Decoding covert speech for intuitive control of brain-computer interfaces based on single-trial EEG: a feasibility study.

For individuals with severe motor deficiencies, controlling external devices such as robotic arms or wheelchairs can be challenging, as many devices require some degree of motor control to be operated, e.g. when controlled using a joystick. A brain-computer interface (BCI) relies only on signals from the brain and may be used as a controller instead of muscles. Motor imagery (MI) has been used in many studies as a control signal for BCIs. However, MI may not be suitable for all control purposes, and several people cannot obtain BCI control with MI. In this study, the aim was to investigate the feasibility of decoding covert speech from single-trial EEG and compare and combine it with MI. In seven healthy subjects, EEG was recorded with twenty-five channels during six different actions: Speaking three words (both covert and overt speech), two arm movements (both motor imagery and execution), and one idle class. Temporal and spectral features were derived from the epochs and classified with a random forest classifier. The average classification accuracy was $67 \pm 9$ % and $75\pm 7$ % for covert and overt speech, respectively; this was 5-10 % lower than the movement classification. The performance of the combined movement-speech decoder was $61 \pm 9$ % and $67\pm 7$ % (covert and overt), but it is possible to have more classes available for control. The possibility of using covert speech for controlling a BCI was outlined; this is a step towards a multimodal BCI system for improved usability.

Evaluation of the Myo armband for the classification of hand motions.

Pattern recognition-based control systems have been widely investigated in prostheses and virtual reality environments to improve amputees' quality of life. Most of these systems use surface electromyography (EMG) to detect user movement intentions. The Myo armband (MYB) is a wireless wearable device, developed by Thalmic Labs, which enables EMG recordings with a limited bandwidth (<100Hz). The aim of this study was to compare MYB's narrow bandwidth with a conventional EMG acquisition system (CONV) that captures the full EMG spectrum to assess its suitability for pattern recognition control. A crossover study was carried out with eight able-bodied participants, performing nine hand gestures. Six features were extracted from the data and classified by Linear Discriminant Analysis (LDA). Results showed a mean classification error of 5.82 ± 3.63% for CONV and 9.86 ± 8.05% for MYB with no significantly difference (P = 0.056). This implies that MYB may be suitable for pattern recognition applications despite the limitation in the bandwidth.

Distribution and symmetrical patellofemoral pain patterns as revealed by high-resolution 3D body mapping: a cross-sectional study.

BACKGROUND: Detailed pain mapping of extent and distribution in individuals with patellofemoral pain (PFP) within and around a complex structure such as the knee has yet to be explored. METHODS: Perceptions of on-going pain from adolescents and young adults (N = 35) with long-standing (>10 months) PFP were collected on high-resolution 3D digital body-schema of the knees. Location, area of pain, pain intensity, laterality, worse side of knee pain, symptom duration, and symmetry in bilateral knee pain were recorded. A threshold for naturally occurring variations in symmetrical knee pain drawings were collected from 18 healthy controls and used in combination with the development a symmetry index (0-1) to create a fuzzy rule for classifying symmetrical and non-symmetrical PFP patterns as compared to a PFP expert. The symmetry index was computed and tested using a correlation coefficient alone or in combination with the Jaccard index and the true and false positive rates (TPR and FPR, respectively) determined. RESULTS: The peripatellar region was the common report of pain location however, novel and nonconforming PFP patterns were identified and the majority of individuals (22 of 27) with bilateral PFP expressed highly-symmetric mirror-image pain. Individuals with symptom duration of 5 years or more had a greater area of pain, compared to those with symptoms for less than 5 years. The total area of pain was correlated to symptom duration for those with extended symptoms durations and a progression towards an "O" shaped pattern emerged. A TPR of 100% for identifying symmetrical knee pain patterns was found however the expert PFP tended to be stricter, as reflected in FPR of 20%. CONCLUSIONS: A high proportion of PFP patterns or symptoms occur in mirrored locations and are exceptionally symmetrical, and long duration of symptoms appear to converge to an 'O' shape. Classifying symmetrical pain patterns is subjective however simple fuzzy rules and correlations can be used to increase objectivity. This study highlights a gap in knowledge of PFP symptom presentation, reveals what may be a natural progression of symptoms, and provides valuable clinical insight for both pain management and treatment.

Classification of hand and wrist tasks of unknown force levels using muscle synergies.

Muscle synergies have been proposed as a way for the central nervous system (CNS) to simplify the generation of motor commands and they have been shown to explain a large portion of the variation in the muscle patterns across a variety of conditions. However, whether human subjects are able to control prostheses proportionally with a small set of synergies has not been tested directly. Here we investigated if muscle synergies can be used to identify different wrist and hand motions. We recorded electromyographic (EMG) activity from eight arm muscles while the subjects exerted seven different intensity levels during the motions when performing seven classes of hand and wrist motion. From these data we extracted the muscle synergies and classified the tasks associated to each contraction intensity profile by linear discriminant analysis (LDA). We compared the performance obtained using muscle synergies with the performance of using the mean absolute values (MAV) as a feature. Also, the consistency of extracted muscle synergies was studied across intensity variations. While the synergies showed relative consistency particularly across closer intensity levels, average classification results generated with the synergies were less accurate than MAVs. These results indicate that although the performance of muscle synergies was very close to MAVs, they do not provide additional information for task identification across different exerted intensity levels.