Deep Neural Network for the Detections of Fall and Physical Activities Using Foot Pressures and Inertial Sensing.

Fall detection and physical activity (PA) classification are important health maintenance issues for the elderly and people with mobility dysfunctions. The literature review showed that most studies concerning fall detection and PA classification addressed these issues individually, and many were based on inertial sensing from the trunk and upper extremities. While shoes are common footwear in daily off-bed activities, most of the aforementioned studies did not focus much on shoe-based measurements. In this paper, we propose a novel footwear approach to detect falls and classify various types of PAs based on a convolutional neural network and recurrent neural network hybrid. The footwear-based detections using deep-learning technology were demonstrated to be efficient based on the data collected from 32 participants, each performing simulated falls and various types of PAs: fall detection with inertial measures had a higher F1-score than detection using foot pressures; the detections of dynamic PAs (jump, jog, walks) had higher F1-scores while using inertial measures, whereas the detections of static PAs (sit, stand) had higher F1-scores while using foot pressures; the combination of foot pressures and inertial measures was most efficient in detecting fall, static, and dynamic PAs.

Proteomic analysis of Antrodia Cinnamomea-induced ER stress in liver cancer cells.

Antrodia Cinnamomea is a fungus species widely used as a herb medicine for hypertension, cancer and handover. Nevertheless, the biological roles of Antrodia Cinnamomea on the molecular mechanism of liver cancer are not entirely understood. To determine whether Antrodia Cinnamomea is able to be used for the treatment of liver cancer and its molecular mechanism, we examined the effect of Antrodia Cinnamomea on the differential proteomic patterns in liver cancer cell lines HepG2 and C3A as well as in Chang's liver cell, a normal liver cell, using quantitative proteomic approach. The proteomic analysis demonstrated that abundance of 82, 125 and 125 proteins was significantly altered in Chang's liver cells, C3A and HepG2, respectively. The experimental outcomes also demonstrated that Antrodia Cinnamomea-induced cytotoxicity in liver cancer cells mostly involved dysregulation of protein folding, cytoskeleton regulation, redox-regulation, glycolysis pathway as well as transcription regulation. Further analysis also revealed that Antrodia Cinnamomea promoted misfolding of intracellular proteins and dysregulate of cellular redox-balance resulting in ER-stress. To sum up our studies demonstrated that the proteomic strategy used in this study offered a tool to investigate the molecular mechanisms of Antrodia Cinnamomea-induced liver cancer cytotoxicity. The proteomic results might be further evaluated as prospective targets in liver cancer treatment.