Four-quadrant CMOS analogue multiplier for artificial neuralnetworks

A four-quadrant CMO analogue multiplier is presented. The proposed multiplier has large dynamic input range, good linearity and can provide either a differential output current or voltage. These properties make the multiplier very suitable for use in the implementation of artificial neural networks     

Trajectory prediction for moving objects using artificial neuralnetworks

A method to predict the trajectory of moving objects in a robotic environment in real-time is proposed and evaluated. The position, velocity, and acceleration of the object are estimated by several neural networks using the six most recent measurements of the object coordinates as inputs. The architecture of the neural nets and the training algorithm are presented and discussed. Simulation results obtained for both 2D and 3D cases are presented to illustrate the performance of the prediction algorithm. Real-time implementation of the neural networks is considered. Finally, the potential of the proposed trajectory prediction method in various applications is discussed     

Chaotic transmission strategies employing artificial neuralnetworks

Two novel chaotic coding and decoding methods based on artificial neural networks (ANNs) are reported which employ the unimodal logistic map (LM) as an example. Coding is carried out by either modulating the LM or by generating the chaotic sequence with ANNs. In simulations speech has been coded and the resulting SNR_sig for the decoded speech has been evaluated. The results demonstrate that the two proposed methods offer a SNR_sig improvement of 4 and 20 dB over the SNR_sig obtained by using the LMS for decoding     

High-order image subsampling using feedforward artificial neuralnetworks

We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). In our method, the high-order subsampling process is decomposed into a sequence of first-order subsampling stages. The first stage employs a tridiagonally symmetrical FANN, which is obtained by applying the design algorithm introduced by Dumitras and Kossentini (see IEEE Trans. Signal Processing, vol.48, p.1446-55, 2000). The second stage employs a small fully connected FANN. The algorithm used to train both FANNs employs information about local edges (extracted using pattern matching) to perform effective subsampling of both high detail and smooth image areas. We show that our multistage first-order subsampling method achieves excellent speed-performance tradeoffs, and it consistently outperforms traditional lowpass filtering and subsampling methods both subjectively and objectively.     

Sensorless control of induction motors by artificial neuralnetworks

In this letter, we propose a voltage-source inverter control working in the open loop of an induction motor measuring the stator current and using an artificial neural network. This technique has the mission to estimate the speed and torque of the rotor without using sensors. With this, a simple and cheap method of control is obtained, with as much precision and robustness as other more complex ones     

Digital systems for artificial neural networks

The current art of digital electronic implementation of neural networks is reviewed. Most of this work has taken place as digital simulations on general-purpose serial or parallel digital computers. Specialized neural network emulation systems have also been developed for more efficient learning and use. Dedicated digital VLSI integrated circuits offer the highest near-term future potential for this technology     

Low-error approximation of artificial neuron sigmoid function and its derivative

A new low-error approximation of the sigmoid function based on the piecewise linear method is proposed. The approximation results, in comparison with those of the state-of-the-art, show the lowest mean absolute and relative errors.     

Generalised scheme for optimal learning in recurrent neuralnetworks

A new learning scheme is proposed for neural network architectures like the Hopfield network and bidirectional associative memory. This scheme, which replaces the commonly used learning rules, follows from the proof of the result that learning in these connectivity architectures is equivalent to learning in the 2-state perceptron. Consequently, optimal learning algorithms for the perceptron can be directly applied to learning in these connectivity architectures. Similar results are established for learning in the multistate perceptron, thereby leading to an optimal learning algorithm. Experimental results are provided to show the superiority of the proposed method     

Learning algorithm for pattern classification using cellular neuralnetworks

A new learning algorithm for pattern classification using cellular neural networks is described. The authors show that patterns belonging to the training set as well as patterns outside it can be classified reliably using the proposed algorithm. Comparisons with well established classification techniques clearly highlight the performances of the approach developed herein     

Multispectral classification of Landsat-images using neuralnetworks

The authors report the application of three-layer back-propagation networks for classification of Landsat TM data on a pixel-by-pixel basis. The results are compared to Gaussian maximum likelihood classification. First, it is shown that the neural network is able to perform better than the maximum likelihood classifier. Secondly, in an extension of the basic network architecture it is shown that textural information can be integrated into the neural network classifier without the explicit definition of a texture measure. Finally, the use of neural networks for postclassification smoothing is examined     

Adaptive speed control for induction motor drives using neuralnetworks

In this paper, the adaptive speed control of induction motor drives using neural networks is presented. To obtain good tracking and regulating control characteristics, a digital two-degree-of-freedom (2DOF) controller is adopted and a design procedure is developed for systematically finding its parameters according to prescribed specifications. The parameters of the controller corresponding to various drive parameter sets are found off-line and used as the training patterns to estimate the connection weights of neural networks, Under normal operation, the true drive parameters are real-time identified and they are converted into the controller parameters through multilayer forward computation by neural networks. The parameters of the 2DOF controller can be adapted to match the desired specifications under various operating conditions     

Cluster analysis preprocessor for path loss modelling using neuralnetworks

The neural networks technique is applied to model path loss of indoor radio propagation. Cluster analysis is employed as a preprocessor to simplify the characterisation of the complicated indoor environment. Simulation results demonstrate that this method is feasible, resulting in a substantial reduction of data input requirement     

Optimum classification of non-Gaussian processes using neuralnetworks

A prerequisite for target detection in synthetic aperture radar and moving target imaging radars is an ability to classify background clutter in an optimal manner. Such radar clutter can frequently be modelled as a correlated nonGaussian process with, for example, Weibull or K statistics. Maximum likelihood (ML) provides an optimum classification scheme but cannot always be formulated when correlations are present. In such circumstances, nonlinear, adaptive filters are required which can learn to classify the clutter types: a role to which neural networks are particularly suited. The authors investigate how closely neural networks can approach optimum classification. To this end, a factorisation technique is presented which aids convergence to the best possible solution obtainable from the training data. The performances of factorised networks are compared with the ML performance and the performances of various intuitive and approximate classification schemes when applied to uncorrelated K distributed images. Furthermore, preliminary results are presented for the classification of correlated processes. It is seen that factorised neural networks can produce an accurate numerical approximation to the ML solution and will thus be of great benefit in radar clutter classification     

DNA ploidy and cell cycle distribution of breast cancer aspiratecells measured by image cytometry and analyzed by artificial neuralnetworks for their prognostic significance

Chromosomal abnormalities are commonly associated with cancer, and their importance in the pathogenesis of the disease has been well recognized. Also recognized in recent years is the possibility that, together with chromosomal abnormalities, DNA ploidy of breast cancer aspirate cells, measured by image cytometric techniques, may correlate with prognosis of the disease. Here, we have examined the use of an artificial neural network to predict: 1) subclinical metastatic disease in the regional lymph nodes and 2) histological assessment, through the analysis of data obtained by image cytometric techniques of fine needle aspirates of breast tumors. The cellular features considered were: 1) DNA ploidy measured in terms of nuclear DNA content as well as by cell cycle distribution; 2) size of the S-phase fraction; and 3) nuclear pleomorphism. A further objective of the study was to analyze individual markers in terms of impact significance on predicting outcome in both cases. DNA ploidy, indicated by cell cycle distribution, was found markedly to influence the prediction of nodal spread of breast cancer, and nuclear pleomorphism to a lesser degree. Furthermore, a comparison between histological assessment and artificial neural network prediction shows a closer correlation between the neural approach and the development of further metastases as indicated in subsequent follow-up, than does histological assessment     

Learn++: an incremental learning algorithm for supervised neuralnetworks

We introduce Learn++, an algorithm for incremental training of neural network (NN) pattern classifiers. The proposed algorithm enables supervised NN paradigms, such as the multilayer perceptron (MLP), to accommodate new data, including examples that correspond to previously unseen classes. Furthermore, the algorithm does not require access to previously used data during subsequent incremental learning sessions, yet at the same time, it does not forget previously acquired knowledge. Learn++ utilizes ensemble of classifiers by generating multiple hypotheses using training data sampled according to carefully tailored distributions. The outputs of the resulting classifiers are combined using a weighted majority voting procedure. We present simulation results on several benchmark datasets as well as a real-world classification task. Initial results indicate that the proposed algorithm works rather well in practice. A theoretical upper bound on the error of the classifiers constructed by Learn++ is also provided     

The computational intractability of training sigmoidal neuralnetworks

We demonstrate that the problem of approximately interpolating a target function by a neural network is computationally intractable. In particular the interpolation training problem for a neural network with two monotone Lipschitzian sigmoidal internal activation functions and one linear output node is shown to be NP-hard and NP-complete if the internal nodes are in addition piecewise ratios of polynomials. This partially answers a question of Blum and Rivest (1992) concerning the NP-completeness of training a logistic sigmoidal 3-node network. An extension of the result is then given for networks with n monotone sigmoidal internal nodes and one convex output node. This indicates that many multivariate nonlinear regression problems may be computationally infeasible     

Left atrial pressure controller design for an artificial heart

This paper describes the application of a dynamic compensator technique to the left atrial controller design for use with a portable artificial heart drive system. The compensator is designed using a method in the field of multivariable control. This controller design is based on the physical models of the actuator and blood pump system. The analysis shows that there exists a minimal compensator with a dimension of one. The computer simulation demonstrates the acceptable, robust control performance of the left atrial pressure for a relatively small parameter variation of the vascular system model when all the poles of the closed-loop system are assigned to appropriate values.     

Comparison of software-reliability-growth predictions: neuralnetworks vs parametric-recalibration

This paper compares empirically the predictive performance of two different methods of software reliability prediction: `neural networks' and `recalibration for parametric models'. Both methods were claimed to predict as good or better than the conventional parametric models that have been used-with limited results so far. Each method applied its own predictability measure, impeding a direct comparison. To be able to compare, this study uses a common predictability measure and common data-sets. This study reveals that neural networks are not only much simpler to use than the recalibration method, but that they are equal or better trend (variable term) predictors. The neural network prediction is further improved by preparing the data with a running average, instead of the traditionally used averages of grouped data points. Neural network predictions do not depend on prior known models. Off-the-shelf neural network software tools make it easy to apply the method     

基于数字地图的导弹可飞行面设计

数字地图预处理是导弹基于数字地图导航的关键技术,提出了一种考虑导弹最大飞行曲率限制的变步长数字地图预处理算法,该算法分区域采用曲率差控制平滑迭代步长,使平滑过程加快,提高迭代速度,平滑后的地形不仅能满足导弹的纵向机动能力的限制,而且能够较好地贴近原地形。最后对算法进行了仿真研究,仿真结果表明该算法可快速完成数字地图的平滑任务,能够为导弹提供理想的可飞行安全曲面。     

多相码信号数字脉压滤波器设计

对较小时宽带宽积相位编码信号的时域副瓣抑制滤波器设计问题进行了研究。在约束主瓣输出为常数时使积分副瓣电平最小化，利用最小二乘算法和加权迭代方法，适当放宽主瓣宽度，以使主副比达到最优。仿真结果表明，该方法的设计结果在一定多普勒频率范围内，与匹配滤波相比，能达到10dB以上的主副比改善，且主瓣宽度展宽不大，信噪比损失小于0．5dB。