F.K. Lam

Fuzzy EMG classification for prosthesis control

This paper proposes a fuzzy approach to classify single-site electromyograph (EMG) signals for multifunctional prosthesis control. While the classification problem is the focus of this paper, the ultimate goal is to improve myoelectric system control performance, and classification is an essential step in the control. Time segmented features are fed to a fuzzy system for training and classification. In order to obtain acceptable training speed and realistic fuzzy system structure, these features are clustered without supervision using the Basic Isodata algorithm at the beginning of the training phase, and the clustering results are used in initializing the fuzzy system parameters. Afterwards, fuzzy rules in the system are trained with the back-propagation algorithm. The fuzzy approach was compared with an artificial neural network (ANN) method on four subjects, and very similar classification results were obtained. It is superior to the latter in at least three points: slightly higher recognition rate; insensitivity to overtraining; and consistent outputs demonstrating higher reliability. Some potential advantages of the fuzzy approach over the ANN approach are also discussed.

Adaptive thresholding by variational method

When using thresholding method to segment an image, a fixed threshold is not suitable if the background is uneven. Here, we propose a new adaptive thresholding method using variational theory. The method requires only one parameter to be selected and the adaptive threshold surface can be found automatically from the original image.

Image Contrast Enhancement by Constrained Local Histogram Equalization

Histogram equalization is a widely used image contrast enhancement method. While global histogram equalization enhances the contrast of the whole image, local histogram equalization can enhance many image details by taking different transformation of the same gray level at different places in the original image. However, the local histogram equalization process often results in unacceptable modification of the original image appearance. In this paper, a constrained local histogram equalization method is proposed to balance the conflicting requirements: enhancement of the image details and the maintenance of the overall image appearance. Our method uses the variational form of histogram equalization so that a constraint condition, which forces the local gray level transformations to change continuously in the spatial domain, can be introduced into the equalization process. Experimental results of different kinds of images show the effect of our method.

Adaptive filtering of evoked potentials with radial-basis-function neural network prefilter

Evoked potentials (EPs) are time-varying signals typically buried in relatively large background noise. To extract the EP more effectively from noise, we had previously developed an approach using an adaptive signal enhancer (ASE) (Chen et al., 1995). ASE requires a proper reference input signal for its optimal performance. Ensemble- and moving window-averages were formerly used with good results. In this paper, we present a new method to provide even more effective reference inputs for the ASE. Specifically, a Gaussian radial basis function neural network (RBFNN) was used to preprocess raw EP signals before serving as the reference input. Since the RBFNN has built-in nonlinear activation functions that enable it to closely fit any function mapping, the output of RBFNN can effectively track the signal variations of EP. Results confirmed the superior performance of ASE with RBFNN over the previous method.

A time domain binaural model based on spatial feature extraction for the head-related transfer function

A complex-valued head-related transfer function (HRTF) can be represented as a real-valued head-related impulse response (HRIR). The interaural time and level cues of HRIRs are extracted to derive the binaural model and also to normalize each measured HRIR. Using the Karhunen-Loeve expansion, normalized HRIRs are modeled as a weighted combination of a set of basis functions in a low-dimensional subspace. The basis functions and the space samples of the weights are obtained from the measured HRIR. A simple linear interpolation algorithm is employed to obtain the modeled binaural HRIRs. The modeled HRIRs are nearly identical to the measured HRIRs from an anesthetized live cat. Typical mean-square errors and cross-correlation coefficients between the 1816 measured and modeled HRIRs are 1% and 0.99, respectively. The real-valued operations and linear interpolating in the model are very effective for speeding up the model computation in real-time implementation. This approach has made it possible to simulate real free-field signals at the two eardrums of a cat via earphones and to study the neuronal responses to such a virtual acoustic space (VAR).

Effect of cage size on ultradian locomotor rhythms of laboratory mice.

The effect of cage size on spontaneous locomotor rhythms of laboratory mice was studied under simulated light-dark (12:12) cycles. On-line image analysis of bodily displacement yielded a locomotor signal over a period of 3 days. Continuous wavelet transform was applied to the signal, and ensemble averaging of eight mice revealed in the time-frequency plot bouts of increased motor activities. Notably, there were two bouts in the dark corresponding to ultradians of periods below 5 h: a first bout at the dark onset (at 0.6-1.0 cycle/h), and a second bout during the second half of the dark period (at 0.4-0.7 cycle/h). These increases of activity were more intense and distinct when the animals were kept inside the larger cage. Furthermore, the first bout disappeared when the animals were kept in the small cage for 3 days.

Real-time data-reusing adaptive learning of a radial basis function network for tracking evoked potentials

Tracking variations in both the latency and amplitude of evoked potential (EP) is important in quantifying properties of the nervous system. Adaptive filtering is a powerful tool for tracking such variations. In this paper, a data-reusing nonlinear adaptive filtering method, based on a radial basis function network (RBFN), is implemented to estimate EP. The RBFN consists of an input layer of source nodes, a single hidden layer of nonlinear processing units and an output layer of linear weights. It has built-in nonlinear activation functions that allow learning of function mappings. Moreover, it produces satisfactory estimates of signals against a background noise without a priori knowledge of the signal, provided that the signal and noise are independent. In clinical situations where EP responses change rapidly, the convergence rate of the algorithm becomes a critical factor. A carefully designed data-reusing RBFN can accelerate the convergence rate markedly and, thus, enhance its performance. Both theoretical analysis and simulation results support the improved performance of our new algorithm.

Measurement of human BAERs by the maximum length sequence technique

The traditional brainstem auditory evoked response (BAER) measurement technique (ensemble averaging) is time-consuming and is not acceptable for some time-critical clinical applications. In the paper the application of a pseudorandom binary sequence, the maximum length sequence, to human BAER measurements is examined. This technique permits a faster click rate to stimulate the test subject, and obtaines a higher signal-to-noise ratio (SNR) response through deconvolution. When compared with conventional averaging, the method can result in an improved SNR or in faster measurement of BAER. The theory of the technique and the experimental setup are presented, and theoretical analysis on the SNR improvement by this technique against averaging is also given. Actual measurements of BAER on both humans and cats indicate that this technique is effective, especially when the measurement time is not too long, or the number of trials is not too large.

Sequential approach to blind source separation using second order statistics

A general result on identifiability for the blind source separation problem, based on second order statistics only, is presented. The separation principle using second order statistics is first proposed. This is followed by a discussion on a number of algorithms to separate the sources one by one.

A Novel Approach to Fast Discrete Fourier Transform

Discrete Fourier transform (DFT) is an important tool in digital signal processing. In the present paper, we propose a novel approach to performing DFT. We transform DFT into a form expressed in discrete moments via a modular mapping and truncating Taylor series expansion. From this, we extend the use of our systolic array for fast computation of moments without any multiplications to one that computes DFT with only a few multiplications and without any evaluations of exponential functions. The multiplication number used in our method isO(Nlog2N/ log2log2N) superior toO(Nlog2N) in FFT. The execution time of the systolic array is onlyO(Nlog2N/ log2log2N) for 1-D DFT andO(Nk) fork-D DFT (k?2). The systolic implementation is a demonstration of the locality of dataflow in the algorithms and hence it implies an easy and potential hardware/VLSI realization. The approach is also applicable to DFT inverses.