Multi-level data fusion strategy based on spectral and image information for identifying varieties of soybean seeds.

Rapid identification of soybean seed varieties is crucial for agricultural production and seed quality. Identifying varieties of soybean seed using conventional chemical methods is time-consuming, destructive, and inappropriate for seed quality evaluation. This study utilized hyperspectral imaging technology (HSI) to identify four varieties of soybean seeds. The hyperspectral images of soybean seeds were collected in the spectral range of 400-1000 nm. A multi-level data fusion strategy based on spectral and image information was proposed to improve the accuracy of model. Subsequently, the multi-level data fusion strategy based on partial least squares discriminant analysis (PLS-DA) was used to establish the classification models of soybean seeds. Compared with the models using individual analytical sources, the results demonstrated that the models with multi-level data fusion strategy obtained better prediction performance. The high-level data fusion (HLDF) based on Bayesian consensus provided the optimal results with an accuracy (Acc) and F1-score of 93.13 % and 93.70 % in the prediction phase, respectively. Therefore, the multi-level data fusion strategy can be used as an identification method for soybean seed varieties and an effective approach to enhance the discriminatory capability of models.

Deep learning for multi-type infectious keratitis diagnosis: A nationwide, cross-sectional, multicenter study.

The main cause of corneal blindness worldwide is keratitis, especially the infectious form caused by bacteria, fungi, viruses, and Acanthamoeba. The key to effective management of infectious keratitis hinges on prompt and precise diagnosis. Nevertheless, the current gold standard, such as cultures of corneal scrapings, remains time-consuming and frequently yields false-negative results. Here, using 23,055 slit-lamp images collected from 12 clinical centers nationwide, this study constructed a clinically feasible deep learning system, DeepIK, that could emulate the diagnostic process of a human expert to identify and differentiate bacterial, fungal, viral, amebic, and noninfectious keratitis. DeepIK exhibited remarkable performance in internal, external, and prospective datasets (all areas under the receiver operating characteristic curves > 0.96) and outperformed three other state-of-the-art algorithms (DenseNet121, InceptionResNetV2, and Swin-Transformer). Our study indicates that DeepIK possesses the capability to assist ophthalmologists in accurately and swiftly identifying various infectious keratitis types from slit-lamp images, thereby facilitating timely and targeted treatment.

Multi-functional adhesive hydrogel as bio-interface for wireless transient pacemaker.

Traditional temporary cardiac pacemakers (TCPs), which employ transcutaneous leads and external wired power systems are battery-dependent and generally non-absorbable with rigidity, thereby necessitating surgical retrieval after therapy and resulting in potentially severe complications. Wireless and bioresorbable transient pacemakers have, hence, emerged recently, though hitting a bottleneck of unfavorable tissue-device bonding interface subject to mismatched mechanical modulus, low adhesive strength, inferior electrical performances, and infection risks. Here, to address such crux, we develop a multifunctional interface hydrogel (MIH) with superior electrical performance to facilitate efficient electrical exchange, comparable mechanical strength to natural heart tissue, robust adhesion property to enable stable device-tissue fixation (tensile strength: ∼30 kPa, shear strength of ∼30 kPa, and peel-off strength: ∼85 kPa), and good bactericidal effect to suppress bacterial growth. Through delicate integration of this versatile MIH with a leadless, battery-free, wireless, and transient pacemaker, the entire system exhibits stable and conformal adhesion to the beating heart while enabling precise and constant electrical stimulation to modulate the cardiac rhythm. It is envisioned that this versatile MIH and the proposed integration framework will have immense potential in overcoming key limitations of traditional TCPs, and may inspire the design of novel bioelectronic-tissue interfaces for next-generation implantable medical devices.

Lactobacillus rhamnosus GG alleviates radiation-induced intestinal injury by modulating intestinal immunity and remodeling gut microbiota.

Radiation injury to the intestine is one of the most common complications in patients undergoing abdominal or pelvic cavity radiotherapy. In this study, we investigated the potential protective effect of Lactobacillus rhamnosus GG (LGG) on radiation-induced intestinal injury and its underlying mechanisms. Mice were assigned to a control group, a 10 Gy total abdominal irradiation (TAI) group, or a group pretreated with 108 CFU LGG for three days before TAI. Small intestine and gut microbiota were analyzed 3.5 days post-exposure. LGG intervention improved intestinal structure, reduced jejunal DNA damage, and inhibited the inflammatory cGAS/STING pathway. Furthermore, LGG reduced M1 proinflammatory macrophage and CD8+ T cell infiltration, restoring the balance between Th17 and Treg cells in the inflamed jejunum. LGG also partially restored the gut microbiota. These findings suggest the possible therapeutic radioprotective effect of probiotics LGG in alleviating radiation-induced intestinal injury by maintaining immune homeostasis and reshaping gut microbiota.

Circadian time-dependent effects of experimental colitis on theophylline disposition and toxicity.

BACKGROUND AND PURPOSE: Drug disposition undergoes significant alteration in patients with inflammatory bowel disease (IBD), yet circadian time-dependency of these changes remains largely unexplored. In this study, we aimed to determine the temporal effects of experimental colitis on drug disposition and toxicity. EXPERIMENTAL APPROACH: RNA-sequencing was used to screen genes relevant to colitis induced by dextran sodium sulfate in mice. Liver microsomes and pharmacokinetic analysis were used to analyze the activity of key enzymes. Dual luciferase assays and chromatin immunoprecipitation (ChIP) were employed to elucidate regulatory mechanisms. KEY RESULTS: RNA sequencing analysis revealed that colitis markedly influenced expression of cytochrome P450 (CYP) enzymes. Specifically, a substantial down-regulation of CYP1A2 and CYP2E1 was observed in livers of mice with colitis at Zeitgeber Time 8 (ZT8), with no significant changes detected at ZT20. At ZT8, the altered expression corresponded to diminished metabolism and enhanced incidence of hepato-cardiac toxicity of theophylline, a substrate specifically metabolized by these enzymes. A combination of assays, integrating liver-specific Bmal1 knockout and targeted activation of BMAL1 showed that dysregulation in CYP1A2 and CYP2E1 during colitis was attributable to perturbed BMAL1 functionality. Luciferase reporter and ChIP assays collectively substantiated the role of BMAL1 in regulating Cyp1a2 and Cyp2e1 transcription through its binding affinity to E-box-like sites. CONCLUSION AND IMPLICATION: Our findings establish a strong link between colitis and chronopharmacology, shedding light on how IBD affects drug disposition and toxicity over time. This research provides a theoretical foundation for optimizing drug dosage in patients with IBD.

Compound sophora decoction alleviates ulcerative colitis by regulating macrophage polarization through cGAS inhibition: network pharmacology and experimental validation.

INTRODUCTION: Ulcerative colitis (UC) is a refractory disease with complex pathogenesis, and its pathogenesis is not clear. The present study aimed to investigate the potential target and related mechanism of Compound Sophora Decoction (CSD) in treating UC. METHODS: A network pharmacology approach predicted the components and targets of CSD to treat UC, and cell and animal experiments confirmed the findings of the approach and a new target for CSD treatment of UC. RESULTS: A total of 155 potential targets were identified for CSD treatment of UC, with some related to macrophage polarization, such as nitric oxide synthase (NOS2), also known as inducible nitric oxide synthase (iNOS). GO and KEGG enrichment analysis indicated that oxidative stress response and multiple inflammatory signaling pathways such as TNF-α may play a significant role. In vitro experiments revealed that Interferon-stimulated DNA (ISD) interference can cause polarization imbalances in Raw 264.7 and bone marrow-derived macrophages (BMDMs). Flow cytometry demonstrated that polarization of macrophages in the intestine, spleen, and lymph nodes in vivo was also unbalanced after dextran sulfate sodium (DSS) modeling with pathological intestinal injury. Both in vitro and in vivo studies indicated that after inducing inflammation, the levels of macrophage polarization-related markers (iNOS and Arg1) and inflammation-related factors (CCL17, IL10, TNF-α, and CXCL10) changed, accompanied by increased expression of cGAS. However, CSD treatment based on inflammation can inhibit the expression of cGAS protein and mRNA, lower the level of inflammatory factors, promote the expression of anti-inflammatory factors, and regulate macrophage polarization. CONCLUSION: We concluded that CSD alleviated DSS-induced UC by inhibiting cGAS, thus regulating macrophage polarization.

Cyclometalated Iridium(III) Complexes Containing Viologen-Modified Phenylpyridine Ligands as Electroluminochromic Active Molecules for Information Display.

Electroluminochromic (ELC) materials have garnered significant research interest because of their potential applications in lighting, displaying, and sensing. These materials exhibit reversible modulation of photoluminescence under low-voltage stimuli. Here five phosphorescent iridium(III) complexes are reported featuring viologen-substituted 2-phenylpyridine (Vppy) ligands acting as electroactive components. Four of the complexes are bis-cyclometalated and coordinated with either neutral bipyridine derivatives or negatively charged 2-picolinate. The remaining complex is heteroleptic tris-cyclometalated, containing one Vppy and two 2-phenylquinoline ligands. Upon photoexcitation, the bis-cyclometalated complexes exhibit orange to red phosphorescence originating from mixed triplet metal-to-ligand charge transfer (3MLCT) and intraligand (3IL) dπ(Ir)/π(Vppy) → π*(Vppy) state, whereas the tris-cyclometalated complex is non-emissive due to a low Ir(IV/III) oxidation potential favoring oxidative quenching by the viologen pendants. When the cationic viologens are electrochemically reduced to their neutral form, the bis-cyclometalated complexes show a remarkable blue-shift in their phosphorescence maxima due to increased energy levels of the Vppy molecular orbitals. In the case of the tris-cyclometalated complex, reduction of the viologen groups interrupts the quenching process, leading to a luminescence turn-on. These complexes are used to develop ELC devices, which exhibit reversible luminescence response in terms of color or on-off switching under a low voltage of 2 V.

Effects of Sodium Vacancies and Concentrations in Na3SO4F Solid Electrolyte.

The sodium-rich solid electrolyte, Na3SO4F (NSOF), holds promise for eco-friendly and resource-abundant energy storage. While the introduction of heterovalent dopants has the potential to enhance its suitability for battery applications by creating Na vacancies, the effect of vacancies and sodium concentrations on sodium conduction remains unclear. In this work, Mg2+ was introduced into Na+ sites in Na3SO4F, generating sodium vacancies with different contents by using solid-state synthesis method. Among the resulting materials, Na2.96Mg0.02SO4F exhibited an ionic conductivity that is two-order-of-magnitude higher than NSOF at 298 K. Notably, as the sodium concentration decreased, the ionic conductivity also declined, revealing an equilibrium between Na vacancies and concentrations. To further investigate the influence of sodium concentration, excess Na+ was introduced into NaMgSO4F, which inherently possesses a lower sodium content by using solid-state synthesis method. However, this adjustment only led to an approximately one-order-of-magnitude enhancement in optimal ionic conductivity at 298 K. Combined with an in situ X-ray diffraction analysis, our findings underscore the greater sensitivity of sodium conduction to variations in sodium vacancies. This study paves the way for the development of ultrafast sodium ion conductors, offering exciting prospects for advanced energy storage solutions.

A three-dimensional liquid diode for soft, integrated permeable electronics.

Wearable electronics with great breathability enable a comfortable wearing experience and facilitate continuous biosignal monitoring over extended periods1-3. However, current research on permeable electronics is predominantly at the stage of electrode and substrate development, which is far behind practical applications with comprehensive integration with diverse electronic components (for example, circuitry, electronics, encapsulation)4-8. Achieving permeability and multifunctionality in a singular, integrated wearable electronic system remains a formidable challenge. Here we present a general strategy for integrated moisture-permeable wearable electronics based on three-dimensional liquid diode (3D LD) configurations. By constructing spatially heterogeneous wettability, the 3D LD unidirectionally self-pumps the sweat from the skin to the outlet at a maximum flow rate of 11.6 ml cm-2 min-1, 4,000 times greater than the physiological sweat rate during exercise, presenting exceptional skin-friendliness, user comfort and stable signal-reading behaviour even under sweating conditions. A detachable design incorporating a replaceable vapour/sweat-discharging substrate enables the reuse of soft circuitry/electronics, increasing its sustainability and cost-effectiveness. We demonstrated this fundamental technology in both advanced skin-integrated electronics and textile-integrated electronics, highlighting its potential for scalable, user-friendly wearable devices.

Bimetallic Nanozyme: A Credible Tag for In Situ-Catalyzed Reporter Deposition in the Lateral Flow Immunoassay for Ultrasensitive Cancer Diagnosis.

The lateral flow immunoassay (LFIA) is a sought-after point-of-care testing platform, yet the insufficient sensitivity of the LFIA limits its application in the detection of tumor biomarkers. Here, a colorimetric signal amplification method, bimetallic nanozyme-mediated in situ-catalyzed reporter deposition (BN-ISCRD), was designed for ultrasensitive cancer diagnosis. The bimetallic nanozyme used, palladium@iridium core-shell nanoparticles (Pd@Ir NPs), had ultrahigh enzyme-like activity, which was further explained by the electron transfer of Pd@Ir NPs and the change in the Gibbs free energy during catalysis through density functional theory calculations. With gastric cancer biomarkers pepsinogen I and pepsinogen II as model targets, this assay could achieve a cutoff value of 10 pg/mL, which was 200-fold lower than that without signal enhancement. The assay was applied to correctly identify 8 positive and 28 negative clinical samples. Overall, this BN-ISCRD-based LFIA showed great merits and potential in the application of ultrasensitive disease diagnosis.

Research on Positioning Accuracy of Mobile Robot in Indoor Environment Based on Improved RTABMAP Algorithm.

Visual simultaneous localization and mapping is a widely used technology for mobile robots to carry out precise positioning in the environment of GNSS technology failure. However, as the robot moves around indoors, its position accuracy will gradually decrease over time due to common and unavoidable environmental factors. In this paper, we propose an improved method called RTABMAP-VIWO, which is based on RTABMAP. The basic idea is to use an Extended Kalman Filter (EKF) framework for fusion attitude estimates from the wheel odometry and IMU, and provide new prediction values. This helps to reduce the local cumulative error of RTABMAP and make it more accurate. We compare and evaluate three kinds of SLAM methods using both public datasets and real indoor scenes. In the dataset experiments, our proposed method reduces the Root-Mean-Square Error (RMSE) coefficient by 48.1% compared to the RTABMAP, and the coefficient is also reduced by at least 29.4% in the real environment experiments. The results demonstrate that the improved method is feasible. By incorporating the IMU into the RTABMAP method, the trajectory and posture errors of the mobile robot are significantly improved.

Synthesis, Characterization, and Reactivity of Tris(imido)chromium(VI) Complexes.

Multiple tris(imido)chromium(VI) complexes, including neutral and ionic compounds, have been synthesized and characterized. (tBuN)2Cr(NHtBu)Cl can be deprotonated by KN(SiMe3)2, yielding K[(tBuN)3CrCl]. This tris(imido) anion undergoes nucleophilic substitution by PPh3 and tBuNH2 to form (tBuN)3Cr(PPh3) and (tBuN)2Cr(NHtBu)2, respectively. (tBuN)2Cr(NHtBu)2 loses one amido proton to form K[(tBuN)3Cr(NHtBu)] upon reaction with KN(SiMe3)2. The imido ligands of K[(tBuN)3CrCl] and (tBuN)3Cr(PPh3) are attacked by the electrophile MeI to produce (tBuN)2Cr(NMetBu)Cl and (tBuN)2Cr(NMetBu)I, respectively. An alternate way to make tris(imido) anions is deprotonation of (tBuN)2Cr(NHtBu)Cl by an alkyl lithium reagent, e.g., Me3SiCH2Li. The resulting Li[(tBuN)3CrCl] was alkylated by a second equivalent of Me3SiCH2Li to form Li[(tBuN)3Cr(CH2SiMe3)]. Reactivity studies of tris(imido) complexes show cycloaddition with PhNCO or CO2 to form metallacycles.

A Monte Carlo resampling based multiple feature-spaces ensemble (MFE) strategy for consistency-enhanced spectral variable selection.

BACKGROUND: Variable selection has gained significant attention as a means to enhance spectroscopic calibration performance. However, existing methods still have certain limitations. Firstly, the selection results are sensitive to the choice of training samples, indicating that the selected variables may not be truly relevant. Secondly, the number of the selected variables is still too large in some situations, and modelling with too many predictors may lead to over-fitting issues. To address these challenges, we propose and implement a novel multiple feature-spaces ensemble (MFE) strategy with the least absolute shrinkage and selection operator (LASSO) method. RESULTS: The MFE strategy synergizes the advantages of LASSO regression and ensemble strategy, thereby facilitating a more robust identification of key variables. We demonstrated the efficacy of our approach through extensive experimentation on publicly available datasets. The results not only demonstrate enhanced consistency in variable selection but also manifest improved prediction performance compared to benchmark methods. SIGNIFICANT: The MFE strategy provided a comprehensive framework for conducting variable importance analysis, leading to robust and consistent variable selection. Furthermore, the improved consistency in variable selection contributes to enhanced prediction performance for spectroscopic calibration, making it more robust and accurate.

Adherence to the 2015-2020 Dietary Guidelines for Americans Compared with the Mediterranean Diet in Relation to Risk of Prediabetes: Results from NHANES 2007-2016.

Prediabetes presents a high-risk state for the development of various diseases and is reversible by adhering to a healthy lifestyle. We conducted this analysis to explore the associations of the Healthy Eating Index-2015 (HEI-2015) and the Alternate Mediterranean Diet Index (aMed index) with the risk of prediabetes. The data were derived from the National Health and Nutrition Examination Survey, including 20,844 participants. Multivariable-adjusted odds ratios (OR) of prediabetes and 95% confidence intervals (CI) by tertile of diet quality scores were estimated using a weighted logistic regression. Compared to those in the lowest tertile, the multivariable-adjusted OR of prediabetes for the highest tertile was 0.82 (95% CI: 0.72, 0.94; p for trend = 0.005) for HEI-2015 and 0.87 (95% CI: 0.76, 0.98; p for trend = 0.02) for the aMed index. After mutual adjustment, the association for HEI-2015 (p for trend = 0.03) but not for the aMed index (p for trend = 0.59) remained significant. Among the component food groups and nutrients, higher intakes of red and processed meat, sodium, and total saturated fatty acids were associated with a higher risk of prediabetes, while moderate alcohol consumption was associated with a lower risk. In conclusion, adherence to the 2015-2020 Dietary Guidelines for Americans, as compared with the Mediterranean Diet, appeared to be more strongly associated with a lower risk of prediabetes among adults in the United States.

A Novel Methacryloyl Chitosan Hydrogel Microneedles Patch with Sustainable Drug Release Property for Effective Treatment of Psoriasis.

Psoriasis is a chronic and recurrent skin disease that often requires long-term treatment, and topical transdermal drug delivery can reduce systemic side effects. However, it is still a challenge in efficient transdermal drug delivery for psoriasis treatment due to low penetration efficiency of most drugs and the abnormal skin conditions of psoriasis patients. Here, a safe and effective methacryloyl chitosan hydrogel microneedles (CSMA hMNs) patch is developed and served as a sustained drug release platform for the treatment of psoriasis. By systematically optimizing the CSMA preparation, CSMA hMNs with excellent morphological characteristics and strong mechanical properties (0.7 N needle-1 ) are prepared with a concentration of only 3% (w/v) CSMA. As a proof-of-concept, methotrexate (MTX) and nicotinamide (NIC) are loaded into CSMA hMNs patch, which can produce a sustained drug release of 80% within 24 h in vitro. In vivo experiments demonstrated that the CSMA hMNs patch can effectively inhibit the skin thickening and spleen enlargement of psoriatic mice and has a good biosafety profile at sufficient therapeutic doses. This study provides a new idea for the preparation of hMN systems using modified CS or other biocompatible materials and offers an effective therapeutic option for psoriasis treatment.

A universal boronate affinity capture-antibody-independent lateral flow immunoassay for point-of-care glycoprotein detection.

Protein glycosylation and other post-translational modifications are involved in many biological processes including growth, development and immune responses, and glycoproteins are also known as biomarkers for cancer, diabetes and cardiovascular diseases. In traditional lateral flow immunoassay (LFIA) for glycoprotein detection, capture antibody (CA) is often required to label targets. However, the production of CA is complicated and expensive, restricting the wide application of LFIA. In this study, we developed a universal boronate affinity CA-independent LFIA method for glycoprotein detection. 4-Mercaptophenylboronic acid (4-MPBA)-modified Au nanoparticles (namely 4-MPBA-AuNPs) were used as LFIA labels, which could generate colorimetric signal and showed outstanding capability to bind glycoprotein. Compared with CA, 4-MPBA molecular as a glycoprotein recognition element had more prominent advantages, e.g., low cost, easy availability and good quality controllability. Take carcinoembryonic antigen (CEA) as model glycoprotein, the limit of detection of this CA-independent LFIA was 1.25 ng/mL by naked eyes, which was 8-fold lower than conventional CA-dependent sandwich LFIA. Significantly, the developed 4-MPBA-AuNPs-based CA-independent LFIA successfully detected 23 CEA-positive samples from 64 suspected human serum samples within 50 min in a nonlaboratory environment, with a 100% accuracy compared to clinical detection method. Therefore, this diagnostic platform could provide an effective tool for point-of-care glycoprotein detection with excellent reproducibility and high specificity.

Injectable rBMSCs-laden hydrogel microspheres loaded with naringin for osteomyelitis treatment.

Osteomyelitis, caused by purulent bacteria invading bone tissue, often occurs in long bones and seriously affects the physical and mental health and working ability of patients; it can even endanger life. However, due to bone cavity structure, osteomyelitis tends to occur inside the bone and thus lacks an effective treatment; anti-inflammatory treatment and repair of bone defects are necessary. Here, we developed injectable hydrogel microspheres loaded with naringin and bone marrow mesenchymal stem cells, which have anti-inflammatory and osteogenic properties. These homogeneous microspheres, ranging from 200 to 1000µm, can be rapidly fabricated using an electro-assisted bio-fabrication method. Interestingly, it was found that microspheres with relatively small diameters (200µm) were more conducive to the initial cell attachment, growth, spread, and later osteogenic differentiation. The developed microspheres can effectively treat tibial osteomyelitis in rats within six weeks, proving their prospects for clinical application.

A Survey on Reinforcement Learning for Recommender Systems.

Recommender systems have been widely applied in different real-life scenarios to help us find useful information. In particular, reinforcement learning (RL)-based recommender systems have become an emerging research topic in recent years, owing to the interactive nature and autonomous learning ability. Empirical results show that RL-based recommendation methods often surpass supervised learning methods. Nevertheless, there are various challenges in applying RL in recommender systems. To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems. To this end, we first provide a thorough overview, comparisons, and summarization of RL approaches applied in four typical recommendation scenarios, including interactive recommendation, conversational recommendation, sequential recommendation, and explainable recommendation. Furthermore, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommender systems, we highlight some potential research directions in this field.

Synthesis and Hydrogen Production Performance of MoP/a-TiO2/Co-ZnIn2S4 Flower-like Composite Photocatalysts.

Semiconductor photocatalysis is an effective strategy for solving the problems of increasing energy demand and environmental pollution. ZnIn2S4-based semiconductor photocatalyst materials have attracted much attention in the field of photocatalysis due to their suitable energy band structure, stable chemical properties, and good visible light responsiveness. In this study, ZnIn2S4 catalysts were modified by metal ion doping, the construction of heterojunctions, and co-catalyst loading to successfully prepare composite photocatalysts. The Co-ZnIn2S4 catalyst synthesized by Co doping and ultrasonic exfoliation exhibited a broader absorption band edge. Next, an a-TiO2/Co-ZnIn2S4 composite photocatalyst was successfully prepared by coating partly amorphous TiO2 on the surface of Co-ZnIn2S4, and the effect of varying the TiO2 loading time on photocatalytic performance was investigated. Finally, MoP was loaded as a co-catalyst to increase the hydrogen production efficiency and reaction activity of the catalyst. The absorption edge of MoP/a-TiO2/Co-ZnIn2S4 was widened from 480 nm to about 518 nm, and the specific surface area increased from 41.29 m2/g to 53.25 m2/g. The hydrogen production performance of this composite catalyst was investigated using a simulated light photocatalytic hydrogen production test system, and the rate of hydrogen production by MoP/a-TiO2/Co-ZnIn2S4 was found to be 2.96 mmol·h-1·g-1, which was three times that of the pure ZnIn2S4 (0.98 mmol·h-1·g-1). After use in three cycles, the hydrogen production only decreased by 5%, indicating that it has good cycle stability.

Research on Lower Limb Step Speed Recognition Method Based on Electromyography.

Wearable exoskeletons play an important role in people's lives, such as helping stroke and amputation patients to carry out rehabilitation training and so on. How to make the exoskeleton accurately judge the human action intention is the basic requirement to ensure that it can complete the corresponding task. Traditional exoskeleton control signals include pressure values, joint angles and acceleration values, which can only reflect the current motion information of the human lower limbs and cannot be used to predict motion. The electromyography (EMG) signal always occurs before a certain movement; it can be used to predict the target's gait speed and movement as the input signal. In this study, the generalization ability of a BP neural network and the timing property of a hidden Markov chain are used to properly fuse the two, and are finally used in the research of this paper. Experiments show that, using the same training samples, the recognition accuracy of the three-layer BP neural network is only 91%, while the recognition accuracy of the fusion discriminant model proposed in this paper can reach 95.1%. The results show that the fusion of BP neural network and hidden Markov chain has a strong solving ability for the task of wearable exoskeleton recognition of target step speed.