In this paper we introduce a procedure, based on the max-min clustering method, that identifies a fixed order of training pattern presentation for fuzzy adaptive resonance theory mapping (ARTMAP). This procedure is referred to as the ordering algorithm, and the combination of this procedure with fuzzy ARTMAP is referred to as ordered fuzzy ARTMAP. Experimental results demonstrate that ordered fuzzy ARTMAP exhibits a generalization performance that is better than the average generalization performance of fuzzy ARTMAP, and in certain cases as good as, or better than the best fuzzy ARTMAP generalization performance. We also calculate the number of operations required by the ordering algorithm and compare it to the number of operations required by the training phase of fuzzy ARTMAP. We show that, under mild assumptions, the number of operations required by the ordering algorithm is a fraction of the number of operations required by fuzzy ARTMAP.

Pattern classification in functional MRI (fMRI) is a novel methodology to automatically identify differences in distributed neural substrates resulting from cognitive tasks. Reliable pattern classification is challenging due to the high dimensionality of fMRI data, the small number of available data sets, interindividual differences, and dependence on the acquisition methodology. Thus, most previous fMRI classification methods were applied in individual subjects. In this study, we developed a novel approach to improve multiclass classification across groups of subjects, field strengths, and fMRI methods. Spatially normalized activation maps were segmented into functional areas using a neuroanatomical atlas and each map was classified separately using local classifiers. A single multiclass output was applied using a weighted aggregation of the classifier's outputs. An Adaboost technique was applied, modified to find the optimal aggregation of a set of spatially distributed classifiers. This Adaboost combined the regionspecific classifiers to achieve improved classification accuracy with respect to conventional techniques. Multiclass classification accuracy was assessed in an fMRI group study with interleaved motor, visual, auditory, and cognitive task design. Data were acquired across 18 subjects at different field strengths (1.5 T, 4 T), with different pulse sequence parameters (voxel size and readout bandwidth). Misclassification rates of the boosted classifier were between 3.5% and 10%, whereas for the single classifier, these were between 15% and 23%, suggesting that the boosted classifier provides a better generalization ability together with better robustness. The high computational speed of boosting classification makes it attractive for real-time fMRI to facilitate online interpretation of dynamically changing activation patterns.Keywords: Functional magnetic resonance imaging; Pattern classification; Support vector machines; Adaboost IntroductionBrain activation changes in response to even simple sensory input and motor tasks encompass a widely distributed network of functional brain areas. Information embedded in the spatial shape and extent of these activation patterns, and differences in voxel-tovoxel time course, are not easily quantified with conventional analysis tools, such as statistical parametric mapping (SPM) (Kiebel and Friston, 2004a,b). Pattern classification in functional MRI (fMRI) is a novel approach, which promises to characterize subtle differences in activation patterns between different tasks. However, automatic and reliable classification of patterns is challenging due to the high dimensionality of fMRI data, the small number of available data sets, interindividual differences in activation patterns, and dependence on the image acquisition methodology. Recent work by Cox and Savoy (2003) demonstrated that linear discriminant analysis and support vector machines (SVM) allow 10-way discrimination of visual activation patterns evoked by the visual presentation of various categories of ...

Given the continuous growth of illicit activities on the Internet, there is a need for intelligent systems to identify malicious web pages. It has been shown that URL analysis is an e↵ective tool for detecting phishing, malware, and other attacks. Previous studies have performed URL classification using a combination of lexical features, network tra c, hosting information, and other strategies. These approaches require time-intensive lookups which introduce significant delay in real-time systems. This paper describes a lightweight approach for classifying malicious web pages using URL lexical analysis alone. The goal is to explore the upper-bound of the classification accuracy of a purely lexical approach. Another aim is to develop an approach which could be used in a real-time system. These goal culminate in the development of a classification system based on lexical analysis of URLs. It correctly classifies URLs of malicious web pages with 99.1% accuracy, a 0.4% false positive rate, an F1-Score of 98.7, and requires 0.62 milliseconds on average. This method substantially outperforms previously published algorithms on out-of-sample data.

Spatial suppression of peripheral regions (outer volume suppression) is used in MR spectroscopic imaging (MRSI) to reduce contamination from strong lipid and water signals. The manual placement of outer volume suppression slices requires significant operator interaction, which is time consuming and introduces variability in volume coverage. Placing a large number of outer volume saturation bands for volumetric MRSI studies is particularly challenging and time consuming, and becomes unmanageable as the number of suppression bands increase. In this study a method is presented that automatically segments a high-resolution MR image in order to identify the peripheral lipid containing regions. This method computes an optimized placement of suppression bands in three dimensions, and is based on the maximization of a criterion function. This criterion function maximizes coverage of peripheral lipid containing areas and minimizes suppression of cortical brain regions, and regions outside of the head.Computer simulation demonstrates automatic placement of sixtenn suppression slices to form a convex hull that covers peripheral lipid containing regions above the base of the brain. In vivo metabolite mapping obtained with short TE proton-echo-planar spectroscopic-imaging (PEPSI) shows that the automatic method yields a placement of suppression slices that is very similar to that of a skilled human operator in terms of lipid suppression and usable brain voxels.

The human brain functions as an efficient system where signals arising from gray matter are transported via white matter tracts to other regions of the brain to facilitate human behavior. However, with a few exceptions, functional and structural neuroimaging data are typically optimized to maximize the quantification of signals arising from a single source. For example, functional magnetic resonance imaging (FMRI) is typically used as an index of gray matter functioning whereas diffusion tensor imaging (DTI) is typically used to determine white matter properties. While it is likely that these signals arising from different tissue sources contain complementary information, the signal processing algorithms necessary for the fusion of neuroimaging data across imaging modalities are still in a nascent stage. In the current paper we present a data-driven method for combining measures of functional connectivity arising from gray matter sources (FMRI resting state data) with different measures of white matter connectivity (DTI). Specifically, a joint independent component analysis (J-ICA) was used to combine these measures of functional connectivity following intensive signal processing and feature extraction within each of the individual modalities. Our results indicate that one of the most predominantly used measures of functional connectivity (activity in the default mode network) is highly dependent on the integrity of white matter connections between the two hemispheres (corpus callosum) and within the cingulate bundles. Importantly, the discovery of this complex relationship of connectivity was entirely facilitated by the signal processing and fusion techniques presented herein and could not have been revealed through separate analyses of both data types as is typically performed in the majority of neuroimaging experiments. We conclude by discussing future applications of this technique to other areas of neuroimaging and examining potential limitations of the methods.

No abstract

We present a generalization of Benford's law for the first significant digit. This generalization is based on keeping two terms of the Fourier expansion of the probability density function of the data in the modular logarithmic domain. We prove that images in the Discrete Cosine Transform domain closely follow this generalization. We use this property to propose an application in image steganalysis, namely, detecting that a given image carries a hidden message.

No abstract