The global prevalence of diabetes is rapidly increasing. Studies support screening and interventions for pre-diabetes, which results in serious complications and diabetes. This study aimed at developing an intelligenc...
详细信息
We applied multicategory machine learning methods to classify 11 neuromuscular disease groups and one control group based on microarray data. To develop multicategory classification models with optimal parameters and ...
In SPECT, scattered photons contribute to the detected signal, reducing contrast and quantification accuracy. Several methods exist to correct scatter, including the dual-energy window technique, but have not been ful...
详细信息
Many proposed EEG-based brain-computer interfaces (BCIs) make use of visual stimuli to elicit steady-state visual evoked potentials (SSVEP), the frequency of which can be mapped to a computer input. However, such a co...
详细信息
ISBN:
(纸本)9781424479276
Many proposed EEG-based brain-computer interfaces (BCIs) make use of visual stimuli to elicit steady-state visual evoked potentials (SSVEP), the frequency of which can be mapped to a computer input. However, such a control scheme can be ineffective if a user has no motor control over their eyes and cannot direct their gaze towards a flashing stimulus to generate such a signal. Tactile-based methods, such as somatosensory steady-state evoked potentials (SSSEP), are a potentially attractive alternative in these scenarios. Here, we compare the neural signals elicited by SSSEP to those elicited by SSVEP in naive BCI users towards evaluating the feasibility of SSSEP-based control of an EEG BCI.
Background: Digital technology is becoming an increasingly popular means of delivering meaningful therapy to individuals with neurological impairments. An understanding of clients' technology use and their perspec...
详细信息
Background: Digital technology is becoming an increasingly popular means of delivering meaningful therapy to individuals with neurological impairments. An understanding of clients' technology use and their perspectives on incorporating technology into rehabilitation can provide researchers and designers with valuable information to inform development of technologies and technology-based rehabilitation programs. Objective: This study was designed to establish the current use and perceptions of gaming, social media, and robotics technologies for rehabilitative purposes from the perspective of adults and children with upper limb impairments to identify barriers and enablers to their adoption and use. Methods: We conducted three focus groups consisting of pediatric (n=7, mean age 11.0 years) and adult (n=8, mean age 60.8 years) participants with hemiparesis affecting their upper limb. We applied thematic analysis methods to the resulting data. Results: We identified three key themes: (1) clients' use of technology in everyday life and rehabilitation, (2) barriers to use, and (3) enablers to therapy. Participants had limited exposure to technology for therapeutic purposes, but all acknowledged the potential benefits in providing motivation and interest for the performance of repetitive task practice. Adult participants requested efficacious, simple, and easy-to-use technology for rehabilitation with programs that could be individualized for them and expressed that they wanted these programs to provide a motivating means of repeated practice of therapeutic movements. In contrast, pediatric participants emphasized a desire for technology for rehabilitation that offered opportunities for social interaction and interactive games involving their whole body and not only their affected limb. Perceived safety and privacy were concerns for both groups. Conclusions: Our findings highlight that all participants were open to the integration of technology into rehabilitation. Adult p
Linear approaches to low-dimensional feature extraction may not be appropriate when statistical data are generated by a nonlinear interaction of parameters. Equally inadequate are linear methods for determining the di...
详细信息
Linear approaches to low-dimensional feature extraction may not be appropriate when statistical data are generated by a nonlinear interaction of parameters. Equally inadequate are linear methods for determining the dimension of the feature space. This article estimates the intrinsic dimension of extracellular action potentials (EAPs), which can be viewed as the minimum number of nonlinearly interacting parameters sufficient to describe the data. When combined with nonlinear feature extraction methods, this information may lead to a more faithful, low-dimensional EAP representation. These points are demonstrated using EAPs recorded experimentally by a multi-sensor electrode.
暂无评论