相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Remote Sensing
Huimin Zhao et al.
Summary: This paper proposes a hybrid classification method based on dual-channel convolutional neural network (DC-CNN) and kernel extreme learning machine (KELM), called PLDC-KELM, to improve spatial-spectral feature extraction ability and classification accuracy of hyperspectral remote sensing images (HRSI).
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Article
Environmental Sciences
Lijian Zhou et al.
Summary: To explore the spatial-spectral features of hyperspectral images, a Shallow-to-Deep Feature Enhancement model based on CNNs and ViT is proposed. It includes three modules: PCA for feature selection, 3D-CNN for shallow spatial-spectral feature extraction, 2D-CNN for channel attention and residual learning, and ViT for joint spatial-spectral feature extraction. Experimental results demonstrate that better classification results can be achieved using this feature enhancement method compared to other methods.
Review
Computer Science, Information Systems
Reaya Grewal et al.
Summary: The growth of HSI analysis is due to advancements that enable cameras to collect continuous spectral information. The classification of HSI is challenging due to redundant spectral bands and limited training samples. Traditional Machine Learning techniques and Deep Learning techniques have been compared and it is observed that DL-based techniques outperform ML-based techniques. Spectral-spatial classification is found to be more effective than pixel-by-pixel classification. The performance of ML and DL-based techniques has been evaluated on commonly used land cover datasets.
Article
Engineering, Biomedical
Yogesh H. Bhosale et al.
Summary: In this study, a CNN model (PulDi-COVID) using CXI is proposed for detecting nine lung diseases, including COVID-19. The experimental results show that PulDi-COVID performs impressively in identifying chronic diseases with COVID-19, achieving an accuracy of 99.70%, surpassing existing convolutional neural networks.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Green & Sustainable Science & Technology
Weiwei Ran et al.
Summary: This study proposes a new spectral-spatial-temporal-based methodology for identifying underground natural gas leakage and stressed vegetation areas using hyperspectral remote sensing images. The experimental results show high accuracy and recall rates of the detection method.
INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL
(2022)
Article
Telecommunications
Monika Sharma et al.
Summary: In this paper, a novel deep learning-based intelligent decision support system is proposed, which achieves promising accuracies with limited training samples using Manifold Batch Structure (MFBS). Three novel approaches have been proposed to design MFBS, including manifold batch scanning approach, referring unlabeled pixels in a semi-supervised way, and a network infrastructure without hyperparameters.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Review
Plant Sciences
Rijad Saric et al.
Summary: Our ability to manipulate the genome exceeds our capacity to measure genetic changes on plant traits. Plant scientists have been using imaging approaches, specifically hyperspectral imaging, to define plant responses to environmental conditions and optimize crop management.
TRENDS IN PLANT SCIENCE
(2022)
Article
Environmental Sciences
Wenmei Li et al.
Summary: This article introduces a solution to the classification of hyperspectral remote sensing images by introducing an attention mechanism and depthwise separable convolution to a three-dimensional convolutional neural network. The proposed models, 3DCNN-AM and 3DCNN-AM-DSC, have been shown to improve classification accuracy and reduce computing time.
Article
Instruments & Instrumentation
Hueseyin Firat et al.
Summary: Hyperspectral remote sensing image analysis is widely used in remote sensing applications, and this study proposed a 3D CNN-based LeNet-5 method for HRSI classification, utilizing PCA for spectral band extraction and achieving 100% overall accuracy in experimental studies.
INFRARED PHYSICS & TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Sanaboina Leela Krishna et al.
Summary: This study proposes a novel deep learning-based fuzzy-twin proximal support vector machine (DL-FTPSVM) kernel neural network model for effective hyperspectral image (HSI) classification. The model is designed to handle the irregularities and training complexities of existing hyperspectral image classifiers. A mapreduce framework is introduced for analyzing large volumes of hyperspectral images, and the fuzzy-twin proximal SVM model is designed with fuzzy twin hyperplanes. Deep learning framework and statistical analysis are used to improve the classification accuracy of the proposed model.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Wei-Chih Huang et al.
Summary: In this study, a novel method utilizing CNNs is proposed for reconstructing hyperspectral cubes from CTIS images. The constructed CNNs demonstrate higher precision and shorter reconstruction time compared to existing algorithms. Furthermore, the network can handle different types of real-world images simultaneously.
Editorial Material
Environmental Sciences
Yongguang Zhang et al.
Summary: This article introduces the recent advances in remote sensing of plant traits and functions, including the shift from monitoring structural parameters to functional traits and the use of hyperspectral techniques to monitor vegetation status across various scales. The eight papers mentioned in this editorial focus on developing new remote sensing techniques and algorithms for retrieving plant functional traits, which will help improve the estimation of vegetation processes such as photosynthesis, water cycle, and carbon cycle.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Silvia Liberata Ullo et al.
Summary: Modern sensors, including AI-enabled sensors, and the Internet of Things have significantly impacted remote sensing and smart agriculture, offering new tools and opportunities for assessment, monitoring, and automation in these fields.
Article
Engineering, Electrical & Electronic
Bishwas Praveen et al.
Summary: The study introduces a new deep learning-based hyperspectral data analysis framework that achieves superior classification performance by efficiently utilizing both spectral and spatial information.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Yanbing Liu et al.
INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS
(2020)
Article
Computer Science, Information Systems
Xinjian Wang et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Alaa Ali Hameed et al.
KNOWLEDGE-BASED SYSTEMS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Asma Elmaizi et al.
SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING IN DATA SCIENCES (ICDS2018)
(2019)