Safe physical interaction with cobots: a multi-modal fusion approach for health monitoring

Health monitoring is a critical aspect of personalized healthcare, enabling early detection, and intervention for various medical conditions. The emergence of cloud-based robot-assisted systems has opened new possibilities for efficient and remote health monitoring. In this paper, we present a Transformer-based Multi-modal Fusion approach for health monitoring, focusing on the effects of cognitive workload, assessment of cognitive workload in human-machine collaboration, and acceptability in human-machine interactions. Additionally, we investigate biomechanical strain measurement and evaluation, utilizing wearable devices to assess biomechanical risks in working environments. Furthermore, we study muscle fatigue assessment during collaborative tasks and propose methods for improving safe physical interaction with cobots. Our approach integrates multi-modal data, including visual, audio, and sensor- based inputs, enabling a holistic assessment of an individual's health status. The core of our method lies in leveraging the powerful Transformer model, known for its ability to capture complex relationships in sequential data. Through effective fusion and representation learning, our approach extracts meaningful features for accurate health monitoring. Experimental results on diverse datasets demonstrate the superiority of our Transformer-based multi- modal fusion approach, outperforming existing methods in capturing intricate patterns and predicting health conditions. The significance of our research lies in revolutionizing remote health monitoring, providing more accurate, and personalized healthcare services.

Biomechanical strain vehicles for fibroblast-directed skeletal myoblast differentiation and myotube functionality in a novel coculture

Skeletal muscle functionality is governed by multiple stimuli, including cytokines and biomechanical strain. Fibroblasts embedded within muscle connective tissue respond to biomechanical strain by secreting cytokines that induce myoblast differentiation and, we hypothesize, regulate myotube function. A coculture was established to allow cross talk between fibroblasts in Bioflex wells and myoblasts on nondeformable coverslips situated above Bioflex wells. Cyclic short-duration strain (CSDS) modeling repetitive stress/injury, acyclic long-duration strain (ALDS) modeling manipulative therapy, and combined strain paradigms (CSDS + ALDS) were applied to fibroblasts. Nonstrained myoblasts in uniculture and coculture served as controls. After fibroblasts had induced myoblast differentiation, myotube contraction was assessed by perfusion of ACh (10(-11)-10(-3) M). CSDS-treated fibroblasts increased myotube contractile sensitivity vs. uniculture (P < 0.05). As contraction is dependent on ACh binding, expression and clustering of nicotinic ACh receptors (nAChRs) were measured. CSDS-treated fibroblasts increased nAChR expression (P < 0.05), which correlated with myotube contraction. ALDS-treated fibroblasts did not significantly affect contraction or nAChR expression. Agrin-treated myotubes were then used to design a computer algorithm to identify α-bungarotoxin-stained nAChR clusters. ALDS-treated fibroblasts increased nAChR clustering (P < 0.05), while CSDS-treated fibroblasts disrupted cluster formation. CSDS-treated fibroblasts produced nAChRs preferentially located in nonclustered regions (P < 0.05). Strain-activated fibroblasts mediate myotube differentiation with multiple functional phenotypes. Similar to muscle injury, CSDS-treated fibroblasts disrupted nAChR clusters and hypersensitized myotube contraction, while ALDS-treated fibroblasts aggregated nAChRs in large clusters, which may have important clinical implications. Cellular strategies aimed at improving muscle functionality, such as through biomechanical strain vehicles that activate fibroblasts to stabilize postsynaptic nAChRs on nearby skeletal muscle, may serve as novel targets in neuromuscular disorders.

Biomechanical strain regulates TNFR2 but not TNFR1 in TMJ cells

We sought to examine whether cyclic tensile strain (CTS) regulates the gene expression of tumor necrosis factor (TNF)-alpha, its receptors TNFR1 and TNFR2, and inducible nitric oxide synthase (iNOS) under inflammatory conditions, and whether these effects of CTS are sustained. Rat temporomandibular joint disc cells (TDC) were exposed to CTS in the presence or absence of interleukin (IL)-1beta for 4 and 24h. Cells were also stimulated with IL-1beta for 24h while being subjected to CTS only for the initial 1, 2, 4, 8, and 12h or the entire 24h incubation time. Furthermore, cells were incubated with IL-1beta for 24, 36, or 48 h while being exposed to CTS only for the initial 8h. Gene expression of TNF-alpha, its receptors, and iNOS was analyzed by RT-PCR, whereas protein synthesis was determined by ELISA for TNF-alpha, immunofluorescence for TNFRs, and Griess reaction for nitric oxide. CTS inhibited the IL-1beta-stimulated synthesis of TNF-alpha, TNFR2, and iNOS. TNFR1 was constitutively expressed but not regulated by IL-1beta or CTS. Application of CTS for only 1 or 2h during a 24h incubation with IL-1beta was sufficient to inhibit IL-1beta-induced upregulation of TNF-alpha, TNFR2, and iNOS. However, for maximal inhibition of these genes a longer exposure of CTS was required. These findings are the first to show that biomechanical signals regulate the expression of TNFR2 but not TNFR1 under inflammatory conditions. Furthermore, the antiinflammatory effects of biomechanical signals on TDC are maintained for prolonged periods of time but are transient.