Multi-class Classification Scheme Research Articles

Multi-site structural damage identification using a multi-label classification scheme of machine learning

This study proposes a new method to locate multi-site structural damage using a data-driven multi-label classification (MLC) method. Differing from the multiclass classification (MCC) scheme that sets each damage case as a category, the MLC method denotes each damage case with multiple labels, with each label indicating the occurrence of damage at a certain location. The MLC method considers the physical correlation between damage cases sharing damage locations which is neglected in the MCC method. This paper uses the instance differentiation algorithm to implement MLC. Damage identification results using numerical and experimental data indicate that the MLC can identify multi-site damage with good accuracy, even for damage cases that are not covered by the training dataset. Through comparison, it is demonstrated that the MLC method outperforms the MCC and binary classification methods for multi-site damage identification. Moreover, MLC preserves generality when tested on unobserved multi-site damage cases.

Comparing Multiclass, Binary, and Hierarchical Machine Learning Classification schemes for variable stars

ABSTRACTUpcoming synoptic surveys are set to generate an unprecedented amount of data. This requires an automatic framework that can quickly and efficiently provide classification labels for several new object classification challenges. Using data describing 11 types of variable stars from the Catalina Real-Time Transient Survey (CRTS), we illustrate how to capture the most important information from computed features and describe detailed methods of how to robustly use information theory for feature selection and evaluation. We apply three machine learning algorithms and demonstrate how to optimize these classifiers via cross-validation techniques. For the CRTS data set, we find that the random forest classifier performs best in terms of balanced accuracy and geometric means. We demonstrate substantially improved classification results by converting the multiclass problem into a binary classification task, achieving a balanced-accuracy rate of ∼99 per cent for the classification of δ Scuti and anomalous Cepheids. Additionally, we describe how classification performance can be improved via converting a ‘flat multiclass’ problem into a hierarchical taxonomy. We develop a new hierarchical structure and propose a new set of classification features, enabling the accurate identification of subtypes of Cepheids, RR Lyrae, and eclipsing binary stars in CRTS data.

A Bio-inspired Algorithm based Multi-class Classification Scheme for Microarray Gene Data.

Microarray gene data is widely known for its high dimensionality and volume. The utilization of microarray gene data is increasing now-a-days, owing to the advancement of medical science. Microarray gene data helps in diagnosing diseases quite accurately. However, processing microarray gene data is difficult and is usually not understandable. Taking this challenge into account, this work presents a user-friendly rule based classification model, which is easily understandable and does not demand users to have prior knowledge. The classification rules are formed with the help of cuckoo search optimization algorithm and the rules are pruned by the associative rule mining. Finally, the classification is performed with the help of the pruned rules. The performance of the proposed approach is satisfactory in terms of accuracy, sensitivity, specificity and time consumption.

Time integration and reject options for probabilistic output of pairwise LVQ

Learning vector quantization (LVQ) constitutes a very popular machine learning technology with applications, for example, in biomedical data analysis, predictive maintenance/quality as well as product individualization. Albeit probabilistic LVQ variants exist, its deterministic counterparts are often preferred due to their better efficiency. The latter do not allow an immediate probabilistic interpretation of its output; hence, a rejection of classification based on confidence values is not possible. In this contribution, we investigate different schemes how to extend and integrate pairwise LVQ schemes to an overall probabilistic output, in comparison with a recent heuristic surrogate measure for the security of the classification, which is directly based on LVQ’s multi-class classification scheme. Furthermore, we propose a canonic way how to fuse these values over a given time window in case a possibly disrupted measurement is taken over a longer time interval to counter the uncertainty of a single point in time. Experimental results indicate that an explicit probabilistic treatment often yields superior results as compared to a standard deterministic LVQ method, but metric learning is able to annul this difference. Fusion over a short time period is beneficial in case of an unclear classification.

New Insights into Multiclass Damage Classification of Tsunami-Induced Building Damage from SAR Images

The fine resolution of synthetic aperture radar (SAR) images enables the rapid detection of severely damaged areas in the case of natural disasters. Developing an optimal model for detecting damage in multitemporal SAR intensity images has been a focus of research. Recent studies have shown that computing changes over a moving window that clusters neighboring pixels is effective in identifying damaged buildings. Unfortunately, classifying tsunami-induced building damage into detailed damage classes remains a challenge. The purpose of this paper is to present a novel multiclass classification model that considers a high-dimensional feature space derived from several sizes of pixel windows and to provide guidance on how to define a multiclass classification scheme for detecting tsunami-induced damage. The proposed model uses a support vector machine (SVM) to determine the parameters of the discriminant function. The generalization ability of the model was tested on the field survey of the 2011 Great East Japan Earthquake and Tsunami and on a pair of TerraSAR-X images. The results show that the combination of different sizes of pixel windows has better performance for multiclass classification using SAR images. In addition, we discuss the limitations and potential use of multiclass building damage classification based on performance and various classification schemes. Notably, our findings suggest that the detectable classes for tsunami damage appear to differ from the detectable classes for earthquake damage. For earthquake damage, it is well known that a lower damage grade can rarely be distinguished in SAR images. However, such a damage grade is apparently easy to identify from tsunami-induced damage grades in SAR images. Taking this characteristic into consideration, we have successfully defined a detectable three-class classification scheme.

Assessment of Radiometric Resolution Impact on Remote Sensing Data Classification Accuracy

Improved sensor characteristics are generally assumed to increase the potential accuracy of image classification and information extraction from remote sensing imagery. However, the increase in data volume caused by these improvements raise challenges associated with the selection, storage, and processing of this data, and with the cost-effective and timely analysis of the remote sensing datasets. Previous research has extensively assessed the relevance and impact of spatial, spectral and temporal resolution of satellite data on classification accuracy, but little attention has been given to the impact of radiometric resolution. This study focuses on the role of radiometric resolution on classification accuracy of remote sensing data through different classification experiments over three different sites. The experiments were carried out using fine and low scale radiometric resolution images classified through a bagging classification tree. The classification experiments addressed different aspects of the classification road map, including among others, binary and multiclass classification schemes, spectrally and spatially enhanced images, as well as pixel and objects as units of the classification. In addition, the impact of image radiometric resolution on computational time and the information content in fine- and low-resolution images was also explored. While in certain cases, higher radiometric resolution has led to up to 8% higher classification accuracies compared to lower resolution radiometric data, other results indicate that higher radiometric resolution does not necessarily imply improved classification accuracy. Also, classification accuracy of spectral indices and texture bands is not related so much to the radiometric resolution of the original remote sensing images but rather to their own radiometric resolution. Overall, the results of this study suggest that data selection and classification need not always adhere to the highest possible radiometric resolution.

Poincaré's section analysis for PPG-based automatic emotion recognition

Given the importance and abundant use of emotional recognition in the human–computer interfaces and multimedia applications, several methods for designing such systems have been reported in the literature. However, the performance of the photoplethysmography (PPG) signal in these devices has not been sufficiently studied. In addition, details of the phase space geometry of this signal have not been investigated in the emotional states up to now. In connection with this issue, Poincaré's sections can quantify the geometric patterns of the trajectory in the high-dimensional phase space. Therefore, this work attempted to propose an automatic emotion recognizer which can characterize the PPG signals during the exposure of emotional music-video. Our focus was to detect and classify dynamical behaviors of the PPG trajectories in three emotional classes of love, hate, and fun using Poincaré's section measures. To this effect, the 2D phase space of PPG was firstly reconstructed. Then, forming the Poincaré's sections in different angles, some geometric indices were extracted. Finally, using support vector machine, the PPG measures were classified into emotional states. Our results showed that basin geometry of the PPG phase states was significantly different in different emotional states. The maximum accuracy rates of 96.67% and 91.11% were achieved for a binary and multi-class classification scheme, respectively. The proposed framework was fast and operated using the single-sensor signal. In conclusion, the dynamical Poincaré's section indices of PPG signals during three emotional states paved the way for designing an online emotion recognition system.

Simultaneous detection of multiple inherited metabolic diseases using GC-MS urinary metabolomics by chemometrics multi-class classification strategies

Metabonomics has been widely used in disease diagnosis and clinically practical methods often require the detection of multi-class bio-samples. In this work, multi-class classification methods were investigated to simultaneously discriminate among 6 inherited metabolic diseases (IMDs) and the normal instances using gas chromatography-mass spectrometry (GC-MS) of urine samples. Two common multi-class classification strategies, one-against-all (OAA) and one-against-one (OAO) were compared and enhanced using a novel ensemble classification strategy (ECS), which developed a set of sequential sub-classifiers by fusion of OAA and OAO and made the final classification decisions using softmax function. GC-MS data of 240 instances of 6 IMDs and healthy controls were classified by different strategies based on orthogonal partial least squares discriminant analysis (OPLS-DA) and particle swarm optimization (PSO) algorithm was performed for feature selection. By OAA and OAO, the classification accuracies were 70.00% and 82.86%, respectively. Using the two methods based on ECS, the total classification accuracies were 0.9143 and 0.9429. The newly proposed ECS will provide a useful multi-class classification tool for simultaneous detection of clinically similar IMDs and promote practical and reliable diagnosis of IMDs using metabonomics data.

Identification of Various Image Operations Using Residual-Based Features

Image forensics has attracted wide attention during the past decade. However, most existing works aim at detecting a certain operation, which means that their proposed features usually depend on the investigated image operation and they consider only binary classification. This usually leads to misleading results if irrelevant features and/or classifiers are used. For instance, a JPEG decompressed image would be classified as an original or median filtered image if it was fed into a median filtering detector. Hence, it is important to develop forensic methods and universal features that can simultaneously identify multiple image operations. Based on extensive experiments and analysis, we find that any image operation, including existing anti-forensics operations, will inevitably modify a large number of pixel values in the original images. Thus, some common inherent statistics such as the correlations among adjacent pixels cannot be preserved well. To detect such modifications, we try to analyze the properties of local pixels within the image in the residual domain rather than the spatial domain considering the complexity of the image contents. Inspired by image steganalytic methods, we propose a very compact universal feature set and then design a multiclass classification scheme for identifying many common image operations. In our experiments, we tested the proposed features as well as several existing features on 11 typical image processing operations and four kinds of anti-forensic methods. The experimental results show that the proposed strategy significantly outperforms the existing forensic methods in terms of both effectiveness and universality.

An Anomalous Noise Events Detector for Dynamic Road Traffic Noise Mapping in Real-Life Urban and Suburban Environments.

One of the main aspects affecting the quality of life of people living in urban and suburban areas is their continued exposure to high Road Traffic Noise (RTN) levels. Until now, noise measurements in cities have been performed by professionals, recording data in certain locations to build a noise map afterwards. However, the deployment of Wireless Acoustic Sensor Networks (WASN) has enabled automatic noise mapping in smart cities. In order to obtain a reliable picture of the RTN levels affecting citizens, Anomalous Noise Events (ANE) unrelated to road traffic should be removed from the noise map computation. To this aim, this paper introduces an Anomalous Noise Event Detector (ANED) designed to differentiate between RTN and ANE in real time within a predefined interval running on the distributed low-cost acoustic sensors of a WASN. The proposed ANED follows a two-class audio event detection and classification approach, instead of multi-class or one-class classification schemes, taking advantage of the collection of representative acoustic data in real-life environments. The experiments conducted within the DYNAMAP project, implemented on ARM-based acoustic sensors, show the feasibility of the proposal both in terms of computational cost and classification performance using standard Mel cepstral coefficients and Gaussian Mixture Models (GMM). The two-class GMM core classifier relatively improves the baseline universal GMM one-class classifier F1 measure by 18.7% and 31.8% for suburban and urban environments, respectively, within the 1-s integration interval. Nevertheless, according to the results, the classification performance of the current ANED implementation still has room for improvement.

Comparison of decision tree based classification strategies to detect external chemical stimuli from raw and filtered plant electrical response

Plants monitor their surrounding environment and control their physiological functions by producing an electrical response. We recorded electrical signals from different plants by exposing them to Sodium Chloride (NaCl), Ozone (O3) and Sulfuric Acid (H2SO4) under laboratory conditions. After applying pre-processing techniques such as filtering and drift removal, we extracted few statistical features from the acquired plant electrical signals. Using these features, combined with different classification algorithms, we used a decision tree based multi-class classification strategy to identify the three different external chemical stimuli. We here present our exploration to obtain the optimum set of ranked feature and classifier combination that can separate a particular chemical stimulus from the incoming stream of plant electrical signals. The paper also reports an exhaustive comparison of similar feature based classification using the filtered and the raw plant signals, containing the high frequency stochastic part and also the low frequency trends present in it, as two different cases for feature extraction. The work, presented in this paper opens up new possibilities for using plant electrical signals to monitor and detect other environmental stimuli apart from NaCl, O3 and H2SO4 in future.

Improved support vector machines model based on multi-spectral parameters

To solve the classification accuracy instability problem of support vector machines (SVM) model caused by using original hyper-spectral data or a single spectral feature as modeling feature vector, an improved SVM model with multi-spectral parameters and joint kernel function is proposed in this paper. The feature vector of SVM model is built by multi-spectral parameters using feature selection method based on information quantity and between-class separability and feature extraction method based on minimum noise fraction. The kernel function of improved SVM model is optimized with linear combination of polynomial kernel function and radial basis kernel function to increase the learn ability and generalization ability. And the multi-class classification strategies based on an improved directed acyclic graph is presented in the proposed method. The airborne hyperspectral remote sensing images collected by pushbroom hyperspectral imager (PHI) and airborne visible infrared imaging spectrometer (AVIRIS) are applied to analyze and evaluate the performance of the proposed method in this paper. The experiment results show that the classification accuracy is better than 90% and the plant fine-classification ability for small sample and similar spectral features is realized.

Multivariate decoding of brain images using ordinal regression

Neuroimaging data are increasingly being used to predict potential outcomes or groupings, such as clinical severity, drug dose response, and transitional illness states. In these examples, the variable (target) we want to predict is ordinal in nature. Conventional classification schemes assume that the targets are nominal and hence ignore their ranked nature, whereas parametric and/or non-parametric regression models enforce a metric notion of distance between classes. Here, we propose a novel, alternative multivariate approach that overcomes these limitations — whole brain probabilistic ordinal regression using a Gaussian process framework. We applied this technique to two data sets of pharmacological neuroimaging data from healthy volunteers. The first study was designed to investigate the effect of ketamine on brain activity and its subsequent modulation with two compounds — lamotrigine and risperidone. The second study investigates the effect of scopolamine on cerebral blood flow and its modulation using donepezil. We compared ordinal regression to multi-class classification schemes and metric regression. Considering the modulation of ketamine with lamotrigine, we found that ordinal regression significantly outperformed multi-class classification and metric regression in terms of accuracy and mean absolute error. However, for risperidone ordinal regression significantly outperformed metric regression but performed similarly to multi-class classification both in terms of accuracy and mean absolute error. For the scopolamine data set, ordinal regression was found to outperform both multi-class and metric regression techniques considering the regional cerebral blood flow in the anterior cingulate cortex. Ordinal regression was thus the only method that performed well in all cases. Our results indicate the potential of an ordinal regression approach for neuroimaging data while providing a fully probabilistic framework with elegant approaches for model selection.

Jumlah Transisi pada Ciri Transisi dalam Pengenalan Pola Tulisan Tangan Aksara Jawa Nglegeno dengan Multiclass Support Vector Machines

<p>Feature extraction is one of the most improtant step on characters recognition system. Transition features is one from many features used on characters recognition system. This paper report a research on handwritten basic Jawanesse characters recognition system to found the proper numbers of transitions used on transition features. To recognize the characters,the Multiclass Support Vector Machines were used. The Directed Acyclic Graph (DAG) SVM were used for multiclass classification strategy and to map each input vector to a higher dimention space, the Gaussian Radial Basis Function (RBF) kernel with parameter 1were used. It can be shown, for basicJawanesse characters recognition system, the optimal numbers of transitions used for transition features is 4 (a half of maximum numbers of transition on all patterns).</p>

A multi-class classification strategy for Fisher scores: Application to signer independent sign language recognition

Fisher kernels combine the powers of discriminative and generative classifiers by mapping the variable-length sequences to a new fixed length feature space, called the Fisher score space. The mapping is based on a single generative model and the classifier is intrinsically binary. We propose a multi-class classification strategy that applies a multi-class classification on each Fisher score space and combines the decisions of multi-class classifiers. We experimentally show that the Fisher scores of one class provide discriminative information for the other classes as well. We compare several multi-class classification strategies for Fisher scores generated from the hidden Markov models of sign sequences. The proposed multi-class classification strategy increases the classification accuracy in comparison with the state of the art strategies based on combining binary classifiers. To reduce the computational complexity of the Fisher score extraction and the training phases, we also propose a score space selection method and show that, similar or even higher accuracies can be obtained by using only a subset of the score spaces. Based on the proposed score space selection method, a signer adaptation technique is also presented that does not require any re-training.

Fault Diagnosis Based on Fuzzy Support Vector Machine with Parameter Tuning and Feature Selection

This study describes a classification methodology based on support vector machines (SVMs), which offer superior classification performance for fault diagnosis in chemical process engineering. The method incorporates an efficient parameter tuning procedure (based on minimization of radius/margin bound for SVM's leave-one-out errors) into a multi-class classification strategy using a fuzzy decision factor, which is named fuzzy support vector machine (FSVM). The datasets generated from the Tennessee Eastman process (TEP) simulator were used to evaluate the classification performance. To decrease the negative influence of the auto-correlated and irrelevant variables, a key variable identification procedure using recursive feature elimination, based on the SVM is implemented, with time lags incorporated, before every classifier is trained, and the number of relatively important variables to every classifier is basically determined by 10-fold cross-validation. Performance comparisons are implemented among several kinds of multi-class decision machines, by which the effectiveness of the proposed approach is proved.

Building multiclass classifiers for remote homology detection and fold recognition.

BackgroundProtein remote homology detection and fold recognition are central problems in computational biology. Supervised learning algorithms based on support vector machines are currently one of the most effective methods for solving these problems. These methods are primarily used to solve binary classification problems and they have not been extensively used to solve the more general multiclass remote homology prediction and fold recognition problems.ResultsWe present a comprehensive evaluation of a number of methods for building SVM-based multiclass classification schemes in the context of the SCOP protein classification. These methods include schemes that directly build an SVM-based multiclass model, schemes that employ a second-level learning approach to combine the predictions generated by a set of binary SVM-based classifiers, and schemes that build and combine binary classifiers for various levels of the SCOP hierarchy beyond those defining the target classes.ConclusionAnalyzing the performance achieved by the different approaches on four different datasets we show that most of the proposed multiclass SVM-based classification approaches are quite effective in solving the remote homology prediction and fold recognition problems and that the schemes that use predictions from binary models constructed for ancestral categories within the SCOP hierarchy tend to not only lead to lower error rates but also reduce the number of errors in which a superfamily is assigned to an entirely different fold and a fold is predicted as being from a different SCOP class. Our results also show that the limited size of the training data makes it hard to learn complex second-level models, and that models of moderate complexity lead to consistently better results.

Automatic 3D Protein Structure Classification without Structural Alignment

In this paper, we present a new scheme named ProtClass for automatic classification of three-dimensional (3D) protein structures. It is a dedicated and unified multiclass classification scheme. Neither detailed structural alignment nor multiple binary classifications are required in this scheme. We adopt a nearest neighbor-based classification strategy. We use a filter-and-refine scheme. In the first step, we filter out the improbable answers using the precalculated parameters from the training data. In the second, we perform a relatively more detailed nearest neighbor search on the remaining answers. We use very concise and effective encoding schemes of the 3D protein structures in both steps. We compare our proposed method against two other dedicated protein structure classification schemes, namely SGM and CPMine. The experimental results show that ProtClass is slightly better in accuracy than SGM and much faster. In comparison with CPMine, ProtClass is much more accurate, while their running times are about the same. We also compare ProtClass against a structural alignment-based classification scheme named DALI, which is found to be more accurate, but extremely slow. The software is available upon request from the authors. The supplementary information on ProtClass method can be found at: http://xena1.ddns.comp.nus.edu.sg/ approximately genesis/PClass.htm.

PCA disjoint models for multiclass cancer analysis using gene expression data

Microarray expression profiling appears particularly promising for a deeper understanding of cancer biology and to identify molecular signatures supporting the histological classification schemes of neoplastic specimens. However, molecular diagnostics based on microarray data presents major challenges due to the overwhelming number of variables and the complex, multiclass nature of tumor samples. Thus, the development of marker selection methods, that allow the identification of those genes that are most likely to confer high classification accuracy of multiple tumor types, and of multiclass classification schemes is of paramount importance. A computational procedure for marker identification and for classification of multiclass gene expression data through the application of disjoint principal component models is described. The identified features represent a rational and dimensionally reduced base for understanding the basic biology of diseases, defining targets for therapeutic intervention, and developing diagnostic tools for the identification and classification of multiple pathological states. The method has been tested on different microarray data sets obtained from various human tumor samples. The results demonstrate that this procedure allows the identification of specific phenotype markers and can classify previously unseen instances in the presence of multiple classes.