The nature of clinical data makes it difficult to quickly select, tune and apply machine learning algorithms to clinical prognosis. As a result, a lot of time is spent searching for the most appropriate machine learning algorithms applicable in clinical prognosis that contains either binary-valued or multi-valued attributes. The study set out to identify and evaluate the performance of machine learning classification schemes applied in clinical prognosis of post-operative life expectancy in the lung cancer patients. Multilayer Perceptron, J48, and the Naive Bayes algorithms were used to train and test models on Thoracic Surgery datasets obtained from the University of California Irvine machine learning repository. Stratified 10-fold cross-validation was used to evaluate baseline performance accuracy of the classifiers. The comparative analysis shows that multilayer perceptron performed best with classification accuracy of 82.3%, J48 came out second with classification accuracy of 81.8%, and Naive Bayes came out the worst with classification accuracy of 74.4%. The quality and outcome of the chosen machine learning algorithms depends on the ingenuity of the clinical miner.
This paper presents the Nataf-Beta Random Field Classifier, a discriminative approach that extends the applicability of the Beta conjugate prior to classification problems. The approach's key feature is to model the probability of a class conditional on attribute values as a random field whose marginals are Beta distributed, and where the parameters of marginals are themselves described by random fields. Although the classification accuracy of the approach proposed does not statistically outperform the best accuracies reported in the literature, it ranks among the top tier for the six benchmark datasets tested. The Nataf-Beta Random Field Classifier is suited as a general purpose classification approach for real-continuous and real-integer attribute value problems.
Restricted Boltzmann machines (RBM) and its variants have become hot research topics recently, and widely applied to many classification problems, such as character recognition and document categorization. Often, classification RBM ignores the interclass relationship or prior knowledge of sharing information among classes. In this paper, we are interested in RBM with the hierarchical prior over classes. We assume parameters for nearby nodes are correlated in the hierarchical tree, and further the parameters at each node of the tree be orthogonal to those at its ancestors. We propose a hierarchical correlated RBM for classification problem, which generalizes the classification RBM with sharing information among different classes. In order to reduce the redundancy between node parameters in the hierarchy, we also introduce orthogonal restrictions to our objective function. We test our method on challenge datasets, and show promising results compared to competitive baselines.
This paper presents our contribution to the ChaLearn Challenge 2015 on Cultural Event Classification. The challenge in this task is to automatically classify images from 50 different cultural events. Our solution is based on the combination of visual features extracted from convolutional neural networks with temporal information using a hierarchical classifier scheme. We extract visual features from the last three fully connected layers of both CaffeNet (pretrained with ImageNet) and our fine tuned version for the ChaLearn challenge. We propose a late fusion strategy that trains a separate low-level SVM on each of the extracted neural codes. The class predictions of the low-level SVMs form the input to a higher level SVM, which gives the final event scores. We achieve our best result by adding a temporal refinement step into our classification scheme, which is applied directly to the output of each low-level SVM. Our approach penalizes high classification scores based on visual features when their time stamp does not match well an event-specific temporal distribution learned from the training and validation data. Our system achieved the second best result in the ChaLearn Challenge 2015 on Cultural Event Classification with a mean average precision of 0.767 on the test set.
For random graphs distributed according to stochastic blockmodels, a special case of latent position graphs, adjacency spectral embedding followed by appropriate vertex classification is asymptotically Bayes optimal; but this approach requires knowledge of and critically depends on the model dimension. In this paper, we propose a sparse representation vertex classifier which does not require information about the model dimension. This classifier represents a test vertex as a sparse combination of the vertices in the training set and uses the recovered coefficients to classify the test vertex. We prove consistency of our proposed classifier for stochastic blockmodels, and demonstrate that the sparse representation classifier can predict vertex labels with higher accuracy than adjacency spectral embedding approaches via both simulation studies and real data experiments. Our results demonstrate the robustness and effectiveness of our proposed vertex classifier when the model dimension is unknown.
Deep learning has shown state-of-art classification performance on datasets such as ImageNet, which contain a single object in each image. However, multi-object classification is far more challenging. We present a unified framework which leverages the strengths of multiple machine learning methods, viz deep learning, probabilistic models and kernel methods to obtain state-of-art performance on Microsoft COCO, consisting of non-iconic images. We incorporate contextual information in natural images through a conditional latent tree probabilistic model (CLTM), where the object co-occurrences are conditioned on the extracted fc7 features from pre-trained Imagenet CNN as input. We learn the CLTM tree structure using conditional pairwise probabilities for object co-occurrences, estimated through kernel methods, and we learn its node and edge potentials by training a new 3-layer neural network, which takes fc7 features as input. Object classification is carried out via inference on the learnt conditional tree model, and we obtain significant gain in precision-recall and F-measures on MS-COCO, especially for difficult object categories. Moreover, the latent variables in the CLTM capture scene information: the images with top activations for a latent node have common themes such as being a grasslands or a food scene, and on on. In addition, we show that a simple k-means clustering of the inferred latent nodes alone significantly improves scene classification performance on the MIT-Indoor dataset, without the need for any retraining, and without using scene labels during training. Thus, we present a unified framework for multi-object classification and unsupervised scene understanding.
Many real-world applications are associated with structured data, where not only input but also output has interplay. However, typical classification and regression models often lack the ability of simultaneously exploring high-order interaction within input and that within output. In this paper, we present a deep learning model aiming to generate a powerful nonlinear functional mapping from structured input to structured output. More specifically, we propose to integrate high-order hidden units, guided discriminative pretraining, and high-order auto-encoders for this purpose. We evaluate the model with three datasets, and obtain state-of-the-art performances among competitive methods. Our current work focuses on structured output regression, which is a less explored area, although the model can be extended to handle structured label classification.
In this paper we present a novel method for robust hyperspectral image classification using context and rejection. Hyperspectral image classification is generally an ill-posed image problem where pixels may belong to unknown classes, and obtaining representative and complete training sets is costly. Furthermore, the need for high classification accuracies is frequently greater than the need to classify the entire image. We approach this problem with a robust classification method that combines classification with context with classification with rejection. A rejection field that will guide the rejection is derived from the classification with contextual information obtained by using the SegSALSA algorithm. We validate our method in real hyperspectral data and show that the performance gains obtained from the rejection fields are equivalent to an increase the dimension of the training sets.
Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best performance, as they do in classification. We show that for instance-level image retrieval, lower layers often perform better than the last layers in convolutional neural networks. We present an approach for extracting convolutional features from different layers of the networks, and adopt VLAD encoding to encode features into a single vector for each image. We investigate the effect of different layers and scales of input images on the performance of convolutional features using the recent deep networks OxfordNet and GoogLeNet. Experiments demonstrate that intermediate layers or higher layers with finer scales produce better results for image retrieval, compared to the last layer. When using compressed 128-D VLAD descriptors, our method obtains state-of-the-art results and outperforms other VLAD and CNN based approaches on two out of three test datasets. Our work provides guidance for transferring deep networks trained on image classification to image retrieval tasks.
Boosting is a learning scheme that combines weak prediction rules to produce a strong composite estimator, with the underlying intuition that one can obtain accurate prediction rules by combining "rough" ones. Although boosting is proved to be consistent and overfitting-resistant, its numerical convergence rate is relatively slow. The aim of this paper is to develop a new boosting strategy, called the re-scale boosting (RBoosting), to accelerate the numerical convergence rate and, consequently, improve the learning performance of boosting. Our studies show that RBoosting possesses the almost optimal numerical convergence rate in the sense that, up to a logarithmic factor, it can reach the minimax nonlinear approximation rate. We then use RBoosting to tackle both the classification and regression problems, and deduce a tight generalization error estimate. The theoretical and experimental results show that RBoosting outperforms boosting in terms of generalization.
Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2$\times$ improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.
This paper presents a novel multi scale gradient and a corner point based shape descriptors. The novel multi scale gradient based shape descriptor is combined with generic Fourier descriptors to extract contour and region based shape information. Shape information based object class detection and classification technique with a random forest classifier has been optimized. Proposed integrated descriptor in this paper is robust to rotation, scale, translation, affine deformations, noisy contours and noisy shapes. The new corner point based interpolated shape descriptor has been exploited for fast object detection and classification with higher accuracy.
Neutrinos are one of the least known elementary particles. The detection of neutrinos is an extremely difficult task since they are affected only by weak sub-atomic force or gravity. Therefore large detectors are constructed to reveal neutrino's properties. Among them the Liquid Argon Time Projection Chamber (LAr-TPC) detectors provide excellent imaging and particle identification ability for studying neutrinos. The computerized methods for automatic reconstruction and identification of particles are needed to fully exploit the potential of the LAr-TPC technique. Herein, the novel method for electron neutrino classification is presented. The method constructs a feature descriptor from images of observed event. It characterizes the signal distribution propagated from vertex of interest, where the particle interacts with the detector medium. The classifier is learned with a constructed feature descriptor to decide whether the images represent the electron neutrino or cascade produced by photons. The proposed approach assumes that the position of primary interaction vertex is known. The method's performance in dependency to the noise in a primary vertex position and deposited energy of particles is studied.
Surface topography refers to the geometric micro-structure of a surface and defines its tactile characteristics (typically in the sub-millimeter range). High-resolution 3D scanning techniques developed recently enable the 3D reconstruction of surfaces including their surface topography. In his paper, we present an efficient image-space technique for the extraction of surface topography from high-resolution 3D reconstructions. Additionally, we filter noise and enhance topographic attributes to obtain an improved representation for subsequent topography classification. Comprehensive experiments show that the our representation captures well topographic attributes and significantly improves classification performance compared to alternative 2D and 3D representations.
We investigate the importance of parts for the tasks of action and attribute classification. We develop a part-based approach by leveraging convolutional network features inspired by recent advances in computer vision. Our part detectors are a deep version of poselets and capture parts of the human body under a distinct set of poses. For the tasks of action and attribute classification, we train holistic convolutional neural networks and show that adding parts leads to top-performing results for both tasks. In addition, we demonstrate the effectiveness of our approach when we replace an oracle person detector, as is the default in the current evaluation protocol for both tasks, with a state-of-the-art person detection system.
We introduce LABR, the largest sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars. We investigate the properties of the dataset, and present its statistics. We explore using the dataset for two tasks: (1) sentiment polarity classification; and (2) ratings classification. Moreover, we provide standard splits of the dataset into training, validation and testing, for both polarity and ratings classification, in both balanced and unbalanced settings. We extend our previous work by performing a comprehensive analysis on the dataset. In particular, we perform an extended survey of the different classifiers typically used for the sentiment polarity classification problem. We also construct a sentiment lexicon from the dataset that contains both single and compound sentiment words and we explore its effectiveness. We make the dataset and experimental details publicly available.
Biologically inspired, from the early HMAX model to Spatial Pyramid Matching, pooling has played an important role in visual recognition pipelines. Spatial pooling, by grouping of local codes, equips these methods with a certain degree of robustness to translation and deformation yet preserving important spatial information. Despite the predominance of this approach in current recognition systems, we have seen little progress to fully adapt the pooling strategy to the task at hand. This paper proposes a model for learning task dependent pooling scheme -- including previously proposed hand-crafted pooling schemes as a particular instantiation. In our work, we investigate the role of different regularization terms showing that the smooth regularization term is crucial to achieve strong performance using the presented architecture. Finally, we propose an efficient and parallel method to train the model. Our experiments show improved performance over hand-crafted pooling schemes on the CIFAR-10 and CIFAR-100 datasets -- in particular improving the state-of-the-art to 56.29% on the latter.
In biospectroscopy, suitably annotated and statistically independent samples (e. g. patients, batches, etc.) for classifier training and testing are scarce and costly. Learning curves show the model performance as function of the training sample size and can help to determine the sample size needed to train good classifiers. However, building a good model is actually not enough: the performance must also be proven. We discuss learning curves for typical small sample size situations with 5 - 25 independent samples per class. Although the classification models achieve acceptable performance, the learning curve can be completely masked by the random testing uncertainty due to the equally limited test sample size. In consequence, we determine test sample sizes necessary to achieve reasonable precision in the validation and find that 75 - 100 samples will usually be needed to test a good but not perfect classifier. Such a data set will then allow refined sample size planning on the basis of the achieved performance. We also demonstrate how to calculate necessary sample sizes in order to show the superiority of one classifier over another: this often requires hundreds of statistically independent test samples or is even theoretically impossible. We demonstrate our findings with a data set of ca. 2550 Raman spectra of single cells (five classes: erythrocytes, leukocytes and three tumour cell lines BT-20, MCF-7 and OCI-AML3) as well as by an extensive simulation that allows precise determination of the actual performance of the models in question.
With the widespread availability of cellphones and cameras that have GPS capabilities, it is common for images being uploaded to the Internet today to have GPS coordinates associated with them. In addition to research that tries to predict GPS coordinates from visual features, this also opens up the door to problems that are conditioned on the availability of GPS coordinates. In this work, we tackle the problem of performing image classification with location context, in which we are given the GPS coordinates for images in both the train and test phases. We explore different ways of encoding and extracting features from the GPS coordinates, and show how to naturally incorporate these features into a Convolutional Neural Network (CNN), the current state-of-the-art for most image classification and recognition problems. We also show how it is possible to simultaneously learn the optimal pooling radii for a subset of our features within the CNN framework. To evaluate our model and to help promote research in this area, we identify a set of location-sensitive concepts and annotate a subset of the Yahoo Flickr Creative Commons 100M dataset that has GPS coordinates with these concepts, which we make publicly available. By leveraging location context, we are able to achieve almost a 7% gain in mean average precision.
Automatic Speech Recognition involves mainly two steps; feature extraction and classification . Mel Frequency Cepstral Coefficient is used as one of the prominent feature extraction techniques in ASR. Usually, the set of all 12 MFCC coefficients is used as the feature vector in the classification step. But the question is whether the same or improved classification accuracy can be achieved by using a subset of 12 MFCC as feature vector. In this paper, Fisher's ratio technique is used for selecting a subset of 12 MFCC coefficients that contribute more in discriminating a pattern. The selected coefficients are used in classification with Hidden Markov Model algorithm. The classification accuracies that we get by using 12 coefficients and by using the selected coefficients are compared.