The emergence of digital music in the Internet calls for a reliable real-time tool to analyze and properly categorize them for the users. To incorporate content or genre queries in Web searches, audio content analysis and classification is imperative. This paper proposes a set of audio content features and a parallel neural network architecture that addresses the task of automated content based audio classification. Feature sets based on signal periodicity, beat information, sub-band energy, mel-frequency cepstral coefficients and wavelet transforms are proposed and each of the feature sets are individually analyzed for their pertinence in the proposed task. A parallel multi-layered perceptron network is proposed which offers a classification accuracy of 84.4% to distinguish between 6 different genres. The proposed architecture is compared with a support vector machine based classifier and is found to perform superiorly than the later.

Our research focuses on finding mathematical representations of biometric features that are not only distinctive, but also invariant to projective transformations. We have chosen hand geometry technology to work with, because it has wide public awareness and acceptance and most important, large space for improvement. Unlike the traditional hand geometry technologies, the hand descriptor in our hand geometry system is constructed using projective-invariant features. Hand identification can be accomplished by a single view of a hand regardless of the viewing angles. The noise immunity and the discriminability possessed by a hand feature vector using different types of projective invariants are studied. We have found an appropriate symmetric polynomial representation of the hand features with which both noise immunity and discrimminability of a hand feature vector are considerably improved. Experimental results show that the system achieves an equal error rate (EER) of 2.1% by a 5-D feature vector on a database of 52 hand images. The EER reduces to 0.00% when the feature vector dimension increases to 18. In this paper, we extend the concept of hand geometry from a geometrical size-based technique that requires physical hand constraints to a projective invariant-based technique that allows free hand motion.

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification.

This paper presents a new model integrating a recurrent neural network (RNN) and a least squares support vector machine (LS-SVM) for classification of document titles according to different predetermined categories. The new model proposed in this paper is abbreviated as neuro-SVM. Based on the neuro-SVM model, a system is implemented, using latent semantic indexing (LSI) to generate probabilistic coefficients from document titles, which are used as the input to the system. The system's performance is demonstrated with a corpus of 96956 words, from University of Denver's Penrose library catalogue and the accuracy rate of the proposed system is found to be 99.66%.

In this paper we present a neural network for detection of fish, from light detection and ranging (LIDAR) data and have described a classification method for distinguishing between water-layer, bottom and fish. Four multi-layer perceptrons (MLP) were developed for the classification purpose, where classes include fish, bottom and water-layer. The LIDAR data gives a sequence of intensity of laser backscatters obtained from laser shots at various heights above the Earth surface. The data is preprocessed to remove the high frequency noise and then a window of the sample is selected for further processing to extract features for classification purposes. We have used linear predictive coding (LPC) analysis for the feature detection purpose. The results show that the detection technique is effective and can do the required classification with a high degree of accuracy. We have tried our approach with four different MLPs and are presenting the data obtained from each of them.

The message delivery time on a low Earth orbit (LEG) satellite network is analyzed. The LEO network is assumed to be seamless and virtual cut-through switching is proposed for use. Equations to calculate the message delivery time and the probability of a message being delivered successfully using no more than a time delay bound for LEO networks, varying in size and connectivity, are derived. The message delivery times of different LEO networks, varying in network connectivity, are compared. Numerical examples show that with the probability of successful delivery =0.99 and the probability of cut-through =0.5, an 8/spl times/8 LEO network with six crosslinks per node can deliver messages 40% faster than with four crosslinks per node for communicating satellites, separated by D hops, where D is the network diameter.>

The paper presents a comparative study of circuit area and performance degradation among four pipelined RISC processors using different precise interrupt methods. The precise interrupt methods studied, include inorder completion, reorder buffer, history file and future file. The VHDL is used to model five machines at the register transfer level. The Synopsys design compiler is used to synthesize these machines as a netlist of CMOS logic gates, then gate counts are obtained. Based on our model architecture and benchmark programs, it shows that the history file method can achieve the highest performance and consume less silicon area than the reorder buffer method and the future file method.>

A three-layer neural network is trained to perform spectral estimation. Excellent performance is found through computer simulations. When compared with an equivalent length radix-2 fast Fourier transform, the neural network has the following advantages: (1) the neural network can suppress the signal magnitude in sidelobes without widening the mainlobe; (2) the neural network completes its computation in two stages regardless of the number of input signal samples; (3) the number of input signal samples does not need to be an integer power of two; and (4) the neural network still generates valid results even if there are 25% broken interconnects uniformly distributed between the output layer and the hidden layer or between the hidden layer and the input layer. An application example of using a three-layer neural network for moving target detection is also included.>

A message-passing computer architecture called the modified mesh-connected parallel computer (MMCPC) is proposed and studied. The MMCPC is designed to be general-purpose parallel architecture suitable for wafer-scale integration. Generalized stochastic Petri nets (GSPNs) are used to model the behavior of the MMCPC. The GSPN performance modeling results show a need for a new processing element (PE). A PE architecture, able to handle data processing and message passing concurrently, is proposed, and the silicon overhead is estimated in comparison with transputerlike PEs. Based on the proposed PE, optimum sizes of the MMCPC for different program structures are derived. A two-dimensional fast Fourier transform problem is used as an example to demonstrate that the MMCPC is a cost-effective performance-enhancement architecture to a real problem.>

We simulate three neural networks on a vector multiprocrssor. The training time can be reduced significantly especially when the training data size is large. These three neural networks are: 1) the feedforward network, 2) the recurrent network and 3) the Hopfield network. The training algorithms are programmed in such a way to best utilize 1) the inherent parallelism in neural computing, and 2) the vector and concurrent operations available on the parallel machine. To prove the correctness of parallelized training algorithms, each neural network is trained to perform a specific function. The feedforward network is trained to perform the Fourier transform, the recurrent network is trained to predict the solution of a delay differential equation, the Hopfield network is trained to solve the traveling salesman problem. The machine we experiment with is the Alliant FX/80.

Parallel Monte Carlo techniques for simulating the evolution of an assembly of charged particles interacting with a background gas medium under the influence of the electrical field are presented. This simulation problem has inherent parallelism in nature. All the particles can be traced independently in a short time interval. We have overcome three major difficulties: 1) the number of particles to be simulated is increasing over time due to the ionization process; 2) the conditional branching statements do not inhibit multiprocessing through proper manual program tuning; 3) concurrency and vectorization are fully utilized through the new parallelized Monte Carlo method. The shared—memory vector multiprocessor Alliant FX/80 has been used for performance measurements. Significant speedup has been achieved.