The conventional computer keyboard is unable to provide a useable communication device for physically disabled persons with such disabilities as muscle atrophy, cerebral palsy, and severe handicap. In this paper, the ...
详细信息
The conventional computer keyboard is unable to provide a useable communication device for physically disabled persons with such disabilities as muscle atrophy, cerebral palsy, and severe handicap. In this paper, the Morse code is selected as a communication adaptive device for entering Mandarin phonetic symbols into a computer. Although a stable typing rate is strictly required for an accurate recognition of Mandarin phonetic Morse code, maintaining this rate is a challenge for the disabled. Therefore, a suitable adaptive automatic recognition method is needed. Four processes are involved in this adaptive Mandarin phonetic Morse code recognition method: space recognition, tone recognition, adaptive processing, and character recognition. Experimental results revealed that the recognition rate generated by the proposed method elicited as high as a 90% improvement over alternative methods from the literature.
Morse code with an easy-to-operate, single switch input system has been shown to be an excellent communication adaptive device. Because maintaining a stable typing rate is not easy for the disabled, the automatic reco...
详细信息
Morse code with an easy-to-operate, single switch input system has been shown to be an excellent communication adaptive device. Because maintaining a stable typing rate is not easy for the disabled, the automatic recognition of Morse code is difficult. Therefore, a suitable adaptive automatic recognition method is needed. This paper presents the application of a least-mean-square algorithm to adaptive Morse code recognition for persons with impaired hand coordination and dexterity. Four processes are involved in this adaptive Morse code recognition method: space recognition, tone recognition, adaptive processing, and character recognition. Statistical analyses demonstrated that the proposed method results in a better recognition rate for the participants tested in comparison to other methods from the literature. (C) IPEM. Published by Elsevier Science Ltd. All rights reserved.
Single-switch communication is an effective auxiliary method for persons with disabilities. However, it is not easy to recognize the Morse codes typed by them. In our earlier proposed Morse code auto-recognition metho...
详细信息
Single-switch communication is an effective auxiliary method for persons with disabilities. However, it is not easy to recognize the Morse codes typed by them. In our earlier proposed Morse code auto-recognition method, using the least-mean-square (LMS) adaptive algorithm, it was demonstrated that the system could successfully recognize the Morse-coded messages at unstable typing speeds. However, the speed variation had to be limited to a range between 0.67 and two times the present speed. In the case of beginners or those with heavy disabilities, this rule can not always be complied with, producing a low recognition rate of 20%. To address this limitation, this paper offers an advanced recognition method which combines the least-mean-square algorithm with a character-by-character matching technique. The recognition rate for this method from simulated and real data from various sources is as high as 75% or more on average. This practical application of the single-switch method means a step forward toward alternative communication for disabled persons. (C) 1997 Elsevier Science Ireland Ltd.
The variable-step-size least-mean-square (VSLMS) algorithm is explored and adopted for tracking of time-varying environments. Two implementations of the VSLMS algorithm are proposed. The emphasis is on the implementat...
详细信息
The variable-step-size least-mean-square (VSLMS) algorithm is explored and adopted for tracking of time-varying environments. Two implementations of the VSLMS algorithm are proposed. The emphasis is on the implementations with different step sizes at various taps of the adaptive filter. General analysis of the VSLMS algorithm appears to be somewhat involved. However, for one implementation a limited analysis of the algorithm is found possible. For this implementation it is shown that, when the input samples to the adaptive filter are zero-mean, Gaussian and uncorrelated with one another, the VSLMS algorithm can adapt itself to select the optimum set of step sizes which results in the best-tracking performance. Simulation experiments with the VSLMS algorithm show that, under fairly mild conditions, both of the proposed implementations adapt toward the optimum step sizes.
Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network tr...
详细信息
Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network training algorithms (including the perceptron rule, the least-mean-square algorithm, three Madaline rules, and the backpropagation technique) are described. The concept underlying these iterative adaptation algorithms is the minimal disturbance principle, which suggests that during training it is advisable to inject new information into a network in a manner that disturbs stored information to the smallest extent possible. The two principal kinds of online rules that have developed for altering the weights of a network are examined for both single-threshold elements and multielement networks. They are error-correction rules, which alter the weights of a network to correct error in the output response to the present input pattern, and gradient rules, which alter the weights of a network during each pattern presentation by gradient descent with the objective of reducing mean-square error (averaged over all training patterns)
We developed a new algorithm for supervised adaptive classifications with rapid incremental learning characteristics in dynamic environments. The new algorithm outperforms the Widrow-Hoff algorithm in applications whe...
详细信息
We developed a new algorithm for supervised adaptive classifications with rapid incremental learning characteristics in dynamic environments. The new algorithm outperforms the Widrow-Hoff algorithm in applications where: (a) real-time response is required, (b) the classifer is subjected to repeated train-then-apply cycles, and (c) the class distributions may change dynamically. The algorithm introduces (a) a dynamic cluster center representation, (b) a “balancing training” strategy, and (c) look-ahead learning by guard bands. Computational overhead for the improved performance is not excessive and strategies are further devised to reduce the overall computational complexity. The new algorithm is benchmarked against the Widrow-Hoff algorithm working as a clutter rejection unit in a target tracking system. Performance is shown for three sets of FLIR image sequence. The new algorithm outperformed the Widrow-Hoff algorithm (in terms of reduced misclassifications, and missed and false target rates). The improvement in missed target rate is very dramatic. The results also show that the new algorithm is not sensitive to parameter-setting.
This paper discusses the theory and implementation of an adaptive controller which can track plant with time-varying parameters as well as time-varying transport delay. It also allows for closed-loop pole placement an...
详细信息
This paper discusses the theory and implementation of an adaptive controller which can track plant with time-varying parameters as well as time-varying transport delay. It also allows for closed-loop pole placement and, because there are no restrictions on closed-loop zeros, good set-point tracking can be achieved. The scheme is based on the well-known least-mean-square algorithm to generate a finite impulse response (F.I.R.) controller and can therefore be implemented readily using one of the new generation signal processor chips.
暂无评论