Detection of Motor Impairment in Parkinson's Disease Via Mobile Touchscreen Typing.

Mobile technology is opening a wide range of opportunities for transforming the standard of care for chronic disorders. Using smartphones as tools for longitudinally tracking symptoms could enable personalization of drug regimens and improve patient monitoring. Parkinson's disease (PD) is an ideal candidate for these tools. At present, evaluation of PD signs requires trained experts to quantify motor impairment in the clinic, limiting the frequency and quality of the information available for understanding the status and progression of the disease. Mobile technology can help clinical decision making by completing the information of motor status between hospital visits. This paper presents an algorithm to detect PD by analyzing the typing activity on smartphones independently of the content of the typed text. We propose a set of touchscreen typing features based on a covariance, skewness, and kurtosis analysis of the timing information of the data to capture PD motor signs. We tested these features, both independently and in a multivariate framework, in a population of 21 PD and 23 control subjects, achieving a sensitivity/specificity of 0.81/0.81 for the best performing feature and 0.73/0.84 for the best multivariate method. The results of the alternating finger-tapping, an established motor test, measured in our cohort are 0.75/0.78. This paper contributes to the development of a home-based, high-compliance, and high-frequency PD motor test by analysis of routine typing on touchscreens.

CA²JU: an Assistive Tool for Children with Cerebral Palsy.

This paper presents CA2JU, a hardware/software tool that aims to help individuals with severe speech or language problems in their communication in order to promote their social and digital inclusion. CA2JU is composed of two applications: CA2JU Accelerated, which makes typing faster by suggesting potential words to the user; and CA2JU Illustrated, which automatically converts a sentence of words into a sequence of pictographic symbols, allowing a user familiar with the symbols to verify whether the written sentence is correct. We have implemented, evaluated in a controlled scenario, and deployed CA2JU in a real environment with children with cerebral palsy. In the controlled settings, the results confirm CA2JU Accelerated speed up typing by reducing the number of clicks made by users, and CA2JU Illustrated obtained high accuracy by suggesting the correct pictograms from sentences. In the real scenario, the two use cases show that the children improved their communication and linguistic abilities.

Investigation of the piezoelectric thimble tactile device operating modes.

A multifunctional device to transfer graphical or text information for blind or visually impaired is presented. The prototype using tactile perception has been designed where information displayed on the screen of electronic device (mobile phone, PC) is transferred by oscillating needle, touching the fingertip. Having the aim to define optimal parameters of the fingertip excitation by needle, the computational analysis of different excitation modes has been carried out. A 3D solid computational finite element model of the skin segment, comprising four main fingertip skin layers (stratum corneum, epidermis, dermis and hypodermis) was built by using ANSYS Workbench FEA software. Harmonic analysis of its stress-strain state under excitation with different frequency (up to 10000 Hz) and harmonic force (0.01 N), acting outer stratum corneum layer in normal direction at one, two or three points has been performed. The influence of the mode of dynamic loading of skin was evaluated (in terms of the tactile signal level) on the basis of the normal and shear elastic strain in dermis, where mechanoreceptors are placed. It is shown that the tactile perception of information, delivered by three vibrating pins, may be influenced by configuration of excitation points (their number and phase of loading) and the frequency of excitation.

P300 speller BCI with a mobile EEG system: comparison to a traditional amplifier.

OBJECTIVE: In a previous study, we presented a low-cost, small and wireless EEG system enabling the recording of single-trial P300 amplitudes in a truly mobile, outdoor walking condition (Debener et al (2012 Psychophysiology 49 1449-53)). Small and wireless mobile EEG systems have substantial practical advantages as they allow for brain activity recordings in natural environments, but these systems may compromise the EEG signal quality. In this study, we aim to evaluate the EEG signal quality that can be obtained with the mobile system. APPROACH: We compared our mobile 14-channel EEG system with a state-of-the-art wired laboratory EEG system in a popular brain-computer interface (BCI) application. N = 13 individuals repeatedly performed a 6 × 6 matrix P300 spelling task. Between conditions, only the amplifier was changed, while electrode placement and electrode preparation, recording conditions, experimental stimulation and signal processing were identical. MAIN RESULTS: Analysis of training and testing accuracies and information transfer rate (ITR) revealed that the wireless mobile EEG amplifier performed as good as the wired laboratory EEG system. A very high correlation for testing ITR between both amplifiers was evident (r = 0.92). Moreover the P300 topographies and amplitudes were very similar for both devices, as reflected by high degrees of association (r > = 0.77). SIGNIFICANCE: We conclude that efficient P300 spelling with a small, lightweight and quick to set up mobile EEG amplifier is possible. This technology facilitates the transfer of BCI applications from the laboratory to natural daily life environments, one of the key challenges in current BCI research.

What skilled typists don't know about the QWERTY keyboard.

We conducted four experiments to investigate skilled typists' explicit knowledge of the locations of keys on the QWERTY keyboard, with three procedures: free recall (Exp. 1), cued recall (Exp. 2), and recognition (Exp. 3). We found that skilled typists' explicit knowledge of key locations is incomplete and inaccurate. The findings are consistent with theories of skilled performance and automaticity that associate implicit knowledge with skilled performance and explicit knowledge with novice performance. In Experiment 4, we investigated whether novice typists acquire more complete explicit knowledge of key locations when learning to touch-type. We had skilled QWERTY typists complete a Dvorak touch-typing tutorial. We then tested their explicit knowledge of the Dvorak and QWERTY key locations with the free recall task. We found no difference in explicit knowledge of the two keyboards, suggesting that typists know little about key locations on the keyboard, whether they are exposed to the keyboard for 2 h or 12 years.

A dual-mode human computer interface combining speech and tongue motion for people with severe disabilities.

We are presenting a new wireless and wearable human computer interface called the dual-mode Tongue Drive System (dTDS), which is designed to allow people with severe disabilities to use computers more effectively with increased speed, flexibility, usability, and independence through their tongue motion and speech. The dTDS detects users' tongue motion using a magnetic tracer and an array of magnetic sensors embedded in a compact and ergonomic wireless headset. It also captures the users' voice wirelessly using a small microphone embedded in the same headset. Preliminary evaluation results based on 14 able-bodied subjects and three individuals with high level spinal cord injuries at level C3-C5 indicated that the dTDS headset, combined with a commercially available speech recognition (SR) software, can provide end users with significantly higher performance than either unimodal forms based on the tongue motion or speech alone, particularly in completing tasks that require both pointing and text entry.

Performance models for automatic evaluation of virtual scanning keyboards.

Virtual scanning keyboards are commonly used augmentative communication aids by persons with severe speech and motion impairments. Designers of virtual scanning keyboards face problems in evaluating alternate designs and hence in choosing the better design among alternatives. Automatic evaluation of designs will be helpful to designers in making the appropriate design choice. In this paper, we present performance models for virtual scanning keyboards that can be used for automatic evaluation. The proposed models address the limitations present in the reported work on similar models. We compared the model predictions with results from user trials and established the validity of the proposed models.

Effect of wrist posture on carpal tunnel pressure while typing.

Long weekly hours of keyboard use may lead to or aggravate carpal tunnel syndrome. The effects of typing on fluid pressure in the carpal tunnel, a possible mediator of carpal tunnel syndrome, are unknown. Twenty healthy subjects participated in a laboratory study to investigate the effects of typing at different wrist postures on carpal tunnel pressure of the right hand. Changes in wrist flexion/extension angle (p = 0.01) and radial/ulnar deviation angle (p = 0.03) independently altered carpal tunnel pressure; wrist deviations in extension or radial deviation were associated with an increase in pressure. The activity of typing independently elevated carpal tunnel pressure (p = 0.001) relative to the static hand held in the same posture. This information can guide the design and use of keyboards and workstations in order to minimize carpal tunnel pressure while typing. The findings may also be useful to clinicians and ergonomists in the management of patients with carpal tunnel syndrome who use a keyboard.

Development of the input equipment for a computer using surface EMG.

SEMG (surface EMG) has many benefits, for example measuring SEMG is easy and a characteristic pattern of SEMG is obtained for each different movement. Therefore, SEMG that is generated by body movement is able to use as a control signal for some electric powered equipments. Our objective is the perfect control of the computer by using SEMG that is generated from forearms. In this paper, we will talk about our developed interface system that works as a keyboard of the computer.

Development and evaluation of a wireless interface for inputting characters using Laplacian EMG.

We developed a compact wireless electrode containing an amplifier, a filter and a transmitter to measure the Laplacian electromyogram (Laplacian EMG) using the source derivation method. We made a character input system by connecting a circuit converting Laplacian EMG signals to clicks, with a personal computer in which a software for scanning character input was installed. We evaluated the system by comparing two integrated EMGs (IEMGs) measured with a conventional amplifier: one measured when the Laplacian EMG was used as an input signal to the system during a character inputting task, and the other measured when the conventional EMG was used. The IEMG was smaller in all of five subjects when the Laplacian EMG was used as the input signal than when the conventional EMG was used.

Keyboarding for students with handwriting problems: a literature review.

A literature review is presented regarding keyboarding for school students experiencing handwriting difficulties. Despite the overall dearth of research, some general conclusions appear warranted. Students need to be able to keyboard at least as fast as they can handwrite and should learn the touch-keyboarding method if possible. Appropriate instruction appears critical for the development of keyboarding competency. The upper elementary age is an appropriate time to start teaching keyboarding, with students possibly requiring 25-30 total hours of instruction. Students experiencing handwriting difficulties might need customized goals and strategies. Although the existing literature regarding the role of performance components in keyboarding provides some direction to clinicians, further investigation is required.

The effect of physical and psychosocial loads on the trapezius muscle activity during computer keying tasks and rest periods.

UNLABELLED: The overall aim was to investigate the effect of psychosocial loads on trapezius muscle activity during computer keying work and during short and long breaks. In 12 female subjects, surface electromyography (EMG) was recorded bilaterally from the upper trapezius muscle during a standardized one hand keying task-interspaced with short (30 s) and long (4 min) breaks-in sessions with and without a combination of cognitive and emotional stressors. Adding psychosocial loads to the same physical work did not increase the activity of the trapezius muscle on either the keying or the control side, both of which remained at median and static EMG activity levels of around 5% and 2.5% of the maximal voluntary electrical activity (EMG(max)), respectively. The difference between the keying and the control side was significant; and further the control side activity was significantly increased above resting level. During both short and long breaks, exposure to psychosocial loads also did not increase the activity of the trapezius muscle either on the side of the keying or the control hand. Of note is that during long breaks the muscle activity of the keying side as well as that of the control side remained at the same level as during the short breaks, which was increased above resting level. This was to be seen from the static and the median EMG activity levels as well as gap times, the overall mean values being: 0.4%EMG(max), 1.1%EMG(max), and 50% in gap time, respectively. IN CONCLUSION: psychosocial loads are not solely responsible for increased non-postural muscle activity; and increasing the duration of breaks does not per se cause muscle relaxation.

A modified Perkins Brailler for text entry into windows applications.

In this paper, we describe how a Perkins Brailler can be adapted so that it can function as a keyboard to a personal computer. The paper describes the earlier work of others and the hardware and software of our system and concludes with indications of how the system may be improved.

Experimental comparisons of data entry by automated speech recognition, keyboard, and mouse.

In a series of experiments isolated-word automated speech recognition (ASR) was compared with keyboard and mouse interfaces for three data entry tasks: textual phrase entry, selection from a list, and numerical data entry. To effect fair comparisons, the tasks were designed to minimize the transaction cycle for each input mode and data type, and the main comparisons used times from only correct data entries. With the hardware and software employed the results indicate that for inputting short phrases, ASR competes only if the typist's speed is below 45 words per minute. For selecting an item from a list, ASR offers an advantage only if the list length exceeds 15 items. For entering numerical data, ASR offers no advantage over keypad or mouse. An extrapolation to latency-free ASR suggests that even as hardware and software become faster, human factors will dominate and the results would shift only slightly in favor of ASR.

ETAT: Expository Text Analysis Tool.

Qualitative methods that analyze the coherence of expository texts not only are time consuming, but also present challenges in collecting data on coding reliability. We describe software that analyzes expository texts more rapidly and produces a notable level of objectivity. ETAT (Expository Text Analysis Tool) analyzes the coherence of expository texts. ETAT adopts a symbolic representational system, known as conceptual graph structures. ETAT follows three steps: segmentation of a text into nodes, classification of the unidentified nodes, and linking the nodes with relational arcs. ETAT automatically constructs a graph in the form of nodes and their interrelationships, along with various attendant statistics and information about noninterrelated, isolated nodes. ETAT was developed in Java, so it is compatible with virtually all computer systems.

Wrist and forearm posture from typing on split and vertically inclined computer keyboards.

A study was conducted on 90 experienced office workers to determine how commercially available alternative computer keyboards affected wrist and forearm posture. The alternative keyboards tested had the QWERTY layout of keys and were of three designs: split fixed angle, split adjustable angle, and vertically inclined (tilted or tented). When set up correctly, commercially available split keyboards reduced mean ulnar deviation of the right and left wrists from 12 degrees to within 5 degrees of a neutral position compared with a conventional keyboard. The finding that split keyboards place the wrist closer to a neutral posture in the radial/ulnar plane substantially reduces one occupational risk factor of work-related musculoskeletal disorders (WMSDs): ulnar deviation of the wrist. Applications of this research include commercially available computer keyboard designs that typists can use and ergonomists can recommend to their clients in order to minimize wrist ulnar deviation from typing.

Activation force and travel effects on overexertion in repetitive key tapping.

Key switch design parameters, including make force, make travel, and over travel, were investigated for minimizing operator-exerted force while maximizing key-tapping speed. A mechanical apparatus was designed, constructed, and used for independently controlling key switch parameters and for directly measuring finger exertions during repetitive key tapping using strain gauge load cells. The task for the 25 participants involved using the index finger of the dominant hand to repeatedly depress a single key as rapidly as possible. Participants received visual and auditory feedback upon a successful keystroke. Peak force exerted decreased 24% and key-tapping rate increased 2% when over travel was distended from 0.0 to 3.0 mm. Although peak force exerted was not significantly affected by make point travel, key-tapping rate increased 2% when make point travel was reduced from 4.0 to 1.0 mm. These results indicate that key switch mechanisms that provide adequate over travel might enable operators to exert less force during repetitive key tapping without inhibiting performance.

Home-based radiology transcription and a productivity pay plan.

Shands Hospital in Gainesville, Fla., decided to evaluate the way it provided transcription services in its radiology department. It identified four goals: increased productivity, decreased operating expense, finding much needed space in the radiology department and increasing employee morale. The department performs 165,000 procedures annually, with 66 radiologists, 29 faculty, and 37 residents and fellows on staff. Six FTEs comprised the transcription pool in the radiology department, with transcription their only duty. Transcriptionists were paid an hourly rate based on their years of service, not their productivity. Evaluation and measurement studies were undertaken by the hospital's management systems engineering department. The transcriptionists' hours were then changed to provide coverage during the periods of heaviest dictation. The productivity level of the transcription staff was also measured and various methods of measurement reviewed. The goal was a pure incentive pay plan that would reward employees for every increase in productivity. The incentive pay plan was phased in over a three-month period. Transcriptionists were paid for work performed, with no base pay beyond minimum wage. The move to home-based transcription was planned. The necessary equipment was identified and various issues specific to working at home were addressed. Approximately six months later, the transcriptionists were set up to work at home. The astounding results achieved are presented: 28% increase in productivity, operational cost savings exceeding $25,000 and a space savings of 238 square feet.