Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (49)

Search Parameters:
Keywords = Euclidean distance discrimination

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 21510 KiB  
Article
Visual Localization Method for Fastener-Nut Disassembly and Assembly Robot Based on Improved Canny and HOG-SED
by Xiangang Cao, Mengzhen Zuo, Guoyin Chen, Xudong Wu, Peng Wang and Yizhe Liu
Appl. Sci. 2025, 15(3), 1645; https://doi.org/10.3390/app15031645 - 6 Feb 2025
Abstract
Visual positioning accuracy is crucial for ensuring the successful execution of nut disassembly and assembly tasks by a fastener-nut disassembly and assembly robot. However, disturbances such as on-site lighting changes, abnormal surface conditions of nuts, and complex backgrounds formed by ballast in complex [...] Read more.
Visual positioning accuracy is crucial for ensuring the successful execution of nut disassembly and assembly tasks by a fastener-nut disassembly and assembly robot. However, disturbances such as on-site lighting changes, abnormal surface conditions of nuts, and complex backgrounds formed by ballast in complex railway environments can lead to poor visual positioning accuracy of the fastener nuts, thereby affecting the success rate of the robot’s continuous disassembly and assembly operations. Additionally, the existing method of detecting fasteners first and then positioning nuts has poor applicability in the field. A direct positioning algorithm for spiral rail spikes that combines an improved Canny algorithm with shape feature similarity determination is proposed in response to these issues. Firstly, CLAHE enhances the image, reducing the impact of varying lighting conditions in outdoor work environments on image details. Then, to address the difficulties in extracting the edges of rail spikes caused by abnormal conditions such as water stains, rust, and oil stains on the nuts themselves, the Canny algorithm is improved through three stages, filtering optimization, gradient boosting, and adaptive thresholding, to reduce the impact of edge loss on subsequent rail spike positioning results. Finally, considering the issue of false fitting due to background interference, such as ballast in gradient Hough transformations, the differences in texture and shape features between the rail spike and interference areas are analyzed. The HOG is used to describe the shape features of the area to be screened, and the similarity between the screened area and the standard rail spike template features is compared based on the standard Euclidean distance to determine the rail spike area. Spiral rail spikes are discriminated based on shape features, and the center coordinates of the rail spike are obtained. Experiments were conducted using images collected from the field, and the results showed that the proposed algorithm, when faced with complex environments with multiple interferences, has a correct detection rate higher than 98% and a positioning error mean of 0.9 mm. It exhibits excellent interference resistance and meets the visual positioning accuracy requirements for robot nut disassembly and assembly operations in actual working environments. Full article
(This article belongs to the Section Applied Industrial Technologies)
Show Figures

Figure 1

21 pages, 5901 KiB  
Article
A Rapid Identification Method for Cottonseed Varieties Based on Near-Infrared Spectral and Generative Adversarial Networks
by Qingxu Li, Hao Li, Renhao Liu, Xiaofeng Dong, Hongzhou Zhang and Wanhuai Zhou
Agriculture 2024, 14(12), 2177; https://doi.org/10.3390/agriculture14122177 - 29 Nov 2024
Viewed by 502
Abstract
China is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varieties. The detection of [...] Read more.
China is a major cotton-growing country with numerous cotton varieties, each exhibiting significant differences in yield and fiber quality. However, the current management of cottonseed varieties is disorganized, resulting in severe homogenization and the presence of counterfeit and mislabeled varieties. The detection of cottonseed variety information has become a critical issue for the Chinese cotton industry. In this study, we collected near-infrared (NIR) spectral data from six cottonseed varieties and constructed a GAN for cottonseed NIR data (GAN-CNIRD) model to generate additional cottonseed NIR data. The Euclidean distance method was used to label the generated NIR data according to the characteristics of the true NIR data. We then applied Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Normalization algorithms to preprocess the combined dataset of generated and real cottonseed NIR data. Feature wavelengths were extracted using Bootstrap Soft Shrinkage (BOSS) and Competitive Adaptive Reweighted Sampling (CARS) algorithms. Subsequently, we developed Linear Discriminant Analysis (LDA), Random subspace method (RSM), and convolutional neural network (CNN) models to classify the cottonseed varieties. The results showed that for the LDA model, the use of feature wavelengths extracted after Normalization-BOSS processing achieved the best performance with an accuracy of 97.00%. For the RSM model, the use of feature wavelengths extracted after SNV-CARS processing achieved the best performance with an accuracy of 98.00%. For the CNN model, the use of feature wavelengths extracted after MSC-CARS processing achieved the best performance with an accuracy of 100.00%. Data augmentation using GAN-CNIRD-generated cottonseed data improved the accuracy of the three optimal models by 6%, 5%, and 6%, respectively. This study provides a crucial reference for the rapid detection of cottonseed variety information and has significant implications for the standardized management of cottonseed varieties. Full article
Show Figures

Figure 1

17 pages, 4999 KiB  
Article
A Comparison of the Impacts of Different Drying Methods on the Volatile Organic Compounds in Ginseng
by Yun Xiang, Manshu Zou, Feilin Ou, Lijun Zhu, Yingying Xu, Qingqing Zhou and Chang Lei
Molecules 2024, 29(22), 5235; https://doi.org/10.3390/molecules29225235 - 5 Nov 2024
Cited by 1 | Viewed by 923
Abstract
Ginseng (Panax ginseng C. A. Meyer) is a valuable plant resource which has been used for centuries as both food and traditional Chinese medicine. It is popular in health research and markets globally. Fresh ginseng has a high moisture content and is [...] Read more.
Ginseng (Panax ginseng C. A. Meyer) is a valuable plant resource which has been used for centuries as both food and traditional Chinese medicine. It is popular in health research and markets globally. Fresh ginseng has a high moisture content and is prone to mold and rot, reducing its nutritional value without proper preservation. Drying treatments are effective for maintaining the beneficial properties of ginseng post-harvest. In this study, we investigated the effects of natural air drying (ND), hot-air drying (HAD), vacuum drying (VD), microwave vacuum drying (MVD), and vacuum freeze drying (VFD) on volatile organic compounds (VOCs) in ginseng. The results showed that the MVD time was the shortest, followed by the VFD, VD, and HAD times, whereas the ND time was the longest, but the VFD is the most beneficial to the appearance and color retention of ginseng. A total of 72 VOCs were obtained and 68 VOCs were identified using the five drying methods based on gas chromatography–ion mobility spectrometry (GC-IMS) technology, including 23 aldehydes, 19 alkenes, 10 alcohols, 10 ketones, 4 esters, 1 furan, and 1 pyrazine, and the ND method was the best for retaining VOCs. GC-IMS fingerprints, principal component analysis (PCA), Euclidean distance analysis, partial least squares discriminant analysis (PLS-DA), and cluster analysis (CA) can distinguish ginseng from different drying methods. A total of 29 VOCs can be used as the main characteristic markers of different drying methods in ginseng. Overall, our findings provide scientific theoretical guidance for optimizing ginseng’s drying methods, aromatic health effects, and flavor quality research. Full article
(This article belongs to the Special Issue Applications of Spectroscopic Techniques in Food Sample Analysis)
Show Figures

Figure 1

24 pages, 7202 KiB  
Article
A WKNN Indoor Fingerprint Localization Technique Based on Improved Discrimination Capability of RSS Similarity
by Baofeng Wang, Qinghai Li, Jia Liu, Zumin Wang, Qiudong Yu and Rui Liang
Sensors 2024, 24(14), 4586; https://doi.org/10.3390/s24144586 - 15 Jul 2024
Viewed by 1012
Abstract
There are various indoor fingerprint localization techniques utilizing the similarity of received signal strength (RSS) to discriminate the similarity of positions. However, due to the varied states of different wireless access points (APs), each AP’s contribution to RSS similarity varies, which affects the [...] Read more.
There are various indoor fingerprint localization techniques utilizing the similarity of received signal strength (RSS) to discriminate the similarity of positions. However, due to the varied states of different wireless access points (APs), each AP’s contribution to RSS similarity varies, which affects the accuracy of localization. In our study, we analyzed several critical causes that affect APs’ contribution, including APs’ health states and APs’ positions. Inspired by these insights, for a large-scale indoor space with ubiquitous APs, a threshold was set for all sample RSS to eliminate the abnormal APs dynamically, a correction quantity for each RSS was provided by the distance between the AP and the sample position to emphasize closer APs, and a priority weight was designed by RSS differences (RSSD) to further optimize the capability of fingerprint distances (FDs, the Euclidean distance of RSS) to discriminate physical distance (PDs, the Euclidean distance of positions). Integrating the above policies for the classical WKNN algorithm, a new indoor fingerprint localization technique is redefined, referred to as FDs’ discrimination capability improvement WKNN (FDDC-WKNN). Our simulation results showed that the correlation and consistency between FDs and PDs are well improved, with the strong correlation increasing from 0 to 76% and the high consistency increasing from 26% to 99%, which confirms that the proposed policies can greatly enhance the discrimination capabilities of RSS similarity. We also found that abnormal APs can cause significant impact on FDs discrimination capability. Further, by implementing the FDDC-WKNN algorithm in experiments, we obtained the optimal K value in both the simulation scene and real library scene, under which the mean errors have been reduced from 2.2732 m to 1.2290 m and from 4.0489 m to 2.4320 m, respectively. In addition, compared to not using the FDDC-WKNN, the cumulative distribution function (CDF) of the localization errors curve converged faster and the error fluctuation was smaller, which demonstrates the FDDC-WKNN having stronger robustness and more stable localization performance. Full article
(This article belongs to the Special Issue Sensors and Techniques for Indoor Positioning and Localization)
Show Figures

Figure 1

16 pages, 10953 KiB  
Article
Detection and Comparison of Volatile Organic Compounds in Four Varieties of Hawthorn Using HS-GC-IMS
by Lijun Zhu, Feilin Ou, Yun Xiang, Bin Wang, Yingchao Mao, Lingfeng Zhu, Qun Zhang and Chang Lei
Separations 2024, 11(4), 100; https://doi.org/10.3390/separations11040100 - 28 Mar 2024
Cited by 1 | Viewed by 1607
Abstract
Hawthorn is a type of natural food with significant medicinal and nutritional properties; it has been listed in the “Both Food and Drug” list by the Chinese Ministry of Health Item List since 1997. However, hawthorn varieties have complex origins, and there are [...] Read more.
Hawthorn is a type of natural food with significant medicinal and nutritional properties; it has been listed in the “Both Food and Drug” list by the Chinese Ministry of Health Item List since 1997. However, hawthorn varieties have complex origins, and there are significant differences in the content, type, and medicinal efficacy of the chemically active ingredients in different varieties of hawthorn. This leads to the phenomenon of mixed varieties and substandard products being passed off as high-quality. In this work, by using headspace gas chromatography–ion mobility spectrometry (HS-GC-IMS), we identified and analyzed volatile organic compounds (VOCs) in four varieties of hawthorn, establishing their characteristic fingerprints. As a result, a total of 153 peaks were detected, and 139 VOCs were also identified. As shown by the fingerprint profiles, the different hawthorn samples contained different VOCs. Meanwhile, by using principal component analysis (PCA), Euclidean distance, and partial least-squares discriminant analysis (PLS-DA), the relationship between the VOCs found in the different varieties of hawthorn was revealed. This study developed a simple, fast, accurate, and sensitive method for identifying, tracking, and evaluating hawthorn varieties. Full article
(This article belongs to the Topic Advances in Analysis of Food and Beverages)
Show Figures

Figure 1

31 pages, 4589 KiB  
Article
Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification
by Chein-I Chang, Yi-Mei Kuo and Kenneth Yeonkong Ma
Remote Sens. 2024, 16(6), 942; https://doi.org/10.3390/rs16060942 - 7 Mar 2024
Viewed by 992
Abstract
Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It [...] Read more.
Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, cluster density and cluster distance, to rank all bands for BS. This paper reinterprets cluster density and cluster distance as band local density (BLD) and band distance (BD) and also introduces a new concept called band prominence value (BPV) as a third indicator. Combining BLD and BD with BPV derives new band prioritization criteria for BS, which can extend the currently used DPC-BS to a new DPC-BS method referred to as band density prominence clustering (BDPC). By taking advantage of the three key indicators of BDPC, i.e., cut-off band distance bc, k nearest neighboring-band local density, and BPV, two versions of BDPC can be derived called bc-BDPC and k-BDPC, both of which are quite different from existing DPC-based BS methods in three aspects. One is that the parameter bc of bc-BDPC and the parameter k of k-BDPC can be automatically determined by the number of clusters and virtual dimensionality (VD), respectively. Another is that instead of using Euclidean distance, a spectral discrimination measure is used to calculate BD as well as inter-band correlation. The most important and significant aspect is a novel idea that combines BPV with BLD and BD to derive new band prioritization criteria for BS. Extensive experiments demonstrate that BDPC generally performs better than DPC-BS as well as many current state-of-the art BS methods. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

26 pages, 6668 KiB  
Article
Supervised Manifold Learning Based on Multi-Feature Information Discriminative Fusion within an Adaptive Nearest Neighbor Strategy Applied to Rolling Bearing Fault Diagnosis
by Hongwei Wang, Linhu Yao, Haoran Wang, Yu Liu, Zhiyuan Li, Di Wang, Ren Hu and Lei Tao
Sensors 2023, 23(24), 9820; https://doi.org/10.3390/s23249820 - 14 Dec 2023
Cited by 3 | Viewed by 1166
Abstract
Rolling bearings are a key component for ensuring the safe and smooth operation of rotating machinery and are very prone to failure. Therefore, intelligent fault diagnosis research on rolling bearings has become a crucial task in the field of mechanical fault diagnosis. This [...] Read more.
Rolling bearings are a key component for ensuring the safe and smooth operation of rotating machinery and are very prone to failure. Therefore, intelligent fault diagnosis research on rolling bearings has become a crucial task in the field of mechanical fault diagnosis. This paper proposes research on the fault diagnosis of rolling bearings based on an adaptive nearest neighbor strategy and the discriminative fusion of multi-feature information using supervised manifold learning (AN-MFIDFS-Isomap). Firstly, an adaptive nearest neighbor strategy is proposed using the Euclidean distance and cosine similarity to optimize the selection of neighboring points. Secondly, three feature space transformation and feature information extraction methods are proposed, among which an innovative exponential linear kernel function is introduced to provide new feature information descriptions for the data, enhancing feature sensitivity. Finally, under the adaptive nearest neighbor strategy, a novel AN-MFIDFS-Isomap algorithm is proposed for rolling bearing fault diagnosis by fusing various feature information and classifiers through discriminative fusion with label information. The proposed AN-MFIDFS-Isomap algorithm is validated on the CWRU open dataset and our experimental dataset. The experiments show that the proposed method outperforms other traditional manifold learning methods in terms of data clustering and fault diagnosis. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

24 pages, 6085 KiB  
Article
SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images
by Xin Li, Feng Xu, Xi Yong, Deqing Chen, Runliang Xia, Baoliu Ye, Hongmin Gao, Ziqi Chen and Xin Lyu
Remote Sens. 2023, 15(23), 5610; https://doi.org/10.3390/rs15235610 - 3 Dec 2023
Cited by 25 | Viewed by 2346
Abstract
Semantic segmentation plays a pivotal role in the intelligent interpretation of remote sensing images (RSIs). However, conventional methods predominantly focus on learning representations within the spatial domain, often resulting in suboptimal discriminative capabilities. Given the intrinsic spectral characteristics of RSIs, it becomes imperative [...] Read more.
Semantic segmentation plays a pivotal role in the intelligent interpretation of remote sensing images (RSIs). However, conventional methods predominantly focus on learning representations within the spatial domain, often resulting in suboptimal discriminative capabilities. Given the intrinsic spectral characteristics of RSIs, it becomes imperative to enhance the discriminative potential of these representations by integrating spectral context alongside spatial information. In this paper, we introduce the spectrum-space collaborative network (SSCNet), which is designed to capture both spectral and spatial dependencies, thereby elevating the quality of semantic segmentation in RSIs. Our innovative approach features a joint spectral–spatial attention module (JSSA) that concurrently employs spectral attention (SpeA) and spatial attention (SpaA). Instead of feature-level aggregation, we propose the fusion of attention maps to gather spectral and spatial contexts from their respective branches. Within SpeA, we calculate the position-wise spectral similarity using the complex spectral Euclidean distance (CSED) of the real and imaginary components of projected feature maps in the frequency domain. To comprehensively calculate both spectral and spatial losses, we introduce edge loss, Dice loss, and cross-entropy loss, subsequently merging them with appropriate weighting. Extensive experiments on the ISPRS Potsdam and LoveDA datasets underscore SSCNet’s superior performance compared with several state-of-the-art methods. Furthermore, an ablation study confirms the efficacy of SpeA. Full article
(This article belongs to the Special Issue Multisource Remote Sensing Image Interpretation and Application)
Show Figures

Figure 1

14 pages, 2656 KiB  
Article
Research on Apple Origins Classification Optimization Based on Least-Angle Regression in Instance Selection
by Bin Li, Yuqi Wang, Lisha Li and Yande Liu
Agriculture 2023, 13(10), 1868; https://doi.org/10.3390/agriculture13101868 - 24 Sep 2023
Cited by 2 | Viewed by 1255
Abstract
Machine learning is used widely in near-infrared spectroscopy (NIRS) for fruit qualification. However, the directly split training set used contains redundant samples, and errors may be introduced into the model. Euclidean distance-based and K-nearest neighbor-based instance selection (IS) methods are widely used to [...] Read more.
Machine learning is used widely in near-infrared spectroscopy (NIRS) for fruit qualification. However, the directly split training set used contains redundant samples, and errors may be introduced into the model. Euclidean distance-based and K-nearest neighbor-based instance selection (IS) methods are widely used to remove useless samples because of their accessibility. However, they either have high accuracy and low compression or vice versa. To compress the sample size while improving the accuracy, the least-angle regression (LAR) method was proposed for classification instance selection, and a discrimination experiment was conducted on a total of four origins of 952 apples. The sample sets were split into the raw training set and testing set; the optimal training samples were selected using the LAR-based instance selection (LARIS) method, and the four other selection methods were compared. The results showed that 26.9% of the raw training samples were selected using LARIS, and the model based on these training samples had the highest accuracy. Thus, the apple origin classification model based on LARIS can achieve the goal of high accuracy and compression and provide experimental support for the least-angle regression algorithm in classification instance selection. Full article
(This article belongs to the Section Digital Agriculture)
Show Figures

Figure 1

13 pages, 2347 KiB  
Article
A Comparative Analysis of the Stomach, Gut, and Lung Microbiomes in Rattus norvegicus
by Taif Shah, Yuhan Wang, Yixuan Wang, Qian Li, Jiuxuan Zhou, Yutong Hou, Binghui Wang and Xueshan Xia
Microorganisms 2023, 11(9), 2359; https://doi.org/10.3390/microorganisms11092359 - 21 Sep 2023
Cited by 2 | Viewed by 2102
Abstract
Urban rats serve as reservoirs for several zoonotic pathogens that seriously endanger public health, destroy stored food, and damage infrastructure due to their close interaction with humans and domestic animals. Here, we characterize the core microbiomes of R. norvegicus’s stomach, gut, and lung [...] Read more.
Urban rats serve as reservoirs for several zoonotic pathogens that seriously endanger public health, destroy stored food, and damage infrastructure due to their close interaction with humans and domestic animals. Here, we characterize the core microbiomes of R. norvegicus’s stomach, gut, and lung using 16S rRNA next-generation Illumina HiSeq sequencing. The USEARCH software (v11) assigned the dataset to operational taxonomic units (OTUs). The alpha diversity index was calculated using QIIME1, while the beta diversity index was determined using the Bray–Curtis and Euclidean distances between groups. Principal component analyses visualized variation across samples based on the OTU information using the R package. Linear discriminant analysis, effect sizes (LEfSe), and phylogenetic investigation were used to identify differentially abundant taxa among groups. We reported an abundance of microbiota in the stomach, and they shared some of them with the gut and lung microbiota. A close look at the microbial family level reveals abundant Lactobacillaceae and Bifidobacteriaceae in the stomach, whereas Lactobacillaceae and Erysipelotrichaceae were more abundant in the gut; in contrast, Alcaligenaceae were abundant in the lungs. At the species level, some beneficial bacteria, particularly Lactobacillus reuteri and Lactobacillus johnsonii, and some potential pathogens, such as Bordetella hinzii, Streptococcus parauberis, Porphyromonas pogonae, Clostridium perfringens, etc., were identified in stomach, gut, and lung samples. Moreover, the alpha and beta diversity indexes revealed significant differences between the groups. Further analysis revealed abundant differential taxonomic biomarkers, i.e., increased Prevotellaceae and Clostridia in the lungs, whereas Campylobacteria and Lachnospirales were richest in the stomachs. In conclusion, we identified many beneficial, opportunistic, and highly pathogenic bacteria, confirming the importance of urban rats for public health. This study recommends a routine survey program to monitor rodent distribution and the pathogens they carry and transmit to humans and other domestic mammals. Full article
(This article belongs to the Special Issue Gut Microbiome in Homeostasis and Disease)
Show Figures

Figure 1

18 pages, 3063 KiB  
Article
Exploring European Eel Anguilla anguilla (L.) Habitat Differences Using Otolith Analysis in Central-Western Mediterranean Rivers and Coastal Lagoons from Sardinia
by Cinzia Podda, Jacopo Culurgioni, Riccardo Diciotti, Francesco Palmas, Elsa Amilhat, Elisabeth Faliex, Fabien Morat, Nicola Fois and Andrea Sabatini
Fishes 2023, 8(8), 386; https://doi.org/10.3390/fishes8080386 - 26 Jul 2023
Cited by 1 | Viewed by 2154
Abstract
An otolith shape and morphometric analysis was performed on European eel (Anguilla anguilla) subpopulations from five rivers and three coastal lagoons of Sardinia (central-western Mediterranean) to assess the role of different habitats on otolith development. Sagittal otolith shape was described by [...] Read more.
An otolith shape and morphometric analysis was performed on European eel (Anguilla anguilla) subpopulations from five rivers and three coastal lagoons of Sardinia (central-western Mediterranean) to assess the role of different habitats on otolith development. Sagittal otolith shape was described by 11 harmonics from elliptic Fourier descriptors. Comparisons among the harmonics were run through canonical discriminant analyses (CDAs). The CDA reclassification rate (75.7%) demonstrated a spatial environmental discrimination among local eel subpopulations of Sardinia. The Euclidean distance values demonstrated a dissimilarity between the river and lagoon groups. The form factor and roundness shape indices were significantly higher in the river group than in the lagoon group. The distances of the first three rings to the otolith core revealed site-specific otolith development. Moreover, the annual otolith growth rate was faster in the lagoon group than in the river group. The differences among the studied sites in terms of sagittal otolith shape could relate to changes in different local stocks potentially related to environmental peculiarities. Establishing a direct correlation between otolith morphology and environmental factors is challenging, and further studies are needed to investigate the relationship between habitat type/environmental variation and growth/body characteristics of eels. Nevertheless, the achieved results suggest that this method can be considered to be a valuable tool for studying the ontogeny of the European eel. Full article
(This article belongs to the Special Issue Biology and Ecology of Eels)
Show Figures

Figure 1

22 pages, 28091 KiB  
Communication
Proof and Application of Discriminating Ocean Oil Spills and Seawater Based on Polarization Ratio Using Quad-Polarization Synthetic Aperture Radar
by Tao Xie, Ruihang Ouyang, Will Perrie, Li Zhao and Xiaoyun Zhang
Remote Sens. 2023, 15(7), 1855; https://doi.org/10.3390/rs15071855 - 30 Mar 2023
Cited by 4 | Viewed by 1539
Abstract
This paper focuses on the proof and application of discriminating between oil spills and seawater (including the “look-alikes”, named low wind areas) based on the polarization ratio. A new relative polarization ratio (PRr) method is proposed, which is based [...] Read more.
This paper focuses on the proof and application of discriminating between oil spills and seawater (including the “look-alikes”, named low wind areas) based on the polarization ratio. A new relative polarization ratio (PRr) method is proposed, which is based on the difference between the scattering mechanism and the dielectric constant for oil spills compared to that of seawater. The case study found that (1) PRr numerically amplifies the contrast between oil spills and seawater, reduces the difference between low wind areas and ordinary seawater, and exhibits better details of the image; (2) the threshold method based on Euclidean distance can obtain the highest classification overall accuracy within the allowable error range, and can be widely used in the study of different incidence angles and environmental conditions; and (3) the identification of oil spills and seawater by the proposed methods can largely avoid the misjudgment of low wind areas as oil spills. Considering visual interpretation as the reference ‘ground truth’, the overall classification accuracy of all cases is more than 95%; only the edge of the diffuse thin oil slick and oil–water mixture is difficult to identify. This method can serve as an effective supplement to existing oil spill detection methods. Full article
(This article belongs to the Section Ocean Remote Sensing)
Show Figures

Graphical abstract

15 pages, 478 KiB  
Article
Ischemic Stroke Lesion Segmentation Using Mutation Model and Generative Adversarial Network
by Rawan Ghnemat, Ashwaq Khalil and Qasem Abu Al-Haija
Electronics 2023, 12(3), 590; https://doi.org/10.3390/electronics12030590 - 25 Jan 2023
Cited by 10 | Viewed by 2689
Abstract
Ischemic stroke lesion segmentation using different types of images, such as Computed Tomography Perfusion (CTP), is important for medical and Artificial intelligence fields. These images are potential resources to enhance machine learning and deep learning models. However, collecting these types of images is [...] Read more.
Ischemic stroke lesion segmentation using different types of images, such as Computed Tomography Perfusion (CTP), is important for medical and Artificial intelligence fields. These images are potential resources to enhance machine learning and deep learning models. However, collecting these types of images is a considerable challenge. Therefore, new augmentation techniques are required to handle the lack of collected images presenting Ischemic strokes. In this paper, the proposed model of mutation model using a distance map is integrated into the generative adversarial network (GAN) to generate a synthetic dataset. The Euclidean distance is used to compute the average distance of each pixel with its neighbor in the right and bottom directions. Then a threshold is used to select the adjacent locations with similar intensities for the mutation process. Furthermore, semi-supervised GAN is enhanced and transformed into supervised GAN, where the segmentation and discriminator are shared the same convolution neural network to reduce the computation process. The mutation and GAN models are trained as an end-to-end model. The results show that the mutation model enhances the dice coefficient of the proposed GAN model by 2.54%. Furthermore, it slightly enhances the recall of the proposed GAN model compared to other GAN models. Full article
Show Figures

Figure 1

15 pages, 1560 KiB  
Article
Industrial Fault Detection Based on Discriminant Enhanced Stacking Auto-Encoder Model
by Bowen Liu, Yi Chai, Yutao Jiang and Yiming Wang
Electronics 2022, 11(23), 3993; https://doi.org/10.3390/electronics11233993 - 2 Dec 2022
Cited by 5 | Viewed by 1648
Abstract
In the recent years, deep learning has been widely used in process monitoring due to its strong ability to extract features. However, with the increasing layers of the deep network, the compression of features by the deep model will lead to the loss [...] Read more.
In the recent years, deep learning has been widely used in process monitoring due to its strong ability to extract features. However, with the increasing layers of the deep network, the compression of features by the deep model will lead to the loss of some valuable information and affect the model’s performance. To solve this problem, a fault detection method based on a discriminant enhanced stacked auto-encoder is proposed. An enhanced stacked auto-encoder network structure is designed, and the original data is added to each hidden layer in the model pre-training process to solve the problem of information loss in the feature extraction process. Then the self-encoding network is combined with spectral regression kernel discriminant analysis. The fault category information is introduced into the features to optimize the features and enhance the discrimination of the extracted features. The Euclidean distance is used for fault detection based on the extracted features. From the Tennessee Eastman process experiment, it can be found that the detection accuracy of this method is about 9.4% higher than that of the traditional stacked auto-encoder method. Full article
Show Figures

Figure 1

22 pages, 1655 KiB  
Article
An Al-Biruni Earth Radius Optimization-Based Deep Convolutional Neural Network for Classifying Monkeypox Disease
by Doaa Sami Khafaga, Abdelhameed Ibrahim, El-Sayed M. El-Kenawy, Abdelaziz A. Abdelhamid, Faten Khalid Karim, Seyedali Mirjalili, Nima Khodadadi, Wei Hong Lim, Marwa M. Eid and Mohamed E. Ghoneim
Diagnostics 2022, 12(11), 2892; https://doi.org/10.3390/diagnostics12112892 - 21 Nov 2022
Cited by 36 | Viewed by 3860
Abstract
Human skin diseases have become increasingly prevalent in recent decades, with millions of individuals in developed countries experiencing monkeypox. Such conditions often carry less obvious but no less devastating risks, including increased vulnerability to monkeypox, cancer, and low self-esteem. Due to the low [...] Read more.
Human skin diseases have become increasingly prevalent in recent decades, with millions of individuals in developed countries experiencing monkeypox. Such conditions often carry less obvious but no less devastating risks, including increased vulnerability to monkeypox, cancer, and low self-esteem. Due to the low visual resolution of monkeypox disease images, medical specialists with high-level tools are typically required for a proper diagnosis. The manual diagnosis of monkeypox disease is subjective, time-consuming, and labor-intensive. Therefore, it is necessary to create a computer-aided approach for the automated diagnosis of monkeypox disease. Most research articles on monkeypox disease relied on convolutional neural networks (CNNs) and using classical loss functions, allowing them to pick up discriminative elements in monkeypox images. To enhance this, a novel framework using Al-Biruni Earth radius (BER) optimization-based stochastic fractal search (BERSFS) is proposed to fine-tune the deep CNN layers for classifying monkeypox disease from images. As a first step in the proposed approach, we use deep CNN-based models to learn the embedding of input images in Euclidean space. In the second step, we use an optimized classification model based on the triplet loss function to calculate the distance between pairs of images in Euclidean space and learn features that may be used to distinguish between different cases, including monkeypox cases. The proposed approach uses images of human skin diseases obtained from an African hospital. The experimental results of the study demonstrate the proposed framework’s efficacy, as it outperforms numerous examples of prior research on skin disease problems. On the other hand, statistical experiments with Wilcoxon and analysis of variance (ANOVA) tests are conducted to evaluate the proposed approach in terms of effectiveness and stability. The recorded results confirm the superiority of the proposed method when compared with other optimization algorithms and machine learning models. Full article
Show Figures

Figure 1

Back to TopTop