Exercise therapy is seen as one of the major treatments for the rehabilitation for patients, particularly using modern technologies, such as virtual reality or augmented reality. Computer-assisted physical rehabilitation training involves measuring performance by analyzing the movement data collected with a sensory system during prescribed rehabilitation exercises. Human activity recognition is a challenging topic for machine learning in the present area of research. Since the sensor-based activity recognition seeks deep knowledge from various low-level sensor readings concerning human activities. In this paper, the Smart Sensor-based Rehabilitation Exercise Recognition (SSRER) system has been proposed using a deep learning framework. For the recognition of rehabilitation exercise with sensor information, a convolutional neural network (CNN) has been used on dynamic platform(D-CNN) where it has sensory data for physical rehabilitation exercise body movement by Gaussian mixture models (GMM). The input signals and GMMs are in various segments contains shapes for many CNN routes. To retrieve the state transition likelihood of hidden states, the Sensor (S-CNN) utilizes the algorithm of improved lossless information compression as discriminant features of various movements. Therefore, the hybridized CNN of the Sensor (S-CNN) and D-CNN are combined with a deep learning classifier to assess every rehabilitation class exercise at different levels. The categorized deep learning methods show improved performance with best-learned features for any rehabilitation exercise. The difference between the best attribute and the test score analyzed mathematically with our collected data and a variety of activity recognition datasets has been illustrated in this article with test results. INDEX TERMS Deep learning model, convolutional neural network, rehabilitation exercise recognition, sensors. I. BACKGROUND AND INTRODUCTION OF REHABILITATION EXERCISE RECOGNITION

Purpose This study aimed to elucidate whether lncRNA ZFAS1 is involved in neuronal apoptosis and inflammation in temporal lobe epilepsy (TLE). Materials and Methods Ninety-six TLE patients were recruited, and their peripheral venous blood was gathered to determine Zfas1 expression with polymerase chain reaction. Neurons were separated from hippocampal tissue of newborn SD rats, and si-Zfas1 or pcDNA3.1-Zfas1 was transfected into the neurons. Inflammatory cytokines released by neurons were determined, and neuronal activities were evaluated through MTT assay, colony formation assay, and flow cytometry. Results Serum levels of Zfas1 were higher in TLE patients than in healthy controls ( p <0.05). Furthermore, Zfas1 expression in neurons was raised by pcDNA3.1-Zfas1 and declined after silencing of Zfas1 ( p <0.05). Transfection of pcDNA-Zfas1 weakened the viability and proliferation of neurons and increased neuronal apoptosis ( p <0.05). Meanwhile, pcDNA3.1-Zfas1 transfection promoted lipopolysaccharide-induced release of cytokines, including tumor necrosis factor-α, interleukin (IL)-1, IL-6, and intercellular adhesion molecule-1 ( p <0.05), and boosted NF-κB activation by elevating the expression of NF-κB p65, pIκBα, and IKKβ in neurons ( p <0.05). Conclusion Our results indicated that lncRNA ZFAS1 exacerbates epilepsy development by promoting neuronal apoptosis and inflammation, implying ZFAS1 as a promising treatment target for epilepsy.

Alzheimer’s disease (AD) is a common dementia and a heterogeneous disease. Previous research has validated that microRNAs (miRNAs) are pivotal regulators in the initiation and development of tremendous diseases including AD. MicroRNA-485-5p (miR-485-5p) was reported to be an important participant implicated in several neurological diseases, but its role in AD still needs to be further investigated. In this research, we explored the biological function of miR-485-5p in AD. RT-qPCR revealed that miR-485-5p expression was downregulated in the hippocampus of APP/PS1 mice. Additionally, miR-485-5p overexpression facilitated the learning and memory capabilities of APP/PS1 mice according to Morris water maze test, fear conditioning test, and immunofluorescent staining. Moreover, CCK-8 assay, flow cytometric analysis, and western blot analysis suggested that miR-485-5p overexpression promoted pericyte viability and prohibited pericyte apoptosis in APP/PS1 mice. Mechanistically, miR-485-5p directly targeted PACS1 in pericytes, as shown in a luciferase reporter assay. In rescue assays, PACS1 overexpression countervailed the effect of miR-485-5p overexpression on pericyte viability and apoptosis. In conclusion, miR-485-5p ameliorates AD progression by targeting PACS1.

The results demonstrate that participants could move the cursor in the 2D plane effectively. The proposed control strategy is based only on a basic two-motor imagery BCI, which enables more people to use it in real-life applications.