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.
The development of robust object-oriented classification approaches suitable for medium to high spatial resolution satellite imagery provides a valid alternative to traditional pixel-based classification approaches. In the past, Support Vector Machines (SVM) have been tested and evaluated only as pixel-based image classifiers. Moving from pixel-based analysis to object-based analysis, a fuzzy classification...
Sleep apnea contributes to a variety of health threatening problems. However, there is a extremely low public and medical awareness of this disease. In order to identify sleep apnea/hyopnea, some effective features have been extracted from ECG signal, PPG signal and EEG signal. In this work, a novel combined of features characterizing physiological signals for monitoring epochs of sleep apnea is presented...
Prediction of preterm labor is of great importance to reduce neonatal death. Analysis of electrohysterogram (EHG) could be considered as a proper tool for this aim. In this paper, the statistical and non-linear features have been extracted from EHG signals and then Support Vector machine (SVM) has been applied for classification between term and preterm labor. The dataset of this research consists...
The Ultra-Wide Band (UWB) signals recently have attracted increasing attention in the area of material identification due to their potential of providing very high data rates at relatively short ranges and their capability of being obtained nondestructively and contactless. The Support Vector Machines (SVM) offers one of the most robust and accurate classification capability among the well-known such...
Over the past decade, the field of automatic speaker recognition has been the subject of extensive research looking for an efficient determination of a person's identity. Despite the essential role played by acoustic characteristics in order to discriminate between speakers. The research of discriminative information about a person remains a major challenge. The main objective of this paper is to...
In this paper, we present, first, a new method for color feature extraction based on SURF detectors. Then, we proved its efficiency for flower image classification. Therefore, we described visual content of the flower images using compact and accurate descriptors. These features are combined and the learning process is performed using a multiple kernel framework with a SVM classifier. The proposed...
To relieve the curse of dimensionality in functional magnetic resonance imaging (fMRI), we combine analysis of variance (ANOVA) with a support vector machine (SVM) to form a feature-based classification method. ANOVA is applied to find a more compact representation of the data by extracting features from fMRI images. A linear kernel SVM classifier is then trained on the selected features. Combining...
Research on scalable machine learning algorithms has gained a considerable amount of traction since the exponential growth in data assets during the past decades. Many Big Data applications resort to somewhat "simple" data modelling techniques due to the computational constraints associated with more complex models. Simple models, while being very efficient to estimate, often fail to capture...
Analysis of safety inventory decision is of great significance to effectively reduce the inventory cost and fund occupancy rate, and to ensure timely material supply of power grid, while analysis of safety inventory decision of power companies is based on material consumption forecasting data. As the industry particularity of power company material consumption, the existing problems of data are not...
Face recognition for biometric purposes has an advantage of being a non-contact process. Various face recognition algorithms has been proposed in the literature. The face recognition system mainly consists of two steps i.e. feature extraction / reduction and classification. One of the most popular tool, Principal Component Analysis (PCA) is used for feature extraction. For classification purpose,...
Machine learning can play a very important role in various crucial applications like data mining and pattern recognition. Machine learning techniques have been widely used in drug discovery and development, particularly in the areas of chemo-informatics, bioinformatics and other types of pharmaceutical research. It has been demonstrated that they are suitable for large high dimensional data, and the...
Parkinson is a disease attacking the nervous system and worsens the work of nervous system over time. This disease is incurable, the therapy existing today is only able to help to relieve the symptoms. Hence, an early diagnose is deemed essential to determine an accurate type of therapy. Parkinson disease can be diagnosed by examining the symptoms apparent to the patient. One of the symptoms is the...
Nature language processing is an important part in data mining, which counts a lot in the internet age. Feature extraction effects the accuracy of text classification. This paper proposes a method of iterative feature space evolution to optimize the result. Adjusting the extended dictionary and the stop word list, we optimize the feature space time and again to get a better classifier model. The final...
In this paper, a novel unsupervised method for learning sparse features combined with support vector machines for classification is proposed. The classical SVM method has restrictions on the large-scale applications. This model uses sparse auto encoder, a deep learning algorithm, to improve the performance. Firstly, we use multiple layers of sparse auto encoder to learn the features of the data. Secondly,...
This work focuses on automatic prediction of the writer's biometrics including gender, handedness and age information. The proposed prediction system is based on the use of Histogram of Oriented Gradients (HOG), which aims to extract gradient directions from the handwritten text. The prediction task is achieved using SVM classifier. Experiments performed on IAM and KHATT datasets, reveal promising...
This paper is an exploration to find a way to get the person attributes in profiles. Considering those attributes exists in large volume of unstructured data, and it is very difficult to gain in a short time. So, we use a method combing the pattern and SVM to extract the person attributes. Firstly, we collect many raw profiles in websites by our configurable crawler. Secondly, we use statistic methods...
In question answering system, the process of classifying a question to appropriate class and identification of the focus word play key role in determining accurate answer. In this paper, we propose an integrated pattern matching and machine learning approach for higher education domain that focuses on factoid question answering. We have developed a question taxonomy for higher education domain and...
P300 speller for Brain-Computer Interface systems aim to provide a direct communication between computer - machine and human brain, without any muscular activity. The communication is provided by detecting the presence of P300 Event Related Potentials (ERPs) in the electroencophelogram (EEG) signals, recorded from scalp. The major problem associated with P300 spellers is the stratification of EEGs...
The application of kernel function made support vector machine one of the research focuses in machine learning field. However, single kernel function is difficult to process complex data efficiently. Multiple kernel method is a common solution for this problem in recent years. The commonly used multiple kernel function is a weighted combination of different kernel function. It lacks the pertinence...
This paper addresses the problem of recognizing handwritten numerals for Gujarati Language. Three methods are presented for feature extraction. One belongs to the spatial domain and other two belongs to the transform domain. In first technique, a new method has been proposed for spatial domain which is based on Freeman chain code. This method obtains the global direction by considering n × n neighbourhood...
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.