Decomposing Task-Relevant Information from Surface Electromyogram for User-Generic Dexterous Finger Force Decoding.

Existing electromyographic (EMG) based motor intent detection algorithms are typically user-specific, and a generic model that can quickly adapt to new users is highly desirable. However, establishing such a model remains a challenge due to high inter-person variability and external interference with EMG signals. In this study, we present a feature disentanglement approach, implemented by an autoencoder-like architecture, designed to decompose user-invariant, motor-task-sensitive high-level representations from user-sensitive, task-irrelevant representations in EMG amplitude features. Our method is usergeneric and can be applied to unseen users for continuous multi-finger force predictions. We evaluated our approach on eight subjects, predicting the force of three fingers (index, middle, and ring-pinky) concurrently. We assessed the decoder's performance through a rigorous leave-onesubject-out validation. Our developed approach consistently outperformed both the conventional EMG amplitude method and a commonly used feature projection approach, principal component analysis (PCA), with a lower force prediction error (RMSE: 6.91 ± 0.45% MVC; R 2 : 0.835 ± 0.026) and a higher finger classification accuracy (83.0 ± 4.5%). The comparison with the state-of-the-art neural networks further demonstrated the superior performance of our method in user-generic force predictions. Overall, our methods provide novel insights into the development of user-generic and accurate neural decoding for myoelectric control of assistive robotic hands.

Isolation, purification, and structural characterization of polysaccharides from Codonopsis pilosula and its therapeutic effects on non-alcoholic fatty liver disease in vitro and in vivo.

Codonopsis pilosula is a famous edible and medicinal plants, in which polysaccharides are recognized as one of the important active ingredients. A neutral polysaccharide (CPP-1) was purified from C. pilosula. The structure was characterized by HPSEC-MALLS-RID, UV, FT-IR, GC-MS, methylation analysis, and NMR. The results showed that CPP-1 was a homogeneous pure polysaccharide, mainly containing fructose and glucose, and a small amount of arabinose. Methylation analysis showed that CPP-1 composed of →1)-Fruf-(2→, Fruf-(1→ and Glcp-(1→ residues. Combined the NMR results the structure of CPP-1 was confirmed as α-D-Glcp-(1 â†’ [2)-ß-D-Fruf-(1 â†’ 2)-ß-D-Fruf-(1]26 â†’ 2)-ß-D-Fruf with the molecular weight of 4.890 × 103 Da. The model of AML12 hepatocyte fat damage was established in vitro. The results showed that CPP-1 could increase the activity of SOD and CAT antioxidant enzymes and reduce the content of MDA, thus protecting cells from oxidative damage. Subsequently, the liver protective effect of CPP-1 was studied in the mouse model of nonalcoholic fatty liver disease (NAFLD) induced by the high-fat diet. The results showed that CPP-1 significantly reduced the body weight, liver index, and body fat index of NAFLD mice, and significantly improved liver function. Therefore, CPP-1 should be a potential candidate for the treatment of NAFLD.

Towards Efficient Neural Decoder for Dexterous Finger Force Predictions.

OBJECTIVE: Dexterous control of robot hands requires a robust neural-machine interface capable of accurately decoding multiple finger movements. Existing studies primarily focus on single-finger movement or rely heavily on multi-finger data for decoder training, which requires large datasets and high computation demand. In this study, we investigated the feasibility of using limited single-finger surface electromyogram (sEMG) data to train a neural decoder capable of predicting the forces of unseen multi-finger combinations. METHODS: We developed a deep forest-based neural decoder to concurrently predict the extension and flexion forces of three fingers (index, middle, and ring-pinky). We trained the model using varying amounts of high-density EMG data in a limited condition (i.e., single-finger data). RESULTS: We showed that the deep forest decoder could achieve consistently commendable performance with 7.0% of force prediction errors and R2 value of 0.874, significantly surpassing the conventional EMG amplitude method and convolutional neural network approach. However, the deep forest decoder accuracy degraded when a smaller amount of data was used for training and when the testing data became noisy. CONCLUSION: The deep forest decoder shows accurate performance in multi-finger force prediction tasks. The efficiency aspect of the deep forest lies in the short training time and small volume of training data, which are two critical factors in current neural decoding applications. SIGNIFICANCE: This study offers insights into efficient and accurate neural decoder training for advanced robotic hand control, which has the potential for real-life applications during human-machine interactions.

DPP-4 exacerbates LPS-induced endothelial cells inflammation via integrin-α5ß1/FAK/AKT signaling.

Endothelial dysfunction plays a pivotal role in the pathogenesis of acute lung injury (ALI)/acute respiratory distress syndrome (ARDS). Dipeptidyl peptidase IV (DPP-4), a cell surface glycoprotein, has been implicated in endothelial inflammation and barrier dysfunction. In this study, the role of DPP-4 on lipopolysaccharide (LPS)-induced pulmonary microvascular endothelial cells (HPMECs) dysfunction and the underlying mechanism were investigated by siRNA-mediated knockdown of DPP-4. Our results indicated that LPS (1 µg/ml) challenge resulted in either the production and releasing of DPP-4, as well as the secretion of IL-6 and IL-8 in HPMECs. DPP-4 knockdown inhibited chemokine releasing and monolayer hyper-permeability in LPS challenged HPMECs. When cocultured with human polymorphonuclear neutrophils (PMNs), DPP4 knockdown suppressed LPS-induced neutrophil-endothelial adhesion, PMN chemotaxis and trans-endothelial migration. Western blotting showed that DPP-4 knockdown attenuated LPS-induced activation of TLR4/NF-κB pathway. Immunoprecipitation and liquid chromatography-tandem mass spectrometry revealed that DPP-4 mediated LPS-induced endothelial inflammation by interacting with integrin-α5ß1. Moreover, exogenous soluble DPP-4 treatment sufficiently activated integrin-α5ß1 downstream FAK/AKT/NF-κB signaling, thereafter inducing ICAM-1 upregulation in HPMECs. Collectively, our results suggest that endothelia synthesis and release DPP-4 under the stress of endotoxin, which interact with integrin-α5ß1 complex in an autocrine or paracrine manner to exacerbate endothelial inflammation and enhance endothelial cell permeability. Therefore, blocking DDP-4 could be a potential therapeutic strategy to prevent endothelial dysfunction in ALI/ARDS.

NLRP3 inflammasome mediates abnormal epithelial regeneration and distal lung remodeling in silica­induced lung fibrosis.

NOD-like receptor protein 3 (NLRP3) inflammasome is closely related to silica particle­induced chronic lung inflammation but its role in epithelial remodeling, repair and regeneration in the distal lung during development of silicosis remains to be elucidated. The present study aimed to determine the effects of the NLRP3 inflammasome on epithelial remodeling and cellular regeneration and potential mechanisms in the distal lung of silica­treated mice at three time points. Pulmonary function assessment, inflammatory cell counting, enzyme­linked immunosorbent assay, histological and immunological analyses, hydroxyproline assay and western blotting were used in the study. Single intratracheal instillation of a silica suspension caused sustained NLRP3 inflammasome activation in the distal lung. Moreover, a time­dependent increase in airway resistance and a decrease in lung compliance accompanied progression of pulmonary fibrosis. In the terminal bronchiole, lung remodeling including pyroptosis (membrane­distributed GSDMD+), excessive proliferation (Ki67+), mucus overproduction (mucin 5 subtype AC and B) and epithelial­mesenchymal transition (decreased E­Cadherin+ and increased Vimentin+), was observed by immunofluorescence analysis. Notably, aberrant spatiotemporal expression of the embryonic lung stem/progenitor cell markers SOX2 and SOX9 and ectopic distribution of bronchioalveolar stem cells were observed in the distal lung only on the 7th day after silica instillation (the early inflammatory phase of silicosis). Western blotting revealed that the Sonic hedgehog/Glioma­associated oncogene (Shh/Gli) and Wnt/ß­catenin pathways were involved in NLRP3 inflammasome activation­mediated epithelial remodeling and dysregulated regeneration during the inflammatory and fibrotic phases. Overall, sustained NLRP3 inflammasome activation led to epithelial remodeling in the distal lung of mice. Moreover, understanding the spatiotemporal profile of dysregulated epithelial repair and regeneration may provide a novel therapeutic strategy for inhalable particle­related chronic inflammatory and fibrotic lung disease.

A Robust Gaze Estimation Approach via Exploring Relevant Electrooculogram Features and Optimal Electrodes Placements.

Gaze estimation, as a technique that reflects individual attention, can be used for disability assistance and assisting physicians in diagnosing diseases such as autism spectrum disorder (ASD), Parkinson's disease, and attention deficit hyperactivity disorder (ADHD). Various techniques have been proposed for gaze estimation and achieved high resolution. Among these approaches, electrooculography (EOG)-based gaze estimation, as an economical and effective method, offers a promising solution for practical applications. OBJECTIVE: In this paper, we systematically investigated the possible EOG electrode locations which are spatially distributed around the orbital cavity. Afterward, quantities of informative features to characterize physiological information of eye movement from the temporal-spectral domain are extracted from the seven differential channels. METHODS AND PROCEDURES: To select the optimum channels and relevant features, and eliminate irrelevant information, a heuristical search algorithm (i.e., forward stepwise strategy) is applied. Subsequently, a comparative analysis of the impacts of electrode placement and feature contributions on gaze estimation is evaluated via 6 classic models with 18 subjects. RESULTS: Experimental results showed that the promising performance was achieved both in the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) within a wide gaze that ranges from -50° to +50°. The MAE and RMSE can be improved to 2.80° and 3.74° ultimately, while only using 10 features extracted from 2 channels. Compared with the prevailing EOG-based techniques, the performance improvement of MAE and RMSE range from 0.70° to 5.48° and 0.66° to 5.42°, respectively. CONCLUSION: We proposed a robust EOG-based gaze estimation approach by systematically investigating the optimal channel/feature combination. The experimental results indicated not only the superiority of the proposed approach but also its potential for clinical application. Clinical and translational impact statement: Accurate gaze estimation is a key step for assisting disabilities and accurate diagnosis of various diseases including ASD, Parkinson's disease, and ADHD. The proposed approach can accurately estimate the points of gaze via EOG signals, and thus has the potential for various related medical applications.

Concurrent Prediction of Dexterous Finger Flexion and Extension Force via Deep Forest.

Neuromuscular injuries can impair hand function and profoundly impacting the quality of life. This has motivated the development of advanced assistive robotic hands. However, the current neural decoder systems are limited in their ability to provide dexterous control of these robotic hands. In this study, we propose a novel method for predicting the extension and flexion force of three individual fingers concurrently using high-density electromyogram (HD-EMG) signals. Our method employs two deep forest models, the flexor decoder and the extensor decoder, to extract relevant representations from the EMG amplitude features. The outputs of the two decoders are integrated through linear regression to predict the forces of the three fingers. The proposed method was evaluated on data from three subjects and the results showed that it consistently outperforms the conventional EMG amplitude-based approach in terms of prediction error and robustness across both target and non-target fingers. This work presents a promising neural decoding approach for intuitive and dexterous control of the fingertip forces of assistive robotic hands.

Cybersecurity in neural interfaces: Survey and future trends.

With the joint advancement in areas such as pervasive neural data sensing, neural computing, neuromodulation and artificial intelligence, neural interface has become a promising technology facilitating both the closed-loop neurorehabilitation for neurologically impaired patients and the intelligent man-machine interactions for general application purposes. However, although neural interface has been widely studied, few previous studies focused on the cybersecurity issues in related applications. In this survey, we systematically investigated possible cybersecurity risks in neural interfaces, together with potential solutions to these problems. Importantly, our survey considers interfacing techniques on both central nervous systems (i.e., brain-computer interfaces) and peripheral nervous systems (i.e., general neural interfaces), covering diverse neural modalities such as electroencephalography, electromyography and more. Moreover, our survey is organized on three different levels: (1) the data level, which mainly focuses on the privacy leakage issue via attacking and analyzing neural database of users; (2) the permission level, which mainly focuses on the prospects and risks to directly use real time neural signals as biometrics for continuous and unobtrusive user identity verification; and (3) the model level, which mainly focuses on adversarial attacks and defenses on both the forward neural decoding models (e.g. via machine learning) and the backward feedback implementation models (e.g. via neuromodulation and stimulation). This is the first study to systematically investigate cybersecurity risks and possible solutions in neural interfaces which covers both central and peripheral nervous systems, and considers multiple different levels to provide a complete picture of this issue.

Sub-regional phase error compensation based on a probability distribution function and gamma precoding.

In this paper, a phase error compensation method based on a probability distribution function (PDF) is proposed to improve the accuracy of phase extraction, which is helpful for three-dimensional (3D) reconstruction. First, the relationship between the gamma and the gray values is established to segment the projection regions. Then a new method based on a PDF is designed to represent the variation degree of phase error, which fits the precoded gamma value in the minimum range of the phase error. After that, the error compensation method is applied to the self-built system and packaged independently from the 3D reconstruction system to unwrap phases with high precision. The experimental results show that the proposed method can reduce the standard deviation of the phase error by 46.9% compared without phase error compensation, and decrease the standard deviation of the phase error by 30% compared with the whole precoding. Generally, our method can effectively avoid overcompensation or under-compensation caused by single global gamma precoding correction, and better reduce the phase error and improve the 3D reconstruction accuracy in the fringe projection system.

[High-intensity laser therapy combined with targeted hand function training for the treatment of grade 1-2 thumb carpometacarpal osteoarthritis].

OBJECTIVE: To explore clinical effect of high-intensity laser therapy(HILT) combined with targeted hand function training on pain and lateral pinch force in grade 1-2 thumb carpometacarpal(CMC) osteoarthritis(OA). METHODS: From April 2020 and April 2022, 42 female patients with thumb CMC OA grade 1 to 2, aged from 58 to 80 years old with an everage of (68.90±7.58) years old were divided into observation group of 21 patients who received HILT and targeted hand function training for 4 weeks, and 21 patients in control group who received ultrashort wave therapy combined with using of an orthosis for 4 weeks. Visual analogue scale(VAS) was applied to evaluate degree of pain, function of finger was evaluated by dynamometer to measure lateral pinch force at baseline, immediately following intervention at 4 and 12 weeks following intervention. RESULTS: VAS and lateral pinch force at immediately and 12 weeks after intervention betwwen two groups were better than that of before intervention(P<0.05). Compared with control group, the degree of pain in observation group improved more(immediately after intervention t=3.37, P<0.05, 12 weeks after intervention t=9.05, P<0.05), lateral pinch force higher than that of control group (immediately after intervention t=-2.55, P<0.05, 12 weeks after intervention t=9.51, P<0.05). CONCLUSION: High-intensity laser therapy combined with targeted hand function training is more effective than traditional methods in improving pain and lateral pinch force in grade 1-2 thumb carpometacarpal osteoarthritis.

Potential candidates for liver resection in liver-confined advanced HCC: a Chinese multicenter observational study.

Background: Advanced hepatocellular carcinoma (HCC) is characterized as symptomatic tumors [performance status (PS) score of 1-2], vascular invasion and extrahepatic spread, but patients with PS1 alone may be eliminated from this stage. Although liver resection is used for liver-confined HCC, its role in patients with PS1 alone remains controversial. Therefore, we aimed to explore its application in such patients and identify potential candidates. Methods: Eligible liver-confined HCC patients undergoing liver resection were retrospectively screened in 15 Chinese tertiary hospitals, with limited tumor burden, liver function and PS scores. Cox-regression survival analysis was used to investigate the prognostic factors and develop a risk-scoring system, according to which patients were substratified using fitting curves and the predictive values of PS were explored in each stratification. Results: From January 2010 to October 2021, 1535 consecutive patients were selected. In the whole cohort, PS, AFP, tumor size and albumin were correlated with survival (adjusted P<0.05), based on which risk scores of every patient were calculated and ranged from 0 to 18. Fitting curve analysis demonstrated that the prognostic abilities of PS varied with risk scores and that the patients should be divided into three risk stratifications. Importantly, in the low-risk stratification, PS lost its prognostic value, and patients with PS1 alone achieved a satisfactory 5-year survival rate of 78.0%, which was comparable with that PS0 patients (84.6%). Conclusion: Selected patients with PS1 alone and an ideal baseline condition may benefit from liver resection and may migrate forward to BCLC stage A.

Robust neural decoding for dexterous control of robotic hand kinematics.

BACKGROUND: Manual dexterity is a fundamental motor skill that allows us to perform complex daily tasks. Neuromuscular injuries, however, can lead to the loss of hand dexterity. Although numerous advanced assistive robotic hands have been developed, we still lack dexterous and continuous control of multiple degrees of freedom in real-time. In this study, we developed an efficient and robust neural decoding approach that can continuously decode intended finger dynamic movements for real-time control of a prosthetic hand. METHODS: High-density electromyogram (HD-EMG) signals were obtained from the extrinsic finger flexor and extensor muscles, while participants performed either single-finger or multi-finger flexion-extension movements. We implemented a deep learning-based neural network approach to learn the mapping from HD-EMG features to finger-specific population motoneuron firing frequency (i.e., neural-drive signals). The neural-drive signals reflected motor commands specific to individual fingers. The predicted neural-drive signals were then used to continuously control the fingers (index, middle, and ring) of a prosthetic hand in real-time. RESULTS: Our developed neural-drive decoder could consistently and accurately predict joint angles with significantly lower prediction errors across single-finger and multi-finger tasks, compared with a deep learning model directly trained on finger force signals and the conventional EMG-amplitude estimate. The decoder performance was stable over time and was robust to variations of the EMG signals. The decoder also demonstrated a substantially better finger separation with minimal predicted error of joint angle in the unintended fingers. CONCLUSIONS: This neural decoding technique offers a novel and efficient neural-machine interface that can consistently predict robotic finger kinematics with high accuracy, which can enable dexterous control of assistive robotic hands.

Low molecular weight fucoidan modified nanoliposomes for the targeted delivery of the anti-inflammation natural product berberine.

The inflammatory response is the basis of many diseases, such as atherosclerosis and ulcerative colitis. Inhibiting inflammatory response is the key to treating these diseases. Berberine hydrochloride (BBR), a natural product, has shown effective inflammation inhibitory activity. However, its distribution throughout the body results in a variety of serious side effects. Currently, there is a lack of targeted delivery systems for BBR to inflammatory sites. In view of the fact that the recruitment of inflammatory cells by activated vascular endothelial cells is a key step in inflammation development. Here, we design a system that can specifically deliver berberine to activated vascular endothelial cells. Low molecular weight fucoidan (LMWF), which can specifically bind to P-selectin, was coupled to PEGylated liposomes (LMWF-Lip), and BBR is encapsulated into LMWF-Lip (LMWF-Lip/BBR). In vitro, LMWF-Lip significantly increases the uptake by activated human umbilical vein endothelial cells (HUVEC). Injection of LMWF-Lip into the tail vein of rats can effectively accumulate in the swollen part of the foot, where it is internalized by the characteristics of activated vascular endothelial cells. LMWF-Lip/BBR can effectively inhibit the expression of P-selectin in activated vascular endothelial cells, and reduce the degree of foot edema and inflammatory response. In addition, compared with free BBR, the toxicity of BBR in LMWF-Lip/BBR to main organs was significantly reduced. These results suggest that wrapping BBR in LMWF-Lip can improve efficacy and reduce its systemic toxicity as a potential treatment for various diseases caused by inflammatory responses.

Microfluidic Approaches for Microactuators: From Fabrication, Actuation, to Functionalization.

Microactuators can autonomously convert external energy into specific mechanical motions. With the feature sizes varying from the micrometer to millimeter scale, microactuators offer many operation and control possibilities for miniaturized devices. In recent years, advanced microfluidic techniques have revolutionized the fabrication, actuation, and functionalization of microactuators. Microfluidics can not only facilitate fabrication with continuously changing materials but also deliver various signals to stimulate the microactuators as desired, and consequently improve microfluidic chips with multiple functions. Herein, this cross-field that systematically correlates microactuator properties and microfluidic functions is comprehensively reviewed. The fabrication strategies are classified into two types according to the flow state of the microfluids: stop-flow and continuous-flow prototyping. The working mechanism of microactuators in microfluidic chips is discussed in detail. Finally, the applications of microactuator-enriched functional chips, which include tunable imaging devices, micromanipulation tools, micromotors, and microsensors, are summarized. The existing challenges and future perspectives are also discussed. It is believed that with the rapid progress of this cutting-edge field, intelligent microsystems may realize high-throughput manipulation, characterization, and analysis of tiny objects and find broad applications in various fields, such as tissue engineering, micro/nanorobotics, and analytical devices.

EIF4A3 stabilizes the expression of lncRNA AGAP2-AS1 to activate cancer-associated fibroblasts via MyD88/NF-κb signaling.

BACKGROUND: Lung cancer (LC) is a fatal malignancy and often accompanied with converting normal fibroblasts to cancer-associated fibroblasts (CAFs). Exosomal lncRNA AGAP2-AS1 has been elucidated to be a potent prognostic factor for LC, while its role in activating CAFs is largely unknown. METHODS: We first extracted exosomes from LC patients and co-cultured them with MRC5 cells to observe the state of MRC5 cells, detect AGAP2-AS1 using real-time quantitative polymerase chain reaction, and then analyze the interaction between EIF4A3 and AGAP2-AS1 using RNA pull down experiments. CCK-8 assay was used to detect cell proliferation. Transwell experiments demonstrated the regulation of MRC5 cells and, finally, the role of MyD88/NF-κB in the downstream mechanism of EIF4A3/AGAP2-AS1 was explored by RNA interference technology and pyrrolidinedithiocarbamic acid inhibition. RESULTS: We demonstrated that exosomes from the LC patients (cancer-exo) notably increased the metastatic ability of MRC-5 cells, promoting the expressions of the CAF biomarkers and lncRNA AGAP2-AS1. Overexpression of lncRNA AGAP2-AS1 prominently activated MRC-5 cells. Moreover, EIF4A3 was upregulated in the cancer-exo-treated MRC-5 cells, and EIF4A3 was verified to bind with lncRNA AGAP2-AS1 to improve its stability. The MyD88/NF-κB signaling pathway was subsequently proved to be positively regulated by lncRNA AGAP2-AS1, and the promotive role of lncRNA AGAP2-AS1 in LC and activating CAFs was confirmed in vivo. CONCLUSIONS: The positive feedback of EIF4A3/AGAP2-AS1/MyD88/NF-κB signaling pathway contributed to the activation of CAFs and exacerbated LC in turn, revealing a novel regulatory axis underlying LC.

A novel Q-learning algorithm based on improved whale optimization algorithm for path planning.

Q-learning is a classical reinforcement learning algorithm and one of the most important methods of mobile robot path planning without a prior environmental model. Nevertheless, Q-learning is too simple when initializing Q-table and wastes too much time in the exploration process, causing a slow convergence speed. This paper proposes a new Q-learning algorithm called the Paired Whale Optimization Q-learning Algorithm (PWOQLA) which includes four improvements. Firstly, to accelerate the convergence speed of Q-learning, a whale optimization algorithm is used to initialize the values of a Q-table. Before the exploration process, a Q-table which contains previous experience is learned to improve algorithm efficiency. Secondly, to improve the local exploitation capability of the whale optimization algorithm, a paired whale optimization algorithm is proposed in combination with a pairing strategy to speed up the search for prey. Thirdly, to improve the exploration efficiency of Q-learning and reduce the number of useless explorations, a new selective exploration strategy is introduced which considers the relationship between current position and target position. Fourthly, in order to balance the exploration and exploitation capabilities of Q-learning so that it focuses on exploration in the early stage and on exploitation in the later stage, a nonlinear function is designed which changes the value of ε in ε-greedy Q-learning dynamically based on the number of iterations. Comparing the performance of PWOQLA with other path planning algorithms, experimental results demonstrate that PWOQLA achieves a higher level of accuracy and a faster convergence speed than existing counterparts in mobile robot path planning. The code will be released at https://github.com/wanghanyu0526/improveQL.git.

Automatic Upper-Limb Brunnstrom Recovery Stage Evaluation via Daily Activity Monitoring.

Motor function assessment is crucial for post-stroke rehabilitation. Conventional evaluation methods are subjective, heavily depending on the experience of therapists. In light of the strong correlation between the stroke severity level and the performance of activities of daily living (ADLs), we explored the possibility of automatically evaluating the upper-limb Brunnstrom Recovery Stage (BRS) via three typical ADLs (tooth brushing, face washing and drinking). Multimodal data (acceleration, angular velocity, surface electromyography) were synchronously collected from 5 upper-limb-worn sensor modules. The performance of BRS evaluation system is known to be variable with different system parameters (e.g., number of sensor modules, feature types and classifiers). We systematically searched for the optimal parameters from different data segmentation strategies (five window lengths and four overlaps), 42 types of features, 12 feature optimization techniques and 9 classifiers with the leave-one-subject-out cross-validation. To achieve reliable and low-cost monitoring, we further explored whether it was possible to obtain a satisfactory result using a relatively small number of sensor modules. As a result, the proposed approach can correctly recognize the stages of all 27 participants using only three sensor modules with the optimized data segmentation parameters (window length: 7s, overlap: 50%), extracted features (simple square integral, slope sign change, modified mean absolute value 1 and modified mean absolute value 2), the feature optimization method (principal component analysis) and the logistic regression classifier. According to the literature, this is the first study to comprehensively optimize sensor configuration and parameters in each stage of the BRS classification framework. The proposed approach can serve as a factor-screening tool towards the automatic BRS classification and is promising to be further used at home.

Random Channel Masks for Regularization of Least Squares-Based Finger EMG-Force Modeling to Improve Cross-Day Performance.

Estimating the finger forces from surface electromyography (sEMG) is essential for diverse applications (e.g., human-machine interfacing). The performance of pre-trained sEMG-force models degenerates significantly when applied on a second day, due to the large cross-day variation of sEMG characteristics. Previous studies mainly employed transfer learning algorithms to tackle this problem. However, transfer learning algorithms normally require data collected on the second day for model calibration, increasing the inconvenience in practical use. In this work, we investigated the effect of model regularization on this issue. Specifically, 256-channel high-density sEMG (HDsEMG) signals with varying finger forces were collected on different days (3-25 days apart). We applied randomly generated channel perturbations ("masks") to feature maps of randomly selected channels in training dataset. The channel masks of the training set were generated randomly and independently in each narrow time window (~20 ms). We assumed that by learning from randomly masked feature maps (randomness is the central aspect), the model would not be biased by a small number of features but would be based on learning from a global perspective, therefore avoiding overfitting to the within-day EMG patterns. Moore-Penrose inverse model regularization was also employed as a baseline method, with results showing that cross-day EMG-force models require a higher tolerance parameter compared with within-day applications. In combination with the Moore-Penrose inverse model regularization, further applying random channel masks to the training set significantly improved model performance in cross-day validation.

Association Between Circulating Regulator of Calcineurin 2 Concentrations With Overweight and Obesity.

Background: Regulator of calcineurin 2 (RCAN2) has been reported to promote food intake and weight gain in animal studies. However, its effect on body weight in humans is unclear. Objective: This study aimed to investigate the relationship between serum RCAN2 concentrations and participants with overweight/obesity. Methods: A cross-sectional study was performed in 872 Chinese adults, including 348 participants with normal weight (NW), 397 participants with overweight (OW), and 127 participants with obesity (OB). All participants were divided into NW, OW and OB groups according to their body mass index (BMI). Serum RCAN2 concentrations were determined by enzyme-linked immunosorbent assay. Results: Serum RCAN2 concentrations gradually increased with the increase of BMI (p < 0.001). The percentages of OW/OB gradually increased in tandem with increasing tertiles of RCAN2 (p < 0.001). Additionally, serum RCAN2 concentrations were significantly correlated with a series of anthropometric and metabolic parameters, predominantly including body weight, BMI, SBP, DBP, total cholesterol, triglycerides, HDL-C, LDL-C (all p < 0.05). Furthermore, logistic regression analysis showed that the risk of OW/OB was significantly increased with the increase of serum RCAN2 concentrations. Receiver operation characteristic (ROC) curve analysis revealed that serum RCAN2, especially serum RCAN2/(AST/ALT) ratio, might serve as a candidate biomarker for obesity. Conclusion: Serum RCAN2 concentrations were increased in subjects with OW/OB. The increased serum RCAN2 concentrations were associated with the increased risks of OW/OB.