Academic literature on the topic 'Keystroke reduction'

The Keybowl keyboard is the first known keyboard alternative to totally eliminate finger movement and drastically reduce wrist motion. With the significant reduction of finger and wrist motion comes concern over where the repetitive forces are being transferred. In typing with the Keybowl, biomechanical requirements are somewhat different than those in using a QWERTY keyboard. One way to help determine how well typists perform biomechanically is through keystroke error analysis. Typing performances were therefore analyzed via keystroke errors to determine if Keybowl “key” activation was different from QWERTY key activation. An error analysis for each character, hand, and gender was performed. This analysis has built a foundation for comparing two very different types of upper extremity motions and how they might affect a proficient QWERTY typist's performance in typing with the Keybowl.

User authentication using keystroke dynamics offers many advances in the domain of cyber security, including no extra hardware cost, continuous monitoring, and nonintrusiveness. Many algorithms have been proposed in the literature. Here, we introduce two new algorithms to the domain: the Gaussian mixture model with the universal background model (GMM-UBM) and the deep belief nets (DBN). Unlike most existing approaches, which only use genuine users’ data at training time, these two generative model-based approaches leverage data from background users to enhance the model’s discriminative capability without seeing the imposter’s data at training time. These two new algorithms make no assumption about the underlying probability distribution and are fast for training and testing. They can also be extended to free text use cases. Evaluations on the CMU keystroke dynamics benchmark dataset show over 58% reduction in the equal error rate over the best published approaches.

Abstract Background An individual’s mental health is best captured by considering the overall associations of biological, behavioral, and social functions that comprise the framework of individual experience. As such, accessing data on various health indicators concurrently can influence prediction of disease progression or change in response to treatment. Data generated passively by smartphones to measure human behavior has generated significant research interest and has increasingly been utilized in psychiatric disorders. In schizophrenia, passive and continuous assessment of how an individual uses their mobile device may give rise to clinically useful markers that can be used to improve treatment processes, adapt treatment choices, identify early risk for relapse to initiate clinical intervention, and develop new clinical models. A promising approach is to leverage current advances in mobile technology, data analytics and machine learning to enable automated and fast phenotyping of digital data. . In this context, the workflow for phenotyping (passive data collection → data storage and curation → trait extraction → machine learning/classification → models/apps for decision support) has to be carefully designed and efficiently executed to minimize resource usage and maximize utility. Digital phenotyping can be used in conjunction with standard care to reduce time to recognition and acknowledgement that worsening of a symptom needs to be addressed, to reduce time to receiving appropriate level of care, to increase ability to analyze and collect data from a variety of sources to improve mental health needs assessment and delivery of services, and to advance outcome measurement through comparison of passive and active data sets. Aim The aim of this pilot study is to test whether a smartphone digital phenotyping application can help detect early signs of treatment failure or response in individuals with chronic schizophrenia after discharge from hospital. Methods 17 individuals with DSM-5 schizophrenia were provided with a smartphone and digital phenotyping app, MindStrong Health app, following discharge from an inpatient psychiatric facility. The participants were followed for 6 months with monthly rater administered evaluations assessing neurocognition (Brief Assessment of Cognition in Schizophrenia (BACS)), symptomatology (PANSS; CGI-S/I), quality of life (SF-36), healthcare utilization, alcohol/drug use, level of clinical insight and depression (Calgary Depression Rating Scale, CDSS). Digital phenotyping data included gestures (swipes, taps, other), orientation (the way the phone is pointing), acceleration (sudden movements of the phone), keystroke patterns with characters encoded, number of calls made, number of emails sent, number of text messages sent, and location information from the GPS. Predictive models were built using multiple machine learning techniques - random forest plots, linear regression and gradient boosting, to predict the target scores based on phone usage patterns. Results Of the 17 enrolled participants, 10 provided analyzable data (i.e., had at least 22 target days with data). There was a gradual reduction of passive data generation due to either non-use of the smart phone or due to non-recharging of the device. The mean PANSS score was 80.12 (14.56). BACS scores corresponding to motor speed (token motor task), verbal fluency (category instances, letter fluency), and attention and processing speed (symbol coding) were found to be highly correlated with a composite digital phenotyping marker while scores on the PANSS or CDSS were not. Discussion The study provides a basis for using smartphone-base mobile apps to use as an augmentation within clinical practice to gather further information on patients outside the clinic setting, focusing on their behavior in the ‘real world.’ In particular, the cognitive data derived from the digital device correlated well with rater administered traditional cognitive ratings. Collecting digital data can provide a much needed window into the lives of patients in between normally scheduled visits, while minimizing costs and inconvenience to the patient. Studies with larger sample sizes are required to assess relationships with relapse, rehospitalizations and treatment failure.

Background: The Ohio State University Comprehensive Cancer Center - James Cancer Hospital and Solve Research Institute is a 356-bed cancer care hospital that is part of The Ohio State University Medical Center. In addition to the inpatient beds, the hospital services 175 ambulatory infusion chairs. Each month, we administer over 6,000 chemotherapy infusions on an IV pump. Smart IV pumps in tandem with hospital information technology infrastructure integrate IV drug administration pump data with the electronic medical record (EMR) and computerized physician order entry to decrease risk of error and increase patient safety. The closed loop system transmits the medication infusion rate and the prescribed dose to the smart pump to deliver the medication. The smart pump in turn transmits the dose and volume delivered to the EMR to accurately capture what the patient received. The ability to wirelessly transmit clinical information from the EMR to automatically program the IV pump with specific data was implemented in March 2018 as part of a system-wide safety initiative to enhance patient safety via the reduction of error during medication administration. Methods: IV pump integration has been in use since March 2018; the organization has robust data on the use of smart pump technology that allowed for comparison of data pre- and postimplementation of pump integration. This includes: total suite usage, count of basic infusions, severe harm averted, total good catches, and event-reporting data. Post-integration, the overall compliance of utilizing pump integration (sending an order from the EMR to the smart IV pump) is also continuously monitored. Results: The implementation of pump interoperability resulted in a safer delivery of infused medications (Figure 1). The use of “basic Infusion” or unprotected infusion function decreased while our use of the appropriate safeguarded pump program increased. The compliance at the medical center increased from about 86% to almost 94%. With increased usage of the pump interoperability, the potential for severe harm as well as human programming errors decreased significantly. Conclusion: The Ohio State University Comprehensive Cancer Center - James Cancer Hospital and Solve Research Institute is able to deliver infused medications via a smart pump in a safer, more automated system with the implementation of pump integration. We are able to reduce the “human factor” in medication delivery by reducing keystrokes and opportunities for manual programming errors. Pre-integration data cannot be isolated for the cancer hospital only, from our post-implementation data we can infer that our chemotherapy infusions are subsequently safer for our patients.

Word prediction has been offered as support for children with spelling difficulties. The literature however has shown wide-ranging results, as the use of word prediction is at the cost of time and fatigue due to increased visual-cognitive demands. Spelling support with word prediction is through word completion, keystroke reduction and the interactive process between spelling and reading. The research project was a cross-over within-subject design using 80 Grade 4 – 6 children with spelling difficulties in a school for special needs. The research task took the form of entering 30 words through an on-screen keyboard, with and without the use of word prediction software. The subjects were divided into four groups, who completed the research task in combinations of one of two equivalent wordlists and the presentation order of the typing method used. The Graded Word Spelling Test, administered before the study began, served to investigate whether there was a relationship between the children’s current spelling knowledge and word prediction efficacy. The results indicated an increase in spelling accuracy with the use of word prediction, but at the cost of time and the tendency to use word approximations, which decreased as grade and age increased. Children’s current spelling knowledge could not serve as an indicator of who would be most likely to benefit from word prediction use. The cross-over design counter-balanced the effects of the inequalities in the two wordlists and the effects of practice and fatigue noted in the presentation order. Further research into the impact that more extensive training and practice would have on word prediction efficacy and the usefulness of word prediction in more functional writing is necessary.
Dissertation (M (Augmentative and Alternative Communication))--University of Pretoria, 2005.
Centre for Augmentative and Alternative Communication (CAAC)
unrestricted