There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from one-dimension spectra only. Author developed several scripts and C programs for datasets preparation, preprocessing and postprocessing of the data. EBLearn library (developed by Pierre Sermanet and Yann LeCun) was used to create ConvNets. Application on dataset of more than 60000 spectra yielded success rate of nearly 95%. This thesis conclusively proved great potential of convolutional neural networks and deep learning methods in astrophysics.
A process centric view of robust PCA (RPCA) allows its fast approximate implementation based on a special form o a deep neural network with weights shared across all layers. However, empirically this fast approximation to RPCA fails to find representations that are parsemonious. We resolve these bad local minima by relaxing the elementwise L1 and L2 priors and instead utilize a structure inducing k-sparsity prior. In a discriminative classification task the newly learned representations outperform these from the original approximate RPCA formulation significantly.
With the increase of information, document classification as one of the methods of text mining, plays vital role in many management and organizing information. Document classification is the process of assigning a document to one or more predefined category labels. Document classification includes different parts such as text processing, term selection, term weighting and final classification. The accuracy of document classification is very important. Thus improvement in each part of classification should lead to better results and higher precision. Term weighting has a great impact on the accuracy of the classification. Most of the existing weighting methods exploit the statistical information of terms in documents and do not consider semantic relations between words. In this paper, an automated document classification system is presented that uses a novel term weighting method based on semantic relations between terms. To evaluate the proposed method, three standard Persian corpuses are used. Experiment results show 2 to 4 percent improvement in classification accuracy compared with the best previous designed system for Persian documents.
In the recent decade, with the enormous growth of digital content in internet and databases, sentiment analysis has received more and more attention between information retrieval and natural language processing researchers. Sentiment analysis aims to use automated tools to detect subjective information from reviews. One of the main challenges in sentiment analysis is feature selection. Feature selection is widely used as the first stage of analysis and classification tasks to reduce the dimension of problem, and improve speed by the elimination of irrelevant and redundant features. Up to now as there are few researches conducted on feature selection in sentiment analysis, there are very rare works for Persian sentiment analysis. This paper considers the problem of sentiment classification using different feature selection methods for online customer reviews in Persian language. Three of the challenges of Persian text are using of a wide variety of declensional suffixes, different word spacing and many informal or colloquial words. In this paper we study these challenges by proposing a model for sentiment classification of Persian review documents. The proposed model is based on lemmatization and feature selection and is employed Naive Bayes algorithm for classification. We evaluate the performance of the model on a manually gathered collection of cellphone reviews, where the results show the effectiveness of the proposed approaches.
This work proposes a texture descriptor based on fractal theory. The method is based on the Bouligand-Minkowski descriptors. We decompose the original image recursively into 4 equal parts. In each recursion step, we estimate the average and the deviation of the Bouligand-Minkowski descriptors computed over each part. Thus, we extract entropy features from both average and deviation. The proposed descriptors are provided by the concatenation of such measures. The method is tested in a classification experiment under well known datasets, that is, Brodatz and Vistex. The results demonstrate that the proposed technique achieves better results than classical and state-of-the-art texture descriptors, such as Gabor-wavelets and co-occurrence matrix.
This paper presents a versatile technique for the purpose of feature selection and extraction - Class Dependent Features (CDFs). We use CDFs to improve the accuracy of classification and at the same time control computational expense by tackling the curse of dimensionality. In order to demonstrate the generality of this technique, it is applied to handwritten digit recognition and text categorization.
In this paper, the problem of classifying synthetic and natural texture images is addressed. To tackle this problem, an innovative method is proposed that combines concepts from corrosion modeling and cellular automata to generate a texture descriptor. The core processes of metal (pitting) corrosion are identified and applied to texture images by incorporating the basic mechanisms of corrosion in the transition function of the cellular automaton. The surface morphology of the image is analyzed before and during the application of the transition function of the cellular automaton. In each iteration the cumulative mass of corroded product is obtained to construct each of the attributes of the texture descriptor. In a final step, this texture descriptor is used for image classification by applying Linear Discriminant Analysis. The method was tested on the well-known Brodatz and Vistex databases. In addition, in order to verify the robustness of the method, its invariance to noise and rotation were tested. To that end, different variants of the original two databases were obtained through addition of noise to and rotation of the images. The results showed that the method is effective for texture classification according to the high success rates obtained in all cases. This indicates the potential of employing methods inspired on natural phenomena in other fields.
Texture analysis and classification remain as one of the biggest challenges for the field of computer vision and pattern recognition. On this matter, Gabor wavelets has proven to be a useful technique to characterize distinctive texture patterns. However, most of the approaches used to extract descriptors of the Gabor magnitude space usually fail in representing adequately the richness of detail present into a unique feature vector. In this paper, we propose a new method to enhance the Gabor wavelets process extracting a fractal signature of the magnitude spaces. Each signature is reduced using a canonical analysis function and concatenated to form the final feature vector. Experiments were conducted on several texture image databases to prove the power and effectiveness of the proposed method. Results obtained shown that this method outperforms other early proposed method, creating a more reliable technique for texture feature extraction.
In this work, we propose a novel technique for obtaining descriptors of gray-level texture images. The descriptors are provided by applying a multiscale transform to the fractal dimension of the image estimated through the probability (Voss) method. The effectiveness of the descriptors is verified in a classification task using benchmark over texture datasets. The results obtained demonstrate the efficiency of the proposed method as a tool for the description and discrimination of texture images.
The economic and production losses in agricultural industry worldwide are due to the presence of diseases in the several kinds of fruits. In this paper, a method for the classification of fruit diseases is proposed and experimentally validated. The image processing based proposed approach is composed of the following main steps; in the first step K-Means clustering technique is used for the defect segmentation, in the second step color and textural cues are extracted and fused from the segmented image, and finally images are classified into one of the classes by using a Multi-class Support Vector Machine. We have considered diseases of apple as a test case and evaluated our approach for three types of apple diseases namely apple scab, apple blotch and apple rot and normal apples without diseases. Our experimentation points out that the proposed fusion scheme can significantly support accurate detection and automatic classification of fruit diseases.
The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this paper, we propose a whole-image CNN regression model, by removing the full connection layer and training the network with continuous feature maps. This is a generic regression framework that fits many applications. We demonstrate this method through two tasks: simultaneous face detection & segmentation, and scene saliency prediction. The result is comparable with other models in the respective fields, using only a small scale network. Since the regression model is trained on corresponding image / feature map pairs, there are no requirements on uniform input size as opposed to the classification model. Our framework avoids classifier design, a process that may introduce too much manual intervention in model development. Yet, it is highly correlated to the classification network and offers some in-deep review of CNN structures.
Topological data analysis offers a rich source of valuable information to study vision problems. Yet, so far we lack a theoretically sound connection to popular kernel-based learning techniques, such as kernel SVMs or kernel PCA. In this work, we establish such a connection by designing a multi-scale kernel for persistence diagrams, a stable summary representation of topological features in data. We show that this kernel is positive definite and prove its stability with respect to the 1-Wasserstein distance. Experiments on two benchmark datasets for 3D shape classification/retrieval and texture recognition show considerable performance gains of the proposed method compared to an alternative approach that is based on the recently introduced persistence landscapes.
In this on-going work, I explore certain theoretical and empirical implications of data transformations under the PCA. In particular, I state and prove three theorems about PCA, which I paraphrase as follows: 1). PCA without discarding eigenvector rows is injective, but looses this injectivity when eigenvector rows are discarded 2). PCA without discarding eigen- vector rows preserves pair-wise distances, but tends to cause pair-wise distances to shrink when eigenvector rows are discarded. 3). For any pair of points, the shrinkage in pair-wise distance is bounded above by an L1 norm reconstruction error associated with the points. Clearly, 3). suggests that there might exist some correlation between shrinkages in pair-wise distances and mean square reconstruction error which is defined as the sum of those eigenvalues associated with the discarded eigenvectors. I therefore decided to perform numerical experiments to obtain the corre- lation between the sum of those eigenvalues and shrinkages in pair-wise distances. In addition, I have also performed some experiments to check respectively the effect of the sum of those eigenvalues and the effect of the shrinkages on classification accuracies under the PCA map. So far, I have obtained the following results on some publicly available data from the UCI Machine Learning Repository: 1). There seems to be a strong cor- relation between the sum of those eigenvalues associated with discarded eigenvectors and shrinkages in pair-wise distances. 2). Neither the sum of those eigenvalues nor pair-wise distances have any strong correlations with classification accuracies. 1
Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger architectures. Though CNNs achieved promising external classification behavior, understanding of their internal work mechanism is still limited. In this work, we attempt to understand the internal work mechanism of CNNs by probing the internal representations in two comprehensive aspects, i.e., visualizing patches in the representation spaces constructed by different layers, and visualizing visual information kept in each layer. We further compare CNNs with different depths and show the advantages brought by deeper architecture.
Image feature classification is a challenging problem in many computer vision applications, specifically, in the fields of remote sensing, image analysis and pattern recognition. In this paper, a novel Self Organizing Map, termed improved SOM (iSOM), is proposed with the aim of effectively classifying Mammographic images based on their texture feature representation. The main contribution of the iSOM is to introduce a new node structure for the map representation and adopting a learning technique based on Kohonen SOM accordingly. The main idea is to control, in an unsupervised fashion, the weight updating procedure depending on the class reliability of the node, during the weight update time. Experiments held on a real Mammographic images. Results showed high accuracy compared to classical SOM and other state-of-art classifiers.
The continual growth of high speed networks is a challenge for real-time network analysis systems. The real time traffic classification is an issue for corporations and ISPs (Internet Service Providers). This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as a pipeline consisting of three modules: packet capture and pre-processing, flow reassembly, and classification with Machine Learning (ML). The modules are built as concurrent processes with well defined data interfaces between them so that any module can be improved and updated independently. In this pipeline, the flow reassembly function becomes the bottleneck of the performance. In this implementation, was used a efficient method of reassembly which results in a average delivery delay of 0.49 seconds, approximately. For the classification module, the performances of the K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexible Naive Bayes (FNB) and AdaBoost Ensemble Learning Algorithm are compared in order to validate our approach.
Text categorization is the process of grouping documents into categories based on their contents. This process is important to make information retrieval easier, and it became more important due to the huge textual information available online. The main problem in text categorization is how to improve the classification accuracy. Although Arabic text categorization is a new promising field, there are a few researches in this field. This paper proposes a new method for Arabic text categorization using vector evaluation. The proposed method uses a categorized Arabic documents corpus, and then the weights of the tested document's words are calculated to determine the document keywords which will be compared with the keywords of the corpus categorizes to determine the tested document's best category.
Melanoma spreads through metastasis, and therefore it has been proven to be very fatal. Statistical evidence has revealed that the majority of deaths resulting from skin cancer are as a result of melanoma. Further investigations have shown that the survival rates in patients depend on the stage of the infection; early detection and intervention of melanoma implicates higher chances of cure. Clinical diagnosis and prognosis of melanoma is challenging since the processes are prone to misdiagnosis and inaccuracies due to doctors subjectivity. This paper proposes an innovative and fully functional smart-phone based application to assist in melanoma early detection and prevention. The application has two major components; the first component is a real-time alert to help users prevent skin burn caused by sunlight; a novel equation to compute the time for skin to burn is thereby introduced. The second component is an automated image analysis module which contains image acquisition, hair detection and exclusion, lesion segmentation, feature extraction, and classification. The proposed system exploits PH2 Dermoscopy image database from Pedro Hispano Hospital for development and testing purposes. The image database contains a total of 200 dermoscopy images of lesions, including normal, atypical, and melanoma cases. The experimental results show that the proposed system is efficient, achieving classification of the normal, atypical and melanoma images with accuracy of 96.3%, 95.7% and 97.5%, respectively.
A fast forward feature selection algorithm is presented in this paper. It is based on a Gaussian mixture model (GMM) classifier. GMM are used for classifying hyperspectral images. The algorithm selects iteratively spectral features that maximizes an estimation of the classification rate. The estimation is done using the k-fold cross validation. In order to perform fast in terms of computing time, an efficient implementation is proposed. First, the GMM can be updated when the estimation of the classification rate is computed, rather than re-estimate the full model. Secondly, using marginalization of the GMM, sub models can be directly obtained from the full model learned with all the spectral features. Experimental results for two real hyperspectral data sets show that the method performs very well in terms of classification accuracy and processing time. Furthermore, the extracted model contains very few spectral channels.
Sparse coding can learn good robust representation to noise and model more higher-order representation for image classification. However, the inference algorithm is computationally expensive even though the supervised signals are used to learn compact and discriminative dictionaries in sparse coding techniques. Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference. But the SNNM module ignores the sparse representations. Therefore, we propose a sparse SNNM module by adding the mixed-norm regularization (l1/l2 norm). The sparse SNNM modules are further stacked to build a sparse deep stacking network (S-DSN). In the experiments, we evaluate S-DSN with four databases, including Extended YaleB, AR, 15 scene and Caltech101. Experimental results show that our model outperforms related classification methods with only a linear classifier. It is worth noting that we reach 98.8% recognition accuracy on 15 scene.