Analysis of event-related fMRI data using best clustering bases

We explore a new paradigm for the analysis of event-related functional magnetic resonance images (fMRI) of brain activity. We regard the fMRI data as a very large set of time series x(i) (t), indexed by the position i of a voxel inside the brain. The decision that a voxel i(o) is activated is based not solely on the value of the fMRI signal at i(o), but rather on the comparison of all time series x(i) (t) in a small neighborhood Wi(o) around i(o). We construct basis functions on which the projection of the fMRI data reveals the organization of the time series x(i) (t) into activated and nonactivated clusters. These clustering basis functions are selected from large libraries of wavelet packets according to their ability to separate the fMRI time series into the activated cluster and a nonactivated cluster. This principle exploits the intrinsic spatial correlation that is present in the data. The construction of the clustering basis functions described in this paper is applicable to a large category of problems where time series are indexed by a spatial variable.     

New clustering approach to chip floorplan using functional data

An approach to chip floorplanning utilising hierarchical and functional information derived using LSI logic design is described. The proposed approach adopts a methodological design process similar to that of expert designers. A new clustering method that can be divided into three phases, namely clustering, cluster classification and placement, is employed in this process. The prototype system is implemented based on AI techniques.     

A game theoretical approach to clustering of ad-hoc and sensor networks

Game theory has been used for decades in fields of science such as economics and biology, but recently it was used to model routing and packet forwarding in wireless ad-hoc and sensor networks. However, the clustering problem, related to self-organization of nodes into large groups, has not been studied under this framework. In this work our objective is to provide a game theoretical modeling of clustering for ad-hoc and sensor networks. The analysis is based on a non-cooperative game approach where each sensor behaves selfishly in order to conserve its energy and thus maximize its lifespan. We prove the Nash Equilibria of the game for pure and mixed strategies, the expected payoffs and the price of anarchy corresponding to these equilibria. Then, we use this analysis to formulate a clustering mechanism (which we called Clustered Routing for Selfish Sensors??CROSS), that can be applied to sensor networks in practice. Comparing this mechanism to a popular clustering technique, we show via simulations that CROSS achieves a performance similar to that of a very popular clustering algorithm.     

An approach to high-performance, high-speed data networks

An approach that establishes a framework of design for high performance that scales well with increasing delay-bandwidth products is described. A basic conceptual model to explain the roles of window and access controls is presented. A static model of the system is then studied. The steady-state distribution of the buffer sizes, asymptotic expressions, and relationships between window size and delay that will be used to control windows are derived. A class of adaptive control schemes is proposed, and some results on simulation studies of one scheme are presented. A fluid model with dynamics is introduced to study fundamental questions of adaptive windows to adaptive rates. Bursty sources are considered. The proposals are then compared with other approaches     

Analysis of fMRI data using improved self-organizing mapping and spatio-temporal metric hierarchical clustering

The self-organizing mapping (SOM) and hierarchical clustering (HC) methods are integrated to detect brain functional activation; functional magnetic resonance imaging (fMRI) data are first processed by SOM to obtain a primary merged neural nodes image, and then by HC to obtain further brain activation patterns. The conventional Euclidean distance metric was replaced by the correlation distance metric in SOM to improve clustering and merging of neural nodes. To improve the use of spatial and temporal information in fMRI data, a new spatial distance (node coordinates in the 2-D lattice) and temporal correlation (correlation degree of each time course in the exemplar matrix) are introduced in HC to merge the primary SOM results. Two simulation studies and two in vivo fMRI data that both contained block-design and event-related experiments revealed that brain functional activation can be effectively detected and that different response patterns can be distinguished using these methods. Our results demonstrate that the improved SOM and HC methods are clearly superior to the statistical parametric mapping (SPM), independent component analysis (ICA), and conventional SOM methods in the block-design, especially in the event-related experiment, as revealed by their performance measured by receiver operating characteristic (ROC) analysis. Our results also suggest that the proposed new integrated approach could be useful in detecting block-design and event-related fMRI data.      

Grey relational analysis based approach for data clustering

This paper generalises the concept of grey relational analysis to develop a technique, called grey relational pattern analysis, for analysing the similarity between given patterns. Based on this technique, a clustering algorithm is proposed for finding cluster centres of a given data set. This approach can be categorised as an unsupervised clustering algorithm because it does not need predetermination of appropriate cluster centres in the initialisation. The problem of determining the optimal number of clusters and optimal locations of cluster centres is also considered. Finally, the approach is used to solve several data clustering problems as examples. In each example, the performance of the proposed algorithm is compared with other well-known algorithms such as the fuzzy c-means method and the hard c-means method. Simulation results demonstrate the effectiveness and feasibility of the proposed method.     

Neural networks applied to traffic management in telephone networks

In this paper the application of neural networks to some of the network management tasks carried out in a regional Bell telephone company is described. Network managers monitor the telephone network for abnormal conditions and have the ability to place controls in the network to improve traffic flow. Conclusions are drawn regarding the utility and effectiveness of the neural networks in automating the network management tasks     

SCE-PSO based clustering approach for load balancing of gateways in wireless sensor networks

Wireless Networks - Wireless sensor networks (WSNs) consist of spatially distributed low power sensor nodes and gateways along with sink to monitor physical or environmental conditions. In...     

fMRI data analysis with nonstationary noise models: a Bayesian approach

The assumption of noise stationarity in the functional magnetic resonance imaging (fMRI) data analysis may lead to the loss of crucial dynamic features of the data and thus result in inaccurate activation detection. In this paper, a Bayesian approach is proposed to analyze the fMRI data with two nonstationary noise models (the time-varying variance noise model and the fractional noise model). The covariance matrices of the time-varying variance noise and the fractional noise after wavelet transform are diagonal matrices. This property is investigated under the Bayesian framework. The Bayesian estimator not only gives an accurate estimate of the weights in general linear model, but also provides posterior probability of activation in a voxel and, hence, avoids the limitations (i.e., using only hypothesis testing) in the classical methods. The performance of the proposed Bayesian methods (under the assumption of different noise models) are compared with the ordinary least squares (OLS) and the weighted least squares (WLS) methods. Results from the simulation studies validate the superiority of the proposed approach to the OLS and WLS methods considering the complex noise structures in the fMRI data.     

An energy-efficient approach to power control and receiver design in wireless data networks

In this paper, the cross-layer design problem of joint multiuser detection and power control is studied, using a game-theoretic approach that focuses on energy efficiency. The uplink of a direct-sequence code-division multiple-access data network is considered, and a noncooperative game is proposed in which users in the network are allowed to choose their uplink receivers as well as their transmit powers to maximize their own utilities. The utility function measures the number of reliable bits transmitted by the user per joule of energy consumed. Focusing on linear receivers, the Nash equilibrium for the proposed game is derived. It is shown that the equilibrium is one where the powers are signal-to-interference-plus-noise ratio-balanced with the minimum mean-square error (MMSE) detector as the receiver. In addition, this framework is used to study power-control games for the matched filter, the decorrelator, and the MMSE detector; and the receivers' performance is compared in terms of the utilities achieved at equilibrium (in bits/joule). The optimal cooperative solution is also discussed and compared with the noncooperative approach. Extensions of the results to the case of multiple receive antennas are also presented. In addition, an admission-control scheme based on maximizing the total utility in the network is proposed.     

Application of Bayesian inference to fMRI data analysis

The methods of Bayesian statistics are applied to the analysis of fMRI data. Three specific models are examined. The first is the familiar linear model with white Gaussian noise. In this section, the Jeffreys' Rule for noninformative prior distributions is stated and it is shown how the posterior distribution may be used to infer activation in individual pixels. Next, linear time-invariant (LTI) systems are introduced as an example of statistical models with nonlinear parameters. It is shown that the Bayesian approach can lead to quite complex bimodal distributions of the parameters when the specific case of a delta function response with a spatially varying delay is analyzed. Finally, a linear model with auto-regressive noise is discussed as an alternative to that with uncorrelated white Gaussian noise. The analysis isolates those pixels that have significant temporal correlation under the model. It is shown that the number of pixels that have a significantly large auto-regression parameter is dependent on the terms used to account for confounding effects.     

Comparison of two exploratory data analysis methods for fMRI: unsupervised clustering versus independent component analysis

Exploratory data-driven methods such as unsupervised clustering and independent component analysis (ICA) are considered to be hypothesis-generating procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). In this paper, we present a comparison between unsupervised clustering and ICA in a systematic fMRI study. The comparative results were evaluated by 1) task-related activation maps, 2) associated time-courses, and 3) receiver operating characteristic analysis. For the fMRI data, a comparative quantitative evaluation between the three clustering techniques, self-organizing map, "neural gas" network, and fuzzy clustering based on deterministic annealing, and the three ICA methods, FastICA, Infomax and topographic ICA was performed. The ICA methods proved to extract features relatively well for a small number of independent components but are limited to the linear mixture assumption. The unsupervised Clustering outperforms ICA in terms of classification results but requires a longer processing time than the ICA methods.     

Dynamic clustering approach with ACO-based mobile sink for data collection in WSNs

Enhancing the network lifetime of wireless sensor networks is an essential task. It involves sensor deployment, cluster formation, routing, and effective utilization of battery units. Clustering and routing are important techniques for adequate enhancement of the network lifetime. Since the existing clustering and routing approaches have high message overhead due to forwarding collected data to sinks or the base station, it creates premature death of sensors and hot-spot issues. The objective of this study is to design a dynamic clustering and optimal routing mechanism for data collection in order to enhance the network lifetime. A new dynamic clustering approach is proposed to prevent premature sensor death and avoid the hot spot problem. In addition, an Ant Colony Optimization (ACO) technique is adopted for effective path selection of mobile sinks. The proposed algorithm is compared with existing routing methodologies, such as LEACH, GA, and PSO. The simulation results show that the proposed cluster head selection algorithm with ACO-based MDC enhances the sensor network lifetime significantly.

     

Optimal selection of routs in data transmission networks. Energy approach

A new algorithm has been proposed for solving the problem of optimal alternative routing based on the energy approach to the network analysis with generalization of Kirchhoff’s laws. This algorithm is the fastest among a wide class of optimization methods based on finding an admissible direction of decreasing the target function. By the example of network analysis it was shown in the case of a quadrature target function this algorithm requires only one iteration for finding an optimal solution that favorably distinguishes it from the gradient projection and other possible methods. Optimization of the same network was conducted by the criterion of average delay minimum that is one of the main criteria used in optimizing networks of queues with representative time of message servicing.     

Packet data over cellular networks: the CDPD approach

Cellular digital packet data is a mobile packet data technology that operates on the spectrum assigned to a telephone cellular network, such as the Advanced Mobile Phone Service. This article undertakes a thorough survey of the CDPD radio interface and explores the main functional layers of this interface. Specifically, it extensively studies the physical layer, the data link layer, and the subnetwork-dependent convergence protocol, and explains their semantics and functional characteristics. Furthermore, it emphasizes several significant aspects such as the medium access procedure, the forward and reverse channel configurations, the data multiplexing scheme, and the channel hopping procedure     

A fuzzy clustering approach to EP estimation

The problem of extracting a useful signal (a response) buried in relatively high amplitude noise has been investigated, under the conditions of low signal-to-noise ratio. In particular, the authors present a method for detecting the “true” response of the brain resulting from repeated auditory stimulation, based on selective averaging of single-trial evoked potentials. Selective averaging: is accomplished in two steps. First, an unsupervised fuzzy-clustering algorithm is employed to identify groups of trials with similar characteristics, using a performance index as an optimization criterion. Then, typical responses are obtained by ensemble averaging of all trials in the same group. Similarity among the resulting estimates is quantified through a synchronization measure, which accounts for the percentage of time that the estimates are in phase. The performance of the classifier is evaluated with synthetic signals of known characteristics, and its usefulness is demonstrated with real electrophysiological data obtained from normal volunteers     

VQ-agglomeration: a novel approach to clustering

A novel approach called `VQ-agglomeration' capable of performing fast and autonomous clustering is presented. The approach involves a vector quantisation (VQ) process followed by an agglomeration algorithm that treats codewords as initial prototypes. Each codeword is associated with a gravisphere that has a well defined attraction radius. The agglomeration algorithm requires that each codeword be moved directly to the centroid of its neighbouring codewords. The movements of codewords in the feature space are synchronous, and will converge quickly to certain sets of concentric circles for which the centroids identify the resulting clusters. Unlike other techniques, such as the k-means and the fuzzy C-means, the proposed approach is free of the initial prototype problem and it does not need pre-specification of the number of clusters. Properties of the agglomeration algorithm are characterised and its convergence is proved