Narrow Results

The standard Morse code defines the tone ratio (dash/dot) and the silent ratio (dash-space/dotspace) as 3:1. Since human typing ratio can't keep this ratio precisely and the two ratios —tone ratio and silent ratio—are not equal, the Morse code can't be recognized automatically. The requirement of the standard ratio is difficult to satisfy even for an ordinary person. As for the unstable Morse code typing pattern, the auto-recognition algorithms in the literature are not good enough in applications. The disabled persons usually have difficulty in maintaining a stable typing speeds and typing ratios, we therefore adopted an Expert-Gating neural network model to implement in single chip and recognize online unstable Morse codes. Also, we used another method—a linear back propagation recalling algorithm, to implement in single chip and recognize unstable Morse codes. From three person tests: Test one is a cerebral palsy; Test two is a beginner: Test three is a skilled expert, we have the results: in the experiment of test one, we have 91.15% (use 6 characters average time series as thresholds) and 91.54% (learning 26 characters) online average recognition rate; test two have 95.77% and 96.15%, and test three have 98.46% and 99.23% respectively. As for linear back propagation recalling method online recognized rate, we have the results from test one: 92.31% online average recognition rate; test two: 96.15%; and test three 99.23% respectively. So, we concluded: The Expert-Gating neural network and the linear back propagation recalling algorithm have successfully overcome the difficulty of analyzing a severely online unstable Morse code time series and successfully implement in single chip to recognize online unstable Morse code.

In this paper, we designed and implemented a user-friendly Chinese phonetic on-screen virtual keyboard key-in system for persons with disabilities. The proposed system inputs the Chinese characters by way of the mouse selecting phonetic symbols. After selecting the initial phonetic symbol, a list of possible phonetic symbol combinations is shown. The proposed system can decrease the number of input clicks needed to select a character, thereby improving typing speed. In addition, the size of the keyboard can be adjusted to increase accuracy and convenience. The system also provides temporary saving and scanning of selections, which makes the keyboard convenient for users. The most frequently typed characters typed by an individual user will be ranked first and this ranking constantly adjusted to facilitate character selection. Moreover, the proposed system shows common combinations of the character typed with other Chinese characters. The system will list all of the possible term correlations for a user to choose from, so that the user spends considerably less time inputting frequently used character combinations. Experimental results showed that the proposed on-screen virtual keyboard system provides an operation interface, which is easier to use, and achieves faster typing speeds compared to two other systems tested.

This study presents a novel mouth-controlled text input (McTin) device that enables users with severe disabilities to access the keyboard and mouse facilities of a standard personal computer via the input of suitable Morse codes processed by sliding window averaging and a fuzzy recognition algorithm. The device offers users the choice of four different modes of operation, namely keyboard-, mouse-, practice-, and remote-control mode. In the keyboard-mode, the user employs a simple mouth-controlled switch to input Morse codes, which the McTin device then translates into the corresponding keyboard character, symbol, or function. In the mouse-mode, the user is able to control the direction of the mouse movement and access the various mouse functions by inputting a maximum of four Morse code elements. The remote-control-mode gives the user the ability to control some of the functions of household appliances such as TV, air conditioner, fan, and lamp. Finally, the practice-mode employs a training environment within which the user may be trained to input Morse codes accurately and quickly via the mouth-controlled switch. Although this study presents the use of a mouth-controlled switch for the input of Morse codes, the form of the input device can be modified to suit the particular requirements of users with different degrees of physical disability. The proposed device has been tested successfully by two users with severe spinal cord injuries to generate text-based articles, send e-mails, draw pictures, and browse the Internet.

This study proposes an Eye input device by electro-oculogram (EOG) recognition for individuals with the motor neuron diseases (MNDs). In this study, the level of the unstable EOG signal is transformed into standard logic level signal by using the baseline tracing algorithm. The standard logic level signal is used as Morse code sequences which is recognized by the sliding fuzzy recognition algorithm embedded in a microprocessor. The result demonstrates that the unstable EOG signals can be successfully transformed into alphanumeric characters and the recognition rate is approximately 99% for the novice users. Accordingly, we designed an inexpensive user computer interface for helping the disabled persons to communicate with others, the user can input text with their eyes to access the computer and household appliances, such as lamps, fans and TV sets.