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.
Our research involves an original method for the intensity of speech defect monitoring in child patients with developmental dysphasia. We have drawn upon a body of knowledge consisting of phonetics, acoustics and ANN applications. The aim of the paper is to compare two methods based on the vowel detector, both of which classify the parameter of developmental dysphasia, with the results of the speech...
This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by genetic algorithms through Mandarin...
In this paper we introduce a novel framework for image classification using local visual descriptors ¨C group fusion sparse representation (GFSR), which casts the classification problem as a linear regression model with sparse constraints of the regression coefficients. Considering the intrinsic discriminative property of prior class label information, and the requirement of local consistency within...
Steganalysis is detecting and decoding hidden data within a given media and is taken as a countermeasure to steganography. There has been quite some effort in audio steganalysis for additive embedding model. But, results are disappointing when they distinguish the cover-audio signal with multiplicative noise and the stego-audio signal. In this paper, multiplicative noise is changed to additive noise...
Web contents are going overwhelming today. The numerous online documents, webpages, e-books, etc. are much useful but obtaining them is also time-consuming. Text categorization is one of the solutions to the issue. For all text categorization method, Support Vector Machines (SVM) is one of the most acceptable one. However, to perform more efficiently on webpages, it is necessary to add improvements...
In this paper, we proposed an approach to Musical Instrument Automatic Recognition. We used seven different musical instruments to be played simultaneously from solos to quartets. Our data have 296 feature vectors that used in audio signal classification by MLP neural networks and K-NN algorithm. Finally, MLP achieved as the best neural network in musical instrument recognition.
Spam has created a significant security problem for computer users everywhere. Spammers take an advantage of defrauds to cover parts of messages that can be used for identification of spam. For instance, a spammer does not need to consume much cost and bandwidth for sending junk mails even more than one hundred emails. On the other hand, from the feature selection perspective, one of the specific...
Representation of depth in a real world environment is an essential attribute of its semantic representation. A coarse estimate of image-depth (defined as mean distance between the object and the observer) is relevant for identifying the context of the scene and can be used to facilitate search and recognition of objects. In this paper, a GLCM based scheme is proposed to analyze the depth information...
K-nearest neighbour (KNN) is a supervised classification technique that is widely used in many fields of study to classify unknown queries based on some known information about the dataset. KNN is known to be robust and simple to implement when dealing with data of small size. However it performs slowly when data are large and have high dimensions. Therefore, KNN classifiers can benefit from the parallelism...
Classification and prediction are effective tools in anomaly and fault detection. They can be used in development of a continuous learning prediction method. Inaccurate classification will result in either too many or too few anomalies or under- and over-diagnosis. The confidence of prediction relies on the accurate determination of class centers and borders based on the adequate training data. This...
Aimed at the imbalance of training samples, isolated points, and the importance degree of class samples of different three questions, this paper put forward a improvement weighted support vector machine (SVM), and give the method of determine the integrated weights, the simulation results show the effectiveness of the method.
This paper proposes a framework for automatic video annotation by exploiting gaze movements during interactive video retrieval. In this context, we use a content-based video search engine to perform video retrieval, during which, we capture the user eye movements with an eye-tracker. We exploit these data by generating feature vectors, which are used to train a classifier that could identify shots...
Peer-to-peer (P2P) networks are becoming more and more popular. eMule is a typical example. In this paper we aim to automatically and accurately find sensitive files in eMule through rating them based on text classification and we propose two feature expansion methods to improve the accuracy of rating. Experimental results demonstrate that the performance improvement of rating is significant by using...
In this paper, a Boosted-PCA algorithm is proposed for efficient classification of two class data. Conventionally, in classification problems, the roles of feature extraction and classification have been distinct, i.e., a feature extraction method and a classifier are applied sequentially to classify input variable into several categories. In this paper, these two steps are combined into one resulting...
In previous work we developed a support vector machine (SVM) approach for detection of microcalcifications (MCs) in mammogram images, which was demonstrated to outperform several existing methods for MC detection in the literature. In this work, we explore whether we can further improve the performance of the SVM detector by exploiting the fact that MCs are inherently invariant to their spatial orientation...
The traditional KNN algorithm for text classification has some insufficiencies, an improved KNN algorithm has been presented in this paper. By use of the clustering center vector, we put the distance of the be classified text and the text category into the similarity calculation formula, and take the ratio of the number of common features appear in two texts and the maximum number of respective features...
Recently, there is a popular belief that classifier combination of different architecture could complement each other for improving results performance. In this paper we introduce a framework to combine results of multiple classifiers for offline Arabic handwriting recognition, by introducing a new scheme of combination of Multi Layer Perceptron and ART1 networks. Besides using two different recognition...
In this paper we propose a new approach to video based face recognition. Our work is based on the Sparse Classification approach which assumes that each test sample can be formed by a linear combination of the training samples of the correct class. Based on this assumption, we formulate the classification problem as one of joint sparse recovery of Multiple Measurement Vectors (MMV). This requires...
This paper explores the possibility of using the Hierarchical Temporal Memory (HTM) machine learning technology to create a profitable software agent for trading financial markets. Technical indicators, derived from intraday tick data for the E-mini S&P 500 futures market (ES), were used as features vectors to the HTM models. All models were configured as binary classifiers, using a simple buy-and-hold...
It is a great challenge for information technology that how to organize and manage large amount of document data, and find users' interested information quickly and exactly. Text classification can achieve the goal of information distributaries and solve the problem of information disorder, and then it can offer the convenience to users to make decisions. Centroid classifier is one of the most efficient...
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.