Assistive Technology最新文献

UNav is a computer-vision-based localization and navigation aid that provides step-by-step route instructions to reach selected destinations without any infrastructure in both indoor and outdoor environments. Despite the initial literature highlighting UNav's potential, clinical efficacy has not yet been rigorously evaluated. Herein, we assess UNav against standard in-person travel directions (SIPTD) for persons with blindness or low vision (PBLV) in an ecologically valid environment using a non-inferiority design. Twenty BLV subjects (age = 38 ± 8.4; nine females) were recruited and asked to navigate to a variety of destinations, over short-range distances (<200 m), in unfamiliar spaces, using either UNav or SIPTD. Navigation performance was assessed with nine dependent variables to assess travel confidence, as well as spatial and temporal performances, including path efficiency, total time, and wrong turns. The results suggest that UNav is not only non-inferior to the standard-of-care in wayfinding (SIPTD) but also superior on 8 out of 9 metrics, as compared to SIPTD. This study highlights the range of benefits computer vision-based aids provide to PBLV in short-range navigation and provides key insights into how users benefit from this systematic form of computer-aided guidance, demonstrating transformative promise for educational attainment, gainful employment, and recreational participation.

People who are blind struggle to gauge water levels in bottles by weight alone. This work shows that combining information about a filled bottle's weight and center of gravity can enhance the accuracy of measuring the water level. Bumps were attached to the sides of cylindrical bottles at positions corresponding to the centers of gravity of water levels between 4 and 9. These bumps allow individuals to use additional information about the center of gravity to measure the water level in the bottle. Eight subjects who were blind participated in the experiment, and the results indicated that using the center of gravity method with a plastic bottle was the most accurate, with an average water level error of 0.04, but it took 57.83 seconds. Contrarily, using the weight method, the plastic bottle yielded the fastest results, with an average time of 6.51 seconds, but it led to an average water level error of 0.88.

A three-level training intervention was developed using the Quality Implementation Framework (QIF) to increase technology transfer of rehabilitation technologies to market. Thirty-two teams completed Level 1, 14 completed Level 2, and 6 completed Level 3. The validated Technology Transfer Readiness Assessment Tool (TTRAT) measured teams' technology transfer progress and the effectiveness of the training program. Teams that completed at least two training levels demonstrated increased technology transfer readiness. Additional team outcomes include receiving other federal awards, FDA designations, and generating sales. Future work includes measuring teams' progress relative to participant demographics and developing additional training content based on gaps in technology transfer readiness. The multi-level training initiative shows it is a promising foundation for training researchers and aspiring entrepreneurs on technology transfer and subsequent technology transfer outcomes.

In the development of communication devices for individuals who are Deafblind, a significant challenge is achieving a seamless transition from human-generated to technology-mediated communication. This study compares the intelligibility of the Australian Deafblind tactile fingerspelling alphabet rendered on the HaptiComm tactile communication device with the same alphabet articulated by a human signer. After a short training period, participants identified the 26 English alphabet letters in both the mediated (device) and non-mediated (human) conditions. Results indicated that while participants easily identified most letters in the non-mediated condition, the mediated condition was more difficult to decipher. Specifically, letters presented on the palm or near the index finger had significantly lower recognition rates. These findings highlight the need for further research on the tactile features of communication devices and emphasize the importance of refining these features to enhance the reliability and readability of mediated tactile communication produced through tactile fingerspelling.

Individuals with cognitive disabilities have challenges with personal navigation and wayfinding, especially when traveling on public transportation. The purpose of this case study is to describe the structure and implementation of the Personal Navigation for Individuals with Disabilities (PNID) education and training program, which is based on a socio-technical architecture for individuals with cognitive disabilities within a fixed-route public bus system. A case study methodology was used to describe preliminary findings of the skills, attributes, and experiences of three individuals with cognitive disabilities as it relates to transportation on fixed-route bus systems in a midsized urban setting. The three individuals completed five training activities: safety, public bus, smartphone, WayFinder App, and fixed-route bus system. The case study provided a preliminary mixed-methods overview of training travelers with cognitive disabilities to use the WayFinder system while accessing fixed-route public bus system. The insights and strategies identified through the case study demonstrate the potential opportunities for development, implementation, and sustainability of the PNID program in other midsized urban settings. The PNID program (i.e. AT service delivery process), in combination with the WayFinder system (i.e. assistive technology), has the potential to meet the unique needs of individuals with cognitive disabilities when accessing public transportation.

Pressure ulcers are a common problem among individuals who, for medical reasons, must spend most of their day in bed. Manually turning a person's body is labor intensive and can easily cause occupational injuries. To compare the effectiveness of a new assisted turning mattress in pressure management with that of a conventional air mattress. This is a single-session crossover trial study. Twenty-four participants confined to bed were transferred onto the selected mattress (assisted turning or conventional air mattresses) in the selected position. Average interface pressures of bony prominences were measured after the participants laid on the mattress in different positions. After the data collection, they were transferred to the second mattress, and the process was repeated. Subjective feedback from participants and caregivers was also acquired immediately following a one-week trial period of assisted turning mattresses. The mean interface pressures were comparable for most body parts between two mattresses. Subjective feedback showed that assisted turning mattresses could relieve caregivers' workload but at the cost of patients' decreased feelings of safety. Assisted turning mattresses are equal to conventional air mattresses in pressure distribution. Proper pressure management through scheduled positional changes is required in assisted turning mattresses.

Automatic speech recognition (ASR) is an emerging technology that has been used in recognizing non-typical speech of people with speech impairment and enhancing the language sample transcription process in communication sciences and disorders. However, the feasibility of using ASR for recognizing speech samples from high-tech Augmentative and Alternative Communication (AAC) systems has not been investigated. This proof-of-concept paper aims to investigate the feasibility of using AAC-ASR to transcribe language samples generated by high-tech AAC systems and compares the recognition accuracy of two published ASR models: CMU Sphinx and Google Speech-to-text. An AAC-ASR model was developed that transcribes simulated AAC speaker language samples. The AAC-ASR model's word error rate (WER) was compared with those of CMU Sphinx and Google Speech-to-text. The WER of the AAC-ASR model outperformed (28.6%) compared with CMU Sphinx and Google when tested on the testing files (70.7% and 86.2% retrospectively). Our results demonstrate the feasibility of using the ASR model to automatically transcribe high-technology AAC-simulated language samples to support language sample analysis. Future steps will focus on developing the model with diverse AAC speech training datasets and understanding the speech patterns of individual AAC users to refine the AAC-ASR model.

This study described and compared use of supported-standing and stepping devices by young children with cerebral palsy, Gross-Motor Function Classification System (GMFCS) levels III-V following power mobility introduction. Data was collected at two time-points, 5-6 months apart, for 42 participants, aged 18-80 months, using the Home Use of Technology for CHildren (HUTCH). Supported-standing and stepping device choice and time in each device remained stable over 6 months. Associations between device use and three functional classifications were examined. Children with more impaired motor, postural and manual abilities were more likely to use a supine stander rather than a prone/upright stander or no stander. Children at GMFCS V tended to use hands-free stepping devices, while support-arms stepping devices were more common for children at GMFCS IV. Only children at GMFCS III used convertible stepping devices. Using power mobility, standers and supported-stepping devices was feasible and 19/34 classified at GMFCS IV/V used all three devices over 6 months. A key finding was that introduction of power mobility did not reduce use of supported-stepping devices at any GMFCS level. Use of multiple upright positioning and mobility devices may assist children with limited mobility to be actively engaged and participate in daily life.

This study aimed to clarify the kinematics, particularly of the shoulder and hip joints, during preparation for manual wheelchair-to-bed transfer (i.e. when flipping up the arm and foot supports). This cross-sectional study included 32 able-bodied individuals. The kinematics of the shoulder and hip joints when the arm and foot supports were flipped up of manual wheelchair, were evaluated using a markerless inertial sensor-based motion capture system. We found that flipping the arm support upwards involved a large amount of abduction, internal and external rotation, flexion, and extension at the shoulder joint, whereas flipping the foot support upwards involved a large amount of flexion at the hip joint. The findings suggest that it is necessary to consider the range of motion required to flip up the arm and foot supports of manual wheelchairs, particularly in those with limited shoulder and hip range of motion such as older people, neuromuscular disorders, and orthopedic disorders.

CLOSER is a computer-based exercise program that aims to improve older adults' health, fitness and social lives. This pilot study aimed to examine the effect of CLOSER, the first computer-based exercise program developed for older adults on a national scale, on those with a history of falls. Forty-eight older adults (71.33 ± 7.47) with a history of falling at least once in the last year were included in the study. Older adults performed CLOSER exercises for (balance maintenance, neck rotation, rhythmic walking, knee flexion and trunk rotation) 2 sessions per week for eight weeks. All individuals were evaluated at baseline and the end of the eighth week. The primary outcome measures were the 30-s Chair-Stand Test (p = 0.002), the Berg Balance Scale (p = 0.002), the Falls Efficacy Scale International (p = 0.003), the Timed Up and Go Test (p = 0.008) and the motivation level (p = 0.007) statistically significant improvements were observed. The results show that a CLOSER-computer-based exercise program effectively increases balance and reduces the risk and fear of falling. In the future, CLOSER could significantly contribute to the healthcare system as an alternative aid for home-based exercise.