Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (t-test p-value <0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved.

Functional electrical stimulation is commonly used to correct drop foot following stroke or multiple sclerosis. This technique is successful for many patients, but previous studies have shown that a significant minority have difficulty identifying correct sites to place the electrodes in order to produce acceptable foot movement. Recently there has been some interest in the use of 'virtual electrodes', the process of stimulating a subset of electrodes chosen from an array, thus allowing the site of stimulation to be moved electronically rather than physically. We have developed an algorithm for automatically determining the best site of stimulation and tested it on a computer linked to a small, battery-powered prototype stimulator with 64 individual output channels. Stimulation was delivered via an 8×8 array adhered to the leg by high-resistivity self-adhesive hydrogel. Ten participants with stroke (ages 53-71 years) and 11 with MS (ages 40-80 years) were recruited onto the study and performed two walks of 10 m for each of the following conditions: own setup (PS), clinician setup (CS), automated setup (AS) and no stimulation (NS). The PS and CS conditions used the participant's own stimulator with two conventional electrodes; the AS condition used the new stimulator and algorithm. Outcome measures were walking speed, foot angle at initial contact and the Borg Rating of Perceived Exertion. Mean walking speed with no stimulation was 0.61 m/s; all FES setups significantly increased speed relative to this (AS p<0.05, PS p<0.01, CS p<0.01). Speed for PS (0.72 m/s) was faster than both AS (0.65 m/s, p<0.01) and CS (0.68 m/s, p<0.05). Frontal plane foot orientation at heel-strike was more neutral for AS (0.3° everted) than in the NS (11.2° inverted, p<0.01), PS (4.5° inverted, p<0.05) and CS (3.1° inverted, p<0.05) conditions. Dorsiflexion angles for AS (4.2°) were larger than NS (-3.0°, p0.05) and less dorsiflexed than CS (6.0°, p<0.05). This proof of principle study has demonstrated that automated setup of an array stimulator produces results broadly comparable to clinician setup. Slower walking speed for automated and clinician setups compared to the participants' own setup may be due to the participants' lack of familiarity with responses different to their usual setups. Automated setup using the method described here seems sufficiently reliable for future longer-term investigation outside the laboratory and may lead to FES becoming more viable for patients who, at present, have difficulty setting up conventional stimulators.

Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental condition that affects, among other things, the movement patterns of children suffering it. Inattention, hyperactivity and impulsive behaviors, major symptoms characterizing ADHD, result not only in differences in the activity levels but also in the activity patterns themselves. This paper proposes and trains a Recurrent Neural Network (RNN) to characterize the moment patterns for normally developing children and uses the trained RNN in order to assess differences in the movement patterns from children with ADHD. Each child is monitored for 24 consecutive hours, in a normal school day, wearing 4 tri-axial accelerometers (one at each wrist and ankle). The results for both medicated and non-medicated children with ADHD, and for different activity levels are presented. While the movement patterns for non-medicated ADHD diagnosed participants showed higher differences as compared to those of normally developing participants, those differences were only statistically significant for medium intensity movements. On the other hand, the medicated ADHD participants showed statistically different behavior for low intensity movements.

Functional electrical stimulation is commonly used to restore function in post-stroke patients in upper and lower limb applications. Location of the electrodes can be a problem hence some research groups have begun to experiment with electrode arrays. Electrode arrays are interfaced with a thin continuous hydrogel sheet which is high resistivity to reduce transverse currents between electrodes in the array. Research using electrode arrays has all been conducted in a laboratory environment over short time periods but it is suspected that this approach will not be feasible over longer time periods due to changes in hydrogel resistivity. High resistivity hydrogel samples were tested by leaving them in contact with the skin over a seven day period. The samples became extremely conductive with resistivities reaching around 10-50 Ωm. The effect of these resistivity changes was studied using finite element analysis to solve for the stationary current quasi-static electric field gradient in the tissue. Electrical stimulation efficiency and focality were calculated for both a high and low resistivity electrode-skin interface layer at different tissue depths. The results showed that low resistivity hydrogel produced significant decreases in stimulation efficiency and focality compared to high resistivity hydrogel.

Real-time monitoring and feedback of tibial acceleration using wireless skin mounted sensors may reduce the risk of tibial stress fractures in runners. The purpose of this study was to assess the agreement between a wireless accelerometer and a gold standard reference accelerometer, both skin mounted, in measuring peak axial tibial acceleration when treadmill running at a range of speeds. A research grade accelerometer was mounted to a wireless accelerometer and attached to the tibia. Peak positive tibial accelerations of 13 participants were compared at 2.5, 3.5 and 4.5 m s^− 1. Intraclass correlation coefficients demonstrated good agreement, with limits of agreement showing accuracy to within 1.2–1.65 g. The wireless accelerometer has scope to be used as a tool to measure peak tibial accelerations during running for the purpose of real-time feedback in gait training systems.