In allusion to the disadvantage of having to obtain the number of clusters of data sets in advance and the sensitivity to selecting initial clustering centers in the k-means algorithm, an improved k-means clustering a...In allusion to the disadvantage of having to obtain the number of clusters of data sets in advance and the sensitivity to selecting initial clustering centers in the k-means algorithm, an improved k-means clustering algorithm is proposed. First, the concept of a silhouette coefficient is introduced, and the optimal clustering number Kopt of a data set with unknown class information is confirmed by calculating the silhouette coefficient of objects in clusters under different K values. Then the distribution of the data set is obtained through hierarchical clustering and the initial clustering-centers are confirmed. Finally, the clustering is completed by the traditional k-means clustering. By the theoretical analysis, it is proved that the improved k-means clustering algorithm has proper computational complexity. The experimental results of IRIS testing data set show that the algorithm can distinguish different clusters reasonably and recognize the outliers efficiently, and the entropy generated by the algorithm is lower.展开更多
In k-means clustering, we are given a set of n data points in d-dimensional space R^d and an integer k and the problem is to determine a set of k points in R^d, called centers, so as to minimize the mean squared dista...In k-means clustering, we are given a set of n data points in d-dimensional space R^d and an integer k and the problem is to determine a set of k points in R^d, called centers, so as to minimize the mean squared distance from each data point to its nearest center. In this paper, we present a simple and efficient clustering algorithm based on the k-means algorithm, which we call enhanced k-means algorithm. This algorithm is easy to implement, requiring a simple data structure to keep some information in each iteration to be used in the next iteration. Our experimental results demonstrated that our scheme can improve the computational speed of the k-means algorithm by the magnitude in the total number of distance calculations and the overall time of computation.展开更多
Fractional vegetation cover(FVC)is an important parameter to measure crop growth.In studies of crop growth monitoring,it is very important to extract FVC quickly and accurately.As the most widely used FVC extraction m...Fractional vegetation cover(FVC)is an important parameter to measure crop growth.In studies of crop growth monitoring,it is very important to extract FVC quickly and accurately.As the most widely used FVC extraction method,the photographic method has the advantages of simple operation and high extraction accuracy.However,when soil moisture and acquisition times vary,the extraction results are less accurate.To accommodate various conditions of FVC extraction,this study proposes a new FVC extraction method that extracts FVC from a normalized difference vegetation index(NDVI)greyscale image of wheat by using a density peak k-means(DPK-means)algorithm.In this study,Yangfumai 4(YF4)planted in pots and Yangmai 16(Y16)planted in the field were used as the research materials.With a hyperspectral imaging camera mounted on a tripod,ground hyperspectral images of winter wheat under different soil conditions(dry and wet)were collected at 1 m above the potted wheat canopy.Unmanned aerial vehicle(UAV)hyperspectral images of winter wheat at various stages were collected at 50 m above the field wheat canopy by a UAV equipped with a hyperspectral camera.The pixel dichotomy method and DPK-means algorithm were used to classify vegetation pixels and non-vegetation pixels in NDVI greyscale images of wheat,and the extraction effects of the two methods were compared and analysed.The results showed that extraction by pixel dichotomy was influenced by the acquisition conditions and its error distribution was relatively scattered,while the extraction effect of the DPK-means algorithm was less affected by the acquisition conditions and its error distribution was concentrated.The absolute values of error were 0.042 and 0.044,the root mean square errors(RMSE)were 0.028 and 0.030,and the fitting accuracy R2 of the FVC was 0.87 and 0.93,under dry and wet soil conditions and under various time conditions,respectively.This study found that the DPK-means algorithm was capable of achieving more accurate results than the pixel dichotomy method in various soil and time conditions and was an accurate and robust method for FVC extraction.展开更多
For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be colle...For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be collected in offline phase. Therefore,collecting training data with positioning information is time consuming which becomes the bottleneck of WLAN indoor localization. In this paper,the traditional semisupervised learning method based on k-NN and ε-NN graph for reducing collection workload of offline phase are analyzed,and the result shows that the k-NN or ε-NN graph are sensitive to data noise,which limit the performance of semi-supervised learning WLAN indoor localization system. Aiming at the above problem,it proposes a l1-graph-algorithm-based semi-supervised learning( LG-SSL) indoor localization method in which the graph is built by l1-norm algorithm. In our system,it firstly labels the unlabeled data using LG-SSL and labeled data to build the Radio Map in offline training phase,and then uses LG-SSL to estimate user's location in online phase. Extensive experimental results show that,benefit from the robustness to noise and sparsity ofl1-graph,LG-SSL exhibits superior performance by effectively reducing the collection workload in offline phase and improving localization accuracy in online phase.展开更多
With the increasing variety of application software of meteorological satellite ground system, how to provide reasonable hardware resources and improve the efficiency of software is paid more and more attention. In th...With the increasing variety of application software of meteorological satellite ground system, how to provide reasonable hardware resources and improve the efficiency of software is paid more and more attention. In this paper, a set of software classification method based on software operating characteristics is proposed. The method uses software run-time resource consumption to describe the software running characteristics. Firstly, principal component analysis (PCA) is used to reduce the dimension of software running feature data and to interpret software characteristic information. Then the modified K-means algorithm was used to classify the meteorological data processing software. Finally, it combined with the results of principal component analysis to explain the significance of various types of integrated software operating characteristics. And it is used as the basis for optimizing the allocation of software hardware resources and improving the efficiency of software operation.展开更多
The K-means method is one of the most widely used clustering methods and has been implemented in many fields of science and technology. One of the major problems of the k-means algorithm is that it may produce empty c...The K-means method is one of the most widely used clustering methods and has been implemented in many fields of science and technology. One of the major problems of the k-means algorithm is that it may produce empty clusters depending on initial center vectors. Genetic Algorithms (GAs) are adaptive heuristic search algorithm based on the evolutionary principles of natural selection and genetics. This paper presents a hybrid version of the k-means algorithm with GAs that efficiently eliminates this empty cluster problem. Results of simulation experiments using several data sets prove our claim.展开更多
Classification systems such as Slope Mass Rating(SMR) are currently being used to undertake slope stability analysis. In SMR classification system, data is allocated to certain classes based on linguistic and experien...Classification systems such as Slope Mass Rating(SMR) are currently being used to undertake slope stability analysis. In SMR classification system, data is allocated to certain classes based on linguistic and experience-based criteria. In order to eliminate linguistic criteria resulted from experience-based judgments and account for uncertainties in determining class boundaries developed by SMR system,the system classification results were corrected using two clustering algorithms, namely K-means and fuzzy c-means(FCM), for the ratings obtained via continuous and discrete functions. By applying clustering algorithms in SMR classification system, no in-advance experience-based judgment was made on the number of extracted classes in this system, and it was only after all steps of the clustering algorithms were accomplished that new classification scheme was proposed for SMR system under different failure modes based on the ratings obtained via continuous and discrete functions. The results of this study showed that, engineers can achieve more reliable and objective evaluations over slope stability by using SMR system based on the ratings calculated via continuous and discrete functions.展开更多
K-means algorithm is one of the most widely used algorithms in the clustering analysis. To deal with the problem caused by the random selection of initial center points in the traditional al- gorithm, this paper propo...K-means algorithm is one of the most widely used algorithms in the clustering analysis. To deal with the problem caused by the random selection of initial center points in the traditional al- gorithm, this paper proposes an improved K-means algorithm based on the similarity matrix. The im- proved algorithm can effectively avoid the random selection of initial center points, therefore it can provide effective initial points for clustering process, and reduce the fluctuation of clustering results which are resulted from initial points selections, thus a better clustering quality can be obtained. The experimental results also show that the F-measure of the improved K-means algorithm has been greatly improved and the clustering results are more stable.展开更多
Several pests feed on leaves,stems,bases,and the entire plant,causing plant illnesses.As a result,it is vital to identify and eliminate the disease before causing any damage to plants.Manually detecting plant disease ...Several pests feed on leaves,stems,bases,and the entire plant,causing plant illnesses.As a result,it is vital to identify and eliminate the disease before causing any damage to plants.Manually detecting plant disease and treating it is pretty challenging in this period.Image processing is employed to detect plant disease since it requires much effort and an extended processing period.The main goal of this study is to discover the disease that affects the plants by creating an image processing system that can recognize and classify four different forms of plant diseases,including Phytophthora infestans,Fusarium graminearum,Puccinia graminis,tomato yellow leaf curl.Therefore,this work uses the Support vector machine(SVM)classifier to detect and classify the plant disease using various steps like image acquisition,Pre-processing,Segmentation,feature extraction,and classification.The gray level co-occurrence matrix(GLCM)and the local binary pattern features(LBP)are used to identify the disease-affected portion of the plant leaf.According to experimental data,the proposed technology can correctly detect and diagnose plant sickness with a 97.2 percent accuracy.展开更多
A high-precision nominal flight profile,involving controllers′intentions is critical for 4Dtrajectory estimation in modern automatic air traffic control systems.We proposed a novel method to effectively improve the a...A high-precision nominal flight profile,involving controllers′intentions is critical for 4Dtrajectory estimation in modern automatic air traffic control systems.We proposed a novel method to effectively improve the accuracy of the nominal flight profile,including the nominal altitude profile and the speed profile.First,considering the characteristics of trajectory data,we developed an improved K-means algorithm.The approach was to measure the similarity between different altitude profiles by integrating the space warp edit distance algorithm,thereby to acquire several fitted nominal flight altitude profiles.This approach breaks the constraints of traditional K-means algorithms.Second,to eliminate the influence of meteorological factors,we introduced historical gridded binary data to determine the en-route wind speed and temperature via inverse distance weighted interpolation.Finally,we facilitated the true airspeed determined by speed triangle relationships and the calibrated airspeed determined by aircraft data model to extract a more accurate nominal speed profile from each cluster,therefore we could describe the airspeed profiles above and below the airspeed transition altitude,respectively.Our experimental results showed that the proposed method could obtain a highly accurate nominal flight profile,which reflects the actual aircraft flight status.展开更多
Generative Adversarial Networks(GANs)are neural networks that allow models to learn deep representations without requiring a large amount of training data.Semi-Supervised GAN Classifiers are a recent innovation in GAN...Generative Adversarial Networks(GANs)are neural networks that allow models to learn deep representations without requiring a large amount of training data.Semi-Supervised GAN Classifiers are a recent innovation in GANs,where GANs are used to classify generated images into real and fake and multiple classes,similar to a general multi-class classifier.However,GANs have a sophisticated design that can be challenging to train.This is because obtaining the proper set of parameters for all models-generator,discriminator,and classifier is complex.As a result,training a single GAN model for different datasets may not produce satisfactory results.Therefore,this study proposes an SGAN model(Semi-Supervised GAN Classifier).First,a baseline model was constructed.The model was then enhanced by leveraging the Sine-Cosine Algorithm and Synthetic Minority Oversampling Technique(SMOTE).SMOTE was used to address class imbalances in the dataset,while Sine Cosine Algorithm(SCA)was used to optimize the weights of the classifier models.The optimal set of hyperparameters(learning rate and batch size)were obtained using grid manual search.Four well-known benchmark datasets and a set of evaluation measures were used to validate the proposed model.The proposed method was then compared against existing models,and the results on each dataset were recorded and demonstrated the effectiveness of the proposed model.The proposed model successfully showed improved test accuracy scores of 1%,2%,15%,and 5%on benchmarking multimedia datasets;Modified National Institute of Standards and Technology(MNIST)digits,Fashion MNIST,Pneumonia Chest X-ray,and Facial Emotion Detection Dataset,respectively.展开更多
The dimensionality of data is increasing very rapidly,which creates challenges for most of the current mining and learning algorithms,such as large memory requirements and high computational costs.The literature inclu...The dimensionality of data is increasing very rapidly,which creates challenges for most of the current mining and learning algorithms,such as large memory requirements and high computational costs.The literature includes much research on feature selection for supervised learning.However,feature selection for unsupervised learning has only recently been studied.Finding the subset of features in unsupervised learning that enhances the performance is challenging since the clusters are indeterminate.This work proposes a hybrid technique for unsupervised feature selection called GAk-MEANS,which combines the genetic algorithm(GA)approach with the classical k-Means algorithm.In the proposed algorithm,a new fitness func-tion is designed in addition to new smart crossover and mutation operators.The effectiveness of this algorithm is demonstrated on various datasets.Fur-thermore,the performance of GAk-MEANS has been compared with other genetic algorithms,such as the genetic algorithm using the Sammon Error Function and the genetic algorithm using the Sum of Squared Error Function.Additionally,the performance of GAk-MEANS is compared with the state-of-the-art statistical unsupervised feature selection techniques.Experimental results show that GAk-MEANS consistently selects subsets of features that result in better classification accuracy compared to others.In particular,GAk-MEANS is able to significantly reduce the size of the subset of selected features by an average of 86.35%(72%–96.14%),which leads to an increase of the accuracy by an average of 3.78%(1.05%–6.32%)compared to using all features.When compared with the genetic algorithm using the Sammon Error Function,GAk-MEANS is able to reduce the size of the subset of selected features by 41.29%on average,improve the accuracy by 5.37%,and reduce the time by 70.71%.When compared with the genetic algorithm using the Sum of Squared Error Function,GAk-MEANS on average is able to reduce the size of the subset of selected features by 15.91%,and improve the accuracy by 9.81%,but the time is increased by a factor of 3.When compared with the machine-learning based methods,we observed that GAk-MEANS is able to increase the accuracy by 13.67%on average with an 88.76%average increase in time.展开更多
The K-means algorithm is widely known for its simplicity and fastness in text clustering.However,the selection of the initial clus?tering center with the traditional K-means algorithm is some random,and therefore,the ...The K-means algorithm is widely known for its simplicity and fastness in text clustering.However,the selection of the initial clus?tering center with the traditional K-means algorithm is some random,and therefore,the fluctuations and instability of the clustering results are strongly affected by the initial clustering center.This paper proposed an algorithm to select the initial clustering center to eliminate the uncertainty of central point selection.The experiment results show that the improved K-means clustering algorithm is superior to the traditional algorithm.展开更多
Cluster analysis is one of the major data analysis methods widely used for many practical applications in emerging areas of data mining. A good clustering method will produce high quality clusters with high intra-clus...Cluster analysis is one of the major data analysis methods widely used for many practical applications in emerging areas of data mining. A good clustering method will produce high quality clusters with high intra-cluster similarity and low inter-cluster similarity. Clustering techniques are applied in different domains to predict future trends of available data and its uses for the real world. This research work is carried out to find the performance of two of the most delegated, partition based clustering algorithms namely k-Means and k-Medoids. A state of art analysis of these two algorithms is implemented and performance is analyzed based on their clustering result quality by means of its execution time and other components. Telecommunication data is the source data for this analysis. The connection oriented broadband data is given as input to find the clustering quality of the algorithms. Distance between the server locations and their connection is considered for clustering. Execution time for each algorithm is analyzed and the results are compared with one another. Results found in comparison study are satisfactory for the chosen application.展开更多
These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to over...These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to overcome these disadvantages of remote sensing image classification in this paper. The SSKFCM algorithm is achieved by introducing a kernel method and semi-supervised learning technique into the standard fuzzy C-means （FCM） algorithm. A set of Beijing-1 micro-satellite＇s multispectral images are adopted to be classified by several algorithms, such as FCM, kernel FCM （KFCM）, semi-supervised FCM （SSFCM） and SSKFCM. The classification results are estimated by corresponding indexes. The results indicate that the SSKFCM algorithm significantly improves the classification accuracy of remote sensing images compared with the others.展开更多
In wireless sensor network cluster architecture is useful because of its inherent suitability for data fusion. In this paper we represent a new approach called Multiple Parameter based Clustering (MPC) embedded with t...In wireless sensor network cluster architecture is useful because of its inherent suitability for data fusion. In this paper we represent a new approach called Multiple Parameter based Clustering (MPC) embedded with the traditional k-means algorithm which takes different parameters (Node energy level, Euclidian distance from the base station, RSSI, Latency of data to reach base station) into consideration to form clusters. Then the effectiveness of the clusters is evaluated based on the uniformity of the node distribution, Node range per cluster, Intra and Inter cluster distance and required energy level of each centroid. Our result shows that by varying multiple parameters we can create clusters with more uniformly distributed nodes, minimize intra and maximize inter cluster distance and elect less power consuming centroid.展开更多
Label propagation is an essential semi-supervised learning method based on graphs,which has a broad spectrum of applications in pattern recognition and data mining.This paper proposes a quantum semi-supervised classif...Label propagation is an essential semi-supervised learning method based on graphs,which has a broad spectrum of applications in pattern recognition and data mining.This paper proposes a quantum semi-supervised classifier based on label propagation.Considering the difficulty of graph construction,we develop a variational quantum label propagation(VQLP)method.In this method,a locally parameterized quantum circuit is created to reduce the parameters required in the optimization.Furthermore,we design a quantum semi-supervised binary classifier based on hybrid Bell and Z bases measurement,which has a shallower circuit depth and is more suitable for implementation on near-term quantum devices.We demonstrate the performance of the quantum semi-supervised classifier on the Iris data set,and the simulation results show that the quantum semi-supervised classifier has higher classification accuracy than the swap test classifier.This work opens a new path to quantum machine learning based on graphs.展开更多
Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification...Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.展开更多
With the increasing number of airports and the expansion of their scale,the aviation network has become complex and hierarchical.In order to investigate the complex network characteristics of aviation networks,this pa...With the increasing number of airports and the expansion of their scale,the aviation network has become complex and hierarchical.In order to investigate the complex network characteristics of aviation networks,this paper constructs a Chinese aviation network model and carries out related research based on complex network theory and K-means algorithm.Initially,the P-space model is employed to construct the Chinese aviation network model.Then,complex network indicators such as degree,clustering coefficient,average path length,betweenness and coreness are selected to investigate the complex characteristics and hierarchical features of aviation networks and explore their causes.Secondly,using K-means clustering algorithm,five values are obtained as the initial clustering parameter K values for each of the aviation network hierarchies classified according to five complex network indicators.Meanwhile,clustering simulation experiments are conducted to obtain the visual clustering results of Chinese aviation network nodes under different K values,as well as silhouette coefficients for evaluating the clustering effect of each indicator in order to obtain the hierarchical classification of aviation networks under different indicators.Finally,the silhouette coefficient is optimal when the K value is 4.Thus,the clustering results of the four layers of the aviation network can be obtained.According to the experimental results,the complex network association discovery method combined with K-means algorithm has better applicability and simplicity,while the accuracy is improved.展开更多
With a sharp increase in the information volume,analyzing and retrieving this vast data volume is much more essential than ever.One of the main techniques that would be beneficial in this regard is called the Clusteri...With a sharp increase in the information volume,analyzing and retrieving this vast data volume is much more essential than ever.One of the main techniques that would be beneficial in this regard is called the Clustering method.Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible.One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm.The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters.Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time.Besides,the selection of appropriate initial seeds can reduce the cluster’s inconsistency.In this paper,we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm.For this purpose,a new method is proposed considering the average distance between objects to determine the initial seeds.Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm.The experimental results showed that our proposed approach outperforms the Chithra with 1.7%and 2.1%in terms of clustering accuracy for Wine and Abalone detection data,respectively.Furthermore,achieved results indicate that comparing with the Reverse Nearest Neighbor(RNN)search approach,the proposed method has a higher convergence speed.展开更多
基金The National Natural Science Foundation of China(No50674086)Specialized Research Fund for the Doctoral Program of Higher Education (No20060290508)the Youth Scientific Research Foundation of China University of Mining and Technology (No2006A047)
文摘In allusion to the disadvantage of having to obtain the number of clusters of data sets in advance and the sensitivity to selecting initial clustering centers in the k-means algorithm, an improved k-means clustering algorithm is proposed. First, the concept of a silhouette coefficient is introduced, and the optimal clustering number Kopt of a data set with unknown class information is confirmed by calculating the silhouette coefficient of objects in clusters under different K values. Then the distribution of the data set is obtained through hierarchical clustering and the initial clustering-centers are confirmed. Finally, the clustering is completed by the traditional k-means clustering. By the theoretical analysis, it is proved that the improved k-means clustering algorithm has proper computational complexity. The experimental results of IRIS testing data set show that the algorithm can distinguish different clusters reasonably and recognize the outliers efficiently, and the entropy generated by the algorithm is lower.
文摘In k-means clustering, we are given a set of n data points in d-dimensional space R^d and an integer k and the problem is to determine a set of k points in R^d, called centers, so as to minimize the mean squared distance from each data point to its nearest center. In this paper, we present a simple and efficient clustering algorithm based on the k-means algorithm, which we call enhanced k-means algorithm. This algorithm is easy to implement, requiring a simple data structure to keep some information in each iteration to be used in the next iteration. Our experimental results demonstrated that our scheme can improve the computational speed of the k-means algorithm by the magnitude in the total number of distance calculations and the overall time of computation.
基金supported by the Beijing Natural Science Foundation,China(4202066)the Central Public-interest Scientific Institution Basal Research Fund,China(JBYWAII-2020-29 and JBYW-AII-2020-31)+1 种基金the Key Research and Development Program of Hebei Province,China(19227407D)the Technology Innovation Project Fund of Chinese Academy of Agricultural Sciences(CAAS-ASTIP2020-All)。
文摘Fractional vegetation cover(FVC)is an important parameter to measure crop growth.In studies of crop growth monitoring,it is very important to extract FVC quickly and accurately.As the most widely used FVC extraction method,the photographic method has the advantages of simple operation and high extraction accuracy.However,when soil moisture and acquisition times vary,the extraction results are less accurate.To accommodate various conditions of FVC extraction,this study proposes a new FVC extraction method that extracts FVC from a normalized difference vegetation index(NDVI)greyscale image of wheat by using a density peak k-means(DPK-means)algorithm.In this study,Yangfumai 4(YF4)planted in pots and Yangmai 16(Y16)planted in the field were used as the research materials.With a hyperspectral imaging camera mounted on a tripod,ground hyperspectral images of winter wheat under different soil conditions(dry and wet)were collected at 1 m above the potted wheat canopy.Unmanned aerial vehicle(UAV)hyperspectral images of winter wheat at various stages were collected at 50 m above the field wheat canopy by a UAV equipped with a hyperspectral camera.The pixel dichotomy method and DPK-means algorithm were used to classify vegetation pixels and non-vegetation pixels in NDVI greyscale images of wheat,and the extraction effects of the two methods were compared and analysed.The results showed that extraction by pixel dichotomy was influenced by the acquisition conditions and its error distribution was relatively scattered,while the extraction effect of the DPK-means algorithm was less affected by the acquisition conditions and its error distribution was concentrated.The absolute values of error were 0.042 and 0.044,the root mean square errors(RMSE)were 0.028 and 0.030,and the fitting accuracy R2 of the FVC was 0.87 and 0.93,under dry and wet soil conditions and under various time conditions,respectively.This study found that the DPK-means algorithm was capable of achieving more accurate results than the pixel dichotomy method in various soil and time conditions and was an accurate and robust method for FVC extraction.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61101122)the National High Technology Research and Development Program of China(Grant No.2012AA120802)the National Science and Technology Major Project of the Ministry of Science and Technology of China(Grant No.2012ZX03004-003)
文摘For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be collected in offline phase. Therefore,collecting training data with positioning information is time consuming which becomes the bottleneck of WLAN indoor localization. In this paper,the traditional semisupervised learning method based on k-NN and ε-NN graph for reducing collection workload of offline phase are analyzed,and the result shows that the k-NN or ε-NN graph are sensitive to data noise,which limit the performance of semi-supervised learning WLAN indoor localization system. Aiming at the above problem,it proposes a l1-graph-algorithm-based semi-supervised learning( LG-SSL) indoor localization method in which the graph is built by l1-norm algorithm. In our system,it firstly labels the unlabeled data using LG-SSL and labeled data to build the Radio Map in offline training phase,and then uses LG-SSL to estimate user's location in online phase. Extensive experimental results show that,benefit from the robustness to noise and sparsity ofl1-graph,LG-SSL exhibits superior performance by effectively reducing the collection workload in offline phase and improving localization accuracy in online phase.
文摘With the increasing variety of application software of meteorological satellite ground system, how to provide reasonable hardware resources and improve the efficiency of software is paid more and more attention. In this paper, a set of software classification method based on software operating characteristics is proposed. The method uses software run-time resource consumption to describe the software running characteristics. Firstly, principal component analysis (PCA) is used to reduce the dimension of software running feature data and to interpret software characteristic information. Then the modified K-means algorithm was used to classify the meteorological data processing software. Finally, it combined with the results of principal component analysis to explain the significance of various types of integrated software operating characteristics. And it is used as the basis for optimizing the allocation of software hardware resources and improving the efficiency of software operation.
文摘The K-means method is one of the most widely used clustering methods and has been implemented in many fields of science and technology. One of the major problems of the k-means algorithm is that it may produce empty clusters depending on initial center vectors. Genetic Algorithms (GAs) are adaptive heuristic search algorithm based on the evolutionary principles of natural selection and genetics. This paper presents a hybrid version of the k-means algorithm with GAs that efficiently eliminates this empty cluster problem. Results of simulation experiments using several data sets prove our claim.
文摘Classification systems such as Slope Mass Rating(SMR) are currently being used to undertake slope stability analysis. In SMR classification system, data is allocated to certain classes based on linguistic and experience-based criteria. In order to eliminate linguistic criteria resulted from experience-based judgments and account for uncertainties in determining class boundaries developed by SMR system,the system classification results were corrected using two clustering algorithms, namely K-means and fuzzy c-means(FCM), for the ratings obtained via continuous and discrete functions. By applying clustering algorithms in SMR classification system, no in-advance experience-based judgment was made on the number of extracted classes in this system, and it was only after all steps of the clustering algorithms were accomplished that new classification scheme was proposed for SMR system under different failure modes based on the ratings obtained via continuous and discrete functions. The results of this study showed that, engineers can achieve more reliable and objective evaluations over slope stability by using SMR system based on the ratings calculated via continuous and discrete functions.
文摘K-means algorithm is one of the most widely used algorithms in the clustering analysis. To deal with the problem caused by the random selection of initial center points in the traditional al- gorithm, this paper proposes an improved K-means algorithm based on the similarity matrix. The im- proved algorithm can effectively avoid the random selection of initial center points, therefore it can provide effective initial points for clustering process, and reduce the fluctuation of clustering results which are resulted from initial points selections, thus a better clustering quality can be obtained. The experimental results also show that the F-measure of the improved K-means algorithm has been greatly improved and the clustering results are more stable.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2023R104)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Several pests feed on leaves,stems,bases,and the entire plant,causing plant illnesses.As a result,it is vital to identify and eliminate the disease before causing any damage to plants.Manually detecting plant disease and treating it is pretty challenging in this period.Image processing is employed to detect plant disease since it requires much effort and an extended processing period.The main goal of this study is to discover the disease that affects the plants by creating an image processing system that can recognize and classify four different forms of plant diseases,including Phytophthora infestans,Fusarium graminearum,Puccinia graminis,tomato yellow leaf curl.Therefore,this work uses the Support vector machine(SVM)classifier to detect and classify the plant disease using various steps like image acquisition,Pre-processing,Segmentation,feature extraction,and classification.The gray level co-occurrence matrix(GLCM)and the local binary pattern features(LBP)are used to identify the disease-affected portion of the plant leaf.According to experimental data,the proposed technology can correctly detect and diagnose plant sickness with a 97.2 percent accuracy.
基金supported by the National Natural Science Foundation of China(Nos.61174180,U1433125)the Jiangsu Province Science Foundation (No.BK20141413)the Chinese Postdoctoral Science Foundation (No.2014M550291)
文摘A high-precision nominal flight profile,involving controllers′intentions is critical for 4Dtrajectory estimation in modern automatic air traffic control systems.We proposed a novel method to effectively improve the accuracy of the nominal flight profile,including the nominal altitude profile and the speed profile.First,considering the characteristics of trajectory data,we developed an improved K-means algorithm.The approach was to measure the similarity between different altitude profiles by integrating the space warp edit distance algorithm,thereby to acquire several fitted nominal flight altitude profiles.This approach breaks the constraints of traditional K-means algorithms.Second,to eliminate the influence of meteorological factors,we introduced historical gridded binary data to determine the en-route wind speed and temperature via inverse distance weighted interpolation.Finally,we facilitated the true airspeed determined by speed triangle relationships and the calibrated airspeed determined by aircraft data model to extract a more accurate nominal speed profile from each cluster,therefore we could describe the airspeed profiles above and below the airspeed transition altitude,respectively.Our experimental results showed that the proposed method could obtain a highly accurate nominal flight profile,which reflects the actual aircraft flight status.
基金This research was supported by Universiti Teknologi PETRONAS,under the Yayasan Universiti Teknologi PETRONAS(YUTP)Fundamental Research Grant Scheme(YUTPFRG/015LC0-308).
文摘Generative Adversarial Networks(GANs)are neural networks that allow models to learn deep representations without requiring a large amount of training data.Semi-Supervised GAN Classifiers are a recent innovation in GANs,where GANs are used to classify generated images into real and fake and multiple classes,similar to a general multi-class classifier.However,GANs have a sophisticated design that can be challenging to train.This is because obtaining the proper set of parameters for all models-generator,discriminator,and classifier is complex.As a result,training a single GAN model for different datasets may not produce satisfactory results.Therefore,this study proposes an SGAN model(Semi-Supervised GAN Classifier).First,a baseline model was constructed.The model was then enhanced by leveraging the Sine-Cosine Algorithm and Synthetic Minority Oversampling Technique(SMOTE).SMOTE was used to address class imbalances in the dataset,while Sine Cosine Algorithm(SCA)was used to optimize the weights of the classifier models.The optimal set of hyperparameters(learning rate and batch size)were obtained using grid manual search.Four well-known benchmark datasets and a set of evaluation measures were used to validate the proposed model.The proposed method was then compared against existing models,and the results on each dataset were recorded and demonstrated the effectiveness of the proposed model.The proposed model successfully showed improved test accuracy scores of 1%,2%,15%,and 5%on benchmarking multimedia datasets;Modified National Institute of Standards and Technology(MNIST)digits,Fashion MNIST,Pneumonia Chest X-ray,and Facial Emotion Detection Dataset,respectively.
文摘The dimensionality of data is increasing very rapidly,which creates challenges for most of the current mining and learning algorithms,such as large memory requirements and high computational costs.The literature includes much research on feature selection for supervised learning.However,feature selection for unsupervised learning has only recently been studied.Finding the subset of features in unsupervised learning that enhances the performance is challenging since the clusters are indeterminate.This work proposes a hybrid technique for unsupervised feature selection called GAk-MEANS,which combines the genetic algorithm(GA)approach with the classical k-Means algorithm.In the proposed algorithm,a new fitness func-tion is designed in addition to new smart crossover and mutation operators.The effectiveness of this algorithm is demonstrated on various datasets.Fur-thermore,the performance of GAk-MEANS has been compared with other genetic algorithms,such as the genetic algorithm using the Sammon Error Function and the genetic algorithm using the Sum of Squared Error Function.Additionally,the performance of GAk-MEANS is compared with the state-of-the-art statistical unsupervised feature selection techniques.Experimental results show that GAk-MEANS consistently selects subsets of features that result in better classification accuracy compared to others.In particular,GAk-MEANS is able to significantly reduce the size of the subset of selected features by an average of 86.35%(72%–96.14%),which leads to an increase of the accuracy by an average of 3.78%(1.05%–6.32%)compared to using all features.When compared with the genetic algorithm using the Sammon Error Function,GAk-MEANS is able to reduce the size of the subset of selected features by 41.29%on average,improve the accuracy by 5.37%,and reduce the time by 70.71%.When compared with the genetic algorithm using the Sum of Squared Error Function,GAk-MEANS on average is able to reduce the size of the subset of selected features by 15.91%,and improve the accuracy by 9.81%,but the time is increased by a factor of 3.When compared with the machine-learning based methods,we observed that GAk-MEANS is able to increase the accuracy by 13.67%on average with an 88.76%average increase in time.
文摘The K-means algorithm is widely known for its simplicity and fastness in text clustering.However,the selection of the initial clus?tering center with the traditional K-means algorithm is some random,and therefore,the fluctuations and instability of the clustering results are strongly affected by the initial clustering center.This paper proposed an algorithm to select the initial clustering center to eliminate the uncertainty of central point selection.The experiment results show that the improved K-means clustering algorithm is superior to the traditional algorithm.
文摘Cluster analysis is one of the major data analysis methods widely used for many practical applications in emerging areas of data mining. A good clustering method will produce high quality clusters with high intra-cluster similarity and low inter-cluster similarity. Clustering techniques are applied in different domains to predict future trends of available data and its uses for the real world. This research work is carried out to find the performance of two of the most delegated, partition based clustering algorithms namely k-Means and k-Medoids. A state of art analysis of these two algorithms is implemented and performance is analyzed based on their clustering result quality by means of its execution time and other components. Telecommunication data is the source data for this analysis. The connection oriented broadband data is given as input to find the clustering quality of the algorithms. Distance between the server locations and their connection is considered for clustering. Execution time for each algorithm is analyzed and the results are compared with one another. Results found in comparison study are satisfactory for the chosen application.
基金Supported by the National High Technology Research and Development Programme （No.2007AA12Z227） and the National Natural Science Foundation of China （No.40701146）.
文摘These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to overcome these disadvantages of remote sensing image classification in this paper. The SSKFCM algorithm is achieved by introducing a kernel method and semi-supervised learning technique into the standard fuzzy C-means （FCM） algorithm. A set of Beijing-1 micro-satellite＇s multispectral images are adopted to be classified by several algorithms, such as FCM, kernel FCM （KFCM）, semi-supervised FCM （SSFCM） and SSKFCM. The classification results are estimated by corresponding indexes. The results indicate that the SSKFCM algorithm significantly improves the classification accuracy of remote sensing images compared with the others.
文摘In wireless sensor network cluster architecture is useful because of its inherent suitability for data fusion. In this paper we represent a new approach called Multiple Parameter based Clustering (MPC) embedded with the traditional k-means algorithm which takes different parameters (Node energy level, Euclidian distance from the base station, RSSI, Latency of data to reach base station) into consideration to form clusters. Then the effectiveness of the clusters is evaluated based on the uniformity of the node distribution, Node range per cluster, Intra and Inter cluster distance and required energy level of each centroid. Our result shows that by varying multiple parameters we can create clusters with more uniformly distributed nodes, minimize intra and maximize inter cluster distance and elect less power consuming centroid.
基金Project supported by the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202108)the National Natural Science Foundation of China(Grant No.U162271070)Scientific Research Fund of Zaozhuang University(Grant No.102061901).
文摘Label propagation is an essential semi-supervised learning method based on graphs,which has a broad spectrum of applications in pattern recognition and data mining.This paper proposes a quantum semi-supervised classifier based on label propagation.Considering the difficulty of graph construction,we develop a variational quantum label propagation(VQLP)method.In this method,a locally parameterized quantum circuit is created to reduce the parameters required in the optimization.Furthermore,we design a quantum semi-supervised binary classifier based on hybrid Bell and Z bases measurement,which has a shallower circuit depth and is more suitable for implementation on near-term quantum devices.We demonstrate the performance of the quantum semi-supervised classifier on the Iris data set,and the simulation results show that the quantum semi-supervised classifier has higher classification accuracy than the swap test classifier.This work opens a new path to quantum machine learning based on graphs.
文摘Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
文摘With the increasing number of airports and the expansion of their scale,the aviation network has become complex and hierarchical.In order to investigate the complex network characteristics of aviation networks,this paper constructs a Chinese aviation network model and carries out related research based on complex network theory and K-means algorithm.Initially,the P-space model is employed to construct the Chinese aviation network model.Then,complex network indicators such as degree,clustering coefficient,average path length,betweenness and coreness are selected to investigate the complex characteristics and hierarchical features of aviation networks and explore their causes.Secondly,using K-means clustering algorithm,five values are obtained as the initial clustering parameter K values for each of the aviation network hierarchies classified according to five complex network indicators.Meanwhile,clustering simulation experiments are conducted to obtain the visual clustering results of Chinese aviation network nodes under different K values,as well as silhouette coefficients for evaluating the clustering effect of each indicator in order to obtain the hierarchical classification of aviation networks under different indicators.Finally,the silhouette coefficient is optimal when the K value is 4.Thus,the clustering results of the four layers of the aviation network can be obtained.According to the experimental results,the complex network association discovery method combined with K-means algorithm has better applicability and simplicity,while the accuracy is improved.
文摘With a sharp increase in the information volume,analyzing and retrieving this vast data volume is much more essential than ever.One of the main techniques that would be beneficial in this regard is called the Clustering method.Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible.One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm.The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters.Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time.Besides,the selection of appropriate initial seeds can reduce the cluster’s inconsistency.In this paper,we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm.For this purpose,a new method is proposed considering the average distance between objects to determine the initial seeds.Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm.The experimental results showed that our proposed approach outperforms the Chithra with 1.7%and 2.1%in terms of clustering accuracy for Wine and Abalone detection data,respectively.Furthermore,achieved results indicate that comparing with the Reverse Nearest Neighbor(RNN)search approach,the proposed method has a higher convergence speed.
