The discrimination of oil spills and look-alike phenomena (e.g., low wind area, wind front area and natural slicks) on Synthetic Aperture Radar (SAR) images is a crucial task in marine oil spill ...detection. Many classification techniques can be employed for this purpose. In order to make the best use of the large variety of statistical and machine learning classification methods, it is necessary to assess their performance differences and make recommendations for classifier selection and improvement. The objective of this paper is to compare different classification techniques for oil-spill detection in RADARSAT-1 imagery. The data of this study consists of 15 features of 192 oil spills and look-alikes identified by Canadian Ice Service between 2004 and 2008 off Canada's east and west coastal areas. The studied classifiers include the Support Vector Machine (SVM), Artificial Neural Network (ANN), tree-based ensemble classifiers (bagging, bundling and boosting), Generalized Additive Model (GAM) and Penalized Linear Discriminant Analysis (PLDA). Two performance measures, the specificity at fixed sensitivity (80%) and the area under the Receiver Operating Characteristic (ROC) curve (AUC), were estimated using cross-validation to evaluate the performance of classifiers at a high sensitivity. Overall, the bundling technique which achieved a median specificity of 90.7%, at sensitivity of 80%, significantly outperformed the second best (i.e. bagging) by 1.5 percentage points, and the worst (i.e. ANN) by 15 percentage points. The median values of AUC measure indicated consistent results. Bundling and bagging achieved comparable median AUC values of about 92%, followed by GAM and PLDA, with ANN yielding the smallest. Most classifiers (SVM, bundling and especially PLDA and ANN) performed significantly better on datasets pre-processed by log-transformation and standardization than on the original dataset. These results demonstrate the importance and benefit of selecting the optimal classifiers for oil spill classification, and configuring the classifiers by proper feature construction techniques.
•We compare different classifiers for marine oil spill discrimination.•The bootstrap-aggregated tree-based techniques achieved the best results.•Pre-processing the original features increased the performance of most classifiers.•Most classifiers rely heavily on geometric shape features and the contextual feature.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPUK
The problem of limited labeled training samples is challenging for the classification of remote sensing imagery. We develop a joint classification and segmentation algorithm to address this problem. ...Our algorithm combines semisupervised learning and conditional random fields (CRFs) into a single framework. The multimodal Gaussian maximum-likelihood classifier is used to estimate the probabilities for the unary potentials of the CRF. Unlike traditional methods based on random fields, region merging is concatenated with the CRF inference to reduce the number of nodes iteratively. Moreover, a semisupervised technique called self-training is used, which iteratively enlarges the training sample set and retrains the classifier. The selection of training samples is based on the region information, so that the risk of assigning wrong labels is largely reduced. The proposed algorithm is applied to hyperspectral image classification, and results on benchmark data sets show that the proposed algorithm significantly improves classification performance after using self-training, and outperforms state-of-the-art spectral-spatial methods for limited labeled training samples.
High-resolution ice concentration maps are of great interest for ship navigation and ice hazard forecasting. In this case study, a convolutional neural network (CNN) has been used to estimate ice ...concentration using synthetic aperture radar (SAR) scenes captured during the melt season. These dual-pol RADARSAT-2 satellite images are used as input, and the ice concentration is the direct output from the CNN. With no feature extraction or segmentation postprocessing, the absolute mean errors of the generated ice concentration maps are less than 10% on average when compared with manual interpretation of the ice state by ice experts. The CNN is demonstrated to produce ice concentration maps with more detail than produced operationally. Reasonable ice concentration estimations are made in melt regions and in regions of low ice concentration.
The effective detection of global urban expansion is the basis of understanding urban sustainability. We propose a fully convolutional network (FCN) and employ it to detect global urban expansion ...from 1992-2016. We found that the global urban land area increased from 274.7 thousand km2-621.1 thousand km2, which is an increase of 346.4 thousand km2 and a growth by 1.3 times. The results display a relatively high accuracy with an average kappa index of 0.5, which is 0.3 higher than those of existing global urban expansion datasets. Three major advantages of the proposed FCN contribute to the improved accuracy, including the integration of multi-source remotely sensed data, the combination of features at multiple scales, and the ability to address the lack of training samples for historical urban land. Thus, the proposed FCN has great potential to effectively detect global urban expansion.
Alzheimer’s disease (AD) is the most common neurodegenerative disease characterized by excessive accumulation of the amyloid-β peptide (Aβ) in the brain, which has been considered to mediate the ...neuroinflammation process. Microglial activation is the main component of neuroimmunoregulation. In recent years, exosomes isolated from human umbilical cord mesenchymal stem cells (hucMSC-exosomes) have been demonstrated to mimic the therapeutic effects of hucMSCs in many inflammation-related diseases. In this study, exosomes from the supernatant of hucMSCs were injected into AD mouse models. We observed that hucMSC-exosomes injection could repair cognitive disfunctions and help to clear Aβ deposition in these mice. Moreover, we found that hucMSC-exosomes injection could modulate the activation of microglia in brains of the mice to alleviated neuroinflammation. The levels of pro-inflammatory cytokines in peripheral blood and brains of mice were increased and the levels of anti-inflammatory cytokines were decreased. We also treated BV2 cells with hucMSC-exosomes in culture medium. HucMSC-exosomes also had inflammatory regulating effects to alternatively activate microglia and modulate the levels of inflammatory cytokines in vitro.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
This study addressed enamel demineralization, a common complication in fixed orthodontic treatment, by evaluating a novel orthodontic adhesive with DMAHDM-PCL composite fibers. These fibers, produced ...through electrospinning, were incorporated into orthodontic adhesive to create experimental formulations at different concentrations and a control group. The study assessed antimicrobial properties, biosafety, and mechanical characteristics. New orthodontic adhesive exhibited significant bacteriostatic effects, reducing bacterial biofilm activity and concentrations. Incorporating 1% and 3% DMAHDM-PCL did not affect cytocompatibility. Animal tests confirmed no inflammatory irritation. Shear bond strength and adhesive residual index results indicated that antimicrobial fibers didn't impact bonding ability. In conclusion, orthodontic adhesives with 3% DMAHDM-PCL fibers are potential antimicrobial bonding materials, offering a comprehensive solution to enamel demineralization in orthodontic patients.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The combination of nonlocal grouping and transformed domain filtering has led to the state-of-the-art denoising techniques. In this paper, we extend this line of study to the denoising of synthetic ...aperture radar (SAR) images based on clustering the noisy image into disjoint local regions with similar spatial structure and denoising each region by the linear minimum mean-square error (LMMSE) filtering in principal component analysis (PCA) domain. Both clustering and denoising are performed on image patches. For clustering, to reduce dimensionality and resist the influence of noise, several leading principal components identified by the minimum description length criterion are used to feed the K-means clustering algorithm. For denoising, to avoid the limitations of the homomorphic approach, we build our denoising scheme on additive signal-dependent noise model and derive a PCA-based LMMSE denoising model for multiplicative noise. Denoised patches of all clusters are finally used to reconstruct the noise-free image. The experiments demonstrate that the proposed algorithm achieved better performance than the referenced state-of-the-art methods in terms of both noise reduction and image detail preservation.
•We are the first to identify ALMT gene family in six Rosaceae species, and a total of 113 ALMT homologous genes were identified.•We are the first to carry out a Genome-Wide analysis of these ALMT ...family genes.•Based on the results of transcriptome data, malate content and qRT-PCR, we identified a gene related with the malate accumulation in pear.•We characterized the function of the candidate gene by transgenic assay.
Aluminum-activated malate transporters (ALMTs) exhibit a variety of physiological roles in plants to regulate fruit quality, but the evolutionary history of the ALMT family in the Rosaceae species remains unknown. In this study, a total of 113 ALMT homologous genes were identified from six Rosaceae species (Pyrus bretschneideri, Malus × domestica, Prunus persica, Fragaria vesca, Prunus mume, and Pyrus communis), and 27 of these sequences came from Chinese white pear, designated PbrALMT. Based on the phylogenetic analysis, we divided these ALMT genes into three main clusters (A–C). Conserved domain analysis indicated that all PbrALMT proteins contained the ALMT domain and the FUSC_2 domain, and fewer proteins included the FUSC domain. The results of subcellular localization experiments showed that parts of PbrALMT proteins containing the FUSC domain were located in the membrane. Collinearity analysis revealed that segmental and dispersed duplications were the primary forces underlying ALMT gene family expansion in the Rosaceae. Calculation of Ka/Ks between the paralogous pairs indicated that all of the genes in the PbrALMT family have evolved under negative selection. Combining the changes of malate content and transcriptome data analysis, five genes belonging to Cluster B were chosen for qRT-PCR, and the results revealed that Pbr020270.1, as a candidate gene, may play important roles in malate accumulation during pear fruit development. Further transgenic assay confirmed the above conclusion. The present study provides a foundation to better understand the molecular evolution of ALMT genes in pear and the functional characterization of these genes in the future.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPUK, ZRSKP
•A gap-filling method was proposed for satellite-derived chlorophyll-a time series.•The neighborhood spatiotemporal information was used to fill the missing values.•The proposed method effectively ...fills missing data in spatial and temporal domains.
Satellite-derived Chlorophyll-a concentration (Chla) time series products are essential for large-scale marine environmental monitoring. However, the plenty of missing pixels in current satellite Chla products severely hinder their applications for marine research, due to cloud contamination, solar glint, and unfavorable observation conditions. This study proposed a Chla time series gap-filling method for MODIS 8-day composite Chla product by integrating spatiotemporal information (STGF). This method employed spatially neighboring pixels with similar temporal variation to fill the missing values in time series, without involving training or auxiliary data. The performance of the STGF is assessed quantitatively and qualitatively. The correlation coefficients (CC) between gap-filled data and actual observations for years of 2004, 2010, 2016, and 2022 across the entire study area are all greater than 0.97. The mean absolute percentage error (MAPE) and root mean square error (RMSE) are less than 16.1 % and 0.233 mg/m3, respectively. The proposed STGF outperformed linear interpolation and the DINEOF algorithm from both spatial and temporal perspectives, suggesting the effectiveness of STGF in handling continuous data gaps and capturing detailed Chla variation patterns, especially in regions with significant variability. The findings suggest that the proposed STGF method offers a viable alternative for filling missing values in Chla time series data. This supports the demand for long-term, large-scale, and high-coverage ocean color remote sensing data in marine environmental studies.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPUK, ZAGLJ, ZRSKP
This letter presents a Bayesian method for hyperspectral image classification based on the sparse representation (SR) of spectral information and the Markov random field modeling of spatial ...information. We introduce a probabilistic SR approach to estimate the class conditional distribution, which proved to be a powerful feature extraction technique to be combined with the label prior distribution in a Bayesian framework. The resulting maximum a priori problem is estimated by a graph-cut-based α-expansion technique. The capabilities of the proposed method are proven in several benchmark hyperspectral images of both agricultural and urban areas.