kinect sensor

Autism spectrum disorders are a type of developmental disorder that primarily disrupt social interactions and communications. Autism has no treatment, but early diagnosis of it is crucial to reduce these effects. The incidence of autism is represented in repetitive patterns of children’s motion. When walking, these children tighten their muscles and cannot control and maintain their body position. Autism is not only a mental health disorder but also a movement disorder.

This study aims to identify autistic children based on data recorded from their gait patterns using a Kinect sensor. The database used in this study comprises walking information, such as joint positions and angles between joints, of 50 autistic and 50 healthy children. Two groups of features were extracted from the Kinect data in this study. The first one was statistical features of joints’ position and angles between joints. The second group was the features based on medical knowledge about autistic children’s behaviors. Then, extracted features were evaluated through statistical tests, and optimal features were selected. Finally, these selected features were classified by naïve Bayes, support vector machine, k‑nearest neighbors, and ensemble classifier.

The highest classification accuracy for medical knowledge‑based features was 87% with 86% sensitivity and 88% specificity using an ensemble classifier; for statistical features, 84% of accuracy was obtained with 86% sensitivity and 82% specificity using naïve Bayes.

The dimension of the resulted feature vector based on autistic children’s medical knowledge was 16, with an accuracy of 87%, showing the superiority of these features compared to 42 statistical features.

Taking into consideration the inversion of the age pyramid in the coming years and the limitations and diseases that predispose the elderly to episodes of falling, it is necessary to develop resources that can address postural balance in this population. The use of virtual rehabilitation, i.e., rehabilitation using electronic platforms, has been increasing due to the increased treatment adherence observed with these methods.

This study was conducted to evaluate the effectiveness of a rehabilitation program using the Kinect sensor (KS) on the postural balance of the elderly.

This was a non-randomized controlled clinical trial in which 10 elderly subjects and 10 younger adults underwent a 10-session rehabilitation protocol lasting 20 minutes per session. Each session involved muscle stretching and motor coordination exercises, as well as use of the KS. The period between the evaluations was five weeks, and the sessions were held three times per week. The initial and final evaluations included the Berg Balance Scale (BBS), the Timed Up and Go (TUG) test and the tandem Romberg test.

After treatment with the KS, the elderly required a longer time to perform the TUG test and had lower static balance results in the tandem Romberg test compared to younger adults; however, there were no significant differences between the pre- and post-treatment values for these two tests within either group (P > 0.05). The elderly scored lower on the BBS than the younger adults both before and after treatment (P = 0.0001 and P = 0.0006, respectively). However, the elderly showed a balance gain according to the BBS scores between the pre- and post-treatment evaluations (P = 0.005), which did not occur in the younger adults (P = 0.31).

The KS is able to promote improvements in static and dynamic postural balance in the elderly, who reached a condition close to what was observed in young adults. This improvement is evident when evaluating the changes using the BBS