The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A new method is presented which combines a deterministic analytical method and a probabilistic measure to classify rock types on the basis of their hyperspectral curve shape. This method is a supervised learning algorithm using Gaussian Processes (GPs) and the Observation Angle Dependent (OAD) covariance function. The OAD covariance function makes use of the properties of the Spectral Angle Mapper...
In Pattern recognition, ensembles of classifiers are used to increase the performance and accuracy of classification systems. The creation of ensembles, selection of base classifiers and combining the decisions of the classifiers is an active research area. In this paper we propose a method of ensemble creation that is based on fuzzy clustering (Fuzzy C Mean) and fuzzy entropy; and named as Fuzzy...
Nowadays the most active research in supervised learning includes an integration of several base classifiers into the combined classification system. Such systems are known under the names multiple classifiers, ensembles methods. This topic attracts an interest of machine learning researchers as multiple classifiers are often much more accurate than the component classifiers that make them up. In...
Most enterprise data is distributed in multiple relational databases with expert-designed schema. Using traditional single-table machine learning techniques over such data not only incur a computational penalty for converting to a ”flat” form (mega-join), even the human-specified semantic information present in the relations is lost. In this paper, we present a two-phase hierarchical meta-classification...
We point out a problem inherent in the optimization scheme of many popular feature selection methods. It follows from the implicit assumption that higher feature selection criterion value always indicates more preferable subset even if the value difference is marginal. This assumption ignores the reliability issues of particular feature preferences, over-fitting and feature acquisition cost. We propose...
Decomposition methods are multiclass classification schemes where the polychotomy is reduced into several dichotomies. Each dichotomy is addressed by a classifier trained on a training set derived from the original one on the basis of the decomposition rule adopted. These new training sets may present a disproportion between the classes, harming the global recognition accuracy. Indeed, traditional...
The Research of detection malware using machine learning method attracts much attention recent years. However, most of research focused on code analysis which is signature-based or analysis of system call sequence in Linux environment. Obviously, all methods have their strengths and weaknesses. In this paper, we concentrate on detection Trojan horse by operation system information in Windows environment...
A prospective buyer interested in a particular item may find out information about the item from various sources, including product reviews. With interactive information sharing facilitated by Web 2.0, a lot of product reviews are available on the web. For a popular item with a large number of reviews, a prospective buyer could use some help in selecting only reviews of interest, such as, only positive...
PSO has been proved as an effective supervised learning system in recent years, but it's not an effective method for incremental learning problems. Aiming at the incremental learning target for classification, a hybrid algorithm of Particle Swarm Optimization (PSO) and Artificial Immune System (AIS) called Immune based PSO (IPSO) is presented in this paper. IPSO inherits the incremental learning ability...
A multi-view based active learning method (AMDWVE) is proposed as a means to optimally construct the training set for supervised classification of hyperspectral data, thereby reducing the effort required to acquire ground reference data. The method explores the intrinsic multi-view information embedded in hyperspectral data. By adaptively and quantitatively measuring the disagreement level of different...
The k-nearest neighbors classifier is simple and often results in good classification performance on problems with unknown and non-normal distributions. However, its selected nearest neighbors on noisy, sparse, or imbalanced data are often inconsistent with our intuition and in turn leads to the worse performance. This paper applies Gestalt visual perceptual laws to design a new KNN classifie r. It...
Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic...
Learning algorithm evaluation is usually focused on classification performance. However, the characteristics and requirements of real-world applications vary greatly. Thus, for a particular application, some evaluation criteria are more important than others. In fact, multiple criteria need to be considered to capture application-specific trade-offs. Many multi-criteria methods can be used for the...
Discretization algorithms have played an important role in many areas such as artificial intelligence, data mining and machine learning. In this paper, we propose an effective bottom-up discretization algorithm, namely EBDA. Firstly, we present a novel merging criterion which not only considers the effect of variance on degrees of freedom in the two merged intervals but also the effect of variance...
Many methods of hyperspectral data classification require the adjustment of learning parameters for their success. To this end, one may fix the learning parameters, offer a functional-based parameter decay, or use a step-wise decrement of the learning parameters after a fixed number of training steps. Each of the three methods described rely on the expertise of user and do not necessarily lend themselves...
Classification is one of the most important procedures in high-resolution remotely sensed image information extraction. This paper introduced Adaboost-SVM algorithm to IKONOS image classification. The classification performance of Adabost-SVM and single SVM were quantitatively analyzed and qualitatively evaluated. The results show that: In the case of small training samples, Adaboost-SVM outperforms...
We describe a proof of concept for class knowledge transfer from a labeled hyperspectral image to an unlabeled image, captured with a different (hyper-/multi-spectral) sensor, when the spatial extents of the images partially overlap. By defining a set of spatio-spectral correspondences between the labeled source image and the unlabeled target image, we create a mapping between the images we can use...
This paper aims to challenge the problem of finding accurate and relevant rules for the task of classification. The scope is to improve the accuracy, or at least to provide a comparable accuracy measure, for classification algorithms implemented so far. Because the task of classification must be as accurate as possible, the paper proposes a method based on genetic algorithms to enhance the speed and...
Most classification studies are done by using all the objects data. It is expected to classify objects by using some subsets data in the total data. A rough set based reduct is a minimal subset of features, which has almost the same discernible power as the entire conditional features. Here, we propose a greedy algorithm to compute a set of rough set reducts which is followed by the k-nearest neighbor...
Semi-supervised kernel learning is an important technique for classification and has been actively studied recently. In this paper, we propose a new semi-supervised spectral kernel learning method to learn a new kernel matrix with both labeled data and unlabeled data, which tunes the spectral of a standard kernel matrix by maximizing the margin between two classes. Our approach can be turned into...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.