Pierre Lavoie

A comparison of automatic word length optimization procedures

This paper presents a comparison of word length determination procedures. It is realized using an automated testbed that exploits a C/C++ fixed-point simulation utility to model the impact of finite word length on overall accuracy. Word length determination procedures find a combination of optimum bit resolutions by computing dissimilarities between fixed-point and floating-point simulation results. The comparison helps to select a procedure that minimizes these dissimilarities and finds an optimal combination of word lengths that meet user specified objectives, in a minimum number of iterations and hardware cost. This comparison was applied on various DSP algorithms.

A what-and-where fusion neural network for recognition and tracking of multiple radar emitters

A neural network recognition and tracking system is proposed for classification of radar pulses in autonomous Electronic Support Measure systems. Radar type information is considered with position-specific information from active emitters in a scene. Type-specific parameters of the input pulse stream are fed to a neural network classifier trained on samples of data collected in the field. Meanwhile, a clustering algorithm is used to separate pulses from different emitters according to position-specific parameters of the input pulse stream. Classifier responses corresponding to different emitters are separated into tracks, or trajectories, one per active emitter, allowing for more accurate identification of radar types based on multiple views of emitter data along each emitter trajectory. Such a What-and-Where fusion strategy is motivated by a similar subdivision of labor in the brain. The fuzzy ARTMAP neural network is used to classify streams of pulses according to radar type using their functional parameters. Simulation results obtained with a radar pulse data set indicate that fuzzy ARTMAP compares favorably to several other approaches when performance is measured in terms of accuracy and computational complexity. Incorporation into fuzzy ARTMAP of negative match tracking (from ARTMAP-IC) facilitated convergence during training with this data set. Other modifications improved classification of data that include missing input pattern components and missing training classes. Fuzzy ARTMAP was combined with a bank of Kalman filters to group pulses transmitted from different emitters based on their position-specific parameters, and with a module to accumulate evidence from fuzzy ARTMAP responses corresponding to the track defined for each emitter. Simulation results demonstrate that the system provides a high level of performance on complex, incomplete and overlapping radar data.

An automatic word length determination method

A method to determine the word length required by implementations of Digital Signal Processing (DSP) algorithms is presented. The method uses a C/C++ fixed-point simulation tool to model the impact of finite word length on overall accuracy. It finds a combination of quasi-optimum bit resolutions in arbitrary data flow graphs by computing dissimilarities between fixed-point and floating-point simulation results. The selected algorithm minimizes these dissimilarities and finds a combination of word lengths that meets objectives specified by the user. This method is applicable to a wide range of DSP algorithms. It was tested on 2 benchmarks, the fifth order elliptic filter and the Inverse Discrete Cosine Transform (IDCT), and arrived to known optimum solutions.

A systolic architecture for fast stack sequential decoders

The troublesome operation of reordering the stack in stack sequential decoders is alleviated by storing the nodes in a systolic priority queue that delivers the true top node in a short and constant amount of time. A new systolic priority queue is described that allows each decoding step, including retrieval, reordering and storage of the nodes, to take place in a single clock period. A complete decoder architecture designed around this queue is compared to a conventional stack-bucket architecture from both speed and cost points of view. The proposed decoder architecture appears to be faster, affordable, and compatible with convolutional codes having long memory and high coding rate. >

Classification of incomplete data using the fuzzy ARTMAP neural network

The fuzzy ARTMAP neural network is used to classify data that is incomplete in one or more ways. These include a limited number of training cases, missing components, missing class labels, and missing classes. Modifications for dealing with such incomplete data are introduced, and performance is assessed on an emitter identification task using a database of radar pulses.

A comparison of self-organizing neural networks for fast clustering of radar pulses

Abstract Four self-organizing neural networks are compared for automatic deinterleaving of radar pulse streams in electronic warfare systems. The neural networks are the Fuzzy Adaptive Resonance Theory, Fuzzy Min–Max Clustering, Integrated Adaptive Fuzzy Clustering, and Self-Organizing Feature Mapping. Given the need for a clustering procedure that offers both accurate results and computational efficiency, these four networks are examined from three perspectives – clustering quality, convergence time, and computational complexity. The clustering quality and convergence time are measured via computer simulation, using a set of radar pulses collected in the field. Estimation of the worst-case running time for each network allows for the assessment of computational complexity. The effect of the pattern presentation order is analyzed by presenting the data not just in random order, but also in radar-like orders called burst and interleaved.

New architectures for fast convolutional encoders and threshold decoders

Several new architectures for high-speed convolution encoders and threshold decoders are developed. In particular, it is shown that new architectures featuring both parallelism and pipelining are promising from a speed point of view. These architectures are practical for a wide range of coding rates and constant lengths. Two integrated circuits featuring these architectures have been designed and fabricated in a CMOS 3- mu m technology. The two circuits have been tested and can be used to build convolutional encoders and definite threshold decoders operating at data rates above 100 Mb/s. It is shown that with these architectures, encoders and threshold decoders could easily be designed to operate at data rates above 1 Gb/s. >

Generalization, discrimination, and multiple categorization using adaptive resonance theory

The internal competition between categories in the adaptive resonance theory (ART) neural model can be biased by replacing the original choice function by one that contains an attentional tuning parameter under external control. For the same input but different values of the attentional tuning parameter, the network can learn and recall different categories with different degrees of generality, thus permitting the coexistence of both general and specific categorizations of the same set of data. Any number of these categorizations can be learned within one and the same network by virtue of generalization and discrimination properties. A simple model in which the attentional tuning parameter and the vigilance parameter of ART are linked together is described. The self-stabilization property is shown to be preserved for an arbitrary sequence of analog inputs, and for arbitrary orderings of arbitrarily chosen vigilance levels.

New VLSI architectures for fast soft-decision threshold decoders

New VLSI architectures for fast convolutional threshold decoders that process soft-quantized channel symbols are presented. The new architectures feature pipelining and parallelism and make it possible to fabricate decoders for data rates up to hundreds of Mbits per second. With these architectures, the data rate is shown to be independent of the memory of the code, implying that fast AAPP (approximate a posteriori probability) decoders can be built for long powerful codes. Furthermore, the architectures are convenient to use with low and high coding rates. Using a typical example it is shown that a soft-decision threshold decoder can provide a substantial coding gain while being less costly to implement than the hard-decision threshold decoder. >

A Metric for Automatic Word-Length Determination of Hardware Datapaths

A metric for the automatic determination of word lengths required for implementing DSP algorithms is proposed. The metric is capable of handling several error models computed between the fixed-point and the floating-point simulation results to model the impact of finite word lengths on the overall accuracy. It grades all the word-length combinations and guides a procedure towards the optimal solution. This metric was implemented in an automatic word-length determination tool to guide its search for better hardware implementations. It enables the creation of a framework for architecture and platform exploration