Pattern recognition is critical to map data handling and their applications.This study presents a model that combines the Shape Context(SC)descriptor and Graph Convolutional Neural Network(GCNN)to classify the pattern...Pattern recognition is critical to map data handling and their applications.This study presents a model that combines the Shape Context(SC)descriptor and Graph Convolutional Neural Network(GCNN)to classify the patterns of interchanges,which are indispensable parts of urban road networks.In the SC-GCNN model,an interchange is modeled as a graph,wherein nodes and edges represent the interchange segments and their connections,respectively.Then,a novel SC descriptor is implemented to describe the contextual information of each interchange segment and serve as descriptive features of graph nodes.Finally,a GCNN is designed by combining graph convolution and pooling operations to process the constructed graphs and classify the interchange patterns.The SC-GCNN model was validated using interchange samples obtained from the road networks of 15 cities downloaded from OpenStreetMap.The classification accuracy was 87.06%,which was higher than that of the image-based AlexNet,GoogLeNet,and Random Forest models.展开更多
To improve the classification method of body type, 103 young female college students in Jiaodong area(Shandong, China) were measured by a 3 D body scanning system, and variables of upper body parts were selected and a...To improve the classification method of body type, 103 young female college students in Jiaodong area(Shandong, China) were measured by a 3 D body scanning system, and variables of upper body parts were selected and analyzed by SPSS software. According to the indices such as the chest ratio, the chest sagittal diameter ratio, and the shoulder angle, the tested population was quickly clustered into six categories by the classification method of “size feature+shape index+front and back indices”, which were divided into flat chest body, graceful body, breast augmentation body, normal body, convex back body, and flat body. The proportion of various body types and classification rules were obtained. According to the classification rules, 103 samples and 15 new females’ body data were analyzed and verified. Finally, according to the descriptive statistical analysis of upper body-related indicators of young female in this area, the height and the chest circumference were selected as independent variables, regression analysis was carried out on 11 related indicators, and the mapping relationship between height and chest circumference was studied, which provided a mathematical model for the design of fit clothing structure of young females in Jiaodong area.展开更多
In this paper, a new shape classification system based on singular value decomposition (SVD) transform using nearest neighbour classifier was proposed. The gray scale image of the shape object was converted into a bla...In this paper, a new shape classification system based on singular value decomposition (SVD) transform using nearest neighbour classifier was proposed. The gray scale image of the shape object was converted into a black and white image. The squared Euclidean distance transform on binary image was applied to extract the boundary image of the shape. SVD transform features were extracted from the the boundary of the object shapes. In this paper, the proposed classification system based on SVD transform feature extraction method was compared with classifier based on moment invariants using nearest neighbour classifier. The experimental results showed the advantage of our proposed classification system.展开更多
For classifying unknown 3-D objects into a set of predetermined object classes, a part-level object classification method based on the improved interpretation tree is presented. The part-level representation is implem...For classifying unknown 3-D objects into a set of predetermined object classes, a part-level object classification method based on the improved interpretation tree is presented. The part-level representation is implemented, which enables a more compact shape description of 3-D objects. The proposed classification method consists of two key processing stages： the improved constrained search on an interpretation tree and the following shape similarity measure computation. By the classification method, both whole match and partial match with shape similarity ranks are achieved; especially, focus match can be accomplished, where different key parts may be labeled and all the matched models containing corresponding key parts may be obtained. A series of experiments show the effectiveness of the presented 3-D object classification method.展开更多
The purpose of this paper was to develop a reliable body shape analysis approach based on cluster analysis, k. nearestneighbor( KNN), and multi-class support vector machine( MSVM). Firstly,a total of 357 Chinese men w...The purpose of this paper was to develop a reliable body shape analysis approach based on cluster analysis, k. nearestneighbor( KNN), and multi-class support vector machine( MSVM). Firstly,a total of 357 Chinese men were selected to make a dataset. Secondly, the experiences of these data were not accumulated to build general models. Five body angles were extracted as independent variables. Four clusters were the most efficient cluster number for our study. Finally,the accuracy of body classifications is compared between KNN and MSVM. In this study,the body classification framework was studied to transfer the body feature data to intuitive types. Moreover,the adaptive made-tomeasure( MTM) framework based on body classification was studied. The case demonstration and analysis show the effectiveness of the study.展开更多
Aomalous changes in the ST segment, including ST level deviation and ST shape change, are the major parameters in clinical electrocardiogram (ECG) diagnosis of myocardial ischemia. Automatic detection of ST segment mo...Aomalous changes in the ST segment, including ST level deviation and ST shape change, are the major parameters in clinical electrocardiogram (ECG) diagnosis of myocardial ischemia. Automatic detection of ST segment morphology can provide a more accurate evidence for clinical diagnosis of myocardial ischemia. In this paper, we proposed a method for classifying the shape of the ST-segment based on the curvature scale space (CSS) technique. First, we established a reference ST set and preprocessed the ECG signal by using the CSS technique. Then, the corner points in the ST-segment were detected at a high scale of the CSS and tracked through multiple lower scales, in order to improve its localization. Finally, the current beat of ST morphology can be distinguished by the corner points. We applied the developed algorithm to the ECG recordings in European ST-T database and QT database to validate the accuracy of the algorithm. The experimental results showed that the average detection accuracy of our algorithm was 91.60%. We could conclude that the proposed method is able to provide a new way for the automatic detection of myocardial ischemia.展开更多
Nonlinearity impairments and distortions have been bothering the bandwidth constrained passive optical network(PON)system for a long time and limiting the develop-ment of capacity in the PON system.Unlike other works ...Nonlinearity impairments and distortions have been bothering the bandwidth constrained passive optical network(PON)system for a long time and limiting the develop-ment of capacity in the PON system.Unlike other works concentrating on the exploration of the complex equalization algorithm,we investigate the potential of constellation shap-ing joint support vector machine(SVM)classification scheme.At the transmitter side,the 8 quadrature amplitude modulation(8QAM)constellation is shaped into three designs to mitigate the influence of noise and distortions in the PON channel.On the receiver side,simple multi-class linear SVM classifiers are utilized to replace complex equalization methods.Simulation results show that with the bandwidth of 25 GHz and overall bitrate of 50 Gbit/s,at 10 dBm input optical power of a 20 km standard single mode fiber(SSMF),and under a hard-decision forward error correction(FEC)threshold,transmission can be realized by employing Circular(4,4)shaped 8QAM joint SVM classifier at the maximal power budget of 37.5 dB.展开更多
The airborne two-dimensional stereo(2D-S) optical array probe has been operating for more than 10 yr, accumulating a large amount of cloud particle image data. However, due to the lack of reliable and unbiased classif...The airborne two-dimensional stereo(2D-S) optical array probe has been operating for more than 10 yr, accumulating a large amount of cloud particle image data. However, due to the lack of reliable and unbiased classification tools,our ability to extract meaningful morphological information related to cloud microphysical processes is limited. To solve this issue, we propose a novel classification algorithm for 2D-S cloud particle images based on a convolutional neural network(CNN), named CNN-2DS. A 2D-S cloud particle shape dataset was established by using the 2D-S cloud particle images observed from 13 aircraft detection flights in 6 regions of China(Northeast, Northwest, North,East, Central, and South China). This dataset contains 33,300 cloud particle images with 8 types of cloud particle shape(linear, sphere, dendrite, aggregate, graupel, plate, donut, and irregular). The CNN-2DS model was trained and tested based on the established 2D-S dataset. Experimental results show that the CNN-2DS model can accurately identify cloud particles with an average classification accuracy of 97%. Compared with other common classification models [e.g., Vision Transformer(ViT) and Residual Neural Network(ResNet)], the CNN-2DS model is lightweight(few parameters) and fast in calculations, and has the highest classification accuracy. In a word, the proposed CNN-2DS model is effective and reliable for the classification of cloud particles detected by the 2D-S probe.展开更多
It is known that size alone, which is often defined as the volume-equivalent diameter, is not sufficient to characterize many particulate products. The shape of crystalline products can be as important as size in many...It is known that size alone, which is often defined as the volume-equivalent diameter, is not sufficient to characterize many particulate products. The shape of crystalline products can be as important as size in many applications, Traditionally, particulate shape is often defined by several simple descriptors such as the maximum length and the aspect ratio. Although these descriptors are intuitive, they result in a loss of information about the original shape. This paper presents a method to use principal component analysis to derive simple latent shape descriptors from microscope images of particulate products made in batch processes, and the use of these descriptors to identify batch-to-batch variations. Data from batch runs of both a laboratory crystalliser and an industrial crystallisation reactor are analysed using the described approach. Qualitative and quantitative comparisons with the use of traditional shape descriptors that have nhwical meanings and Fourier shape descriptors are also made.展开更多
基金supported by the National Natural Science Foundation of China[grant numbers 42071450 and 42001415].
文摘Pattern recognition is critical to map data handling and their applications.This study presents a model that combines the Shape Context(SC)descriptor and Graph Convolutional Neural Network(GCNN)to classify the patterns of interchanges,which are indispensable parts of urban road networks.In the SC-GCNN model,an interchange is modeled as a graph,wherein nodes and edges represent the interchange segments and their connections,respectively.Then,a novel SC descriptor is implemented to describe the contextual information of each interchange segment and serve as descriptive features of graph nodes.Finally,a GCNN is designed by combining graph convolution and pooling operations to process the constructed graphs and classify the interchange patterns.The SC-GCNN model was validated using interchange samples obtained from the road networks of 15 cities downloaded from OpenStreetMap.The classification accuracy was 87.06%,which was higher than that of the image-based AlexNet,GoogLeNet,and Random Forest models.
文摘To improve the classification method of body type, 103 young female college students in Jiaodong area(Shandong, China) were measured by a 3 D body scanning system, and variables of upper body parts were selected and analyzed by SPSS software. According to the indices such as the chest ratio, the chest sagittal diameter ratio, and the shoulder angle, the tested population was quickly clustered into six categories by the classification method of “size feature+shape index+front and back indices”, which were divided into flat chest body, graceful body, breast augmentation body, normal body, convex back body, and flat body. The proportion of various body types and classification rules were obtained. According to the classification rules, 103 samples and 15 new females’ body data were analyzed and verified. Finally, according to the descriptive statistical analysis of upper body-related indicators of young female in this area, the height and the chest circumference were selected as independent variables, regression analysis was carried out on 11 related indicators, and the mapping relationship between height and chest circumference was studied, which provided a mathematical model for the design of fit clothing structure of young females in Jiaodong area.
基金This paper received financial support towards the cost of its publication from the Deanship of Research and Graduate Studies at Applied Science University, Amman, Jordan.
文摘In this paper, a new shape classification system based on singular value decomposition (SVD) transform using nearest neighbour classifier was proposed. The gray scale image of the shape object was converted into a black and white image. The squared Euclidean distance transform on binary image was applied to extract the boundary image of the shape. SVD transform features were extracted from the the boundary of the object shapes. In this paper, the proposed classification system based on SVD transform feature extraction method was compared with classifier based on moment invariants using nearest neighbour classifier. The experimental results showed the advantage of our proposed classification system.
基金The National Basic Research Program of China(973Program)(No2006CB303105)the Research Foundation of Bei-jing Jiaotong University (NoK06J0170)
文摘For classifying unknown 3-D objects into a set of predetermined object classes, a part-level object classification method based on the improved interpretation tree is presented. The part-level representation is implemented, which enables a more compact shape description of 3-D objects. The proposed classification method consists of two key processing stages： the improved constrained search on an interpretation tree and the following shape similarity measure computation. By the classification method, both whole match and partial match with shape similarity ranks are achieved; especially, focus match can be accomplished, where different key parts may be labeled and all the matched models containing corresponding key parts may be obtained. A series of experiments show the effectiveness of the presented 3-D object classification method.
基金Talent Project of Xiamen University of Technology,China(No.90030617)
文摘The purpose of this paper was to develop a reliable body shape analysis approach based on cluster analysis, k. nearestneighbor( KNN), and multi-class support vector machine( MSVM). Firstly,a total of 357 Chinese men were selected to make a dataset. Secondly, the experiences of these data were not accumulated to build general models. Five body angles were extracted as independent variables. Four clusters were the most efficient cluster number for our study. Finally,the accuracy of body classifications is compared between KNN and MSVM. In this study,the body classification framework was studied to transfer the body feature data to intuitive types. Moreover,the adaptive made-tomeasure( MTM) framework based on body classification was studied. The case demonstration and analysis show the effectiveness of the study.
文摘Aomalous changes in the ST segment, including ST level deviation and ST shape change, are the major parameters in clinical electrocardiogram (ECG) diagnosis of myocardial ischemia. Automatic detection of ST segment morphology can provide a more accurate evidence for clinical diagnosis of myocardial ischemia. In this paper, we proposed a method for classifying the shape of the ST-segment based on the curvature scale space (CSS) technique. First, we established a reference ST set and preprocessed the ECG signal by using the CSS technique. Then, the corner points in the ST-segment were detected at a high scale of the CSS and tracked through multiple lower scales, in order to improve its localization. Finally, the current beat of ST morphology can be distinguished by the corner points. We applied the developed algorithm to the ECG recordings in European ST-T database and QT database to validate the accuracy of the algorithm. The experimental results showed that the average detection accuracy of our algorithm was 91.60%. We could conclude that the proposed method is able to provide a new way for the automatic detection of myocardial ischemia.
文摘Nonlinearity impairments and distortions have been bothering the bandwidth constrained passive optical network(PON)system for a long time and limiting the develop-ment of capacity in the PON system.Unlike other works concentrating on the exploration of the complex equalization algorithm,we investigate the potential of constellation shap-ing joint support vector machine(SVM)classification scheme.At the transmitter side,the 8 quadrature amplitude modulation(8QAM)constellation is shaped into three designs to mitigate the influence of noise and distortions in the PON channel.On the receiver side,simple multi-class linear SVM classifiers are utilized to replace complex equalization methods.Simulation results show that with the bandwidth of 25 GHz and overall bitrate of 50 Gbit/s,at 10 dBm input optical power of a 20 km standard single mode fiber(SSMF),and under a hard-decision forward error correction(FEC)threshold,transmission can be realized by employing Circular(4,4)shaped 8QAM joint SVM classifier at the maximal power budget of 37.5 dB.
基金Supported by the National Key Research and Development Program of China (2019YFC1510301)Key Innovation Team Fund of the China Meteorological Administration (CMA2022ZD10)Basic Research Fund of the Chinese Academy of Meteorological Sciences(2021Y010)。
文摘The airborne two-dimensional stereo(2D-S) optical array probe has been operating for more than 10 yr, accumulating a large amount of cloud particle image data. However, due to the lack of reliable and unbiased classification tools,our ability to extract meaningful morphological information related to cloud microphysical processes is limited. To solve this issue, we propose a novel classification algorithm for 2D-S cloud particle images based on a convolutional neural network(CNN), named CNN-2DS. A 2D-S cloud particle shape dataset was established by using the 2D-S cloud particle images observed from 13 aircraft detection flights in 6 regions of China(Northeast, Northwest, North,East, Central, and South China). This dataset contains 33,300 cloud particle images with 8 types of cloud particle shape(linear, sphere, dendrite, aggregate, graupel, plate, donut, and irregular). The CNN-2DS model was trained and tested based on the established 2D-S dataset. Experimental results show that the CNN-2DS model can accurately identify cloud particles with an average classification accuracy of 97%. Compared with other common classification models [e.g., Vision Transformer(ViT) and Residual Neural Network(ResNet)], the CNN-2DS model is lightweight(few parameters) and fast in calculations, and has the highest classification accuracy. In a word, the proposed CNN-2DS model is effective and reliable for the classification of cloud particles detected by the 2D-S probe.
文摘It is known that size alone, which is often defined as the volume-equivalent diameter, is not sufficient to characterize many particulate products. The shape of crystalline products can be as important as size in many applications, Traditionally, particulate shape is often defined by several simple descriptors such as the maximum length and the aspect ratio. Although these descriptors are intuitive, they result in a loss of information about the original shape. This paper presents a method to use principal component analysis to derive simple latent shape descriptors from microscope images of particulate products made in batch processes, and the use of these descriptors to identify batch-to-batch variations. Data from batch runs of both a laboratory crystalliser and an industrial crystallisation reactor are analysed using the described approach. Qualitative and quantitative comparisons with the use of traditional shape descriptors that have nhwical meanings and Fourier shape descriptors are also made.
