335 Views
36 Pages

CDTS2: Causal Downstreamer with Causally Disentangled Trend and Seasonality Time-Series Representations

  • Juhyun Lyu,
  • Junghee Kim,
  • Sangmin Lee,
  • Wonbin Ahn and ,
  • Woohyung Lim and
  • Nam Soo Kim
  • + 1 author+ 0 author

10 September 2026

Time-series representation learning decomposes signals into interpretable factors such as trend and seasonality, and disentangled representation learning assigns these factors to distinct latent dimensions, enhancing interpretability and forecasting...

(This article belongs to the Special Issue Advanced AI and Machine Learning Techniques for Time Series Analysis and Pattern Recognition)
  • Article
  • Open Access
8 Citations
2,686 Views
15 Pages

9 April 2024

In recent years, community detection has received increasing interest. In network analysis, community detection refers to the identification of tightly connected subsets of nodes, which are called “communities” or “groups”, in...

(This article belongs to the Special Issue Advanced Computational Intelligence)
  • Article
  • Open Access
8 Citations
1,636 Views
19 Pages

17 December 2025

Financial fraud detection is critical to modern economic security, yet remains challenging due to collusive group behavior, temporal drift, and severe class imbalance. Most existing graph neural network (GNN) detectors rely on pairwise edges and corr...

  • Article
  • Open Access
570 Views
21 Pages

7 July 2026

Structural atrophy and metabolic dysfunction provide complementary biomarkers for Alzheimer’s disease (AD), and their joint modeling may support diagnostic assessment and cognitive score estimation. However, many multimodal methods rely on glob...

(This article belongs to the Section Neuroscience)
  • Article
  • Open Access
1 Citations
464 Views
31 Pages

24 July 2026

Hyperspectral images (HSIs) demonstrate significant potential in agricultural applications, but conventional classification methods face challenges in adequately extracting complex spatial–spectral features. While deep learning approaches provi...

(This article belongs to the Section AI Remote Sensing)