Sharif Digital Repository

Purpose: Cardiac arrhythmia is one of the most common heart diseases that can have serious consequences. Thus, heartbeat arrhythmias classification is very important to help diagnose and treat. To develop the automatic classification of heartbeats, recent advances in signal processing can be employed. The Hidden Markov Model (HMM) is a powerful statistical tool with the ability to learn different dynamics of the real time-series such as cardiac signals. Materials and Methods: In this study, a hierarchy of HMMs named Layered HMM (LHMM) was presented to classify heartbeats from the two-channel electrocardiograms. For training in the first layer, the morphology of the heartbeats was used as... 

Social tagging is a process in which many users add metadata to a shared content. Through the past few years, the popularity of social tagging has grown on the web. In this paper we investigated the use of social tags for web page classification: adding new web pages to an existing web directory. A web directory is a general human-edited directory of web pages. It classifies a collection of pages into a wide range of hierarchical categories. The problem with manual construction and maintenance of web directories is the significant need of time and effort by human experts. Our proposed method is based on applying different automatic approaches of using social tags for extending web... 

Recently, tree structures have become a popular way for storing and manipulating huge amount of data. Classification of these data can facilitate storage, retrieval, indexing, query answering and different processing operations. In this paper, we present C-Classifier and M-Classifier algorithms for rule based classification of tree structured data. These algorithms are based on extracting especial tree patterns from training dataset. These tree patterns, i.e. closed tree patterns and maximal tree patterns are capable of extracting characteristics of training trees completely and non-redundantly. Our experiments show that M-Classifier significantly reduces running time and complexity. As... 

This paper presents a novel hybrid approach for intrusion detection in computer networks. The proposed approach combines an evolutionary based fuzzy system with an artificial immune system to generate high quality fuzzy classification rules. The performance of final fuzzy classification system has been investigated using the KDD-Cup99 benchmark dataset. The results indicate that in comparison to several traditional techniques, such as C4.5, Naïve Bayes, k-NN and SVM, the proposed hybrid approach achieves better classification accuracies for most of the classes of the intrusion detection classification problem. Therefore, the resulted fuzzy classification rules can be used to produce a... 

Data mining is a very popular technique which is successfully used in many areas. The aim of this paper is to present a Hybrid model for data classification from input datasets. The proposed model extracts knowledge using fuzzy rule based systems and performs classification task by fuzzy if-then rules. The proposed method performs the classification task and extracts required knowledge using fuzzy rule based systems which consists of fuzzy if-then rules. In order to do so the hybrid ant colony and simulated annealing algorithms have been used to optimize extracted fuzzy rule set. "ACSA", a self development data mining software system based on swarm intelligence, is applied to experiment on... 

We present an attempt to improve the performance of multi-class image segmentation systems based on a multilevel description of segments. The multi-class image segmentation system used in this paper marks the segments in an image, describes the segments via multilevel feature vectors and passes the vectors to a multi-class object classifier. The focus of this paper is on the segment description section. We first propose a robust, scale-invariant texture feature set, named directional differences (DDs). This feature is designed by investigating the flaws of conventional texture features. The advantages of DDs are justified both analytically and experimentally. We have conducted several... 

Dimensionality reduction is a necessary task in data mining when working with high dimensional data. A type of dimensionality reduction is feature selection. Feature selection based on feature ranking has received much attention by researchers. The major reasons are its scalability, ease of use, and fast computation. Feature ranking methods can be divided into different categories and may use different measures for ranking features. Recently, ensemble methods have entered in the field of ranking and achieved more accuracy among others. Accordingly, in this paper a Heterogeneous ensemble based algorithm for feature ranking is proposed. The base ranking methods in this ensemble structure are... 

Computer-Aided Diagnosis (CAD) systems are widely used for detection of various kinds of abnormalities in mammography images. Masses are one type of these abnormalities which are mostly characterized by their margin and shape. For classification of masses proper features are needed to be extracted. However, the number of well-known features for describing margin is much fewer than geometrical, shape, and textural ones. In addition, most of the existing margin features are highly dependent on segmentation accuracy. In this work, new features for describing margin of masses are presented which can handle inaccuracies in segmentation. These features are obtained from a set of waveforms by... 

In large databases, availability of labeled training data is mostly prohibitive in classification. Semi-supervised algorithms are employed to tackle the lack of labeled training data problem. Video databases are the epitome for such a scenario; that is why semi-supervised learning has found its niche in it. Graph-based methods are a promising platform for semi-supervised video classification. Based on the multiview characteristic of video data, different features have been proposed (such as SIFT, STIP and MFCC) which can be utilized to build a graph. In this paper, we have proposed a new classification method which fuses the results of manifold regularization over different graphs. Our... 

One of the main challenges of data streams is the occurrence of concept drift. Concept drift is the change of target (or feature) distribution, and can occur in different types: sudden, gradual, incremental or recurring. Because of the forgetting mechanism existing in the data stream learning process, recurring concepts has received much attention recently, and became a challenging problem. This paper tries to exploit the existence of recurring concepts in the learning process and improve the classification of data streams. It uses a pool of concepts to detect the reoccurrence of a concept using two methods: a Bayesian, and a heuristic method. Two approaches are used in the classification... 

This study focuses on the mode classification of phones speaker modes using GMM 1. In this regard, speech data in both enabled and disabled speaker modes of cell phones and telephones were collected, processed and classified into two different categories. The different mixture numbers (1 to 4) of GMM and wave files sizes of 10, 20, 40 and 80 kb were tested in order to obtain an optimal condition for classification. The GMM method attained 87.99% correct classification rate on test data. This classification is important for speech enabled IVR 2 systems [1], dialog systems and many systems in speech processing in the sense that it could help to load an optimum model for increasing system... 

In this letter, a spatially weighted sparse unmixing approach is proposed as a front-end for hyperspectral image classification using a linear SVM. The idea is to partition the pixels of a hyperspectral image into a number of disjoint spatial neighborhoods. Since neighboring pixels are often composed of similar materials, their sparse codes are encouraged to have similar sparsity patterns. This is accomplished by means of a reweighted ℓ1 framework where it is assumed that fractional abundances of neighboring pixels are distributed according to a common Laplacian Scale Mixture (LSM) prior with a shared scale parameter. This shared parameter determines which endmembers contribute to the group... 

In multi-label classification problems, each instance can simultaneously have multiple labels. Since the whole number of available labels in real-world applications tends to be (very) large, multi-label classification becomes an important challenge and recently label space dimension reduction (LSDR) methods have received attention. These methods first encode the output space to a low-dimensional latent space. Afterwards, they predict the latent space from the feature space and reconstruct the original output space using a suitable decoding method. The encoding method can be implicit which learns a code matrix in the latent space by solving an optimization problem or explicit which learns a... 

In this paper, we propose and compare various approaches of feature and decision fusion for human action classification in a multi-view framework. The key difference between the employed methods is in the nature of extracted features in each view and the stage we fuse data from all cameras to classify the activity. At the feature extraction stage we utilize three different methods. At the decision making stage, the features obtained by the cameras are combined in a single classifier, or a classifier for each camera produces a local decision which is combined with decisions from other cameras for a global decision. We have employed our method on a fall detection dataset, and all the fusion... 

In this paper, a novel classification approach is presented. This approach uses fuzzy if-then rules for classification task and employs a hybrid optimization method to improve the accuracy and comprehensibility of obtained outcome. The mentioned optimization method has been formulated by simulated annealing and genetic algorithm. In fact, the genetic operators have been used as perturb functions at the core of simulated annealing heuristic. Results of proposed approach have been compared with several well-known methods such as Naïve Bayes, Support Vector Machine, Decision Tree, k-NN, and GBML, and show that our method performs the classification task as well as other famous algorithms. ©... 

Multi-label classification with a large set of labels is a challenging task. Label-Space Dimension Reduction (LSDR) is the most popular approach that addresses this problem. LSDR methods project the high-dimensional label vectors onto a low-dimensional space that can be predicted from the feature space. Many LSDR methods assume that the training data provide complete label vector for all training samples while this assumption is usually violated particularly when label vectors are high dimensional. In this paper, we propose a probabilistic model that has an effective mechanism to handle missing and noisy labels. In the proposed Bayesian network model, a set of auxiliary random variables,... 

Traditional learning algorithms cannot perform well in scenarios where training data (source domain data) that are used to learn the model have a different distribution with test data (target domain data). The domain adaptation that intends to compensate this problem is an important capability for an intelligent agent. This paper presents a domain adaptation method which learns to adapt the data distribution of the source domain to that of the target domain where no labeled data of the target domain is available (and just unlabeled data are available for the target domain). Our method jointly learns a low dimensional representation space and an adaptive classifier. In fact, we try to find a... 

Multi-label classification is a learning task in which each data sample can belong to more than one class. Until now, some methods that are based on reducing the dimensionality of the label space have been proposed. However, these methods have not used specific properties of the label space for this purpose. In this paper, we intend to find a hidden space in which both the input feature vectors and the label vectors are embedded. We propose a modified Non-Negative Matrix Factorization (NMF) method that is suitable for decomposing the label matrix and finding a proper hidden space by a feature-aware approach. We consider that the label matrix is binary and also in this matrix some deserving...