Concomitant with the rapid global urbanization process, land use change detection has been the focus and "hot spot" of global change research all the time. In the present study, the rigorous orthorectification was first applied to the SPOT-5 data to guarantee precise geometric correction and image registration. Afterwards, a methodology integrating PCA-enhancement and multi-source classifier was adopted to detect the land use changes in urban area. The results show that the first three PCs derived from multi-temporal-PCA contain most of the spectral information among which unchanged land use is highlighted in PC1 and PC2, and changed land use is mainly enhanced in PC3. The following multi-source classifier integrating unsupervised classifier (ISODATA) and supervised classifier (Maximum Likelihood) accurately extracts all the information. The findings from accuracy assessment demonstrate that the overall accuracy for the proposed method reaches 92.58, KAPPA coefficient is 0.92, and proving figures are also produced for the user's and producer's accuracies. It was further found that the proposed method yielded better accuracy than that of traditional post-classification comparison approach.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
[Spatio-temporal Evolution of Carbon Emissions and Emission Reduction Paths in the Northern Farming-pastoral Ecotone].
Huan Jing Ke Xue
January 2025
College of Natural Resources and Environment, Northwest A&F University, Yangling 712100, China.
The farming-pastoral ecotone has an important strategic place in the energy supply and ecological layout of China. Thus, exploring the spatial and temporal variation characteristics of carbon emissions in this region will help to deeply understand the information on the historical carbon emissions in China's energy production bases and provide data references for the formulation of differentiated emission reduction policies and the promotion of regional energy-saving and carbon-reducing measures, which is of great significance for the realization of low-carbon economic development. This study constructed a spatialization model of carbon emissions based on land use, night lighting, and provincial energy consumption data； explored the spatiotemporal changes and aggregation characteristics of carbon emissions in the farming-pastoral ecotone from 1995 to 2020 using the global Moran's index and hotspot analysis； and then combined it with the slack-based measure model to calculate the carbon emission efficiency and emission reduction potential of each city from 2010 to 2020 and classify cities to propose a differentiated emission reduction path.
View Article and Find Full Text PDFPrivacy-preserving multi-source semi-supervised domain adaptation for seizure prediction.
Cogn Neurodyn
December 2024
Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027 Anhui China.
Domain adaptation (DA) has been frequently used to solve the inter-patient variability problem in EEG-based seizure prediction. However, existing DA methods require access to the existing patients' data when adapting the model, which leads to privacy concerns. Besides, most of them treat the whole existing patients' data as one single source and attempt to minimize the discrepancy with the target patient.
View Article and Find Full Text PDFDisentangled global and local features of multi-source data variational autoencoder: An interpretable model for diagnosing IgAN via multi-source Raman spectral fusion techniques.
Artif Intell Med
December 2024
College of Software, Xinjiang University, Urumqi 830046, China. Electronic address:
A single Raman spectrum reflects limited molecular information. Effective fusion of the Raman spectra of serum and urine source domains helps to obtain richer feature information. However, most of the current studies on immunoglobulin A nephropathy (IgAN) based on Raman spectroscopy are based on small sample data and low signal-to-noise ratio.
View Article and Find Full Text PDFEffect of patient-contextual skin images in human- and artificial intelligence-based diagnosis of melanoma: Results from the 2020 SIIM-ISIC melanoma classification challenge.
J Eur Acad Dermatol Venereol
December 2024
Frazer Institute, Dermatology Research Centre, The University of Queensland, Brisbane, Queensland, Australia.
Background: While the high accuracy of reported AI tools for melanoma detection is promising, the lack of holistic consideration of the patient is often criticized. Along with medical history, a dermatologist would also consider intra-patient nevi patterns, such that nevi that are different from others on a given patient are treated with suspicion.
Objective: To evaluate whether patient-contextual lesion-images improves diagnostic accuracy for melanoma in a dermoscopic image-based AI competition and a human reader study.
D4A: An efficient and effective defense across agnostic adversarial attacks.
Neural Netw
November 2024
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China; Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China; School of Computer Science and Engineering, Guangxi Normal University, Guilin, China. Electronic address:
Recent studies show that Graph Neural Networks (GNNs) are vulnerable to structure adversarial attacks, which draws attention to adversarial defenses in graph data. Previous defenses designed heuristic defense strategies for specific attacks or graph properties, and are no longer sufficiently robust across all these attacks. To address this problem, we discuss the abnormal behaviors of GNNs in structure perturbations from a posterior distribution perspective.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!