Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algor...Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.展开更多
The detection and characterization of non-metallic inclusions are essential for clean steel production.Recently,imaging analysis combined with high-dimensional data processing of metallic materials using artificial in...The detection and characterization of non-metallic inclusions are essential for clean steel production.Recently,imaging analysis combined with high-dimensional data processing of metallic materials using artificial intelligence(AI)-based machine learning(ML)has developed rapidly.This technique has achieved impressive results in the field of inclusion classification in process metallurgy.The present study surveys the ML modeling of inclusion prediction in advanced steels,including the detection,classification,and feature prediction of inclusions in different steel grades.Studies on clean steel with different features based on data and image analysis via ML are summarized.Regarding the data analysis,the inclusion prediction methodology based on ML establishes a connection between the experimental parameters and inclusion characteristics and analyzes the importance of the experimental parameters.Regarding the image analysis,the focus is placed on the classification of different types of inclusions via deep learning,in comparison with data analysis.Finally,further development of inclusion analyses using ML-based methods is recommended.This work paves the way for the application of AIbased methodologies for ultraclean-steel studies from a sustainable metallurgy perspective.展开更多
The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and hist...The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.展开更多
Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importan...Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.展开更多
Image recognition is widely used in different application areas such as shape recognition, gesture recognition and eye recognition. In this research, we introduced image recognition using efficient invariant moments a...Image recognition is widely used in different application areas such as shape recognition, gesture recognition and eye recognition. In this research, we introduced image recognition using efficient invariant moments and Principle Component Analysis (PCA) for gray and color images using different number of invariant moments. We used twelve moments for each image of gray images and Hu’s seven moments for color images to decrease dimensionality of the problem to 6 PCA’s for gray and 5 PCA’s for color images and hence the recognition time. PCA is then employed to decrease dimensionality of the problem and hence the recognition time and this is our main objective. The PCA is derived from Karhunen-Loeve’s transformation. Given an N-dimensional vector representation of each image, PCA tends to find a K-dimensional subspace whose basis vectors correspond to the maximum variance direction in the original image space. This new subspace is normally lower dimensional (K N). Three known datasets are used. The first set is the known Flower dataset. The second is the Africans dataset, and the third is the Shapes dataset. All these datasets were used by many researchers.展开更多
Due to the low spatial resolution of images taken from the Chang＇e-1 （CE-I） orbiter, the details of the lunar surface are blurred and lost. Considering the limited spatial resolution of image data obtained by a CCD...Due to the low spatial resolution of images taken from the Chang＇e-1 （CE-I） orbiter, the details of the lunar surface are blurred and lost. Considering the limited spatial resolution of image data obtained by a CCD camera on CE-1, an example-based super-resolution （SR） algorithm is employed to obtain high- resolution （HR） images. SR reconstruction is important for the application of image data to increase the resolution of images. In this article, a novel example-based algorithm is proposed to implement SR reconstruction by single-image analysis, and the computational cost is reduced compared to other example-based SR methods. The results show that this method can enhance the resolution of images using SR and recover detailed information about the lunar surface. Thus it can be used for surveying HR terrain and geological features. Moreover, the algorithm is significant for the HR processing of remotely sensed images obtained by other imaging systems.展开更多
Total-body positron emission tomography(TB-PET)has ultra-high sensitivity and the unique ability to conduct dynamic imaging of the entire body.Both the hardware configuration and the data acquired from a TB-PET scanne...Total-body positron emission tomography(TB-PET)has ultra-high sensitivity and the unique ability to conduct dynamic imaging of the entire body.Both the hardware configuration and the data acquired from a TB-PET scanner differ from those of the conventional short axial field-of-view scanners.Therefore,various aspects concerning data processing need careful consideration when implementing TB-PET in clinical settings.Additionally,advances in data analysis are needed to fully uncover the potential of these systems.Although some progress has been achieved,further research and innovation in scan data management are necessary.In this report,we provide a comprehensive overview of the current progress,challenges,and possible future directions for TB-PET data processing and analysis.For a review of clinical applications,please find the other review accompanying this paper.展开更多
Based on the 16d-composite MODIS （moderate resolution imaging spectroradiometer）-NDVI（normalized difference vegetation index） time-series data in 2004, vegetation in North Tibet Plateau was classified and seasonal...Based on the 16d-composite MODIS （moderate resolution imaging spectroradiometer）-NDVI（normalized difference vegetation index） time-series data in 2004, vegetation in North Tibet Plateau was classified and seasonal variations on the pixels selected from different vegetation type were analyzed. The Savitzky-Golay filtering algorithm was applied to perform a filtration processing for MODIS-NDVI time-series data. The processed time-series curves can reflect a real variation trend of vegetation growth. The NDVI time-series curves of coniferous forest, high-cold meadow, high-cold meadow steppe and high-cold steppe all appear a mono-peak model during vegetation growth with the maximum peak occurring in August. A decision-tree classification model was established according to either NDVI time-series data or land surface temperature data. And then, both classifying and processing for vegetations were carried out through the model based on NDVI time-series curves. An accuracy test illustrates that classification results are of high accuracy and credibility and the model is conducive for studying a climate variation and estimating a vegetation production at regional even global scale.展开更多
A data processing method was proposed for eliminating the end restraint in triaxial tests of soil. A digital image processing method was used to calculate the local deformations and local stresses for any region on th...A data processing method was proposed for eliminating the end restraint in triaxial tests of soil. A digital image processing method was used to calculate the local deformations and local stresses for any region on the surface of triaxial soil specimens. The principle and implementation of this digital image processing method were introduced as well as the calculation method for local mechanical properties of soil specimens. Comparisons were made between the test results calculated by the data from both the entire specimen and local regions, and it was found that the deformations were more uniform in the middle region compared with the entire specimen. In order to quantify the nonuniform characteristic of deformation, the non-uniformity coefficients of strain were defined and calculated. Traditional and end-lubricated triaxial tests were conducted under the same condition to investigate the effects of using local region data for deformation calculation on eliminating the end restraint of specimens. After the statistical analysis of all test results, it was concluded that for the tested soil specimen with the size of 39.1 mm × 80 ram, the utilization of the middle 35 mm region of traditional specimens in data processing had a better effect on eliminating end restraint compared with end lubrication. Furthermore, the local data analysis in this paper was validated through the comparisons with the test results from other researchers.展开更多
Automatic road detection, in dense urban areas, is a challenging application in the remote sensing community. This is mainly because of physical and geometrical variations of road pixels, their spectral similarity to ...Automatic road detection, in dense urban areas, is a challenging application in the remote sensing community. This is mainly because of physical and geometrical variations of road pixels, their spectral similarity to other features such as buildings, parking lots and sidewalks, and the obstruction by vehicles and trees. These problems are real obstacles in precise detection and identification of urban roads from high-resolution satellite imagery. One of the promising strategies to deal with this problem is using multi-sensors data to reduce the uncertainties of detection. In this paper, an integrated object-based analysis framework was developed for detecting and extracting various types of urban roads from high-resolution optical images and Lidar data. The proposed method is designed and implemented using a rule-oriented approach based on a masking strategy. The overall accuracy (OA) of the final road map was 89.2%, and the kappa coefficient of agreement was 0.83, which show the efficiency and performance of the method in different conditions and interclass noises. The results also demonstrate the high capability of this object-based method in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite images and Lidar data.展开更多
Red tide is an ecological disaster caused by the excessive proliferation of photosynthetic algae in the ocean.The frequent occurrences of red tide have brought serious harms to the marine aquaculture and caused signif...Red tide is an ecological disaster caused by the excessive proliferation of photosynthetic algae in the ocean.The frequent occurrences of red tide have brought serious harms to the marine aquaculture and caused significant economic losses to the marine industry.Red tide prediction can alleviate and even stop the long-term damages to marine ecosystems,which helps maintain the ecological balance of the ocean environment and contributes to the Sustainable Development Goal of“life below water”formulated by the United Nations.Aiming at red tide prediction using remote sensing technology,this study proposed a novel approach of red tide prediction using time-series hyperspectral observations,and examined the proposed method in the Xinghai Bay,China.Three spectral indices,namely the twoband ratio(TBR),the three-band spectral index(TBSI),and the fluorescence baseline height(FLH),were used to reduce the dimensionality of hyperspectral data and extract spectral features.Two machine learning models including the random forest(RF)and the support vector machine(SVM)were employed to predict whether red tide would occur on a target day based on the time-series spectral indices obtained in the previous days.By comparing and analyzing the prediction results of multiple machine learning models trained with different spectral indices and temporal lengths,it is found that both the RF and the SVM models can predict the red tide outbreaks at the accuracies over 0.9 using adequate temporal lengths of input data.When the temporal length of input data is limited,however,it is suggested to use the RF model,which accurately predicts red tide outbreaks using the temporal input of the 2-d TBSI.The proposed method is expected to provide oceanic and maritime agencies with early warnings on red tide outbreaks and ensure the safety of the coastal environment in large spatial scales using optical remote sensing technology.展开更多
The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they ofte...The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they often face challenges such as lengthy computation times and limited accuracy.To achieve rapid and accurate matching between the targeted ballistic curve and complex grain shape,this paper proposes a novel reverse design method for SRM propellant grain based on time-series data imaging and convolutional neural network(CNN).First,a finocyl grain shape-internal ballistic curve dataset is created using parametric modeling techniques to comprehensively cover the design space.Next,the internal ballistic time-series data is encoded into three-channel images,establishing a potential relationship between the ballistic curves and their image representations.A CNN is then constructed and trained using these encoded images.Once trained,the model enables efficient inference of propellant grain dimensions from a target internal ballistic curve.This paper conducts comparative experiments across various neural network models,validating the effectiveness of the feature extraction method that transforms internal ballistic time-series data into images,as well as its generalization capability across different CNN architectures.Ignition tests were performed based on the predicted propellant grain.The results demonstrate that the relative error between the experimental internal ballistic curves and the target curves is less than 5%,confirming the validity and feasibility of the proposed reverse design methodology.展开更多
Deconvolution in radio interferometry faces challenges due to incomplete sampling of the visibilities in the spatial frequency domain caused by a limited number of antenna baselines,resulting in an ill-posed inverse p...Deconvolution in radio interferometry faces challenges due to incomplete sampling of the visibilities in the spatial frequency domain caused by a limited number of antenna baselines,resulting in an ill-posed inverse problem.Reconstructing dirty images into clean ones is crucial for subsequent scientific analysis.To address these challenges,we propose a U-Net based method that extracts high-level information from the dirty image and reconstructs a clean image by effectively reducing artifacts and sidelobes.The U-Net architecture,consisting of an encoder-decoder structure and skip connections,facilitates the flow of information and preserves spatial details.Using simulated data of radio galaxies,we train our model and evaluate its performance on the testing set.Compared with the CLEAN method and the visibility and image conditioned denoising diffusion probabilistic model,our proposed model can effectively reconstruct both extended sources and faint point sources with higher values in the structural similarity index measure and the peak signal-to-noise ratio.Furthermore,we investigate the impact of noise on the model performance,demonstrating its robustness under varying noise levels.展开更多
In the task of classifying massive celestial data,the accurate classification of galaxies,stars,and quasars usually relies on spectral labels.However,spectral data account for only a small fraction of all astronomical...In the task of classifying massive celestial data,the accurate classification of galaxies,stars,and quasars usually relies on spectral labels.However,spectral data account for only a small fraction of all astronomical observation data,and the target source classification information in vast photometric data has not been accurately measured.To address this,we propose a novel deep learning-based algorithm,YL8C4Net,for the automatic detection and classification of target sources in photometric images.This algorithm combines the YOLOv8 detection network with the Conv4Net classification network.Additionally,we propose a novel magnitude-based labeling method for target source annotation.In the performance evaluation,the YOLOv8 achieves impressive performance with average precision scores of 0.824 for AP@0.5 and 0.795 for AP@0.5:0.95.Meanwhile,the constructed Conv4Net attains an accuracy of 0.8895.Overall,YL8C4Net offers the advantages of fewer parameters,faster processing speed,and higher classification accuracy,making it particularly suitable for large-scale data processing tasks.Furthermore,we employed the YL8C4Net model to conduct target source detection and classification on photometric images from 20 sky regions in SDSS-DR17.As a result,a catalog containing about 9.39 million target source classification results has been preliminarily constructed,thereby providing valuable reference data for astronomical research.展开更多
Against the backdrop of massive sky survey data,the automated detection,classification,and parameter computation of targets have emerged as critical areas demanding urgent breakthroughs.However,in detection and classi...Against the backdrop of massive sky survey data,the automated detection,classification,and parameter computation of targets have emerged as critical areas demanding urgent breakthroughs.However,in detection and classification tasks,model accuracy is often constrained by issues such as small target sizes and insufficient feature information.To address this challenge,we innovatively constructs a fully automated astronomical image analysis pipeline that combines point source detection and classification,galaxy morphological classification,and parameter computation,forming an end-to-end solution.This pipeline achieves automated detection and morphological classification of both point sources and extended sources,and it is also able to compute the basic parameters of galaxy targets.The pipeline first accomplishes the detection and localization of target sources using the YOLOv9 model,and then leverages the optimized ResNet-AE model to initially categorize the detected targets into three major classes:stars,quasars,and galaxies.To tackle the problem of small sizes in some galaxy targets,we filtered out samples with larger sizes and distinct contours.Drawing on morphological characteristics,these samples were further classified into six categories via the DenseNet-SE4 model:barred spiral galaxies,cigar galaxies,elliptical galaxies,intermediate galaxies,spiral galaxies,and irregular galaxies.Following this classification,parameter computation was conducted on the targets.Experimental results show that the detection model has achieved better performance than previous studies,with a mean average precision of 85.20%at Intersection over Union values ranging from 0.5 to 0.95.Both classification models also reached an accuracy of over 85%on the test set.Compared with classical CNN networks,these two classification models boast higher precision,and the computation of target parameters has also yielded reliable outcomes.Experiments verify that this pipeline can act as a supplementary tool for astronomical image processing and be applied to data mining and analysis work in sky surveys.展开更多
The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the ...The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.展开更多
The hard X-ray modulation telescope （HXMT） mission is mainly devoted to performing an all-sky survey at 1- 250 keV with both high sensitivity and high spatial resolution. The observed data reduction as well as the i...The hard X-ray modulation telescope （HXMT） mission is mainly devoted to performing an all-sky survey at 1- 250 keV with both high sensitivity and high spatial resolution. The observed data reduction as well as the image reconstruction for HXMT can be achieved by using the direct demodulation method （DDM）. However the original DDM is too computationally expensive for multi-dimensional data with high resolution to be employed for HXMT data. We propose an accelerated direct demodulation method especially adapted for data from HXMT. Simulations are also presented to demonstrate this method.展开更多
The Internet of Multimedia Things(IoMT)refers to a network of interconnected multimedia devices that communicate with each other over the Internet.Recently,smart healthcare has emerged as a significant application of ...The Internet of Multimedia Things(IoMT)refers to a network of interconnected multimedia devices that communicate with each other over the Internet.Recently,smart healthcare has emerged as a significant application of the IoMT,particularly in the context of knowledge‐based learning systems.Smart healthcare systems leverage knowledge‐based learning to become more context‐aware,adaptable,and auditable while maintain-ing the ability to learn from historical data.In smart healthcare systems,devices capture images,such as X‐rays,Magnetic Resonance Imaging.The security and integrity of these images are crucial for the databases used in knowledge‐based learning systems to foster structured decision‐making and enhance the learning abilities of AI.Moreover,in knowledge‐driven systems,the storage and transmission of HD medical images exert a burden on the limited bandwidth of the communication channel,leading to data trans-mission delays.To address the security and latency concerns,this paper presents a lightweight medical image encryption scheme utilising bit‐plane decomposition and chaos theory.The results of the experiment yield entropy,energy,and correlation values of 7.999,0.0156,and 0.0001,respectively.This validates the effectiveness of the encryption system proposed in this paper,which offers high‐quality encryption,a large key space,key sensitivity,and resistance to statistical attacks.展开更多
The aggregation of data in recent years has been expanding at an exponential rate. There are various data generating sources that are responsible for such a tremendous data growth rate. Some of the data origins includ...The aggregation of data in recent years has been expanding at an exponential rate. There are various data generating sources that are responsible for such a tremendous data growth rate. Some of the data origins include data from the various social media, footages from video cameras, wireless and wired sensor network measurements, data from the stock markets and other financial transaction data, supermarket transaction data and so on. The aforementioned data may be high dimensional and big in Volume, Value, Velocity, Variety, and Veracity. Hence one of the crucial challenges is the storage, processing and extraction of relevant information from the data. In the special case of image data, the technique of image compressions may be employed in reducing the dimension and volume of the data to ensure it is convenient for processing and analysis. In this work, we examine a proof-of-concept multiresolution analytics that uses wavelet transforms, that is one popular mathematical and analytical framework employed in signal processing and representations, and we study its applications to the area of compressing image data in wireless sensor networks. The proposed approach consists of the applications of wavelet transforms, threshold detections, quantization data encoding and ultimately apply the inverse transforms. The work specifically focuses on multi-resolution analysis with wavelet transforms by comparing 3 wavelets at the 5 decomposition levels. Simulation results are provided to demonstrate the effectiveness of the methodology.展开更多
Attitude is one of the crucial parameters for space objects and plays a vital role in collision prediction and debris removal.Analyzing light curves to determine attitude is the most commonly used method.In photometri...Attitude is one of the crucial parameters for space objects and plays a vital role in collision prediction and debris removal.Analyzing light curves to determine attitude is the most commonly used method.In photometric observations,outliers may exist in the obtained light curves due to various reasons.Therefore,preprocessing is required to remove these outliers to obtain high quality light curves.Through statistical analysis,the reasons leading to outliers can be categorized into two main types:first,the brightness of the object significantly increases due to the passage of a star nearby,referred to as“stellar contamination,”and second,the brightness markedly decreases due to cloudy cover,referred to as“cloudy contamination.”The traditional approach of manually inspecting images for contamination is time-consuming and labor-intensive.However,we propose the utilization of machine learning methods as a substitute.Convolutional Neural Networks and SVMs are employed to identify cases of stellar contamination and cloudy contamination,achieving F1 scores of 1.00 and 0.98 on a test set,respectively.We also explore other machine learning methods such as ResNet-18 and Light Gradient Boosting Machine,then conduct comparative analyses of the results.展开更多
文摘Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.
基金support from the National Key Research and Development Program of China(No.2024YFB3713705)is acknowledgedWangzhong Mu would like to acknowledge the Strategic Mobility,Sweden(SSF,No.SM22-0039)+1 种基金the Swedish Foundation for International Cooperation in Research and Higher Education(STINT,No.IB2022-9228)the Jernkontoret(Sweden)for supporting this clean steel research.Gonghao Lian would like to acknowledge China Scholarship Council(CSC,No.202306080032).
文摘The detection and characterization of non-metallic inclusions are essential for clean steel production.Recently,imaging analysis combined with high-dimensional data processing of metallic materials using artificial intelligence(AI)-based machine learning(ML)has developed rapidly.This technique has achieved impressive results in the field of inclusion classification in process metallurgy.The present study surveys the ML modeling of inclusion prediction in advanced steels,including the detection,classification,and feature prediction of inclusions in different steel grades.Studies on clean steel with different features based on data and image analysis via ML are summarized.Regarding the data analysis,the inclusion prediction methodology based on ML establishes a connection between the experimental parameters and inclusion characteristics and analyzes the importance of the experimental parameters.Regarding the image analysis,the focus is placed on the classification of different types of inclusions via deep learning,in comparison with data analysis.Finally,further development of inclusion analyses using ML-based methods is recommended.This work paves the way for the application of AIbased methodologies for ultraclean-steel studies from a sustainable metallurgy perspective.
文摘The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.
文摘Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.
文摘Image recognition is widely used in different application areas such as shape recognition, gesture recognition and eye recognition. In this research, we introduced image recognition using efficient invariant moments and Principle Component Analysis (PCA) for gray and color images using different number of invariant moments. We used twelve moments for each image of gray images and Hu’s seven moments for color images to decrease dimensionality of the problem to 6 PCA’s for gray and 5 PCA’s for color images and hence the recognition time. PCA is then employed to decrease dimensionality of the problem and hence the recognition time and this is our main objective. The PCA is derived from Karhunen-Loeve’s transformation. Given an N-dimensional vector representation of each image, PCA tends to find a K-dimensional subspace whose basis vectors correspond to the maximum variance direction in the original image space. This new subspace is normally lower dimensional (K N). Three known datasets are used. The first set is the known Flower dataset. The second is the Africans dataset, and the third is the Shapes dataset. All these datasets were used by many researchers.
基金funded by the National Natural Science Foundation of China (Grant No. 51575388)
文摘Due to the low spatial resolution of images taken from the Chang＇e-1 （CE-I） orbiter, the details of the lunar surface are blurred and lost. Considering the limited spatial resolution of image data obtained by a CCD camera on CE-1, an example-based super-resolution （SR） algorithm is employed to obtain high- resolution （HR） images. SR reconstruction is important for the application of image data to increase the resolution of images. In this article, a novel example-based algorithm is proposed to implement SR reconstruction by single-image analysis, and the computational cost is reduced compared to other example-based SR methods. The results show that this method can enhance the resolution of images using SR and recover detailed information about the lunar surface. Thus it can be used for surveying HR terrain and geological features. Moreover, the algorithm is significant for the HR processing of remotely sensed images obtained by other imaging systems.
基金Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province,Grant/Award Number:2023B1212060052Shenzhen Science and Technology Innovation Committee,Grant/Award Number:20220531100209020Guangdong Science and Technology Department,Grant/Award Number:2022A1515110716。
文摘Total-body positron emission tomography(TB-PET)has ultra-high sensitivity and the unique ability to conduct dynamic imaging of the entire body.Both the hardware configuration and the data acquired from a TB-PET scanner differ from those of the conventional short axial field-of-view scanners.Therefore,various aspects concerning data processing need careful consideration when implementing TB-PET in clinical settings.Additionally,advances in data analysis are needed to fully uncover the potential of these systems.Although some progress has been achieved,further research and innovation in scan data management are necessary.In this report,we provide a comprehensive overview of the current progress,challenges,and possible future directions for TB-PET data processing and analysis.For a review of clinical applications,please find the other review accompanying this paper.
基金the Frontier Program of the Knowledge Innovation Program of Chinese Academy of Sciences
文摘Based on the 16d-composite MODIS （moderate resolution imaging spectroradiometer）-NDVI（normalized difference vegetation index） time-series data in 2004, vegetation in North Tibet Plateau was classified and seasonal variations on the pixels selected from different vegetation type were analyzed. The Savitzky-Golay filtering algorithm was applied to perform a filtration processing for MODIS-NDVI time-series data. The processed time-series curves can reflect a real variation trend of vegetation growth. The NDVI time-series curves of coniferous forest, high-cold meadow, high-cold meadow steppe and high-cold steppe all appear a mono-peak model during vegetation growth with the maximum peak occurring in August. A decision-tree classification model was established according to either NDVI time-series data or land surface temperature data. And then, both classifying and processing for vegetations were carried out through the model based on NDVI time-series curves. An accuracy test illustrates that classification results are of high accuracy and credibility and the model is conducive for studying a climate variation and estimating a vegetation production at regional even global scale.
基金Supported by Major State Basic Research Development Program of China("973" Program,No.2010CB731502)
文摘A data processing method was proposed for eliminating the end restraint in triaxial tests of soil. A digital image processing method was used to calculate the local deformations and local stresses for any region on the surface of triaxial soil specimens. The principle and implementation of this digital image processing method were introduced as well as the calculation method for local mechanical properties of soil specimens. Comparisons were made between the test results calculated by the data from both the entire specimen and local regions, and it was found that the deformations were more uniform in the middle region compared with the entire specimen. In order to quantify the nonuniform characteristic of deformation, the non-uniformity coefficients of strain were defined and calculated. Traditional and end-lubricated triaxial tests were conducted under the same condition to investigate the effects of using local region data for deformation calculation on eliminating the end restraint of specimens. After the statistical analysis of all test results, it was concluded that for the tested soil specimen with the size of 39.1 mm × 80 ram, the utilization of the middle 35 mm region of traditional specimens in data processing had a better effect on eliminating end restraint compared with end lubrication. Furthermore, the local data analysis in this paper was validated through the comparisons with the test results from other researchers.
文摘Automatic road detection, in dense urban areas, is a challenging application in the remote sensing community. This is mainly because of physical and geometrical variations of road pixels, their spectral similarity to other features such as buildings, parking lots and sidewalks, and the obstruction by vehicles and trees. These problems are real obstacles in precise detection and identification of urban roads from high-resolution satellite imagery. One of the promising strategies to deal with this problem is using multi-sensors data to reduce the uncertainties of detection. In this paper, an integrated object-based analysis framework was developed for detecting and extracting various types of urban roads from high-resolution optical images and Lidar data. The proposed method is designed and implemented using a rule-oriented approach based on a masking strategy. The overall accuracy (OA) of the final road map was 89.2%, and the kappa coefficient of agreement was 0.83, which show the efficiency and performance of the method in different conditions and interclass noises. The results also demonstrate the high capability of this object-based method in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite images and Lidar data.
基金The National Natural Science Foundation of China under contract No.42406188the Natural Science Foundation of Liaoning Province under contract No.2024-BS-022+1 种基金the Dalian High-Level Talent Innovation Program under contract No.2022RG02the Fundamental Research Funds for the Central Universities under contract No.3132025107.
文摘Red tide is an ecological disaster caused by the excessive proliferation of photosynthetic algae in the ocean.The frequent occurrences of red tide have brought serious harms to the marine aquaculture and caused significant economic losses to the marine industry.Red tide prediction can alleviate and even stop the long-term damages to marine ecosystems,which helps maintain the ecological balance of the ocean environment and contributes to the Sustainable Development Goal of“life below water”formulated by the United Nations.Aiming at red tide prediction using remote sensing technology,this study proposed a novel approach of red tide prediction using time-series hyperspectral observations,and examined the proposed method in the Xinghai Bay,China.Three spectral indices,namely the twoband ratio(TBR),the three-band spectral index(TBSI),and the fluorescence baseline height(FLH),were used to reduce the dimensionality of hyperspectral data and extract spectral features.Two machine learning models including the random forest(RF)and the support vector machine(SVM)were employed to predict whether red tide would occur on a target day based on the time-series spectral indices obtained in the previous days.By comparing and analyzing the prediction results of multiple machine learning models trained with different spectral indices and temporal lengths,it is found that both the RF and the SVM models can predict the red tide outbreaks at the accuracies over 0.9 using adequate temporal lengths of input data.When the temporal length of input data is limited,however,it is suggested to use the RF model,which accurately predicts red tide outbreaks using the temporal input of the 2-d TBSI.The proposed method is expected to provide oceanic and maritime agencies with early warnings on red tide outbreaks and ensure the safety of the coastal environment in large spatial scales using optical remote sensing technology.
文摘The reverse design of solid rocket motor(SRM)propellant grain involves determining the grain geometry to closely match a predefined internal ballistic curve.While existing reverse design methods are feasible,they often face challenges such as lengthy computation times and limited accuracy.To achieve rapid and accurate matching between the targeted ballistic curve and complex grain shape,this paper proposes a novel reverse design method for SRM propellant grain based on time-series data imaging and convolutional neural network(CNN).First,a finocyl grain shape-internal ballistic curve dataset is created using parametric modeling techniques to comprehensively cover the design space.Next,the internal ballistic time-series data is encoded into three-channel images,establishing a potential relationship between the ballistic curves and their image representations.A CNN is then constructed and trained using these encoded images.Once trained,the model enables efficient inference of propellant grain dimensions from a target internal ballistic curve.This paper conducts comparative experiments across various neural network models,validating the effectiveness of the feature extraction method that transforms internal ballistic time-series data into images,as well as its generalization capability across different CNN architectures.Ignition tests were performed based on the predicted propellant grain.The results demonstrate that the relative error between the experimental internal ballistic curves and the target curves is less than 5%,confirming the validity and feasibility of the proposed reverse design methodology.
基金supported by the National SKA Program of China(2020SKA0110300,2020SKA0110201)the National Natural Science Foundation of China(NSFC,grant Nos.12433012 and 12373097)+1 种基金the Guangdong Province Project of the Basic and Applied Basic Research Foundation(2024A1515011503)the Guangzhou Science and Technology Funds(2023A03J0016).
文摘Deconvolution in radio interferometry faces challenges due to incomplete sampling of the visibilities in the spatial frequency domain caused by a limited number of antenna baselines,resulting in an ill-posed inverse problem.Reconstructing dirty images into clean ones is crucial for subsequent scientific analysis.To address these challenges,we propose a U-Net based method that extracts high-level information from the dirty image and reconstructs a clean image by effectively reducing artifacts and sidelobes.The U-Net architecture,consisting of an encoder-decoder structure and skip connections,facilitates the flow of information and preserves spatial details.Using simulated data of radio galaxies,we train our model and evaluate its performance on the testing set.Compared with the CLEAN method and the visibility and image conditioned denoising diffusion probabilistic model,our proposed model can effectively reconstruct both extended sources and faint point sources with higher values in the structural similarity index measure and the peak signal-to-noise ratio.Furthermore,we investigate the impact of noise on the model performance,demonstrating its robustness under varying noise levels.
基金supported by the National Natural Science Foundation of China (NSFC, Grant No. U1731128)
文摘In the task of classifying massive celestial data,the accurate classification of galaxies,stars,and quasars usually relies on spectral labels.However,spectral data account for only a small fraction of all astronomical observation data,and the target source classification information in vast photometric data has not been accurately measured.To address this,we propose a novel deep learning-based algorithm,YL8C4Net,for the automatic detection and classification of target sources in photometric images.This algorithm combines the YOLOv8 detection network with the Conv4Net classification network.Additionally,we propose a novel magnitude-based labeling method for target source annotation.In the performance evaluation,the YOLOv8 achieves impressive performance with average precision scores of 0.824 for AP@0.5 and 0.795 for AP@0.5:0.95.Meanwhile,the constructed Conv4Net attains an accuracy of 0.8895.Overall,YL8C4Net offers the advantages of fewer parameters,faster processing speed,and higher classification accuracy,making it particularly suitable for large-scale data processing tasks.Furthermore,we employed the YL8C4Net model to conduct target source detection and classification on photometric images from 20 sky regions in SDSS-DR17.As a result,a catalog containing about 9.39 million target source classification results has been preliminarily constructed,thereby providing valuable reference data for astronomical research.
基金supported by the National Natural Science Foundation of China(NSFC,grant No.U1731128)。
文摘Against the backdrop of massive sky survey data,the automated detection,classification,and parameter computation of targets have emerged as critical areas demanding urgent breakthroughs.However,in detection and classification tasks,model accuracy is often constrained by issues such as small target sizes and insufficient feature information.To address this challenge,we innovatively constructs a fully automated astronomical image analysis pipeline that combines point source detection and classification,galaxy morphological classification,and parameter computation,forming an end-to-end solution.This pipeline achieves automated detection and morphological classification of both point sources and extended sources,and it is also able to compute the basic parameters of galaxy targets.The pipeline first accomplishes the detection and localization of target sources using the YOLOv9 model,and then leverages the optimized ResNet-AE model to initially categorize the detected targets into three major classes:stars,quasars,and galaxies.To tackle the problem of small sizes in some galaxy targets,we filtered out samples with larger sizes and distinct contours.Drawing on morphological characteristics,these samples were further classified into six categories via the DenseNet-SE4 model:barred spiral galaxies,cigar galaxies,elliptical galaxies,intermediate galaxies,spiral galaxies,and irregular galaxies.Following this classification,parameter computation was conducted on the targets.Experimental results show that the detection model has achieved better performance than previous studies,with a mean average precision of 85.20%at Intersection over Union values ranging from 0.5 to 0.95.Both classification models also reached an accuracy of over 85%on the test set.Compared with classical CNN networks,these two classification models boast higher precision,and the computation of target parameters has also yielded reliable outcomes.Experiments verify that this pipeline can act as a supplementary tool for astronomical image processing and be applied to data mining and analysis work in sky surveys.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Funding Program,Grant No.(FRP-1443-15).
文摘The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11173038 and 11103022)the Tsinghua University Initiative Scientific Research Program (Grant No. 20111081102)
文摘The hard X-ray modulation telescope （HXMT） mission is mainly devoted to performing an all-sky survey at 1- 250 keV with both high sensitivity and high spatial resolution. The observed data reduction as well as the image reconstruction for HXMT can be achieved by using the direct demodulation method （DDM）. However the original DDM is too computationally expensive for multi-dimensional data with high resolution to be employed for HXMT data. We propose an accelerated direct demodulation method especially adapted for data from HXMT. Simulations are also presented to demonstrate this method.
文摘The Internet of Multimedia Things(IoMT)refers to a network of interconnected multimedia devices that communicate with each other over the Internet.Recently,smart healthcare has emerged as a significant application of the IoMT,particularly in the context of knowledge‐based learning systems.Smart healthcare systems leverage knowledge‐based learning to become more context‐aware,adaptable,and auditable while maintain-ing the ability to learn from historical data.In smart healthcare systems,devices capture images,such as X‐rays,Magnetic Resonance Imaging.The security and integrity of these images are crucial for the databases used in knowledge‐based learning systems to foster structured decision‐making and enhance the learning abilities of AI.Moreover,in knowledge‐driven systems,the storage and transmission of HD medical images exert a burden on the limited bandwidth of the communication channel,leading to data trans-mission delays.To address the security and latency concerns,this paper presents a lightweight medical image encryption scheme utilising bit‐plane decomposition and chaos theory.The results of the experiment yield entropy,energy,and correlation values of 7.999,0.0156,and 0.0001,respectively.This validates the effectiveness of the encryption system proposed in this paper,which offers high‐quality encryption,a large key space,key sensitivity,and resistance to statistical attacks.
文摘The aggregation of data in recent years has been expanding at an exponential rate. There are various data generating sources that are responsible for such a tremendous data growth rate. Some of the data origins include data from the various social media, footages from video cameras, wireless and wired sensor network measurements, data from the stock markets and other financial transaction data, supermarket transaction data and so on. The aforementioned data may be high dimensional and big in Volume, Value, Velocity, Variety, and Veracity. Hence one of the crucial challenges is the storage, processing and extraction of relevant information from the data. In the special case of image data, the technique of image compressions may be employed in reducing the dimension and volume of the data to ensure it is convenient for processing and analysis. In this work, we examine a proof-of-concept multiresolution analytics that uses wavelet transforms, that is one popular mathematical and analytical framework employed in signal processing and representations, and we study its applications to the area of compressing image data in wireless sensor networks. The proposed approach consists of the applications of wavelet transforms, threshold detections, quantization data encoding and ultimately apply the inverse transforms. The work specifically focuses on multi-resolution analysis with wavelet transforms by comparing 3 wavelets at the 5 decomposition levels. Simulation results are provided to demonstrate the effectiveness of the methodology.
基金funded by the National Natural Science Foundation of China(NSFC,Nos.12373086 and 12303082)CAS“Light of West China”Program+2 种基金Yunnan Revitalization Talent Support Program in Yunnan ProvinceNational Key R&D Program of ChinaGravitational Wave Detection Project No.2022YFC2203800。
文摘Attitude is one of the crucial parameters for space objects and plays a vital role in collision prediction and debris removal.Analyzing light curves to determine attitude is the most commonly used method.In photometric observations,outliers may exist in the obtained light curves due to various reasons.Therefore,preprocessing is required to remove these outliers to obtain high quality light curves.Through statistical analysis,the reasons leading to outliers can be categorized into two main types:first,the brightness of the object significantly increases due to the passage of a star nearby,referred to as“stellar contamination,”and second,the brightness markedly decreases due to cloudy cover,referred to as“cloudy contamination.”The traditional approach of manually inspecting images for contamination is time-consuming and labor-intensive.However,we propose the utilization of machine learning methods as a substitute.Convolutional Neural Networks and SVMs are employed to identify cases of stellar contamination and cloudy contamination,achieving F1 scores of 1.00 and 0.98 on a test set,respectively.We also explore other machine learning methods such as ResNet-18 and Light Gradient Boosting Machine,then conduct comparative analyses of the results.
