Search

Mean shift tracking fails when the velocity of target is so large that the target's window kernel in the previous frame can not cover the target in the current frame. Combination of mean shift and single Kalman filter also fails when the target's velocity changed suddenly. To deal with the problem of tracking image target that has large and changing velocity, an efficient image tracking method integrated mean shift and double model filters is proposed. Two motion models can switch each other by using a probabilistic likelihood. Experiment results show the method integrated mean shift and double model filters can successfully keep tracking target, no matter the target's velocity is large or small, changing or constant, with modest requirement of computation resource. [ABSTRACT FROM AUTHOR]

In this paper, a human action recognition method using a hybrid neural network is presented. The method consists of three stages: preprocessing, feature extraction, and pattern classification. For feature extraction, we propose a modified convolutional neural network (CNN) which has a three-dimensional receptive field. The CNN generates a set of feature maps from the action descriptors which are derived from a spatiotemporal volume. A weighted fuzzy min-max (WFMM) neural network is used for the pattern classification stage. We introduce a feature selection technique using the WFMM model to reduce the dimensionality of the feature space. Two kinds of relevance factors between features and pattern classes are defined to analyze the salient features. [ABSTRACT FROM AUTHOR]

This Letter deals with the global exponential synchronization of a class of chaotic neural networks with time delays. Based on the the Halanay inequality technique and the Lyapunov stability theory, a delay-independent and decentralized control law is derived to ensure the exponential synchronization of the model and the simpler, less conservative and more efficient results are easy to be verified in engineering applications. Finally, an illustrative example is given to demonstrate the effectiveness of the presented synchronization scheme. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a common tool to explore brain activities ranging from concentrated cognitive efforts to sleepiness. For the issue of sleepiness, pupil behavior can provide some information regarding alertness. The issue of sleepiness can be reflected by EEG energy. Specifically, intrusion of EEG theta wave activity into the beta activity of active wakefulness has been interpreted as ensuing sleepiness. This paper develops an innovative signal classification method that is capable of differentiating subjects with sleep disorder of obstructive sleep apnea (OSA) which cause excessive daytime sleepiness (EDS) from normal control subjects who do not have a sleep disorder. The theta energy ratios are calculated from the 2-second sliding windows by Fourier transform. An artificial neural network of modified ART2 is utilized to identify subjects with OSA from a combined group of subjects including healthy controls. This grouping from the neural network is then compared with the actual diagnostic classification of subjects as OSA or healthy controls and it is found to be 91% accurate in differentiating between the two groups. [ABSTRACT FROM AUTHOR]

Shape description is the precondition for shape matching and retrieval. The more robust and stable primitives to describe shapes are global topological properties, but obtaining global topological properties is still an obstacle in computer vision. Motivated by the difference sensitivity of short-range connection in biology vision, we present a novel global descriptor to describe the entire topology of simple closed 2D shape in this paper. We employ two novel strategies - the zigzag rule, which approximates shape to an elaborate polygonal curve, and cost function which combines global configurations as well as local information of the line stimulations as our punishments. With these two key steps the descriptor is robust to translation, scaling and rotation. Experimental results show the model gain good performance on matching and retrieval for silhouettes. Even for images with occlusion the result is excellent and reasonable. [ABSTRACT FROM AUTHOR]

For the optional control to the trans-femoral prosthesis and natural gait, an ongoing investigation of lower limb prosthesis model with myoelectrical control was presented. In this research, the surface electromyographic signals of lower limb were extracted to be switch signal, and translate into movement information. Considering every muscle's different physiologic tendency, fuzzy support vector regression method was applied to establish an intelligent black box that can interpret the physiological signals to accurate information of knee joint angle. It achieves a comparable or better performance than other methods, and provides a more native gait to the prosthesis user. [ABSTRACT FROM AUTHOR]

In [1], we developed two methods to automatically identify the contribution of the recording reference signal from multi-channel intracranial Electroencephalography (iEEG) recordings. In this study, we subtract the reference recording contribution to iEEG and obtain corrected iEEG. We then investigate three commonly used iEEG metrics: spectral power, phase synchrony, and magnitude squared coherence (MSC) for common referential iEEG, corrected iEEG and bipolar montage iEEG. We find significant differences among the three iEEG metrics, and are able to determine the contribution from the recording reference to each metric. Generally, reference signals with smaller amplitude yield lower phase synchrony and reference signals with larger amplitude increase phase synchrony. Reference signals with spectral peaks increase coherence. Reference signal with low power may have no significant impact on calculated coherence. Bipolar EEG usually yields small phase synchrony or MSC values and may obscure the actual phase synchrony or MSC values between two local sources. [ABSTRACT FROM AUTHOR]

Detecting the boundaries of protein domains has been an important and challenging problem in experimental and computational structural biology. In this paper the domain detection is first taken as an imbalanced data learning problem. A novel undersampling method using distance-based maximal entropy in the feature space of SVMs is proposed. On multiple sequence alignments that are derived from a database search, multiple measures are defined to quantify the domain information content of each position along the sequence. The overall accuracy is about 87% together with high sensitivity and specificity. Simulation results demonstrate that the utility of the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general imbalanced datasets. [ABSTRACT FROM AUTHOR]

In prediction of secondary structure of proteins there are always some suspected segments. These suspected segments confuse people and lower the accuracy of prediction methods. To deal with this problem, a set of neural networks (NNs) are built based on helix, strand and coil segments selected from PDB. The test performance of these NNs on training data is perfect without surprise. However the prediction on test data is not good enough because the training data are lake of great representativeness. The results support the fact that closer neighbor vectors have the similar outputs of NNs. One can improve representativeness of training data without enlarging data scale as long as select less data from dense region and more from sparse region on condition that distribution of sample data has been known. [ABSTRACT FROM AUTHOR]

Accurate classification of samples using gene expression frofiles is very important in cancer detection and treatment. In this paper, a novel EPA-KNN (Emerging Patterns Advanced-K Nearest Neighbors) gene classification algorithm is proposed. Bayes estimation is applied for the computation of entropy to improve its reliability, and RCP (Random Cut Point) is presented to strengthen the generalization about unknown test samples. With these improvements, the EPAs are acquired. Then an EPA based classifier is constructed inspired by KNN. The experimental results show the new algorithm is feasible and effective. [ABSTRACT FROM AUTHOR]

Confocal Raman spectroscopy is known to have strong potential for providing noninvasive dermatological diagnosis of skin cancer. According to the previous work, various well known methods including maximum a posteriori probability classifier (MAP), linear classifier using minimum squared error (MSE) and multi layer perceptron networks classifier (MLP) showed competitive results for basal cell carcinoma (BCC) detection. The experimental results are hard to interpret, however, since the classifiers uses global features obtained by principal component analysis (PCA). In this paper, we propose a method that can identify which regions of the spectra are discriminating for BCC detection. For the purpose, 5 and 7 Gaussian prototypes were built located on the typical peak position of BCC and normal (NOR) tissue spectra respectively. Every spectrum is approximated by a linear combination of the Gaussian prototypes. Decision tree is then applied to identify which prototypes are important for the detection of BCC. Among 12 prototypes, 5 discriminating prototypes were selected and the associated weights were used as an input feature vector. According to the experiments involving 216 confocal Raman spectra, support vector machines (SVM) gave 97.4% sensitivity, which confirms that the peak regions corresponding to the selected features are significant for BCC detection and the proposed fitting method is effective. [ABSTRACT FROM AUTHOR]

The detection of explosives and illicit material in passengers' luggage for the purpose of station security is an important area in public traffic security. This paper presents a method for X-ray image recognition based on fuzzy rule and parallel neural networks. Neural networks have been widely used in various fields. However, the computing efficiency decreases rapidly if the scale of neural network increases. In this paper, a new method of X-ray image recognition based on the fuzzy-neuron system is proposed. In fuzzy rules method, a test pattern may belong to several classes with different degrees. A neural networks classifier is just for one class and used to make sure if the pattern is really belonged to that class based on fuzzy rules, they are combined to obtain the recognition result. From the experience results, the new method performs well. [ABSTRACT FROM AUTHOR]

Micorarray data are often extremely asymmetric in dimensionality, such as thousands or even tens of thousands of genes and a few hundreds of samples. Such extreme asymmetry between the dimensionality of genes and samples presents several challenges to conventional clustering and classification methods. In this paper, a novel ensemble method based on correlation analysis is proposed. Firstly, in order to extract useful features and reduce dimensionality, different feature selection methods based on correlation analysis are used to form different feature subsets. Then a pool of candidate base classifiers is generated to learn the subsets which are re-sampling from the different feature subsets. At last, appropriate classifiers are selected to construct the classification committee using EDA (Estimation of Distribution Algorithms) algorithm. Experiments show that the proposed method produces the best recognition rates on two benchmark databases. [ABSTRACT FROM AUTHOR]

The increasing growth of biological sequence data demands better and efficient analysis methods. Effective detection of various regulatory signals in these sequences requires the knowledge of characteristics, dependencies, and relationship of nucleotides in the surrounding region of the regulatory signals. A higher order Markov model is generally regarded as a useful technique for modeling higher order dependencies of the nucleotides. However, its implementation requires estimating a large number of computationally expensive parameters. In this paper, we propose a hybrid method consisting of a first order Markov model for sequence data preprocessing and a multilayer perceptron neural network for classification. The Markov model captures the compositional features and dependencies of nucleotides in terms of probabilistic parameters which are used as inputs to the classifier. The classifier combines the Markov probabilities nonlinearly for signal detection. When applied to the splice site detection problem using three widely used data sets, it is observed that the proposed hybrid method is able to model higher order dependencies with better classification accuracies. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to classify three types of tremor, including parkinsonian, essential and physiological tremors, by using bispectrum analysis of time series of hand tremor and neural network. The acceleration signals of hand tremor from voluntary subjects were recorded and the features of diagonal slices of bispectrum were extracted. A simple BP artificial neural network classifier based on LM algorithm has been used for classification. The study indicates the accuracy rate is over 92.9%. The results show that the method has a better performance than other methods, such as time or frequency domain analysis,and provide a new approach to classify tremor for clinical neurosurgeon. [ABSTRACT FROM AUTHOR]

Air-pressure limit value is an important conditional parameter of artificial respiration. The pulmonary characteristics are very different according to the person. For setting appropriate ventilation conditions fitting to each patient, it is necessary to establish a mathematical model describing the mechanism of human respiratory system, and to know the pulmonary characteristic of each patient via identification of the model. For this purpose, two types of respiratory system models have been proposed by the authors. These models are expressed as second order nonlinear differential equations with air-volume variant elastic coefficient and air-volume variant resistive coefficient. In the first type of model, elastic coefficient is expressed as polynomial function of air-volume, while in the second type of model, elastic coefficient is expressed by RBF network. The model with polynomial expression of elastance has the advantage that the structure is simple. On the other hand, the model with RBF expression of elastance has better numerical stability against to the model with polynomial expression of elastance. In this paper, a decision method of air-pressure limit value based on the respiration model with RBF expression of elastance is proposed. This method adopt a numerical technique to find the point of saturation starting point in the elastance curve, So direct calculation of radius of curvature can be avoided. The proposed method is validated by an example of application to practical clinical data. [ABSTRACT FROM AUTHOR]

The relative performances of different classifiers applied to the same data are typically analyzed using the Receiver Operator Characteristic framework (ROC). This paper proposes a further analysis by explaining the operation of classifiers using low-order Boolean rules to fit the predicted response surfaces using the Orthogonal Search Based Rule Extraction algorithm (OSRE). Four classifiers of malignant or benign ovarian tumours are considered. The models analyzed are two Logistic Regression models and two Multi-Layer Perceptrons with Automatic Relevance Determination (MLP-ARD) each applied to a specific alternative covariate subset. While all models have comparable classification rates by Area Under ROC (AUC) the classification varies for individual cases and so do the resulting explanatory rules. Two sets of clinically plausible rules are obtained which account for over one half of the malignancy cases, with near-perfect specificity. These rules are simple, explicit and can be prospectively validated in future studies. [ABSTRACT FROM AUTHOR]

This study presents a human sensibility evaluation method using neural network and multiple-template method on electroencephalogram (EEG). For our research objective, 10-channel EEG signals are collected from the healthy subjects. After the necessary preprocessing is performed on the acquired signals, the various EEG parameters are estimated and their discriminating performance is evaluated in terms of pattern classification capability. In our study, Linear Prediction (LP) coefficients are utilized as the feature parameters extracting the characteristics of EEG signal, and a multi-layer neural network is evaluated for indicating the degree of human sensibility. Also, the estimation for human comfortableness is performed by varying temperature and humidity environment factors and our results showed that our proposed scheme achieved the good performance for evaluating human sensibility. [ABSTRACT FROM AUTHOR]

Method for extracting the specified rhythms of clinical electroencephalogram (EEG) is proposed using the wavelet packet decomposition. Based on the ability of accurately resolving the signal into desired time-frequency components, EEG signals are preprocessed and decomposed into a series of rhythms for many clinical applications. Specified dynamic EEG rhythms can be accurately filtered with designed wavelet structure. In addition, we present a wavelet packet entropy method for processing of EEG signal. Both relative wavelet packet energy and wavelet packet entropy are presented as the quantitative parameter to measure the complexity of the EEG signal. Several experiments with real EEG signals are carried out to show that the proposed method excels the common discrete wavelet decomposition. The presented procedure can isolate specific EEG rhythms accurately and is also regarded as an efficient method for analyzing non-stationary signals in practice. [ABSTRACT FROM AUTHOR]

In this paper, we detect threshold-driven phase transitions in the homogeneous random neural network. When the neurons are arranged as one dimension, the critical threshold is two, while in two dimensions counterpart, the critical threshold is four. We declare that random neural network is a specific case of Abstract neural automata. So we conclude that phase transitions in the random neural network can produce thought in human brain. We successfully apply the network to interpret the relation between diseases and syndrome in Traditional Chinese Medicine. [ABSTRACT FROM AUTHOR]

It is difficult to directly co-register the 3D FMT (Fluorescence Molecular Tomography) image of a small tumor in a mouse whose maximal diameter is only a few mm with a larger CT image of the entire animal that spans about ten cm. This paper proposes a new method to register 2D flat and projected CT image first to facilitate the registration between small 3D FMT images and large CT images. And a novel algorithm Bayesian Iterative Closest Point (BICP) is introduced and validated in 2D affine registration. The visualization of the alignment of the 3D FMT and CT image through 2D registration shows promising results that would lead to automated 3D registration. [ABSTRACT FROM AUTHOR]

Some foot plant pathologies, like cave and flat foot, are normally detected by a human expert by means of footprint images. Nevertheless, the lack of trained personal to accomplish such massive first screening detection efforts precludes the routinely diagnostic of the above mentioned pathologies. In this work an innovative automatic system for foot plant pathologies based on neural networks (NN) is presented. We propose the use of principal components analysis to reduce the number of inputs to the NN and therefore increasing the efficiency of the training algorithm. The results achieved with this system evidence the feasibility of establishing automatic diagnosis systems based on the footprint image. These systems are of a great value specially in apart areas and are also suited to carry on massive first screening health campaigns. [ABSTRACT FROM AUTHOR]

How to locate the neural activation sources effectively and precisely from the magnetoencephalographic (MEG) recording is a critical issue for the clinical neurology and brain functions research. Multiple signal classification (MUSIC) algorithm and recursive MUSIC algorithm are widely used to locate multiple dipolar sources from the MEG data. The drawback of these algorithms is that they run very slowly when scanning a three-dimensional head volume globally. In order to solve this problem, a novel MEG sources localization scheme based on genetic algorithm (GA) is proposed. First, this scheme uses the property of global optimum of GA to estimate the rough source location. Then, combined with grids in small area, the accurate dipolar source localization is performed. Furthermore, we introduce the adaptive crossover and mutation probability, two-point crossover operator, periodical substitution and niche strategies to overcome the disadvantage of GA which falls into local optimum occasionally. Experimental results show that the proposed scheme can improve the speed of source localization greatly and its accuracy is satisfactory. [ABSTRACT FROM AUTHOR]

There are fewer effective methods to accurately discriminate the coronary microcirculatory dysfunction from the normal coronary microcirculation. Rather than traditional approaches only considering a single hemodynamic parameter, a novel scheme is proposed based on the generalized relevance learning vector quantization (GRLVQ) using multiple parameters (features). Naturally integrating the tasks of feature selection and classification, this scheme circularly adopts GRLVQ to gradually prune the unimportant features according to their weighting factors. In each circulation, the prototypes are generated for classification and the classification accuracy is obtained. Finally, the feature subset with the highest classification accuracy is selected and the corresponding classifier is also achieved. This approach not only simplifies the classifier but also enhances the classification performance. The method is verified on the physiological data collected from animals, and proved to be superior to the traditional single-parameter method. [ABSTRACT FROM AUTHOR]

In this paper we propose a comparative study of Artificial Neural Networks (ANN) and Artificial Immune Systems. Artificial Immune Systems (AIS) represent a novel paradigm in the field of computational intelligence based on the mechanisms that allow vertebrate immune systems to face attacks from foreign agents (called antigens). Several similarities as well as differences have been shown by Dasgupta in [1]. Here we present a comparative study of these two approaches considering evolutions of the concepts of ANN and AIS, respectively hybrid neural systems, Artificial Immune Recognition Systems (AIRS) and aiNet. We tried to establish a comparison among these three methods using a well known dataset, namely the Wisconsin Breast Cancer Database. We observed interesting trends in systems' performances and capabilities. Peculiarities of these systems have been analyzed, possible strength points and ideal contexts of application suggested. These and other considerations will be addressed in the rest of this manuscript. [ABSTRACT FROM AUTHOR]

Many different approaches for the modeling of neural networks were presented in the literature (e.g. [4]). Generally the object-oriented approach proved itself as most appropriate. It provides a concise but comprehensive framework for the design of neural networks in terms of its static and dynamic components, i.e. the information structure and its methods in the object-oriented notion. This paper presents a framework for the conceptual and physical integration of neural networks into object-relational database systems. The static components comprise the structural parts of a neural network, as the neurons and connections, higher topological structures as layers, blocks and network systems. The dynamic components are the behavioral characteristics, as the creation, training and evaluation of the network. Finally the implementation of the new NeuroOracle system based on the proposed framework is presented. [ABSTRACT FROM AUTHOR]

Detection of biomarkers capable of predicting a patient's risk of major adverse cardiac events (MACE) is of clinical significance. Due to the high dynamic range of the protein concentration in human blood, applying proteomics techniques for protein profiling can generate large arrays of data for development of optimized clinical biomarker panels. The objective of this study is to discover an optimized subset of biomarkers for predicting risk of MACE containing less than ten biomarkers. In this paper, we connect linear SVM with PLS feature selection and extraction. A simplified PLS algorithm selects a subset of biomarkers and extracts latent variables and prediction performance of linear SVM is dramatically improved. The proposed method is compared with a widely used PLS-Logistic Discriminant solution and several other reported methods based on the MACE prediction experiments. [ABSTRACT FROM AUTHOR]

Provide these intelligent medical services, it is necessary to understand the situation information generated in a hospital. There should be infra technologies that can classify and control the information for processing situation data, not mere collection of conceptual information, with clear standards. This paper, as a study to seize the information generated from medical situation more clearly, understood the property of data using neural network and applied the security ratings of information so that the system to provide the user appropriate to designated rating with analyzed medical information is established. It will be an effective measure to enhance the effectiveness of medical devices and backup data already introduced and understand the various medical data that will be generated from medical devices to be introduced. [ABSTRACT FROM AUTHOR]

Topological structure of Probability Neural Network (PNN) is usually complex when it is trained with large-scale and high-redundant training samples. Aiming this problem, PNN is analyzed and simplified by using probability calculation and multiplication formula. At first, input data of training samples was statistical analyzed by using Principal Component Analysis (PCA). PNN topological structure was optimized based on the statistical results. Subsequently, a complete learning algorithm was provided to avoid the artificial set of smoothing parameters. And Simulated Annealing (SA) coefficient was introduced to increase learning speed and stability. Eventually, the optimized PNN was applied to real problem. The test result validated that the optimized PNN had simpler structure and higher efficiency than typical PNN in the application with large-scale and high-redundant training samples. [ABSTRACT FROM AUTHOR]

With Kohonen's self-organizing map based brain MRI image segmentation, there are still some regions which are not partitioned accurately, particularly in the transitional regions of gray matter and white matter, or cerebrospinal fluid and gray matter. In this paper, we propose a dynamically growing hierarchical self-organizing map integrated with a multi-scale feature vector to overcome the problem mentioned above, which uses the spatial relationships between image pixels and using multi-scale processing method to reduce the noise effect and the classification ambiguity. The efficacy of our approach is validated by extensive experiments using both simulated and real MRI images. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new super-resolution face hallucination and recognition method based on Independent Component Analysis (ICA). Firstly, ICA is used to build a linear mixing relationship between high-resolution (HR) face image and independent HR source faces images. The linear mixing coefficients are retained, thus the corresponding low-resolution (LR) face image is represented by linear mixture of down-sampled source faces images. So, when the source faces images are obtained by training a set of HR face images, unconstrained least square is utilized to obtain mixing coefficients to a LR image for hallucination and recognition. Experiments show that the accuracy of face recognition is insensitive to image size and the number of HR source faces images when image size is larger than 8×8, and the resolution and quality of the hallucinated face image are greatly enhanced over the LR ones, which is very helpful for human recognition. [ABSTRACT FROM AUTHOR]

With independent component analysis (ICA) to realize the blind separation from mixed acoustic objects, a recognition method based on support vector machine/Gaussian mixture models (SVM/GMM) is proposed through extracting linear prediction coefficient (LPC) feature. It is revealed that LPC is consistently better than wavelet energy feature, ICA is efficient algorithm to estimate the unknown signal level. This method uses the output of GMM to adjust the probabilistic output of SVM. The validity of the ICA and SVM/GMM model is verified via examples in mixed acoustic objects recognition system. [ABSTRACT FROM AUTHOR]

The high non-linearity, serious time-variability and uncertainty result in a number of very challenging problems in working on the monitoring and control of biological processes. Many important variables are difficult to measure during monitoring and control. Software sensors can give estimation to unmeasured state variables according to the measured information provided by online measuring instruments available in the system. This offers an alternative feasible program for online measurement. A hybrid soft measurement model that combines principal component analysis with artificial neural networks is applied to monitor the sequencing batch reactor (SBR) process. Simulation results show that the most unmeasured variables can be predicted and the method can capture the main trend of the data. [ABSTRACT FROM AUTHOR]

Two-dimensional principal component analysis (2DPCA) proposed recently overcome a limitation of principal component analysis (PCA) which is expensive computational cost. Symmetrical principal component analysis (SPCA) is also a better feature extraction technique because it utilizes effectively the symmetrical property of human face. This paper presents a symmetry based two-dimensional principal component analysis (S2DPCA), which combines the advantages of 2DPCA and of the SPCA. The experimental results show that S2DPCA is competitive with or superior to 2DPCA and SPCA. [ABSTRACT FROM AUTHOR]

Based on eigenvalue decomposition, a novel efficient K-HPC algorithm is developed in this paper, which is easy to implement. And it enables us to detect the number of hyperplanes and helps to avoid local minima by overestimating the number of hyperplanes. A confidence index is proposed to evaluate which estimated hyperplanes are most significant and which are spurious. So we can choose those significant hyperplanes with high rank priority and remove the spurious hyperplanes according to their corresponding confidence indices. Furthermore, a multilayer clustering framework called "multilayer K-HPC" is proposed to further improve the clustering results. The K-HPC approach can be directly applied to sparse component analysis (SCA) to develop efficient SCA algorithm. Two examples including a sparse component analysis example demonstrate the proposed algorithm. [ABSTRACT FROM AUTHOR]

The ability to predict traffic variables such as speed, travel time and flow, based on real time and historic data, collected by various systems in transportation networks, is vital to the intelligent transportation systems (ITS). The present paper proposes a method based on Principal Component Analysis and Support Vector Regression (PCA-SVR) for a short-term simultaneously prediction of network traffic flow which is multidimensional compared with traditional single point. Data from a typical traffic network of Beijing City, China are used for the analysis. Other models such as ANN and ARIMA are also developed as a comparison of the performance of both these techniques is carried out to show the effectiveness of the novel method. [ABSTRACT FROM AUTHOR]

Extracting proper features is crucial to the performance of a pattern recognition system. Since the goal of a pattern recognition system is to recognize a pattern correctly, a natural measure of "goodness" of extracted features is the probability of classification error. However, popular feature extraction techniques like principal component analysis (PCA), Fisher linear discriminant analysis (FLD), and independent component analysis (ICA) extract features that are not directly related to the classification accuracy. In this paper, we present two linear discriminant analysis algorithms (LDA) whose criterion functions are directly based on minimum probability of classification error, or the Bayes error. We term these two linear discriminants as recursive Bayesian linear discriminant I (RBLD-I) and recursive Bayesian linear discriminant II (RBLD-II). Experiments on databases from UCI Machine Learning Repository show that the two novel linear discriminants achieve superior classification performance over recursive FLD (RFLD). [ABSTRACT FROM AUTHOR]

Histograms are data objects that are commonly used to characterize media objects like image, video, audio etc. Symbolic Data Analysis (SDA) is a field which deals with extracting knowledge and relationship from such complex data objects. The current research scenario of SDA has contributions related to dimensionality reduction of interval kind data. This paper makes an important attempt to analyze a symbolic data set for dimensionality reduction when the features are of histogram type. The result of an in-depth analysis of such a histogram data set has lead to proposing basic arithmetic and definitions related to histogram data. The basic arithmetic has been used for dimensionality reduction modeling of histogram data set through Histogram PCA. The modeling procedure is demonstrated by experiments with 700x3 data, iris data and 80X data. The utility/applicability of Histogram PCA is validated by clustering the above data. [ABSTRACT FROM AUTHOR]

The data obtained from any process may be corrupted with noise and outliers which may lead to false-alarm when applying conventional PCA to process monitoring. To overcome the above mentioned limitations of conventional PCA, an approach is developed by combining the ability of wavelets and moving median filter with PCA. This method utilizes the quality of wavelets and moving median filter to preprocess the data to eliminate noise and outliers. At last, this method is applied to fault detection and has a good effect which proves the method is effective and feasible. [ABSTRACT FROM AUTHOR]

Aiming at the problems happened in the practical application of traditional Principle Component Analysis (PCA), the concept of Relative Principle Component (RPC) and method of Relative Principle Component Analysis (RPCA) are put forward. Meanwhile, some concepts such as Relative Transform (RT), "Rotundity" Scatter and so on are introduced. The new algorithm can overcome some disadvantages of traditional PCA for compressing data when data is "Rotundity" Scatter. A simulation has been used to demonstrate the effectiveness and practicability of the algorithm proposed. The RPCs selected by RPCA are more representative, and the way to choose RPCs is more flexible, so that the application of the new algorithm will be very extensive. [ABSTRACT FROM AUTHOR]

In recent years, many efforts have been put in applying the concept of reconfigurable computing to neural networks. In our previous pursuits, an innovative self-organizing learning array (SOLAR) was developed. However, traditional multiplexer method to achieve reconfigurable connection has its limit for larger networks. In this paper, we propose a novel pipeline structure, which offers flexible, possibly large number of dynamically configurable connections and which utilizes each node's computing ability. The hardware resources demand of the proposed structure is a linear function of the network size, which is especially useful for building a large network that can handle complicated real-world applications. [ABSTRACT FROM AUTHOR]

The traditional enhancement of X-ray digital subtraction angiography (DSA) is to subtract the mask image and living image so as to remove the background such as ribs, spine, cathers, organs and etc, and obtain the enhanced vessel trees. However, the DSA have serious motion artifacts, poor local contrast and noises, when subtraction technique is used, some tiny vessels are broken, and even disappeared when visualized. To attack the problem, we use independent component analysis instead of subtraction technique. This technique is proved to be very efficient to enhance vessels. Experimental results of simulated data and several clinical data show that the proposed method is robust and can obtain good vessel trees. [ABSTRACT FROM AUTHOR]

In our previous work we presented a variation of Self-Organizing Map (SOM), CSOM that applies a different learning mechanism useful for situations where the aim is to extract rules from a data set characterized by continuous input features. The main change is that the weights on the network links are replaced by ranges which allows for a direct extraction of the underlying rule. In this paper we extend our work by allowing the CSOM to handle mixed data types and continuous class attributes. These extensions called for an appropriate adjustment in the network pruning method that uses the Symmetrical Tau (τ) criterion for measuring the predictive capability of cluster attributes. Publicly available real world data sets were used for evaluating the proposed method and the results demonstrate the effectiveness of the method as a whole for extracting optimal rules from a trained SOM. [ABSTRACT FROM AUTHOR]

An approach to network anomaly detection is investigated, based on dynamic self-organizing maps (DSOM) and ant colony optimization (ACO) clustering. The basic idea of the method is to produce the cluster by DSOM and ACO. With the classified data instances, anomaly data clusters can be easily identified by normal cluster ratio. And then the identified cluster can be used in real data detection. In the traditional clustering-based intrusion detection algorithms, clustering using a simple distance-based metric and detection based on the centers of clusters, which generally degrade detection accuracy and efficiency. Our approach based on DSOM and ACO clustering can settle these problems effectively. The experiment results show that our approach can detect unknown intrusions efficiently in the real network connections. [ABSTRACT FROM AUTHOR]

The application of hierarchical self organizing maps (HSOM) to the segmentation of cell migration images, obtained during high-content screening in molecular medicine, is described. The segmentation is critical to our larger project for developing methods for the automatic annotation of cell migration images. The HSOM appears to perform better than the conventional computer-vision methods of histogram thresholding, edge detection, and the newer techniques involving single-layer SOMs. However, the HSOM techniques have to be complemented by region-based techniques to improve the quality of the segmented images. [ABSTRACT FROM AUTHOR]

An edge detection method by combining image entropy and Self -Organizing Map (SOM) is proposed in this paper. First, according to information theory image entropy is used to curve up the smooth region and the region of gray level abruptly changed. Then we transform the gray level image to ideal binary pattern of pixels. We define six classes' edge and six edge prototype vectors. These edge prototype vectors are fed into input layer of the Self-Organizing Map (SOM). Classifying the type of edge through this network, the edge image is obtained. At last, the speckle edges are discarded from the edge image. Experimental results show that it gained better edge image compared with Canny edge detection method. [ABSTRACT FROM AUTHOR]

In this paper, a novel application of the backpropagation network using a self-organised layer inspired by immune algorithm is used for the prediction of financial time series. The simulations assess the data from two time series: Firstly the daily exchange rate between the US dollar and the Euro for the period from the 3rd January 2000 until the 4th November 2005, giving approximately 1525 data points. Secondly the IBM common stock closing price for the period from the 17th May 1961 until the 2nd November 1962, establishing 360 trading days as data points. The backpropagation network with the self-organising immune system algorithm produced an increase in profits of approximately 2% against the standard back propagation network, in the simulation, for the prediction of the IBM common stock price. However there was a slightly lower profit for the US dollar/Euro exchange rate prediction. [ABSTRACT FROM AUTHOR]

Genetic algorithm is introduced to network optimization to overcome the limitation of conventional SOM network. Based on this idea, a new model of structural adapting self-organizing neural network is proposed. In this model, each neuron is regarded as individual of evolutionary population and three operators are constructed as follows:growing operator, pruning operator and stochastic creating operator. In the algorithm, the accumulative error of neuron is selected as fitness function each iteration, and the neurons on compete layer are generated or deleted adaptively according to the values of fitness function until there is not any change of neuron on compete layer. Simulation experiments indicate that this structural adaptive network has better performance than conventional SOM network. [ABSTRACT FROM AUTHOR]

An object recognition algorithm is put forward based on statistical character of contourlet transform and multi-object wavelet neural network (MWNN). A contourlet-based feature extraction method is proposed, which forms the feature vector taking advantage of the statistical attribution in each sub-band of contourlet transform. And then the extracted features are weighted according to their dispersion degree of data. WNN is used as classifier, which combines the extraction local singularity of wavelet transform and adaptive of artificial neural network. With the application in an aircraft recognition system, the experimental data showed the efficiency of this algorithm for automation target recognition. Keywords: Automatic target recpgnition, Wavelet neural network, Contourlet transform, Feature extraction. [ABSTRACT FROM AUTHOR]

In this paper, we propose a face recognition method from a single image per person, called the common subfaces, to solve the "one sample per person" problem. Firstly the single image per person is divided into multiple sub-images, which are regarded as the training samples for feature extraction. Then we propose a novel formulation of common vector analysis from the space isomorphic mapping view for feature extraction. In the procedure of recognition, the common vector of the subfaces from the test face image is derived with the similar procedure to the common vector, which is then compared with the common vector of each class to predict the class label of query face. The experimental results suggest that the proposed common subfaces approach provides a better representation of individual common feature and achieves a higher recognition rate in the face recognition from a single image per person compared with the traditional methods. [ABSTRACT FROM AUTHOR]