Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribut...Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribute management methods based on manual extraction face several issues,such as high costs for attribute extraction,long processing times,unstable accuracy,and poor scalability.To address these problems,this paper proposes an attribute mining technology for access control institutions based on hybrid capsule networks.This technology leverages transfer learning ideas,utilizing Bidirectional Encoder Representations from Transformers(BERT)pre-trained language models to achieve vectorization of unstructured text data resources.Furthermore,we have designed a novel end-to-end parallel hybrid network structure,where the parallel networks handle global and local information features of the text that they excel at,respectively.By employing techniques such as attention mechanisms,capsule networks,and dynamic routing,effective mining of security attributes for access control resources has been achieved.Finally,we evaluated the performance level of the proposed attribute mining method for access control institutions through experiments on the medical referral text resource dataset.The experimental results show that,compared with baseline algorithms,our method adopts a parallel network structure that can better balance global and local feature information,resulting in improved overall performance.Specifically,it achieves a comprehensive performance enhancement of 2.06%to 8.18%in the F1 score metric.Therefore,this technology can effectively provide attribute support for access control of unstructured text big data resources.展开更多
Different dosage forms can significantly impact pharmacokinetics in vivo,leading to varied effects and potential adverse reactions.This study aimed to evaluate the efficacy,safety,and cost-effectiveness of isosorbide ...Different dosage forms can significantly impact pharmacokinetics in vivo,leading to varied effects and potential adverse reactions.This study aimed to evaluate the efficacy,safety,and cost-effectiveness of isosorbide mononitrate sustained-release capsules(IMSRC)combined with conventional treatments,compared to isosorbide mononitrate tablets(IMT)combined with conventional treatments,for managing angina pectoris in patients with coronary heart diseases.A network meta-analysis(NMA)was conducted to assess the efficacy and safety of IMSRC and IMT.Relevant literature was sourced from databases,including PubMed,Embase,Cochrane Library,ScienceDirect,Web of Science,CNKI,Wanfang,and VIP,covering publications up to July 2023.The cost-effectiveness analysis(CEA)was performed from the perspective of China’s healthcare system,utilizing inputs derived from the NMA.The analysis included 15 studies.The NMA results revealed no significant difference in efficacy and safety between IMSRC plus conventional treatments and IMT plus conventional treatments.However,both combinations were more effective than conventional treatments without isosorbide mononitrate.No differences in safety were observed among the three groups.The surface under the cumulative ranking(SUCRA)of the NMA indicated that IMT had a slight edge over IMSRC in the total effective rate of angina pectoris,whereas IMSRC showed higher probabilities for markedly effective rate and ECG effective rate compared to IMT.The incidence of adverse events was ranked as IMT>conventional preparation>IMSRC.The CEA results highlighted that the incremental cost-effectiveness ratios(ICERs)for the markedly effective and total effective rates of angina pectoris were-133.41 and-260.20,respectively.The ICERs for ECG effective rates were-83.34 and-234.24,respectively.In conclusion,while IMSRC combined with conventional treatments and IMT combined with conventional treatments were similar in efficacy and safety,IMSRC proved to be more economical.展开更多
In order to solve the problem that the star point positioning accuracy of the star sensor in near space is decreased due to atmospheric background stray light and rapid maneuvering of platform, this paper proposes a s...In order to solve the problem that the star point positioning accuracy of the star sensor in near space is decreased due to atmospheric background stray light and rapid maneuvering of platform, this paper proposes a star point positioning algorithm based on the capsule network whose input and output are both vectors. First, a PCTL (Probability-Coordinate Transformation Layer) is designed to represent the mapping relationship between the probability output of the capsule network and the star point sub-pixel coordinates. Then, Coordconv Layer is introduced to implement explicit encoding of space information and the probability is used as the centroid weight to achieve the conversion between probability and star point sub-pixel coordinates, which improves the network’s ability to perceive star point positions. Finally, based on the dynamic imaging principle of star sensors and the characteristics of near-space environment, a star map dataset for algorithm training and testing is constructed. The simulation results show that the proposed algorithm reduces the MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) of the star point positioning by 36.1% and 41.7% respectively compared with the traditional algorithm. The research results can provide important theory and technical support for the scheme design, index demonstration, test and evaluation of large dynamic star sensors in near space.展开更多
OBJECTIVE:To explore the potential molecular mechanism of Qigu capsule(芪骨胶囊,QGC) in the treatment of sarcopenia through network pharmacology and to verify it experimentally.METHODS:The active compounds of QGC and ...OBJECTIVE:To explore the potential molecular mechanism of Qigu capsule(芪骨胶囊,QGC) in the treatment of sarcopenia through network pharmacology and to verify it experimentally.METHODS:The active compounds of QGC and common targets between QGC and sarcopenia were screened from databases.Then the herbs-compounds-targets network,and protein-protein interaction(PPI) network was constructed.Gene ontology(GO) and Kyoto Encyclopedia of Genes and Genomes(KEGG) pathway enrichment analysis were performed by R software.Next,we used a dexamethasone-induced sarcopenia mouse model to evaluate the anti-sarcopenic mechanism of QGC.RESULTS:A total of 57 common targets of QGC and sarcopenia were obtained.Based on the enrichment analysis of GO and KEGG,we took the phosphatidylinositol 3-kinase(PI3K)/protein kinase B(Akt) signaling pathway as a key target to explore the mechanism of QGC on sarcopenia.Animal experiments showed that QGC could increase muscle strength and inhibit muscle fiber atrophy.In the model group,the expression of muscle ring finger-1 and Atrogin-1 were increased,while myosin heavy chain was decreased,QGC treatment reversed these changes.Moreover,compared with the model group,the expressions of pPI3K,p-Akt,p-mammalian target of rapamycin and pForkhead box O3 in the QGC group were all upregulated.CONCLUSION:QGC exerts an anti-sarcopenic effect by activating PI3K/Akt signaling pathway to regulate skeletal muscle protein metabolism.展开更多
Convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, Caps...Convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, CapsNet overcomesthese limitations by vectorizing information through increased directionality and magnitude, ensuring that spatialinformation is not overlooked. Therefore, this study proposes a novel expression recognition technique calledCAPSULE-VGG, which combines the strengths of CapsNet and convolutional neural networks. By refining andintegrating features extracted by a convolutional neural network before introducing theminto CapsNet, ourmodelenhances facial recognition capabilities. Compared to traditional neural network models, our approach offersfaster training pace, improved convergence speed, and higher accuracy rates approaching stability. Experimentalresults demonstrate that our method achieves recognition rates of 74.14% for the FER2013 expression dataset and99.85% for the CK+ expression dataset. By contrasting these findings with those obtained using conventionalexpression recognition techniques and incorporating CapsNet’s advantages, we effectively address issues associatedwith convolutional neural networks while increasing expression identification accuracy.展开更多
Background:The purpose of the study was to investigate the active ingredients and potential biochemical mechanisms of Juanbi capsule in knee osteoarthritis based on network pharmacology,molecular docking and animal ex...Background:The purpose of the study was to investigate the active ingredients and potential biochemical mechanisms of Juanbi capsule in knee osteoarthritis based on network pharmacology,molecular docking and animal experiments.Methods:Chemical components for each drug in the Juanbi capsule were obtained from Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform,while the target proteins for knee osteoarthritis were retrieved from the Drugbank,GeneCards,and OMIM databases.The study compared information on knee osteoarthritis and the targets of drugs to identify common elements.The data was imported into the STRING platform to generate a protein-protein interaction network diagram.Subsequently,a“component-target”network diagram was created using the screened drug components and target information with Cytoscape software.Common targets were imported into Metascape for GO function and KEGG pathway enrichment analysis.AutoDockTools was utilized to predict the molecular docking of the primary chemical components and core targets.Ultimately,the key targets were validated through animal experiments.Results:Juanbi capsule ameliorated Knee osteoarthritis mainly by affecting tumor necrosis factor,interleukin1β,MMP9,PTGS2,VEGFA,TP53,and other cytokines through quercetin,kaempferol,andβ-sitosterol.The drug also influenced the AGE-RAGE,interleukin-17,tumor necrosis factor,Relaxin,and NF-κB signaling pathways.The network pharmacology analysis results were further validated in animal experiments.The results indicated that Juanbi capsule could decrease the levels of tumor necrosis factor-αand interleukin-1βin the serum and synovial fluid of knee osteoarthritis rats and also down-regulate the expression levels of MMP9 and PTGS2 proteins in the articular cartilage.Conclusion:Juanbi capsule may improve the knee bone microstructure and reduce the expression of inflammatory factors of knee osteoarthritis via multiple targets and multiple signaling pathways.展开更多
There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan...There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan and forecasting the reaction of the patient to the adopted treatment.For this reason,the development of convolutional neural networks(CNNs)for the task of lung cancer classification has recently seen a trend in attention.CNNs have great potential,but they need a lot of training data and struggle with input alterations.To address these limitations of CNNs,a novel machine-learning architecture of capsule networks has been presented,and it has the potential to completely transform the areas of deep learning.Capsule networks,which are the focus of this work,are interesting because they can withstand rotation and affine translation with relatively little training data.This research optimizes the performance of CapsNets by designing a new architecture that allows them to perform better on the challenge of lung cancer classification.The findings demonstrate that the proposed capsule network method outperforms CNNs on the lung cancer classification challenge.CapsNet with a single convolution layer and 32 features(CN-1-32),CapsNet with a single convolution layer and 64 features(CN-1-64),and CapsNet with a double convolution layer and 64 features(CN-2-64)are the three capsulel networks developed in this research for lung cancer classification.Lung nodules,both benign and malignant,are classified using these networks using CT images.The LIDC-IDRI database was utilized to assess the performance of those networks.Based on the testing results,CN-2-64 network performed better out of the three networks tested,with a specificity of 98.37%,sensitivity of 97.47%and an accuracy of 97.92%.展开更多
Objective:To explore the mechanism of action of Zangjiangzhi capsule(ZJZC)in treating hyperlipidemia(HLP).Methods:The components of ZJZC were analyzed and identified using ultra-high performance liquid chromatography ...Objective:To explore the mechanism of action of Zangjiangzhi capsule(ZJZC)in treating hyperlipidemia(HLP).Methods:The components of ZJZC were analyzed and identified using ultra-high performance liquid chromatography with Q-Exactive Orbitrap tandem mass spectrometry(UHPLC-Q-Exactive-Orbitrap-MS/MS).Network pharmacology analysis was used to explore the mechanism of action of ZJZC in HLP treatment.The SwissTargetPrediction database was used to predict compound targets,and GeneCards,DisGeNet,OMIM,and DRUGBANK databases were used to identify HLP-related targets.Proteineprotein interaction diagrams were constructed using the STRING database.The targets were subjected to gene ontology and Kyoto Encyclopedia of Genes and Genomes(KEGG)enrichment analysis.The“herbingredient-target”network was visualized using Cytoscape.Preliminary validation was performed using molecular docking and enzyme-linked immunosorbent assay.Results:Ninety compounds were identified in ZJZC,including 34 flavonoids,12 phenols,10 terpenoids,10 alkaloids,8 organic acids,8 anthraquinones,and 9 other compounds.In total,904 targets were identified for these compounds.Among them,158 targets intersected with the HLP target network.Network pharmacology analysis showed that MAPK1,PPAR-a,RXRA,HSP90AA1,PIK3R1,AKT1,PIK3CA,IL6,TNF,and ESR1 are the key targets of action.KEGG enrichment analysis identified 164 pathways.Among these,the AGE-RAGE signaling pathway in diabetic complications,lipid and atherosclerosis pathways,regulation of lipids in adipocytes,and insulin resistance are related to HLP.Molecular docking showed good affinity between the key targets and ingredients.Further,ZJZC treatment in mice resulted in lower expression of MAPK1 protein and increased expression of PPAR-a protein,which have been shown to be strongly associated with HLP.Conclusions:This study showed that ZJZC contains various active ingredients and can modulate multiple targets and pathways associated with HLP,providing evidence at the molecular level for its clinical application in the treatment of HLP.展开更多
BACKGROUND Video capsule endoscopy(VCE)is a noninvasive technique used to examine small bowel abnormalities in both adults and children.However,manual review of VCE images is time-consuming and labor-intensive,making ...BACKGROUND Video capsule endoscopy(VCE)is a noninvasive technique used to examine small bowel abnormalities in both adults and children.However,manual review of VCE images is time-consuming and labor-intensive,making it crucial to develop deep learning methods to assist in image analysis.AIM To employ deep learning models for the automatic classification of small bowel lesions using pediatric VCE images.METHODS We retrospectively analyzed VCE images from 162 pediatric patients who underwent VCE between January 2021 and December 2023 at the Children's Hospital of Nanjing Medical University.A total of 2298 high-resolution images were extracted,including normal mucosa and lesions(erosions/erythema,ulcers,and polyps).The images were split into training and test datasets in a 4:1 ratio.Four deep learning models:DenseNet121,Visual geometry group-16,ResNet50,and vision transformer were trained using 5-fold cross-validation,with hyperparameters adjusted for optimal classification performance.The models were evaluated based on accuracy,precision,recall,F1-score,and area under the receiver operating curve(AU-ROC).Lesion visualization was performed using gradient-weighted class activation mapping.RESULTS Abdominal pain was the most common indication for VCE,accounting for 62%of cases,followed by diarrhea,vomiting,and gastrointestinal bleeding.Abnormal lesions were detected in 93 children,with 38 diagnosed with inflammatory bowel disease.Among the deep learning models,DenseNet121 and ResNet50 demonstrated excellent classification performance,achieving accuracies of 90.6%[95%confidence interval(CI):89.2-92.0]and 90.5%(95%CI:89.9-91.2),respectively.The AU-ROC values for these models were 93.7%(95%CI:92.9-94.5)for DenseNet121 and 93.4%(95%CI:93.1-93.8)for ResNet50.CONCLUSION Our deep learning-based diagnostic tool developed in this study effectively classified lesions in pediatric VCE images,contributing to more accurate diagnoses and increased diagnostic efficiency.展开更多
The conventional troubleshooting methods for high-speed railway on-board equipment, with over-reliance on personnel experience, is characterized by one-sidedness and low efficiency. In the process of high-speed train ...The conventional troubleshooting methods for high-speed railway on-board equipment, with over-reliance on personnel experience, is characterized by one-sidedness and low efficiency. In the process of high-speed train operation, numerous text-based onboard logs are recorded by on-board computers. Machine learning methods can help technicians make a correct judgment of fault types using the on-board log reasonably. Therefore, a fault classification model of on-board equipment based on attention capsule networks is proposed. This paper presents an empirical exploration of the application of a capsule network with dynamic routing in fault classification. A capsule network can encode the internal spatial part-whole relationship between various entities to identify the fault types. As the importance of each word in the on-board log and the dependencies between them have a significant impact on fault classification, an attention mechanism is incorporated into the capsule network to distill important information. Considering the imbalanced distribution of normal data and fault data in the on-board log, the focal loss function is introduced into the model to adjust the imbalanced data. The experiments are conducted on the on-board log of a railway bureau and compared with other baseline models. The experimental results demonstrate that our model outperforms the compared baseline methods, proving the superiority and competitiveness of our model.展开更多
OBJECTIVE To explore the new indications and key mechanism of Bazi Bushen capsule(BZBS)by network pharmacology and in vitro experiment.METHODS The potential tar⁃get profiles of the components of BZBS were pre⁃dicted.S...OBJECTIVE To explore the new indications and key mechanism of Bazi Bushen capsule(BZBS)by network pharmacology and in vitro experiment.METHODS The potential tar⁃get profiles of the components of BZBS were pre⁃dicted.Subsequently,new indications for BZBS were predicted by disease ontology(DO)enrich⁃ment analysis and initially validated by GO and KEGG pathway enrichment analysis.Further⁃more,the therapeutic target of BZBS acting on AD signaling pathway were identified by intersec⁃tion analysis.Two Alzheimer′s disease(AD)cell models,BV-2 and SH-SY5Y,were used to pre⁃liminarily verify the anti-AD efficacy and mecha⁃nism of BZBS in vitro.RESULTS In total,1499 non-repeated ingredients were obtained from 16 herbs in BZBS formula,and 1320 BZBS targets with high confidence were predicted.Disease enrichment results strongly suggested that BZBS formula has the potential to be used in the treat⁃ment of AD.In vitro experiments showed that BZ⁃BS could significantly reduce the release of TNF-αand IL-6 and the expression of COX-2 and PSEN1 in Aβ25-35-induced BV-2 cells.BZBS reduced the apoptosis rate of Aβ25-35 induced SH-SY5Y cells,significantly increased mitochon⁃drial membrane potential,reduced the expres⁃sion of Caspase3 active fragment and PSEN1,and increased the expression of IDE.CONCLU⁃SIONS BZBS formula has a potential use in the treatment of AD,which is achieved through regu⁃lation of ERK1/2,NF-κB signaling pathways,and GSK-3β/β-catenin signaling pathway.Further⁃more,the network pharmacology technology is a feasible drug repurposing strategy to reposition new clinical use of approved TCM and explore the mechanism of action.The study lays a foun⁃dation for the subsequent in-depth study of BZBS in the treatment of AD and provides a basis for its application in the clinical treatment of AD.展开更多
Mobile phones are an essential part of modern life.The two popular mobile phone platforms,Android and iPhone Operating System(iOS),have an immense impact on the lives of millions of people.Among these two,Android curr...Mobile phones are an essential part of modern life.The two popular mobile phone platforms,Android and iPhone Operating System(iOS),have an immense impact on the lives of millions of people.Among these two,Android currently boasts more than 84%market share.Thus,any personal data put on it are at great risk if not properly protected.On the other hand,more than a million pieces of malware have been reported on Android in just 2021 till date.Detecting and mitigating all this malware is extremely difficult for any set of human experts.Due to this reason,machine learning-and specifically deep learning-has been utilized in the recent past to resolve this issue.However,deep learning models have primarily been designed for image analysis.While this line of research has shown promising results,it has been difficult to really understand what the features extracted by deep learning models are in the domain of malware.Moreover,due to the translation invariance property of popular models based on ConvolutionalNeural Network(CNN),the true potential of deep learning for malware analysis is yet to be realized.To resolve this issue,we envision the use of Capsule Networks(CapsNets),a state-of-the-art model in deep learning.We argue that since CapsNets are orientation-based in terms of images,they can potentially be used to capture spatial relationships between different features at different locations within a sequence of opcodes.We design a deep learning-based architecture that efficiently and effectively handles very large scale malware datasets to detect Androidmalware without resorting to very deep networks.This leads tomuch faster detection as well as increased accuracy.We achieve state-of-the-art F1 score of 0.987 with an FPR of just 0.002 for three very large,real-world malware datasets.Our code is made available as open source and can be used to further enhance our work with minimal effort.展开更多
Objective: To investigate the possible mechanism of Yiqing Capsules in the treatment of upper respiratory tract infection based on network pharmacology. Methods: The main active components of Yiqing Capsules were sele...Objective: To investigate the possible mechanism of Yiqing Capsules in the treatment of upper respiratory tract infection based on network pharmacology. Methods: The main active components of Yiqing Capsules were selected on TCMSP database;the targets of upper respiratory tract infection were selected on GeneCards database. The drug-compound-target network and PPi network were constructed through STRING database and soft Cytoscape 3.7.2. Soft R was used to perform GO enrichment analysis and KEGG pathway enrichment analysis of main targets. Results: According to the screening conditions, 48 active compounds and 171 related targets were obtained. GO enrichment analysis obtained 2333 items, KEGG pathway enrichment analysis obtained 2248 items, including Kaposi sarcoma-associated herpesvirus infection, Human cytomegalovirus infection, Epstein-Barr virus infection, PI3K-Akt signaling pathway, etc. Conclusion: Yiqing capsules play a therapeutic role in upper respiratory tract infection through multi-target and multi-pathway.展开更多
Objective:Lingzhihuang capsule(LZHC)is a natural product that consists of 10 commonly used medicinal plants,and it is used in traditional Chinese medicine to promote people’s overall health.Previously,LZHC was succes...Objective:Lingzhihuang capsule(LZHC)is a natural product that consists of 10 commonly used medicinal plants,and it is used in traditional Chinese medicine to promote people’s overall health.Previously,LZHC was successfully used as adjuvant therapy for treating patients with cancer.However,the chemical constituents of LZHC and their potential biological functions remain unclear.The aim of this study is to investigate the major bioactive compounds in LZHC and predict their pharmacological targets.Methods:The LZHC constituents were putatively identified by ultra-high performance liquid chromatography coupled with timeof-flight mass spectrometry combined with mass spectrometry-based molecular networking.The targets were predicted using SwissTargetPrediction software,and the associated gene ontology and Kyoto encyclopedia of genes and genomes pathways were analyzed using the Database for Annotation,Visualization,and Integrated Discovery.The mass spectrometry-based molecular network and compound-target-pathway network were constructed using Cytoscape 3.8.0 software.Results:We putatively identified 94 compounds of LZHC by mass spectrometry-based molecular networking,including triterpene(the main structural type)and other clusters(ie,flavonoids and organic acids).Our results suggested that multiple pivotal targets were regulated by LZHC,including tumor necrosis factor,nitric oxide synthase 2,glucocorticoid receptor,estrogen receptor,3-oxo-5-alpha-steroid 4-dehydrogenase 2,prostaglandin e2 receptor ep4 subtype,estrogen receptor beta,phosphatidylinositol 4,5-bisphosphate 3-kinase catalytic subunit alpha isoform,mitogen-activated protein kinase 3,and racalpha serine,which are related to signal transduction,positive regulation of transcription from RNA polymerase II promoters,oxidation-reduction processes,inflammatory responses,and other biological processes.Functional annotation of those targets suggested that several signaling pathways may be regulated by LZHC,such as cancer-related proteoglycans,the PI3K-Aktsignaling pathway,and the cAMP-signaling pathway.Conclusions:Our findings reveal the chemical constituents of LZHC and provided scientific support for the efficacy of LZHC in terms of immune regulation,anti-aging,and tumor suppression.展开更多
The intrinsic hypoxic tumor microenvironment and limited accumulation of photosensitizers(PSs) result in unsatisfied efficiency of photodynamic therapy(PDT).To enhance the PDT efficiency against solid tumors,a functio...The intrinsic hypoxic tumor microenvironment and limited accumulation of photosensitizers(PSs) result in unsatisfied efficiency of photodynamic therapy(PDT).To enhance the PDT efficiency against solid tumors,a functional oxygen self-supplying and PS-delivering nanosystem is fabricated via the combination of catalase(CAT),chlorin e6(Ce6) and metal-phenolic network(MPN) capsule.It is demonstrated that the CAT encapsulated in the capsules(named CCM capsules) could catalyze the degradation of hydrogen peroxide(H;O;) to produce molecular oxygen(O;),which could be converted into cytotoxicity reactive oxygen species(ROS) by surface-loaded Ce6 under 660 nm laser irradiation,leading to synergistic anticancer effects in vitro and in vivo.Therefore,the application of CCM capsule could be a promising strategy to improve PDT effectiveness.展开更多
State-of-the-art model-driven Direction-Of-Arrival(DOA)estimation methods for multipath signals face great challenges in practical application because of the dependence on the precise multipath model.In this paper,we ...State-of-the-art model-driven Direction-Of-Arrival(DOA)estimation methods for multipath signals face great challenges in practical application because of the dependence on the precise multipath model.In this paper,we introduce a framework,based on deep learning,for synchronizing perturbation auto-elimination with effective DOA estimation in multipath environment.Firstly,a signal selection mechanism is introduced to roughly locate specific signals to spatial subregion via frequency domain filters and compressive sensing-based method.Then,we set the mean of the correlation matrix’s row vectors as the input feature to construct the spatial spectrum by the corresponding single network within the parallel deep capsule networks.The proposed method enhances the generalization capability to untrained scenarios and the adaptability to non-ideal conditions,e.g.,lower SNRs,smaller snapshots,unknown reflection coefficients and perturbational steering vectors,which make up for the defects of the previous model-driven methods.Simulations are carried out to demonstrate the superiority of the proposed method.展开更多
基金supported by National Natural Science Foundation of China(No.62102449).
文摘Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribute management methods based on manual extraction face several issues,such as high costs for attribute extraction,long processing times,unstable accuracy,and poor scalability.To address these problems,this paper proposes an attribute mining technology for access control institutions based on hybrid capsule networks.This technology leverages transfer learning ideas,utilizing Bidirectional Encoder Representations from Transformers(BERT)pre-trained language models to achieve vectorization of unstructured text data resources.Furthermore,we have designed a novel end-to-end parallel hybrid network structure,where the parallel networks handle global and local information features of the text that they excel at,respectively.By employing techniques such as attention mechanisms,capsule networks,and dynamic routing,effective mining of security attributes for access control resources has been achieved.Finally,we evaluated the performance level of the proposed attribute mining method for access control institutions through experiments on the medical referral text resource dataset.The experimental results show that,compared with baseline algorithms,our method adopts a parallel network structure that can better balance global and local feature information,resulting in improved overall performance.Specifically,it achieves a comprehensive performance enhancement of 2.06%to 8.18%in the F1 score metric.Therefore,this technology can effectively provide attribute support for access control of unstructured text big data resources.
基金The 2022 Ministry of Education General Project for Humanities and Social Sciences Research(Grant No.22YJAZH147)the General Subject of Guangzhou Philosophy and Social Science Development“14th Five-Year Plan”in 2023(Grant No.2023GZYB68)+2 种基金China University Industry-Academia-Research Innovation Fund-Huatong Guokang Medical Research Special Project(Grant No.2023HT017)2024 Guangdong Province General Project for the Planning of Philosophy and Social Sciences(Grant No.GD24CGL29)the Innovation Team Project of Colleges and Universities in Guangdong Province(Grant No.2022WCXTD011).
文摘Different dosage forms can significantly impact pharmacokinetics in vivo,leading to varied effects and potential adverse reactions.This study aimed to evaluate the efficacy,safety,and cost-effectiveness of isosorbide mononitrate sustained-release capsules(IMSRC)combined with conventional treatments,compared to isosorbide mononitrate tablets(IMT)combined with conventional treatments,for managing angina pectoris in patients with coronary heart diseases.A network meta-analysis(NMA)was conducted to assess the efficacy and safety of IMSRC and IMT.Relevant literature was sourced from databases,including PubMed,Embase,Cochrane Library,ScienceDirect,Web of Science,CNKI,Wanfang,and VIP,covering publications up to July 2023.The cost-effectiveness analysis(CEA)was performed from the perspective of China’s healthcare system,utilizing inputs derived from the NMA.The analysis included 15 studies.The NMA results revealed no significant difference in efficacy and safety between IMSRC plus conventional treatments and IMT plus conventional treatments.However,both combinations were more effective than conventional treatments without isosorbide mononitrate.No differences in safety were observed among the three groups.The surface under the cumulative ranking(SUCRA)of the NMA indicated that IMT had a slight edge over IMSRC in the total effective rate of angina pectoris,whereas IMSRC showed higher probabilities for markedly effective rate and ECG effective rate compared to IMT.The incidence of adverse events was ranked as IMT>conventional preparation>IMSRC.The CEA results highlighted that the incremental cost-effectiveness ratios(ICERs)for the markedly effective and total effective rates of angina pectoris were-133.41 and-260.20,respectively.The ICERs for ECG effective rates were-83.34 and-234.24,respectively.In conclusion,while IMSRC combined with conventional treatments and IMT combined with conventional treatments were similar in efficacy and safety,IMSRC proved to be more economical.
文摘In order to solve the problem that the star point positioning accuracy of the star sensor in near space is decreased due to atmospheric background stray light and rapid maneuvering of platform, this paper proposes a star point positioning algorithm based on the capsule network whose input and output are both vectors. First, a PCTL (Probability-Coordinate Transformation Layer) is designed to represent the mapping relationship between the probability output of the capsule network and the star point sub-pixel coordinates. Then, Coordconv Layer is introduced to implement explicit encoding of space information and the probability is used as the centroid weight to achieve the conversion between probability and star point sub-pixel coordinates, which improves the network’s ability to perceive star point positions. Finally, based on the dynamic imaging principle of star sensors and the characteristics of near-space environment, a star map dataset for algorithm training and testing is constructed. The simulation results show that the proposed algorithm reduces the MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) of the star point positioning by 36.1% and 41.7% respectively compared with the traditional algorithm. The research results can provide important theory and technical support for the scheme design, index demonstration, test and evaluation of large dynamic star sensors in near space.
基金Shanghai Clinical Research Center for Chronic Musculoskeletal Diseases (20MC1920600)Shanghai Key Clinical Specialty "Traditional Chinese Medicine Orthopaedic Traumatology"(shslczdzk03901)+3 种基金The Second Round of Construction Project of National TCM Academic School Inheritance Studio "Shi's Trauma Department"[Letter of the People's Education of Traditional Chinese Medicine (2019) No.62]Shanghai High-level Local Universities "Chronic Muscle and Bone Damage Research and Transformation" Innovation Team [No.3 of Shanghai Education Commission (2022)]Program for Shanghai High-Level Local University Innovation Team (SZY20220315)Shanghai Shenkang Hospital Development Center Clinical Three-year Action Plan (SHDC2020CR3090B)。
文摘OBJECTIVE:To explore the potential molecular mechanism of Qigu capsule(芪骨胶囊,QGC) in the treatment of sarcopenia through network pharmacology and to verify it experimentally.METHODS:The active compounds of QGC and common targets between QGC and sarcopenia were screened from databases.Then the herbs-compounds-targets network,and protein-protein interaction(PPI) network was constructed.Gene ontology(GO) and Kyoto Encyclopedia of Genes and Genomes(KEGG) pathway enrichment analysis were performed by R software.Next,we used a dexamethasone-induced sarcopenia mouse model to evaluate the anti-sarcopenic mechanism of QGC.RESULTS:A total of 57 common targets of QGC and sarcopenia were obtained.Based on the enrichment analysis of GO and KEGG,we took the phosphatidylinositol 3-kinase(PI3K)/protein kinase B(Akt) signaling pathway as a key target to explore the mechanism of QGC on sarcopenia.Animal experiments showed that QGC could increase muscle strength and inhibit muscle fiber atrophy.In the model group,the expression of muscle ring finger-1 and Atrogin-1 were increased,while myosin heavy chain was decreased,QGC treatment reversed these changes.Moreover,compared with the model group,the expressions of pPI3K,p-Akt,p-mammalian target of rapamycin and pForkhead box O3 in the QGC group were all upregulated.CONCLUSION:QGC exerts an anti-sarcopenic effect by activating PI3K/Akt signaling pathway to regulate skeletal muscle protein metabolism.
基金the following funds:The Key Scientific Research Project of Anhui Provincial Research Preparation Plan in 2023(Nos.2023AH051806,2023AH052097,2023AH052103)Anhui Province Quality Engineering Project(Nos.2022sx099,2022cxtd097)+1 种基金University-Level Teaching and Research Key Projects(Nos.ch21jxyj01,XLZ-202208,XLZ-202106)Special Support Plan for Innovation and Entrepreneurship Leaders in Anhui Province。
文摘Convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, CapsNet overcomesthese limitations by vectorizing information through increased directionality and magnitude, ensuring that spatialinformation is not overlooked. Therefore, this study proposes a novel expression recognition technique calledCAPSULE-VGG, which combines the strengths of CapsNet and convolutional neural networks. By refining andintegrating features extracted by a convolutional neural network before introducing theminto CapsNet, ourmodelenhances facial recognition capabilities. Compared to traditional neural network models, our approach offersfaster training pace, improved convergence speed, and higher accuracy rates approaching stability. Experimentalresults demonstrate that our method achieves recognition rates of 74.14% for the FER2013 expression dataset and99.85% for the CK+ expression dataset. By contrasting these findings with those obtained using conventionalexpression recognition techniques and incorporating CapsNet’s advantages, we effectively address issues associatedwith convolutional neural networks while increasing expression identification accuracy.
基金funding from the Basic Research Project of the Education Department of Shaanxi Province(21JC010,21JP035)the Young and Middle-Aged Scientific Research and Innovation Team of the Shaanxi Provincial Administration of Traditional Chinese Medicine(2022SLRHLJ001)the 2023 Central Financial Transfer Payment Local Project“Innovation and Improvement of Five Types of Hospital Preparations,Such as Roumudan Granules”.
文摘Background:The purpose of the study was to investigate the active ingredients and potential biochemical mechanisms of Juanbi capsule in knee osteoarthritis based on network pharmacology,molecular docking and animal experiments.Methods:Chemical components for each drug in the Juanbi capsule were obtained from Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform,while the target proteins for knee osteoarthritis were retrieved from the Drugbank,GeneCards,and OMIM databases.The study compared information on knee osteoarthritis and the targets of drugs to identify common elements.The data was imported into the STRING platform to generate a protein-protein interaction network diagram.Subsequently,a“component-target”network diagram was created using the screened drug components and target information with Cytoscape software.Common targets were imported into Metascape for GO function and KEGG pathway enrichment analysis.AutoDockTools was utilized to predict the molecular docking of the primary chemical components and core targets.Ultimately,the key targets were validated through animal experiments.Results:Juanbi capsule ameliorated Knee osteoarthritis mainly by affecting tumor necrosis factor,interleukin1β,MMP9,PTGS2,VEGFA,TP53,and other cytokines through quercetin,kaempferol,andβ-sitosterol.The drug also influenced the AGE-RAGE,interleukin-17,tumor necrosis factor,Relaxin,and NF-κB signaling pathways.The network pharmacology analysis results were further validated in animal experiments.The results indicated that Juanbi capsule could decrease the levels of tumor necrosis factor-αand interleukin-1βin the serum and synovial fluid of knee osteoarthritis rats and also down-regulate the expression levels of MMP9 and PTGS2 proteins in the articular cartilage.Conclusion:Juanbi capsule may improve the knee bone microstructure and reduce the expression of inflammatory factors of knee osteoarthritis via multiple targets and multiple signaling pathways.
文摘There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan and forecasting the reaction of the patient to the adopted treatment.For this reason,the development of convolutional neural networks(CNNs)for the task of lung cancer classification has recently seen a trend in attention.CNNs have great potential,but they need a lot of training data and struggle with input alterations.To address these limitations of CNNs,a novel machine-learning architecture of capsule networks has been presented,and it has the potential to completely transform the areas of deep learning.Capsule networks,which are the focus of this work,are interesting because they can withstand rotation and affine translation with relatively little training data.This research optimizes the performance of CapsNets by designing a new architecture that allows them to perform better on the challenge of lung cancer classification.The findings demonstrate that the proposed capsule network method outperforms CNNs on the lung cancer classification challenge.CapsNet with a single convolution layer and 32 features(CN-1-32),CapsNet with a single convolution layer and 64 features(CN-1-64),and CapsNet with a double convolution layer and 64 features(CN-2-64)are the three capsulel networks developed in this research for lung cancer classification.Lung nodules,both benign and malignant,are classified using these networks using CT images.The LIDC-IDRI database was utilized to assess the performance of those networks.Based on the testing results,CN-2-64 network performed better out of the three networks tested,with a specificity of 98.37%,sensitivity of 97.47%and an accuracy of 97.92%.
基金supported by the National Natural Science Foundation of China(22067016)the Project of Qinghai Outstanding Youth Fund Project(2023-ZJ-964J).
文摘Objective:To explore the mechanism of action of Zangjiangzhi capsule(ZJZC)in treating hyperlipidemia(HLP).Methods:The components of ZJZC were analyzed and identified using ultra-high performance liquid chromatography with Q-Exactive Orbitrap tandem mass spectrometry(UHPLC-Q-Exactive-Orbitrap-MS/MS).Network pharmacology analysis was used to explore the mechanism of action of ZJZC in HLP treatment.The SwissTargetPrediction database was used to predict compound targets,and GeneCards,DisGeNet,OMIM,and DRUGBANK databases were used to identify HLP-related targets.Proteineprotein interaction diagrams were constructed using the STRING database.The targets were subjected to gene ontology and Kyoto Encyclopedia of Genes and Genomes(KEGG)enrichment analysis.The“herbingredient-target”network was visualized using Cytoscape.Preliminary validation was performed using molecular docking and enzyme-linked immunosorbent assay.Results:Ninety compounds were identified in ZJZC,including 34 flavonoids,12 phenols,10 terpenoids,10 alkaloids,8 organic acids,8 anthraquinones,and 9 other compounds.In total,904 targets were identified for these compounds.Among them,158 targets intersected with the HLP target network.Network pharmacology analysis showed that MAPK1,PPAR-a,RXRA,HSP90AA1,PIK3R1,AKT1,PIK3CA,IL6,TNF,and ESR1 are the key targets of action.KEGG enrichment analysis identified 164 pathways.Among these,the AGE-RAGE signaling pathway in diabetic complications,lipid and atherosclerosis pathways,regulation of lipids in adipocytes,and insulin resistance are related to HLP.Molecular docking showed good affinity between the key targets and ingredients.Further,ZJZC treatment in mice resulted in lower expression of MAPK1 protein and increased expression of PPAR-a protein,which have been shown to be strongly associated with HLP.Conclusions:This study showed that ZJZC contains various active ingredients and can modulate multiple targets and pathways associated with HLP,providing evidence at the molecular level for its clinical application in the treatment of HLP.
文摘BACKGROUND Video capsule endoscopy(VCE)is a noninvasive technique used to examine small bowel abnormalities in both adults and children.However,manual review of VCE images is time-consuming and labor-intensive,making it crucial to develop deep learning methods to assist in image analysis.AIM To employ deep learning models for the automatic classification of small bowel lesions using pediatric VCE images.METHODS We retrospectively analyzed VCE images from 162 pediatric patients who underwent VCE between January 2021 and December 2023 at the Children's Hospital of Nanjing Medical University.A total of 2298 high-resolution images were extracted,including normal mucosa and lesions(erosions/erythema,ulcers,and polyps).The images were split into training and test datasets in a 4:1 ratio.Four deep learning models:DenseNet121,Visual geometry group-16,ResNet50,and vision transformer were trained using 5-fold cross-validation,with hyperparameters adjusted for optimal classification performance.The models were evaluated based on accuracy,precision,recall,F1-score,and area under the receiver operating curve(AU-ROC).Lesion visualization was performed using gradient-weighted class activation mapping.RESULTS Abdominal pain was the most common indication for VCE,accounting for 62%of cases,followed by diarrhea,vomiting,and gastrointestinal bleeding.Abnormal lesions were detected in 93 children,with 38 diagnosed with inflammatory bowel disease.Among the deep learning models,DenseNet121 and ResNet50 demonstrated excellent classification performance,achieving accuracies of 90.6%[95%confidence interval(CI):89.2-92.0]and 90.5%(95%CI:89.9-91.2),respectively.The AU-ROC values for these models were 93.7%(95%CI:92.9-94.5)for DenseNet121 and 93.4%(95%CI:93.1-93.8)for ResNet50.CONCLUSION Our deep learning-based diagnostic tool developed in this study effectively classified lesions in pediatric VCE images,contributing to more accurate diagnoses and increased diagnostic efficiency.
基金supported by National Natural Science Foundation of China(No.61763025)Gansu Science and Technology Program Project(No.18JR3RA104)+1 种基金Industrial support program for colleges and universities in Gansu Province(No.2020C-19)Lanzhou Science and Technology Project(No.2019-4-49)。
文摘The conventional troubleshooting methods for high-speed railway on-board equipment, with over-reliance on personnel experience, is characterized by one-sidedness and low efficiency. In the process of high-speed train operation, numerous text-based onboard logs are recorded by on-board computers. Machine learning methods can help technicians make a correct judgment of fault types using the on-board log reasonably. Therefore, a fault classification model of on-board equipment based on attention capsule networks is proposed. This paper presents an empirical exploration of the application of a capsule network with dynamic routing in fault classification. A capsule network can encode the internal spatial part-whole relationship between various entities to identify the fault types. As the importance of each word in the on-board log and the dependencies between them have a significant impact on fault classification, an attention mechanism is incorporated into the capsule network to distill important information. Considering the imbalanced distribution of normal data and fault data in the on-board log, the focal loss function is introduced into the model to adjust the imbalanced data. The experiments are conducted on the on-board log of a railway bureau and compared with other baseline models. The experimental results demonstrate that our model outperforms the compared baseline methods, proving the superiority and competitiveness of our model.
基金Chinese Academy of Engi⁃neering Strategic Consulting Project(2022-XY-45)S&T Program of Hebei(22372502D)+1 种基金Scien⁃tific Research Project of Hebei Provincial Admin⁃istration of Traditional Chinese Medicine(023172)and Scientific Research Project of Hebei Provincial Administration of Traditional Chinese Medicine(2021273)。
文摘OBJECTIVE To explore the new indications and key mechanism of Bazi Bushen capsule(BZBS)by network pharmacology and in vitro experiment.METHODS The potential tar⁃get profiles of the components of BZBS were pre⁃dicted.Subsequently,new indications for BZBS were predicted by disease ontology(DO)enrich⁃ment analysis and initially validated by GO and KEGG pathway enrichment analysis.Further⁃more,the therapeutic target of BZBS acting on AD signaling pathway were identified by intersec⁃tion analysis.Two Alzheimer′s disease(AD)cell models,BV-2 and SH-SY5Y,were used to pre⁃liminarily verify the anti-AD efficacy and mecha⁃nism of BZBS in vitro.RESULTS In total,1499 non-repeated ingredients were obtained from 16 herbs in BZBS formula,and 1320 BZBS targets with high confidence were predicted.Disease enrichment results strongly suggested that BZBS formula has the potential to be used in the treat⁃ment of AD.In vitro experiments showed that BZ⁃BS could significantly reduce the release of TNF-αand IL-6 and the expression of COX-2 and PSEN1 in Aβ25-35-induced BV-2 cells.BZBS reduced the apoptosis rate of Aβ25-35 induced SH-SY5Y cells,significantly increased mitochon⁃drial membrane potential,reduced the expres⁃sion of Caspase3 active fragment and PSEN1,and increased the expression of IDE.CONCLU⁃SIONS BZBS formula has a potential use in the treatment of AD,which is achieved through regu⁃lation of ERK1/2,NF-κB signaling pathways,and GSK-3β/β-catenin signaling pathway.Further⁃more,the network pharmacology technology is a feasible drug repurposing strategy to reposition new clinical use of approved TCM and explore the mechanism of action.The study lays a foun⁃dation for the subsequent in-depth study of BZBS in the treatment of AD and provides a basis for its application in the clinical treatment of AD.
文摘Mobile phones are an essential part of modern life.The two popular mobile phone platforms,Android and iPhone Operating System(iOS),have an immense impact on the lives of millions of people.Among these two,Android currently boasts more than 84%market share.Thus,any personal data put on it are at great risk if not properly protected.On the other hand,more than a million pieces of malware have been reported on Android in just 2021 till date.Detecting and mitigating all this malware is extremely difficult for any set of human experts.Due to this reason,machine learning-and specifically deep learning-has been utilized in the recent past to resolve this issue.However,deep learning models have primarily been designed for image analysis.While this line of research has shown promising results,it has been difficult to really understand what the features extracted by deep learning models are in the domain of malware.Moreover,due to the translation invariance property of popular models based on ConvolutionalNeural Network(CNN),the true potential of deep learning for malware analysis is yet to be realized.To resolve this issue,we envision the use of Capsule Networks(CapsNets),a state-of-the-art model in deep learning.We argue that since CapsNets are orientation-based in terms of images,they can potentially be used to capture spatial relationships between different features at different locations within a sequence of opcodes.We design a deep learning-based architecture that efficiently and effectively handles very large scale malware datasets to detect Androidmalware without resorting to very deep networks.This leads tomuch faster detection as well as increased accuracy.We achieve state-of-the-art F1 score of 0.987 with an FPR of just 0.002 for three very large,real-world malware datasets.Our code is made available as open source and can be used to further enhance our work with minimal effort.
文摘Objective: To investigate the possible mechanism of Yiqing Capsules in the treatment of upper respiratory tract infection based on network pharmacology. Methods: The main active components of Yiqing Capsules were selected on TCMSP database;the targets of upper respiratory tract infection were selected on GeneCards database. The drug-compound-target network and PPi network were constructed through STRING database and soft Cytoscape 3.7.2. Soft R was used to perform GO enrichment analysis and KEGG pathway enrichment analysis of main targets. Results: According to the screening conditions, 48 active compounds and 171 related targets were obtained. GO enrichment analysis obtained 2333 items, KEGG pathway enrichment analysis obtained 2248 items, including Kaposi sarcoma-associated herpesvirus infection, Human cytomegalovirus infection, Epstein-Barr virus infection, PI3K-Akt signaling pathway, etc. Conclusion: Yiqing capsules play a therapeutic role in upper respiratory tract infection through multi-target and multi-pathway.
基金the Foundation of State Key Laboratory of Component-based Chinese Medicine(Grant No.CBCM2020104).
文摘Objective:Lingzhihuang capsule(LZHC)is a natural product that consists of 10 commonly used medicinal plants,and it is used in traditional Chinese medicine to promote people’s overall health.Previously,LZHC was successfully used as adjuvant therapy for treating patients with cancer.However,the chemical constituents of LZHC and their potential biological functions remain unclear.The aim of this study is to investigate the major bioactive compounds in LZHC and predict their pharmacological targets.Methods:The LZHC constituents were putatively identified by ultra-high performance liquid chromatography coupled with timeof-flight mass spectrometry combined with mass spectrometry-based molecular networking.The targets were predicted using SwissTargetPrediction software,and the associated gene ontology and Kyoto encyclopedia of genes and genomes pathways were analyzed using the Database for Annotation,Visualization,and Integrated Discovery.The mass spectrometry-based molecular network and compound-target-pathway network were constructed using Cytoscape 3.8.0 software.Results:We putatively identified 94 compounds of LZHC by mass spectrometry-based molecular networking,including triterpene(the main structural type)and other clusters(ie,flavonoids and organic acids).Our results suggested that multiple pivotal targets were regulated by LZHC,including tumor necrosis factor,nitric oxide synthase 2,glucocorticoid receptor,estrogen receptor,3-oxo-5-alpha-steroid 4-dehydrogenase 2,prostaglandin e2 receptor ep4 subtype,estrogen receptor beta,phosphatidylinositol 4,5-bisphosphate 3-kinase catalytic subunit alpha isoform,mitogen-activated protein kinase 3,and racalpha serine,which are related to signal transduction,positive regulation of transcription from RNA polymerase II promoters,oxidation-reduction processes,inflammatory responses,and other biological processes.Functional annotation of those targets suggested that several signaling pathways may be regulated by LZHC,such as cancer-related proteoglycans,the PI3K-Aktsignaling pathway,and the cAMP-signaling pathway.Conclusions:Our findings reveal the chemical constituents of LZHC and provided scientific support for the efficacy of LZHC in terms of immune regulation,anti-aging,and tumor suppression.
基金supported by the Innovation Project of Jinan Science and Technology Bureau (No. 2020GXRC022)the Project for Scientific Research Innovation Team of Young Scholar in Colleges and Universities of Shandong Province (No. 2020KJC001)the National Natural Science Foundation of China (No. 21677090)。
文摘The intrinsic hypoxic tumor microenvironment and limited accumulation of photosensitizers(PSs) result in unsatisfied efficiency of photodynamic therapy(PDT).To enhance the PDT efficiency against solid tumors,a functional oxygen self-supplying and PS-delivering nanosystem is fabricated via the combination of catalase(CAT),chlorin e6(Ce6) and metal-phenolic network(MPN) capsule.It is demonstrated that the CAT encapsulated in the capsules(named CCM capsules) could catalyze the degradation of hydrogen peroxide(H;O;) to produce molecular oxygen(O;),which could be converted into cytotoxicity reactive oxygen species(ROS) by surface-loaded Ce6 under 660 nm laser irradiation,leading to synergistic anticancer effects in vitro and in vivo.Therefore,the application of CCM capsule could be a promising strategy to improve PDT effectiveness.
基金supported by the Program for Innovative Research Groups of the Hunan Provincial Natural Science Foundation of China(No.2019JJ10004)。
文摘State-of-the-art model-driven Direction-Of-Arrival(DOA)estimation methods for multipath signals face great challenges in practical application because of the dependence on the precise multipath model.In this paper,we introduce a framework,based on deep learning,for synchronizing perturbation auto-elimination with effective DOA estimation in multipath environment.Firstly,a signal selection mechanism is introduced to roughly locate specific signals to spatial subregion via frequency domain filters and compressive sensing-based method.Then,we set the mean of the correlation matrix’s row vectors as the input feature to construct the spatial spectrum by the corresponding single network within the parallel deep capsule networks.The proposed method enhances the generalization capability to untrained scenarios and the adaptability to non-ideal conditions,e.g.,lower SNRs,smaller snapshots,unknown reflection coefficients and perturbational steering vectors,which make up for the defects of the previous model-driven methods.Simulations are carried out to demonstrate the superiority of the proposed method.
