Biomedical subjects

N Sundararajan

Publications and source records attributed to N Sundararajan.

7 recordsLinked to original sources

PubMed2006

A fast and accurate online sequential learning algorithm for feedforward networks.

In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.

Algorithms↗

PubMed2004

Text-independent speaker verification using Minimal Resource Allocation Networks.

This paper presents a text-independent speaker verification system based on an online Radial Basis Function (RBF) network referred to as Minimal Resource Allocation Network (MRAN). MRAN is a sequential learning RBF, in which hidden neurons are added or removed as training progresses. LP-derived cepstral coefficients are used as feature vectors during training and verification phases. The performance of MRAN is compared with other well-known RBF and Elliptical Basis Function (EBF) based speaker verification methods in terms of error rates and computational complexity on a series of speaker verification experiments. The experiments use data from 258 speakers from the phonetically balancedcontinuous speech corpus TIMIT. The results show that MRAN produces comparable error rates to other methods with much less computational complexity.

Algorithms↗

PubMed2003

Novel neutral network approach to call admission control in high-speed networks.

This paper presents a novel Call Admission Control (CAC) scheme which adopts the neural network approach, namely Minimal Resource Allocation Network (MRAN) and its extended version EMRAN. Though the current focus is on the Call Admission Control (CAC) for Asynchronous Transfer Mode (ATM) networks, the scheme is applicable to most high-speed networks. As there is a need for accurate estimation of the required bandwidth for different services, the proposed scheme can offer a simple design procedure and provide a better control in fulfilling the Quality of Service (QoS) requirements. MRAN and EMRAN are on-line learning algorithms to facilitate efficient admission control in different traffic environments. Simulation results show that the proposed CAC schemes are more efficient than the two conventional CAC approaches, the Peak Bandwidth Allocation scheme and the Cell Loss Ratio (CLR) upperbound formula scheme. The prediction precision and computational time of MRAN and EMRAN algorithms are also investigated. Both MRAN and EMRAN algorithms yield similar performance results, but the EMRAN algorithm has less computational load.

Algorithms↗

PubMed2000

Complex-valued minimal resource allocation network for nonlinear signal processing.

This paper presents a sequential learning algorithm and evaluates its performance on complex valued signal processing problems. The algorithm is referred to as Complex Minimal Resource Allocation Network (CMRAN) algorithm and it is an extension of the MRAN algorithm originally developed for online learning in real valued RBF networks. CMRAN has the ability to grow and prune the (complex) RBF network's hidden neurons to ensure a parsimonious network structure. The performance of the learning algorithm is illustrated using two applications from signal processing of communication systems. The first application considers identification of a nonlinear complex channel. The second application considers the use of CMRAN to QAM digital channel equalization problems. Simulation results presented clearly show that CMRAN is very effective in modeling and equalization with performance achieved often being superior to that of some of the well known methods.

Algorithms↗

PubMed1999

Impact of the hydrodyne process on tenderness, microbial load, and sensory characteristics of pork longissimus muscle.

Paired, boneless pork loin muscles were obtained from 76 market hogs to evaluate tenderness, meat quality characteristics, sensory attributes, and microbial characterization of pork muscle exposed to the Hydrodyne Process (H) compared with untreated control (C) loin. A subset of 16 paired loins was randomly selected for use in sensory evaluation and microbial characterization. Loins were vacuum packaged and immersed in a heat shrink tank prior to the H treatment. The Hydrodyne treatment exposed the loin to the pressure equivalent of a 150-g explosive, generating a pressure distribution of approximately 703 kg/cm2 at the surface of the samples. Meat quality assessments taken following treatment included subjective color, firmness/wetness, marbling scores (1 to 5 scale), Minolta reflectance and color readings, drip loss, and lipid content. The P-value for statistical significance for main effects and interactions was set at <.05 in all analyses. Administration of H resulted in a 17% improvement in Warner-Bratzler shear force (2.69 vs. 3.24 kg), with the shear force similar at two end-point cooking times (11 and 16 min) corresponding to approximately 75 and 83 degrees C, respectively. No differences between H and C were observed for color score, firmness score, Minolta L, Minolta Y, or drip loss on uncooked samples. The H loins had lower marbling scores (P<.05) and intramuscular lipid (P<.05) content than the paired C loin. Sensory evaluation on the randomly selected (n = 16) paired loins samples showed no improvement in Warner-Bratzler shear force. Sensory panelists were also unable to detect a difference between H and C loins for both initial and sustained tenderness scores. No differences between H and C loins were found for pork flavor, off-flavor, cohesiveness, or number of chews before swallowing, but H loins had a significantly lower juiciness score and more cooking loss than C loins. Microbial analysis results showed no differences in coliform bacteria counts, aerobic plate counts, and no detectable levels of Escherichia coli bacteria in any loins. The findings support the ability of the Hydrodyne procedure to improve tenderness without impacting other muscle quality attributes of pork.

Animals↗

PubMed1997

A sequential learning scheme for function approximation using minimal radial basis function neural networks.

This article presents a sequential learning algorithm for function approximation and time-series prediction using a minimal radial basis function neural network (RBFNN). The algorithm combines the growth criterion of the resource-allocating network (RAN) of Platt (1991) with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The resulting network leads toward a minimal topology for the RBFNN. The performance of the algorithm is compared with RAN and the enhanced RAN algorithm of Kadirkamanathan and Niranjan (1993) for the following benchmark problems: (1) hearta from the benchmark problems database PROBEN1, (2) Hermite polynomial, and (3) Mackey-Glass chaotic time series. For these problems, the proposed algorithm is shown to realize RBFNNs with far fewer hidden neurons with better or same accuracy.

Algorithms↗

PubMed1995

Analysis of training set parallelism for backpropagation neural networks.

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper analyzes training set parallelism for feedforward neural networks when implemented on a transputer array configured in a pipelined ring topology. Theoretical expressions for the time per epoch (iteration) and optimal size of a processor network are derived when the training set is equally distributed among the processing nodes. These show that the speed up is a function of the number of patterns per processor, communication overhead per epoch and the total number of processors in the topology. Further analysis of how to optimally distribute the training set on a given processor network when the number of patterns in the training set is not an integer multiple of the number of processors, is also carried out. It is shown that optimal allocation of patterns in such cases is a mixed integer programming problem. Using this analysis it is found that equal distribution of training patterns among the processors is not the optimal way to allocate the patterns even when the training set is an integer multiple of the number of processors. Extension of the analysis to processor networks comprising processors of different speeds is also carried out. Experimental results from a T805 transputer array are presented to verify all the theoretical results.

Algorithms↗