PyTorchKR Papers

최신 논문

총 11,809편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1312.6974

Piecewise regression mixture for simultaneous functional data clustering and optimal segmentation

This paper introduces a novel mixture model-based approach for simultaneous clustering and optimal segmentation of functional data which are curves presenting regime changes. The proposed model consists in a finite mixture of piecewise polynomial regression models. Each piecewise polynomial regression model is associated with a cluster, and within each cluster, each piecewise polynomial component is associated with a regime (i.e., a segment). We derive two approaches for learning the model parameters. The former is an estimation approach and consists in maximizing the observed-data likelihood via a dedicated expectation-maximization (EM) algorithm. A fuzzy partition of the curves in K clusters is then obtained at convergence by maximizing the posterior cluster probabilities. The latter however is a classification approach and optimizes a specific classification likelihood criterion through a dedicated classification expectation-maximization (CEM) algorithm. The optimal curve segmentation is performed by using dynamic programming. In the classification approach, both the curve clustering and the optimal segmentation are performed simultaneously as the CEM learning proceeds. We show that the classification approach is the probabilistic version that generalizes the deterministic K-means-like algorithm proposed in H\'ebrail et al. (2010). The proposed approach is evaluated using simulated curves and real-world curves. Comparisons with alternatives including regression mixture models and the K-means like algorithm for piecewise regression demonstrate the effectiveness of the proposed approach.

arXiv:1401.3531

Highly comparative feature-based time-series classification

A highly comparative, feature-based approach to time series classification is introduced that uses an extensive database of algorithms to extract thousands of interpretable features from time series. These features are derived from across the scientific time-series analysis literature, and include summaries of time series in terms of their correlation structure, distribution, entropy, stationarity, scaling properties, and fits to a range of time-series models. After computing thousands of features for each time series in a training set, those that are most informative of the class structure are selected using greedy forward feature selection with a linear classifier. The resulting feature-based classifiers automatically learn the differences between classes using a reduced number of time-series properties, and circumvent the need to calculate distances between time series. Representing time series in this way results in orders of magnitude of dimensionality reduction, allowing the method to perform well on very large datasets containing long time series or time series of different lengths. For many of the datasets studied, classification performance exceeded that of conventional instance-based classifiers, including one nearest neighbor classifiers using Euclidean distances and dynamic time warping and, most importantly, the features selected provide an understanding of the properties of the dataset, insight that can guide further scientific investigation.

arXiv:1405.4308

Coarse-to-Fine Classification via Parametric and Nonparametric Models for Computer-Aided Diagnosis

Classification is one of the core problems in Computer-Aided Diagnosis (CAD), targeting for early cancer detection using 3D medical imaging interpretation. High detection sensitivity with desirably low false positive (FP) rate is critical for a CAD system to be accepted as a valuable or even indispensable tool in radiologists' workflow. Given various spurious imagery noises which cause observation uncertainties, this remains a very challenging task. In this paper, we propose a novel, two-tiered coarse-to-fine (CTF) classification cascade framework to tackle this problem. We first obtain classification-critical data samples (e.g., samples on the decision boundary) extracted from the holistic data distributions using a robust parametric model (e.g., \cite{Raykar08}); then we build a graph-embedding based nonparametric classifier on sampled data, which can more accurately preserve or formulate the complex classification boundary. These two steps can also be considered as effective "sample pruning" and "feature pursuing + $k$NN/template matching", respectively. Our approach is validated comprehensively in colorectal polyp detection and lung nodule detection CAD systems, as the top two deadly cancers, using hospital scale, multi-site clinical datasets. The results show that our method achieves overall better classification/detection performance than existing state-of-the-art algorithms using single-layer classifiers, such as the support vector machine variants \cite{Wang08}, boosting \cite{Slabaugh10}, logistic regression \cite{Ravesteijn10}, relevance vector machine \cite{Raykar08}, $k$-nearest neighbor \cite{Murphy09} or spectral projections on graph \cite{Cai08}.

arXiv:1405.3410

Efficient classification using parallel and scalable compressed model and Its application on intrusion detection

In order to achieve high efficiency of classification in intrusion detection, a compressed model is proposed in this paper which combines horizontal compression with vertical compression. OneR is utilized as horizontal com-pression for attribute reduction, and affinity propagation is employed as vertical compression to select small representative exemplars from large training data. As to be able to computationally compress the larger volume of training data with scalability, MapReduce based parallelization approach is then implemented and evaluated for each step of the model compression process abovementioned, on which common but efficient classification methods can be directly used. Experimental application study on two publicly available datasets of intrusion detection, KDD99 and CMDC2012, demonstrates that the classification using the compressed model proposed can effectively speed up the detection procedure at up to 184 times, most importantly at the cost of a minimal accuracy difference with less than 1% on average.

arXiv:1405.3295

Effects of Sampling Methods on Prediction Quality. The Case of Classifying Land Cover Using Decision Trees

Clever sampling methods can be used to improve the handling of big data and increase its usefulness. The subject of this study is remote sensing, specifically airborne laser scanning point clouds representing different classes of ground cover. The aim is to derive a supervised learning model for the classification using CARTs. In order to measure the effect of different sampling methods on the classification accuracy, various experiments with varying types of sampling methods, sample sizes, and accuracy metrics have been designed. Numerical results for a subset of a large surveying project covering the lower Rhine area in Germany are shown. General conclusions regarding sampling design are drawn and presented.

arXiv:1402.1892

Thresholding Classifiers to Maximize F1 Score

This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a binary classifier when one class is rare. Micro average, macro average, and per instance average F1 scores are used in multilabel classification. For any classifier that produces a real-valued output, we derive the relationship between the best achievable F1 score and the decision-making threshold that achieves this optimum. As a special case, if the classifier outputs are well-calibrated conditional probabilities, then the optimal threshold is half the optimal F1 score. As another special case, if the classifier is completely uninformative, then the optimal behavior is to classify all examples as positive. Since the actual prevalence of positive examples typically is low, this behavior can be considered undesirable. As a case study, we discuss the results, which can be surprising, of applying this procedure when predicting 26,853 labels for Medline documents.

arXiv:1312.5419

Large-scale Multi-label Text Classification - Revisiting Neural Networks

Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural network (NN) architecture that aims at minimizing pairwise ranking error. Instead, we propose to use a comparably simple NN approach with recently proposed learning techniques for large-scale multi-label text classification tasks. In particular, we show that BP-MLL's ranking loss minimization can be efficiently and effectively replaced with the commonly used cross entropy error function, and demonstrate that several advances in neural network training that have been developed in the realm of deep learning can be effectively employed in this setting. Our experimental results show that simple NN models equipped with advanced techniques such as rectified linear units, dropout, and AdaGrad perform as well as or even outperform state-of-the-art approaches on six large-scale textual datasets with diverse characteristics.

arXiv:1405.6524

Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning

Automatic species classification of birds from their sound is a computational tool of increasing importance in ecology, conservation monitoring and vocal communication studies. To make classification useful in practice, it is crucial to improve its accuracy while ensuring that it can run at big data scales. Many approaches use acoustic measures based on spectrogram-type data, such as the Mel-frequency cepstral coefficient (MFCC) features which represent a manually-designed summary of spectral information. However, recent work in machine learning has demonstrated that features learnt automatically from data can often outperform manually-designed feature transforms. Feature learning can be performed at large scale and "unsupervised", meaning it requires no manual data labelling, yet it can improve performance on "supervised" tasks such as classification. In this work we introduce a technique for feature learning from large volumes of bird sound recordings, inspired by techniques that have proven useful in other domains. We experimentally compare twelve different feature representations derived from the Mel spectrum (of which six use this technique), using four large and diverse databases of bird vocalisations, with a random forest classifier. We demonstrate that MFCCs are of limited power in this context, leading to worse performance than the raw Mel spectral data. Conversely, we demonstrate that unsupervised feature learning provides a substantial boost over MFCCs and Mel spectra without adding computational complexity after the model has been trained. The boost is particularly notable for single-label classification tasks at large scale. The spectro-temporal activations learned through our procedure resemble spectro-temporal receptive fields calculated from avian primary auditory forebrain.

arXiv:1405.6444

The role of dimensionality reduction in linear classification

Dimensionality reduction (DR) is often used as a preprocessing step in classification, but usually one first fixes the DR mapping, possibly using label information, and then learns a classifier (a filter approach). Best performance would be obtained by optimizing the classification error jointly over DR mapping and classifier (a wrapper approach), but this is a difficult nonconvex problem, particularly with nonlinear DR. Using the method of auxiliary coordinates, we give a simple, efficient algorithm to train a combination of nonlinear DR and a classifier, and apply it to a RBF mapping with a linear SVM. This alternates steps where we train the RBF mapping and a linear SVM as usual regression and classification, respectively, with a closed-form step that coordinates both. The resulting nonlinear low-dimensional classifier achieves classification errors competitive with the state-of-the-art but is fast at training and testing, and allows the user to trade off runtime for classification accuracy easily. We then study the role of nonlinear DR in linear classification, and the interplay between the DR mapping, the number of latent dimensions and the number of classes. When trained jointly, the DR mapping takes an extreme role in eliminating variation: it tends to collapse classes in latent space, erasing all manifold structure, and lay out class centroids so they are linearly separable with maximum margin.

arXiv:1405.5829

Node Classification in Uncertain Graphs

In many real applications that use and analyze networked data, the links in the network graph may be erroneous, or derived from probabilistic techniques. In such cases, the node classification problem can be challenging, since the unreliability of the links may affect the final results of the classification process. If the information about link reliability is not used explicitly, the classification accuracy in the underlying network may be affected adversely. In this paper, we focus on situations that require the analysis of the uncertainty that is present in the graph structure. We study the novel problem of node classification in uncertain graphs, by treating uncertainty as a first-class citizen. We propose two techniques based on a Bayes model and automatic parameter selection, and show that the incorporation of uncertainty in the classification process as a first-class citizen is beneficial. We experimentally evaluate the proposed approach using different real data sets, and study the behavior of the algorithms under different conditions. The results demonstrate the effectiveness and efficiency of our approach.

arXiv:1405.4589

A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm

A large number of experimental data shows that Support Vector Machine (SVM) algorithm has obvious advantages in text classification, handwriting recognition, image classification, bioinformatics, and some other fields. To some degree, the optimization of SVM depends on its kernel function and Slack variable, the determinant of which is its parameters $\delta$ and c in the classification function. That is to say,to optimize the SVM algorithm, the optimization of the two parameters play a huge role. Ant Colony Optimization (ACO) is optimization algorithm which simulate ants to find the optimal path.In the available literature, we mix the ACO algorithm and Parallel algorithm together to find a well parameters.

arXiv:1405.4574

Kronecker PCA Based Spatio-Temporal Modeling of Video for Dismount Classification

We consider the application of KronPCA spatio-temporal modeling techniques [Greenewald et al 2013, Tsiligkaridis et al 2013] to the extraction of spatiotemporal features for video dismount classification. KronPCA performs a low-rank type of dimensionality reduction that is adapted to spatio-temporal data and is characterized by the T frame multiframe mean and covariance of p spatial features. For further regularization and improved inverse estimation, we also use the diagonally corrected KronPCA shrinkage methods we presented in [Greenewald et al 2013]. We apply this very general method to the modeling of the multivariate temporal behavior of HOG features extracted from pedestrian bounding boxes in video, with gender classification in a challenging dataset chosen as a specific application. The learned covariances for each class are used to extract spatiotemporal features which are then classified, achieving competitive classification performance.

arXiv:1404.4095

Multi-borders classification

The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification problems into binary classification problems is specified using a recursive control language.

arXiv:1406.0824

Supervised classification-based stock prediction and portfolio optimization

As the number of publicly traded companies as well as the amount of their financial data grows rapidly, it is highly desired to have tracking, analysis, and eventually stock selections automated. There have been few works focusing on estimating the stock prices of individual companies. However, many of those have worked with very small number of financial parameters. In this work, we apply machine learning techniques to address automated stock picking, while using a larger number of financial parameters for individual companies than the previous studies. Our approaches are based on the supervision of prediction parameters using company fundamentals, time-series properties, and correlation information between different stocks. We examine a variety of supervised learning techniques and found that using stock fundamentals is a useful approach for the classification problem, when combined with the high dimensional data handling capabilities of support vector machine. The portfolio our system suggests by predicting the behavior of stocks results in a 3% larger growth on average than the overall market within a 3-month time period, as the out-of-sample test suggests.

arXiv:1405.7626

Classification of Basmati Rice Grain Variety using Image Processing and Principal Component Analysis

All important decisions about the variety of rice grain end product are based on the different features of rice grain.There are various methods available for classification of basmati rice. This paper proposed a new principal component analysis based approach for classification of different variety of basmati rice. The experimental result shows the effectiveness of the proposed methodology for various samples of different variety of basmati rice.

arXiv:1405.6922

Large Scale, Large Margin Classification using Indefinite Similarity Measures

Despite the success of the popular kernelized support vector machines, they have two major limitations: they are restricted to Positive Semi-Definite (PSD) kernels, and their training complexity scales at least quadratically with the size of the data. Many natural measures of similarity between pairs of samples are not PSD e.g. invariant kernels, and those that are implicitly or explicitly defined by latent variable models. In this paper, we investigate scalable approaches for using indefinite similarity measures in large margin frameworks. In particular we show that a normalization of similarity to a subset of the data points constitutes a representation suitable for linear classifiers. The result is a classifier which is competitive to kernelized SVM in terms of accuracy, despite having better training and test time complexities. Experimental results demonstrate that on CIFAR-10 dataset, the model equipped with similarity measures invariant to rigid and non-rigid deformations, can be made more than 5 times sparser while being more accurate than kernelized SVM using RBF kernels.

arXiv:1405.6914

Supervised Dictionary Learning by a Variational Bayesian Group Sparse Nonnegative Matrix Factorization

Nonnegative matrix factorization (NMF) with group sparsity constraints is formulated as a probabilistic graphical model and, assuming some observed data have been generated by the model, a feasible variational Bayesian algorithm is derived for learning model parameters. When used in a supervised learning scenario, NMF is most often utilized as an unsupervised feature extractor followed by classification in the obtained feature subspace. Having mapped the class labels to a more general concept of groups which underlie sparsity of the coefficients, what the proposed group sparse NMF model allows is incorporating class label information to find low dimensional label-driven dictionaries which not only aim to represent the data faithfully, but are also suitable for class discrimination. Experiments performed in face recognition and facial expression recognition domains point to advantages of classification in such label-driven feature subspaces over classification in feature subspaces obtained in an unsupervised manner.

arXiv:1405.6684

Visualizing Random Forest with Self-Organising Map

Random Forest (RF) is a powerful ensemble method for classification and regression tasks. It consists of decision trees set. Although, a single tree is well interpretable for human, the ensemble of trees is a black-box model. The popular technique to look inside the RF model is to visualize a RF proximity matrix obtained on data samples with Multidimensional Scaling (MDS) method. Herein, we present a novel method based on Self-Organising Maps (SOM) for revealing intrinsic relationships in data that lay inside the RF used for classification tasks. We propose an algorithm to learn the SOM with the proximity matrix obtained from the RF. The visualization of RF proximity matrix with MDS and SOM is compared. What is more, the SOM learned with the RF proximity matrix has better classification accuracy in comparison to SOM learned with Euclidean distance. Presented approach enables better understanding of the RF and additionally improves accuracy of the SOM.

arXiv:1405.6667

Inferring gender of a Twitter user using celebrities it follows

This paper addresses the task of user gender classification in social media, with an application to Twitter. The approach automatically predicts gender by leveraging observable information such as the tweet behavior, linguistic content of the user's Twitter feed and the celebrities followed by the user. This paper first evaluates linguistic content based features using LIWC dictionary and popular neighborhood features using Wikipedia and Freebase. Then augments both features which yielded a significant increase in the accuracy for gender prediction. Results show that rich linguistic features combined with popular neighborhood prove valuables and promising for additional user classification needs.

arXiv:1406.1943

Structured Dictionary Learning for Classification

Sparsity driven signal processing has gained tremendous popularity in the last decade. At its core, the assumption is that the signal of interest is sparse with respect to either a fixed transformation or a signal dependent dictionary. To better capture the data characteristics, various dictionary learning methods have been proposed for both reconstruction and classification tasks. For classification particularly, most approaches proposed so far have focused on designing explicit constraints on the sparse code to improve classification accuracy while simply adopting $l_0$-norm or $l_1$-norm for sparsity regularization. Motivated by the success of structured sparsity in the area of Compressed Sensing, we propose a structured dictionary learning framework (StructDL) that incorporates the structure information on both group and task levels in the learning process. Its benefits are two-fold: (i) the label consistency between dictionary atoms and training data are implicitly enforced; and (ii) the classification performance is more robust in the cases of a small dictionary size or limited training data than other techniques. Using the subspace model, we derive the conditions for StructDL to guarantee the performance and show theoretically that StructDL is superior to $l_0$-norm or $l_1$-norm regularized dictionary learning for classification. Extensive experiments have been performed on both synthetic simulations and real world applications, such as face recognition and object classification, to demonstrate the validity of the proposed DL framework.