Dual-Path Vision Transformer用于急性缺血性脑卒中辅助诊断

急性缺血性脑卒中是由于脑组织血液供应障碍导致的脑功能障碍,数字减影脑血管造影(DSA)是诊断脑血管疾病的金标准。基于患者的正面和侧面DSA图像,对急性缺血性脑卒中的治疗效果进行分级评估,构建基于Vision Transformer的双路径图像分类智能模型DPVF。为了提高辅助诊断速度,基于EdgeViT的轻量化设计思想进行了模型的构建;为了使模型保持轻量化的同时具有较高的精度,提出空间-通道自注意力模块,促进Transformer模型捕获更全面的特征信息,提高模型的表达能力;此外,对于DPVF的两分支的特征融合,构建交叉注意力模块对两分支输出进行交叉融合,促使模型提取更丰富的特征,从而提高模型表现。实验结果显示DPVF在测试集上的准确率达98.5%,满足实际需求。

A dual-RPA based lateral flow strip for sensitive,on-site detection of CP4-EPSPS and Cry1Ab/Ac genes in genetically modified crops

Traditional transgenic detection methods require high test conditions and struggle to be both sensitive and efficient.In this study,a one-tube dual recombinase polymerase amplification(RPA)reaction system for CP4-EPSPS and Cry1Ab/Ac was proposed and combined with a lateral flow immunochromatographic assay,named“Dual-RPA-LFD”,to visualize the dual detection of genetically modified(GM)crops.In which,the herbicide tolerance gene CP4-EPSPS and the insect resistance gene Cry1Ab/Ac were selected as targets taking into account the current status of the most widespread application of insect resistance and herbicide tolerance traits and their stacked traits.Gradient diluted plasmids,transgenic standards,and actual samples were used as templates to conduct sensitivity,specificity,and practicality assays,respectively.The constructed method achieved the visual detection of plasmid at levels as low as 100 copies,demonstrating its high sensitivity.In addition,good applicability to transgenic samples was observed,with no cross-interference between two test lines and no influence from other genes.In conclusion,this strategy achieved the expected purpose of simultaneous detection of the two popular targets in GM crops within 20 min at 37°C in a rapid,equipmentfree field manner,providing a new alternative for rapid screening for transgenic assays in the field.

Electron-distribution control via Pt/NC and MoC/NC dual junction:Boosted hydrogen electro-oxidation and theoretical study

The scarcity,high cost and susceptibility to CO of Platinum severely restrict its application in alkaline hydrogen oxidation reaction(HOR).Hybridizing Pt with other transition metals provides an effective strategy to modulate its catalytic HOR performance,but at the cost of mass activity due to the coverage of modifiers on Pt surface.Herein,we constructed dual junctions'Pt/nitrogen-doped carbon(Pt/NC)andδ-MoC/NC to modify electronic structure of Pt via interfacial electron transfer to acquire Pt-MoC@NC catalyst with electron-deficient Pt nanoparticles,simultaneously endowing it with high mass activity and durability of alkaline HOR.Moreover,the unique structure of Pt-MoC@NC endows Pt with a high COtolerance at 1,000 ppm CO/H_(2),a quality that commercial Pt-C catalyst lacks.The theoretical calculations not only confirm the diffusion of electrons from Pt/NC to Mo C/NC could occur,but also demonstrate the negative shift of Pt d-band center for the optimized binding energies of*H,*OH and CO.

SUMS OF DUAL TOEPLITZ PRODUCTS ON THE ORTHOGONAL COMPLEMENTS OF FOCK-SOBOLEV SPACES

We consider dual Toeplitz operators on the orthogonal complements of the FockSobolev spaces of all nonnegative real orders.First,for symbols in a certain class containing all bounded functions,we study the problem of when an operator which is finite sums of the dual Toeplitz products is compact or zero.Next,for bounded symbols,we construct a symbol map and exhibit a short exact sequence associated with the C^(*)-algebra generated by all dual Toeplitz operators with bounded symbols.

A Sustainable Dual Cross‑Linked Cellulose Hydrogel Electrolyte for High‑Performance Zinc‑Metal Batteries

Aqueous rechargeable Zn-metal batteries(ARZBs)are considered one of the most promising candidates for grid-scale energy storage.However,their widespread commercial application is largely plagued by three major challenges:The uncontrollable Zn dendrites,notorious parasitic side reactions,and sluggish Zn^(2+) ion transfer.To address these issues,we design a sustainable dual crosslinked cellulose hydrogel electrolyte,which has excellent mechanical strength to inhibit dendrite formation,high Zn^(2+) ions binding capacity to suppress side reaction,and abundant porous structure to facilitate Zn^(2+) ions migration.Consequently,the Zn||Zn cell with the hydrogel electrolyte can cycle stably for more than 400 h under a high current density of 10 mA cm^(−2).Moreover,the hydrogel electrolyte also enables the Zn||polyaniline cell to achieve high-rate and long-term cycling performance(>2000 cycles at 2000 mA g^(−1)).Remarkably,the hydrogel electrolyte is easily accessible and biodegradable,making the ARZBs attractive in terms of scalability and sustainability.

Mg/Fe site-specific dual-doping to boost the performance of cobalt-free nickle-rich layered oxide cathode for high-energy lithium-ion batteries

Layer-type LiNi0.9Mn0.1O2is promising to be the primary cathode material for lithium-ion batteries(LIBs)due to its excellent electrochemical performance.Unfortunately,the cathode with high nickel content suffers from severely detrimental structural transformation that causes rapid capacity attenuation.Herein,site-specific dual-doping with Fe and Mg ions is proposed to enhance the structural stability of LiNi0.9Mn0.1O2.The Fe3+dopants are inserted into transition metal sites(3b)and can favorably provide additional redox potential to compensate for charge and enhance the reversibility of anionic redox.The Mg ions are doped into the Li sites(3a)and serve as O_(2)^(-)-Mg^(2+)-O_(2)^(-)pillar to reinforce the electrostatic cohesion between the two adjacent transition-metal layers,which further suppress the cracking and the generation of harmful phase transitions,ultimately improving the cyclability.The theoretical calculations,including Bader charge and crystal orbital Hamilton populations(COHP)analyses,confirm that the doped Fe and Mg can form stable bonds with oxygen and the electrostatic repulsion of O_(2)^(-)-O_(2)^(-)can be effectively suppressed,which effectively mitigates oxygen anion loss at the high delithiation state.This dual-site doping strategy offers new avenues for understanding and regulating the crystalline oxygen redox and demonstrates significant potential for designing high-performance cobalt-free nickel-rich cathodes.

A Dual-Cluster-Head Based Medium Access Control for Large-Scale UAV Ad-Hoc Networks

Unmanned Aerial Vehicle(UAV)ad hoc network has achieved significant growth for its flexibility,extensibility,and high deployability in recent years.The application of clustering scheme for UAV ad hoc network is imperative to enhance the performance of throughput and energy efficiency.In conventional clustering scheme,a single cluster head(CH)is always assigned in each cluster.However,this method has some weaknesses such as overload and premature death of CH when the number of UAVs increased.In order to solve this problem,we propose a dual-cluster-head based medium access control(DCHMAC)scheme for large-scale UAV networks.In DCHMAC,two CHs are elected to manage resource allocation and data forwarding cooperatively.Specifically,two CHs work on different channels.One of CH is used for intra-cluster communication and the other one is for inter-cluster communication.A Markov chain model is developed to analyse the throughput of the network.Simulation result shows that compared with FM-MAC(flying ad hoc networks multi-channel MAC,FM-MAC),DCHMAC improves the throughput by approximately 20%~50%and prolongs the network lifetime by approximately 40%.

Liposomal dual delivery systems in visceral leishmaniasis enhance the synergistic effects of combination therapy:A promise for the future

Visceral leishmaniasis(VL)is a neglected tropical disease,and this review has summarized the current treatment scenario and its prospects.It also highlights alternative approaches used by research groups in India and around the world to develop cutting-edge and potent anti-leishmanial treatments.Even though numerous medications could be utilized to treat VL,the limitations of current treatments including their toxicity,cost,route of administration,and duration of doses,have contributed to the emergence of resistance.Combination therapy might be a better option due to its shorter duration,easier route of administration,and ability to extend the lifespan of individual drugs.However,there is a risk of not delivering both the drugs to the target site together,which can be overcome by the liposomal entrapment of those drugs and at a time knock an opportunity to reduce the dosage of amphotericin B if the combination drug provides a synergistic effect with it.Therefore,this review presents a novel strategy to fight against VL by introducing dual drug-loaded liposomes.

Zonal activation of molecular carbon dioxide and hydrogen over dual sites Ni-Co-MgO catalyst for CO_(2) methanation:Synergistic catalysis of Ni and Co species

An in-depth mechanism in zonal activation of CO_(2)and H2molecular over dual-active sites has not been revealed yet.Here,Ni-Co-MgO was rationally constructed to elucidate the CO_(2)methanation mechanism.The abundant surface nickel and cobalt components as active sites led to strong Ni-Co interaction with charge transfer from nickel to cobalt.Notably,electron-enriched Coδ-species participated in efficient chemisorption and activation of CO_(2)to generate monodentate carbonate.Simultaneously,plentiful available Ni0sites facilitated H2dissociation,thus CO_(2)and H2were smoothly activated at zones of Coδ-species and Ni0,respectively.Detailed in situ DRIFTS,quasi situ XPS,TPSR,and DFT calculations substantiated a new formate evolution mechanism via monodentate carbonate instead of traditional bidentate carbonate based on synergistic catalysis of Coδ-species and Ni0.The zonal activation of CO_(2)and H2by tuning electron behaviors of double-center catalysts can boost heterogeneous catalytic hydrogenation performance.

A novel small-signal equivalent circuit model for GaN HEMTs incorporating a dual-field-plate

An accurate and novel small-signal equivalent circuit model for GaN high-electron-mobility transistors(HEMTs)is proposed,which considers a dual-field-plate(FP)made up of a gate-FP and a source-FP.The equivalent circuit of the overall model is composed of parasitic elements,intrinsic transistors,gate-FP,and source-FP networks.The equivalent circuit of the gate-FP is identical to that of the intrinsic transistor.In order to simplify the complexity of the model,a series combination of a resistor and a capacitor is employed to represent the source-FP.The analytical extraction procedure of the model parameters is presented based on the proposed equivalent circuit.The verification is carried out on a 4×250μm GaN HEMT device with a gate-FP and a source-FP in a 0.45μm technology.Compared with the classic model,the proposed novel small-signal model shows closer agreement with measured S-parameters in the range of 1.0 to 18.0 GHz.

Current optimization-based control of dual three-phase PMSM for low-frequency temperature swing reduction

In this paper,a control scheme based on current optimization is proposed for dual three-phase permanent-magnet synchronous motor(DTP-PMSM)drive to reduce the low-frequency temperature swing.The reduction of temperature swing can be equivalent to reducing maximum instantaneous phase copper loss in this paper.First,a two-level optimization aiming at minimizing maximum instantaneous phase copper loss at each electrical angle is proposed.Then,the optimization is transformed to a singlelevel optimization by introducing the auxiliary variable for easy solving.Considering that singleobjective optimization trades a great total copper loss for a small reduction of maximum phase copper loss,the optimization considering both instantaneous total copper loss and maximum phase copper loss is proposed,which has the same performance of temperature swing reduction but with lower total loss.In this way,the proposed control scheme can reduce maximum junction temperature by 11%.Both simulation and experimental results are presented to prove the effectiveness and superiority of the proposed control scheme for low-frequency temperature swing reduction.

DCFNet:An Effective Dual-Branch Cross-Attention Fusion Network for Medical Image Segmentation

Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Transformers have made significant progress.However,there are some limitations in the current integration of CNN and Transformer technology in two key aspects.Firstly,most methods either overlook or fail to fully incorporate the complementary nature between local and global features.Secondly,the significance of integrating the multiscale encoder features from the dual-branch network to enhance the decoding features is often disregarded in methods that combine CNN and Transformer.To address this issue,we present a groundbreaking dual-branch cross-attention fusion network(DCFNet),which efficiently combines the power of Swin Transformer and CNN to generate complementary global and local features.We then designed the Feature Cross-Fusion(FCF)module to efficiently fuse local and global features.In the FCF,the utilization of the Channel-wise Cross-fusion Transformer(CCT)serves the purpose of aggregatingmulti-scale features,and the Feature FusionModule(FFM)is employed to effectively aggregate dual-branch prominent feature regions from the spatial perspective.Furthermore,within the decoding phase of the dual-branch network,our proposed Channel Attention Block(CAB)aims to emphasize the significance of the channel features between the up-sampled features and the features generated by the FCFmodule to enhance the details of the decoding.Experimental results demonstrate that DCFNet exhibits enhanced accuracy in segmentation performance.Compared to other state-of-the-art(SOTA)methods,our segmentation framework exhibits a superior level of competitiveness.DCFNet’s accurate segmentation of medical images can greatly assist medical professionals in making crucial diagnoses of lesion areas in advance.

Scattering of Water Waves by Dual Symmetric Inclined Floating Porous Barriers Using the DBEM

The scattering of normally incident water waves by two surface-piercing inclined perforated barriers in water with a uniform finite depth is investigated within the framework of linear water wave theory.Considering that thin barriers are zero-thickness,a novel numerical method involving the the coupling of the dual boundary element method(DBEM)with damping layers is applied.In order to effectively damp out the reflected waves,two damping layers,instead of pseudoboundaries are implemented near the two side boundaries of the computational domain.Thus,the modified linearized free surface boundary conditions are formulated and used for solving both the ordinary boundary integral equation as well as the hypersingular boundary integral equation for degenerate boundaries.The newly developed numerical method is validated against analytical methods using the matched eigenfunction expansion method for the special case of two vertical barriers or the inclined angle to the vertical being zero.The influence of the length of the two damping layers has been discussed.Moreover,these findings are also validated against previous results for several cases.After validation,the numerical results for the reflection coefficient,transmission coefficient and dissipation coefficient are obtained by varying the inclination angle and porosity-effect parameter.The effects of both the inclination angle and the porosity on the amplitudes of wave forces acting on both the front and rear barriers are also investigated.It is found that the effect of the inclination angle mainly shifts the location of the extremal values of the reflection and the transmission coefficients.Additionally,a moderate value of the porosity-parameter is quite effective at dissipating wave energy and mitigating the wave loads on dual barriers.

Dual mobility in primary total hip arthroplasty:A temptation from the devil or a blessing from above

Dual mobility(DM)bearings have gained significant attention in the field of total hip arthroplasty(THA)as a valid treatment option in cases of revision for instability after THA whereas its use in primary THA is still a matter of debate.This manuscript explores the pathology,incidence,diagnosis,treatment options,prognosis,ongoing studies in the literature,and future perspectives related to the use of DM bearings employed in primary THA.DM bearings are primarily designed to address one of the major concerns in THA:Instability of the prosthetic hip.Instability is both for the surgeon and the patient a devastating postoperative complication,leading to significant pain and subsequent apprehension by the patient and may require revision surgeries.The use of DM implants poses the worry of wear-related complications,such as accelerated polyethylene wear and osteolysis,which also pose challenges to long-term implant survival.This technique has seen a steady rise in recent years,with multiple studies reporting favorable outcomes.The incidence of their utilization varies among institutions and surgeons,reflecting differing preferences and patient populations.The diagnosis of instability and wear-related complications in THA often involves clinical assessment,imaging modalities such as X-rays,computed tomography scans,and sometimes advanced imaging techniques like magnetic resonance imaging.DM bearings can be considered as an option when patients present neurologic pathologies such as Parkinson's disease or recurrent dislocations after THA.DM bearings provide an additional articulation point within the implant,facilitating a greater range of motion and inherent stability.This design allows for reduced risk of dislocation and improved functional outcomes.Various implant manufacturers offer different designs and sizes of DM bearings to suit individual patient needs.Current literature suggests that the use of DM bearings in primary THA has demonstrated promising outcomes in terms of enhanced stability,reduced dislocation rates,and improved patient satisfaction.However,long-term studies with larger patient cohorts are necessary to establish the durability and longevity of these implants.Several ongoing studies are investigating the role of DM bearings in primary THA.These studies focus on evaluating longterm implant survivorship,assessing wear patterns,analyzing patient-reported outcomes,and comparing the effectiveness of DM bearings with traditional THA designs.The future of DM bearings in primary THA holds potential for further advancements.Research efforts are aimed at refining implant materials,optimizing designs,and studying the influence of surgical techniques on implant performance.Additionally,continued investigation into the long-term outcomes and cost-effectiveness of DM bearings will play a crucial role in shaping their future use.While further research is warranted,the current evidence supports their potential as a beneficial solution in improving surgical outcomes and patient satisfaction.

High-throughput computational screening and in vitro evaluation identifies 5-(4-oxo-4H-3,1-benzoxazin-2-yl)-2-[3-(4-oxo-4H-3,1-benzoxazin-2-yl)phenyl]-1H-isoindole-1,3(2H)-dione(C3),as a novel EGFR—HER2 dual inhibitor in gastric tumors

Gastric cancers are caused primarily due to the activation and amplification of the EGFR or HER2 kinases resulting in cell proliferation,adhesion,angiogenesis,and metastasis.Conventional therapies are ineffective due to the intra-tumoral heterogeneity and concomitant genetic mutations.Hence,dual inhibition strategies are recommended to increase potency and reduce cytotoxicity.In this study,we have conducted computational high-throughput screening of the ChemBridge library followed by in vitro assays and identified novel selective inhibitors that have a dual impediment of EGFR/HER2 kinase activities.Diversity-based High-throughput Virtual Screening(D-HTVS)was used to screen the whole ChemBridge small molecular library against EGFR and HER2.The atomistic molecular dynamic simulation was conducted to understand the dynamics and stability of the protein-ligand complexes.EGFR/HER2 kinase enzymes,KATOIII,and Snu-5 cells were used for in vitro validations.The atomistic Molecular Dynamics simulations followed by solvent-based Gibbs binding free energy calculation of top molecules,identified compound C3(5-(4-oxo-4H-3,1-benzoxazin-2-yl)-2-[3-(4-oxo-4H-3,1-benzoxazin-2-yl)phenyl]-1H-isoindole-1,3(2H)-dione)to have a good affinity for both EGFR and HER2.The predicted compound,C3,was promising with better binding energy,good binding pose,and optimum interactions with the EGFR and HER2 residues.C3 inhibited EGFR and HER2 kinases with IC50 values of 37.24 and 45.83 nM,respectively.The GI50 values of C3 to inhibit KATOIII and Snu-5 cells were 84.76 and 48.26 nM,respectively.Based on these findings,we conclude that the identified compound C3 showed a conceivable dual inhibitory activity on EGFR/HER2 kinase,and therefore can be considered as a plausible lead-like molecule for treating gastric cancers with minimal side effects,though testing in higher models with pharmacokinetic approach is required.

A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.

Preliminary Reflections on the Establishment of a New Energy System for the Achievement of Dual Carbon Goals

China has pledged to the world to achieve carbon peak in 10 years and carbon neutrality in 30 years.This is an extremely arduous task,as it faces numerous challenges,including high energy consumption,heavy reliance on coal within its energy mix,and a large base of carbon emissions that must be controlled.To this end,it is necessary to advance the new energy security strategy of“Four Revolutions,One Cooperation”to a deeper level.According to interpretations from various parties,the new energy system is preliminarily summarized to have six features:new energy structure,new system form,new industrial system,new governance system,new system and mechanism,and new regulatory method.Considering building a new energy system comprehensively,“Ten Commitments”have been proposed to help achieve the dual-carbon goals.The specific measures include:ensuring the security and stability of energy supply,accelerating the transformation to green and low-carbon energy,giving priority to energy conservation and efficiency improvement,promoting multi-energy complementation and synergistic and integrated development,enhancing the digital intelligence level in the energy industry,developing centralized and distributed energy,advancing the rural energy revolution,developing critical and core technological equipment and the comprehensive energy service industry,and promoting high-quality development of the Belt and Road Initiative.

Discussion on the application prospect of the transient electromagnetic method based on the dual launcher and mine advanced detection

The dual transmitter implements the equivalent anti-magnetic flux transient electromagnetic method, which can effectively reduce the scope of the transient electromagnetic detection blind area. However, this method is rarely reported in the detection of pipelines in urban geophysical exploration and the application of coal mines. Based on this, this paper realizes the equivalent anti-magnetic flux transient electromagnetic method based on the dual launcher. The suppression effect of this method on the blind area is analyzed by physical simulation. And the detection experiment of underground pipelines is carried out outdoors. The results show that the dual launcher can significantly reduce the turn-off time, thereby effectively reducing the impact of the blind area on the detection results, and the pipeline detection results verify the device’s effectiveness. Finally, based on the ground experimental results, the application prospect of mine advanced detection is discussed. Compared with other detection fields, the formation of blind areas is mainly caused by the equipment. If the dual launcher can be used to reduce the blind area, the accuracy of advanced detection can be improved more effectively. The above research results are of great significance for improving the detection accuracy of the underground transient electromagnetic method.

Energy-Saving Distributed Flexible Job Shop Scheduling Optimization with Dual Resource Constraints Based on Integrated Q-Learning Multi-Objective Grey Wolf Optimizer

The distributed flexible job shop scheduling problem(DFJSP)has attracted great attention with the growth of the global manufacturing industry.General DFJSP research only considers machine constraints and ignores worker constraints.As one critical factor of production,effective utilization of worker resources can increase productivity.Meanwhile,energy consumption is a growing concern due to the increasingly serious environmental issues.Therefore,the distributed flexible job shop scheduling problem with dual resource constraints(DFJSP-DRC)for minimizing makespan and total energy consumption is studied in this paper.To solve the problem,we present a multi-objective mathematical model for DFJSP-DRC and propose a Q-learning-based multi-objective grey wolf optimizer(Q-MOGWO).In Q-MOGWO,high-quality initial solutions are generated by a hybrid initialization strategy,and an improved active decoding strategy is designed to obtain the scheduling schemes.To further enhance the local search capability and expand the solution space,two wolf predation strategies and three critical factory neighborhood structures based on Q-learning are proposed.These strategies and structures enable Q-MOGWO to explore the solution space more efficiently and thus find better Pareto solutions.The effectiveness of Q-MOGWO in addressing DFJSP-DRC is verified through comparison with four algorithms using 45 instances.The results reveal that Q-MOGWO outperforms comparison algorithms in terms of solution quality.

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.