Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, t...Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, these existing algorithms create only the hard and fuzzy partitions for multi-view objects,which are often located in highly-overlapping areas of multi-view feature space. The adoption of hard and fuzzy partition ignores the ambiguity and uncertainty in the assignment of objects, likely leading to performance degradation. To address these issues, we propose a novel sparse reconstructive multi-view evidential clustering algorithm(SRMVEC). Based on a sparse reconstructive procedure, SRMVEC learns a shared affinity matrix across views, and maps multi-view objects to a 2-dimensional humanreadable chart by calculating 2 newly defined mathematical metrics for each object. From this chart, users can detect the number of clusters and select several objects existing in the dataset as cluster centers. Then, SRMVEC derives a credal partition under the framework of evidence theory, improving the fault tolerance of clustering. Ablation studies show the benefits of adopting the sparse reconstructive procedure and evidence theory. Besides,SRMVEC delivers effectiveness on benchmark datasets by outperforming some state-of-the-art methods.展开更多
Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewpriv...Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.展开更多
The use of lithium-sulfur batteries under high sulfur loading and low electrolyte concentrations is severely restricted by the detrimental shuttling behavior of polysulfides and the sluggish kinetics in redox processe...The use of lithium-sulfur batteries under high sulfur loading and low electrolyte concentrations is severely restricted by the detrimental shuttling behavior of polysulfides and the sluggish kinetics in redox processes.Two-dimensional(2D)few layered black phosphorus with fully exposed atoms and high sulfur affinity can be potential lithium-sulfur battery electrocatalysts,which,however,have limitations of restricted catalytic activity and poor electrochemical/chemical stability.To resolve these issues,we developed a multifunctional metal-free catalyst by covalently bonding few layered black phosphorus nanosheets with nitrogen-doped carbon-coated multiwalled carbon nanotubes(denoted c-FBP-NC).The experimental characterizations and theoretical calculations show that the formed polarized P-N covalent bonds in c-FBP-NC can efficiently regulate electron transfer from NC to FBP and significantly promote the capture and catalysis of lithium polysulfides,thus alleviating the shuttle effect.Meanwhile,the robust 1D-2D interwoven structure with large surface area and high porosity allows strong physical confinement and fast mass transfer.Impressively,with c-FBP-NC as the sulfur host,the battery shows a high areal capacity of 7.69 mAh cm^(−2) under high sulfur loading of 8.74 mg cm^(−2) and a low electrolyte/sulfur ratio of 5.7μL mg^(−1).Moreover,the assembled pouch cell with sulfur loading of 4 mg cm^(−2) and an electrolyte/sulfur ratio of 3.5μL mg^(−1) shows good rate capability and outstanding cyclability.This work proposes an interfacial and electronic structure engineering strategy for fast and durable sulfur electrochemistry,demonstrating great potential in lithium-sulfur batteries.展开更多
The effects of nano-CaO contents on the microstructure,mechanical properties and corrosion resistance of lean Mg-1Zn alloy were investigated.The results showed that the addition of nano-CaO significantly refined the g...The effects of nano-CaO contents on the microstructure,mechanical properties and corrosion resistance of lean Mg-1Zn alloy were investigated.The results showed that the addition of nano-CaO significantly refined the grain size and improved mechanical properties of the Mg-1Zn alloy.At the same time,CaO reacted with molten Mg in situ to form nano-MgO,whose corrosion product in SBF solution was the same with the degradation product of Mg matrix,resulting in the enhanced compactness of the Mg(OH)_(2) layer and reduced corrosion rate of matrix.The Mg-1Zn alloy had lower corrosion resistance due to excessively large grain size and shedding of corrosion products.The composite with 0.5 wt.%CaO had the best corrosion resistance with a weight loss of 9.875 mg·y^(-1)·mm^(-2)due to the small number of Ca_(2)Mg_(6)Zn_(3) phase and suitable grain size.While for composites with high content of CaO(0.7 wt.%and 1.0 wt.%),they had lower corrosion resistance due to the coexistence of large number of Ca_(2)Mg_(6)Zn_(3) and Mg_(2)Ca at grain boundaries,especially for 1.0 wt.%CaO composite,resulting from the strong micro-galvanic corrosion.展开更多
This paper presents a study on the design strategy of leaning-type arch bridges.The main characteristics of leaning-type arch bridges are first introduced;Kunshan Yufeng Bridge is taken as an example to discuss differ...This paper presents a study on the design strategy of leaning-type arch bridges.The main characteristics of leaning-type arch bridges are first introduced;Kunshan Yufeng Bridge is taken as an example to discuss different aspects of a design strategy,which includes self-system optimization,selection of beam length and bridge deck position,and other aspects.This paper can be used as a reference to further improve and develop bridge design.展开更多
BACKGROUND A new nomenclature consensus has emerged for liver diseases that were previously known as non-alcoholic fatty liver disease(NAFLD)and metabolic dysfunction-associated fatty liver disease(MAFLD).They are now...BACKGROUND A new nomenclature consensus has emerged for liver diseases that were previously known as non-alcoholic fatty liver disease(NAFLD)and metabolic dysfunction-associated fatty liver disease(MAFLD).They are now defined as metabolic dysfunction-associated steatotic liver disease(MASLD),which includes cardiometabolic criteria in adults.This condition,extensively studied in obese or overweight patients,constitutes around 30%of the population,with a steady increase worldwide.Lean patients account for approximately 10%-15%of the MASLD population.However,the pathogenesis is complex and is not well understood.AIM To systematically review the literature on the diagnosis,pathogenesis,characteristics,and prognosis in lean MASLD patients and provide an interpretation of these new criteria.METHODS We conducted a comprehensive database search on PubMed and Google Scholar between January 2012 and September 2023,specifically focusing on lean NAFLD,MAFLD,or MASLD patients.We include original articles with patients aged 18 years or older,with a lean body mass index categorized according to the World Health Organization criteria,using a cutoff of 25 kg/m2 for the general population and 23 kg/m2 for the Asian population.RESULTS We include 85 studies in our analysis.Our findings revealed that,for lean NAFLD patients,the prevalence rate varied widely,ranging from 3.8%to 34.1%.The precise pathogenesis mechanism remained elusive,with associations found in genetic variants,epigenetic modifications,and adaptative metabolic response.Common risk factors included metabolic syndrome,hypertension,and type 2 diabetes mellitus,but their prevalence varied based on the comparison group involving lean patients.Regarding non-invasive tools,Fibrosis-4 index outperformed the NAFLD fibrosis score in lean patients.Lifestyle modifications aided in reducing hepatic steatosis and improving cardiometabolic profiles,with some medications showing efficacy to a lesser extent.However,lean NAFLD patients exhibited a worse prognosis compared to the obese or overweight counterpart.CONCLUSION MASLD is a complex disease comprising epigenetic,genetic,and metabolic factors in its pathogenesis.Results vary across populations,gender,and age.Limited data exists on clinical practice guidelines for lean patients.Future studies employing this new nomenclature can contribute to standardizing and generalizing results among lean patients with steatotic liver disease.展开更多
Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The signif...Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The significance of low-rank prior in MVSC is emphasized, highlighting its role in capturing the global data structure across views for improved performance. However, it faces challenges with outlier sensitivity due to its reliance on the Frobenius norm for error measurement. Addressing this, our paper proposes a Low-Rank Multi-view Subspace Clustering Based on Sparse Regularization (LMVSC- Sparse) approach. Sparse regularization helps in selecting the most relevant features or views for clustering while ignoring irrelevant or noisy ones. This leads to a more efficient and effective representation of the data, improving the clustering accuracy and robustness, especially in the presence of outliers or noisy data. By incorporating sparse regularization, LMVSC-Sparse can effectively handle outlier sensitivity, which is a common challenge in traditional MVSC methods relying solely on low-rank priors. Then Alternating Direction Method of Multipliers (ADMM) algorithm is employed to solve the proposed optimization problems. Our comprehensive experiments demonstrate the efficiency and effectiveness of LMVSC-Sparse, offering a robust alternative to traditional MVSC methods.展开更多
Lithium–sulfur(Li–S) batteries have received widespread attention, and lean electrolyte Li–S batteries have attracted additional interest because of their higher energy densities. This review systematically analyze...Lithium–sulfur(Li–S) batteries have received widespread attention, and lean electrolyte Li–S batteries have attracted additional interest because of their higher energy densities. This review systematically analyzes the effect of the electrolyte-to-sulfur(E/S) ratios on battery energy density and the challenges for sulfur reduction reactions(SRR) under lean electrolyte conditions. Accordingly, we review the use of various polar transition metal sulfur hosts as corresponding solutions to facilitate SRR kinetics at low E/S ratios(< 10 μL mg~(-1)), and the strengths and limitations of different transition metal compounds are presented and discussed from a fundamental perspective. Subsequently, three promising strategies for sulfur hosts that act as anchors and catalysts are proposed to boost lean electrolyte Li–S battery performance. Finally, an outlook is provided to guide future research on high energy density Li–S batteries.展开更多
Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-ti...Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-tic EEG signals and develop artificial intelligence(AI)-assist recognition,a multi-view transfer learning(MVTL-LSR)algorithm based on least squares regression is proposed in this study.Compared with most existing multi-view transfer learning algorithms,MVTL-LSR has two merits:(1)Since traditional transfer learning algorithms leverage knowledge from different sources,which poses a significant risk to data privacy.Therefore,we develop a knowledge transfer mechanism that can protect the security of source domain data while guaranteeing performance.(2)When utilizing multi-view data,we embed view weighting and manifold regularization into the transfer framework to measure the views’strengths and weaknesses and improve generalization ability.In the experimental studies,12 different simulated multi-view&transfer scenarios are constructed from epileptic EEG signals licensed and provided by the Uni-versity of Bonn,Germany.Extensive experimental results show that MVTL-LSR outperforms baselines.The source code will be available on https://github.com/didid5/MVTL-LSR.展开更多
Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application scenarios.With the introduction of end-to-end direct regression methods,the fi...Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application scenarios.With the introduction of end-to-end direct regression methods,the field has entered a new stage of development.However,the regression results of joints that are more heavily influenced by external factors are not accurate enough even for the optimal method.In this paper,we propose an effective feature recalibration module based on the channel attention mechanism and a relative optimal calibration strategy,which is applied to themulti-viewmulti-person 3D human pose estimation task to achieve improved detection accuracy for joints that are more severely affected by external factors.Specifically,it achieves relative optimal weight adjustment of joint feature information through the recalibration module and strategy,which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding joints.We call this method as the Efficient Recalibration Network(ER-Net).Finally,experiments were conducted on two benchmark datasets for this task,Campus and Shelf,in which the PCP reached 97.3% and 98.3%,respectively.展开更多
In multi-view image localization task,the features of the images captured from different views should be fused properly.This paper considers the classification-based image localization problem.We propose the relationa...In multi-view image localization task,the features of the images captured from different views should be fused properly.This paper considers the classification-based image localization problem.We propose the relational graph location network(RGLN)to perform this task.In this network,we propose a heterogeneous graph construction approach for graph classification tasks,which aims to describe the location in a more appropriate way,thereby improving the expression ability of the location representation module.Experiments show that the expression ability of the proposed graph construction approach outperforms the compared methods by a large margin.In addition,the proposed localization method outperforms the compared localization methods by around 1.7%in terms of meter-level accuracy.展开更多
Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency o...Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.展开更多
目的利用精益六西格玛(lean six sigma,LSS)管理中的界定、测量、分析、改进和控制(define,measure,analyze,improve,control;DMAIC)模型,优化妊娠合并脑血管病患者就医流程,提高患者就医效率,保障母婴安全。方法2021年12月,首都医科大...目的利用精益六西格玛(lean six sigma,LSS)管理中的界定、测量、分析、改进和控制(define,measure,analyze,improve,control;DMAIC)模型,优化妊娠合并脑血管病患者就医流程,提高患者就医效率,保障母婴安全。方法2021年12月,首都医科大学附属北京天坛医院根据DMAIC模型,对危重孕产妇的就诊流程进行优化:梳理就诊流程,明确到院—医嘱开立、采血—送检、医嘱开立—影像学检查为院内延误的关键环节,对上述环节进行流程跟踪及分析,找出延误原因,并采取改进措施,优化流程。本研究回顾性纳入流程优化前(2019年1月—2021年12月)的妊娠合并脑血管病患者为优化前组,流程优化后(2022年1月—2023年12月)的患者为优化后组。比较两组患者就诊流程中的到院—医嘱开立、采血—送检、医嘱开立—影像学检查、到院—办理住院的时间。结果急诊就诊流程优化后,妊娠合并脑血管病患者的总体就诊效率提高。到院—医嘱开立[24.0(13.5~38.5)min vs.39.0(17.5~98.0)min,P=0.027]、医嘱开立—影像学检查[48.0(10.0~73.0)min vs.65.5(22.7~90.7)min,P=0.025]以及到院—办理入院总时间[120.0(93.0~149.0)min vs.218.0(123.0~382.7)mi n,P<0.001]均较优化前缩短,差异有统计学意义;采血—送检时间有缩短趋势,但优化前后差异无统计学意义。结论使用DMAIC模型能够明确流程优化的关键环节,优化妊娠合并脑血管病患者的急诊就诊流程。展开更多
基金supported in part by NUS startup grantthe National Natural Science Foundation of China (52076037)。
文摘Although many multi-view clustering(MVC) algorithms with acceptable performances have been presented, to the best of our knowledge, nearly all of them need to be fed with the correct number of clusters. In addition, these existing algorithms create only the hard and fuzzy partitions for multi-view objects,which are often located in highly-overlapping areas of multi-view feature space. The adoption of hard and fuzzy partition ignores the ambiguity and uncertainty in the assignment of objects, likely leading to performance degradation. To address these issues, we propose a novel sparse reconstructive multi-view evidential clustering algorithm(SRMVEC). Based on a sparse reconstructive procedure, SRMVEC learns a shared affinity matrix across views, and maps multi-view objects to a 2-dimensional humanreadable chart by calculating 2 newly defined mathematical metrics for each object. From this chart, users can detect the number of clusters and select several objects existing in the dataset as cluster centers. Then, SRMVEC derives a credal partition under the framework of evidence theory, improving the fault tolerance of clustering. Ablation studies show the benefits of adopting the sparse reconstructive procedure and evidence theory. Besides,SRMVEC delivers effectiveness on benchmark datasets by outperforming some state-of-the-art methods.
文摘Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.
基金Jiangsu Provincial Department of Science and Technology,Grant/Award Number:BK20201190Fundamental Research Funds for“Young Talent Support Plan”of Xi'an Jiaotong University,Grant/Award Number:HG6J003+1 种基金“1000-Plan program”of Shaanxi Province and the Velux Foundations through the research center V-Sustain,Grant/Award Number:9455National Key R&D Program of China,。
文摘The use of lithium-sulfur batteries under high sulfur loading and low electrolyte concentrations is severely restricted by the detrimental shuttling behavior of polysulfides and the sluggish kinetics in redox processes.Two-dimensional(2D)few layered black phosphorus with fully exposed atoms and high sulfur affinity can be potential lithium-sulfur battery electrocatalysts,which,however,have limitations of restricted catalytic activity and poor electrochemical/chemical stability.To resolve these issues,we developed a multifunctional metal-free catalyst by covalently bonding few layered black phosphorus nanosheets with nitrogen-doped carbon-coated multiwalled carbon nanotubes(denoted c-FBP-NC).The experimental characterizations and theoretical calculations show that the formed polarized P-N covalent bonds in c-FBP-NC can efficiently regulate electron transfer from NC to FBP and significantly promote the capture and catalysis of lithium polysulfides,thus alleviating the shuttle effect.Meanwhile,the robust 1D-2D interwoven structure with large surface area and high porosity allows strong physical confinement and fast mass transfer.Impressively,with c-FBP-NC as the sulfur host,the battery shows a high areal capacity of 7.69 mAh cm^(−2) under high sulfur loading of 8.74 mg cm^(−2) and a low electrolyte/sulfur ratio of 5.7μL mg^(−1).Moreover,the assembled pouch cell with sulfur loading of 4 mg cm^(−2) and an electrolyte/sulfur ratio of 3.5μL mg^(−1) shows good rate capability and outstanding cyclability.This work proposes an interfacial and electronic structure engineering strategy for fast and durable sulfur electrochemistry,demonstrating great potential in lithium-sulfur batteries.
基金the financial support for this work from the National Natural Science Foundation of China(Nos.52171241,52201301 and 51871166)。
文摘The effects of nano-CaO contents on the microstructure,mechanical properties and corrosion resistance of lean Mg-1Zn alloy were investigated.The results showed that the addition of nano-CaO significantly refined the grain size and improved mechanical properties of the Mg-1Zn alloy.At the same time,CaO reacted with molten Mg in situ to form nano-MgO,whose corrosion product in SBF solution was the same with the degradation product of Mg matrix,resulting in the enhanced compactness of the Mg(OH)_(2) layer and reduced corrosion rate of matrix.The Mg-1Zn alloy had lower corrosion resistance due to excessively large grain size and shedding of corrosion products.The composite with 0.5 wt.%CaO had the best corrosion resistance with a weight loss of 9.875 mg·y^(-1)·mm^(-2)due to the small number of Ca_(2)Mg_(6)Zn_(3) phase and suitable grain size.While for composites with high content of CaO(0.7 wt.%and 1.0 wt.%),they had lower corrosion resistance due to the coexistence of large number of Ca_(2)Mg_(6)Zn_(3) and Mg_(2)Ca at grain boundaries,especially for 1.0 wt.%CaO composite,resulting from the strong micro-galvanic corrosion.
文摘This paper presents a study on the design strategy of leaning-type arch bridges.The main characteristics of leaning-type arch bridges are first introduced;Kunshan Yufeng Bridge is taken as an example to discuss different aspects of a design strategy,which includes self-system optimization,selection of beam length and bridge deck position,and other aspects.This paper can be used as a reference to further improve and develop bridge design.
文摘BACKGROUND A new nomenclature consensus has emerged for liver diseases that were previously known as non-alcoholic fatty liver disease(NAFLD)and metabolic dysfunction-associated fatty liver disease(MAFLD).They are now defined as metabolic dysfunction-associated steatotic liver disease(MASLD),which includes cardiometabolic criteria in adults.This condition,extensively studied in obese or overweight patients,constitutes around 30%of the population,with a steady increase worldwide.Lean patients account for approximately 10%-15%of the MASLD population.However,the pathogenesis is complex and is not well understood.AIM To systematically review the literature on the diagnosis,pathogenesis,characteristics,and prognosis in lean MASLD patients and provide an interpretation of these new criteria.METHODS We conducted a comprehensive database search on PubMed and Google Scholar between January 2012 and September 2023,specifically focusing on lean NAFLD,MAFLD,or MASLD patients.We include original articles with patients aged 18 years or older,with a lean body mass index categorized according to the World Health Organization criteria,using a cutoff of 25 kg/m2 for the general population and 23 kg/m2 for the Asian population.RESULTS We include 85 studies in our analysis.Our findings revealed that,for lean NAFLD patients,the prevalence rate varied widely,ranging from 3.8%to 34.1%.The precise pathogenesis mechanism remained elusive,with associations found in genetic variants,epigenetic modifications,and adaptative metabolic response.Common risk factors included metabolic syndrome,hypertension,and type 2 diabetes mellitus,but their prevalence varied based on the comparison group involving lean patients.Regarding non-invasive tools,Fibrosis-4 index outperformed the NAFLD fibrosis score in lean patients.Lifestyle modifications aided in reducing hepatic steatosis and improving cardiometabolic profiles,with some medications showing efficacy to a lesser extent.However,lean NAFLD patients exhibited a worse prognosis compared to the obese or overweight counterpart.CONCLUSION MASLD is a complex disease comprising epigenetic,genetic,and metabolic factors in its pathogenesis.Results vary across populations,gender,and age.Limited data exists on clinical practice guidelines for lean patients.Future studies employing this new nomenclature can contribute to standardizing and generalizing results among lean patients with steatotic liver disease.
文摘Multi-view Subspace Clustering (MVSC) emerges as an advanced clustering method, designed to integrate diverse views to uncover a common subspace, enhancing the accuracy and robustness of clustering results. The significance of low-rank prior in MVSC is emphasized, highlighting its role in capturing the global data structure across views for improved performance. However, it faces challenges with outlier sensitivity due to its reliance on the Frobenius norm for error measurement. Addressing this, our paper proposes a Low-Rank Multi-view Subspace Clustering Based on Sparse Regularization (LMVSC- Sparse) approach. Sparse regularization helps in selecting the most relevant features or views for clustering while ignoring irrelevant or noisy ones. This leads to a more efficient and effective representation of the data, improving the clustering accuracy and robustness, especially in the presence of outliers or noisy data. By incorporating sparse regularization, LMVSC-Sparse can effectively handle outlier sensitivity, which is a common challenge in traditional MVSC methods relying solely on low-rank priors. Then Alternating Direction Method of Multipliers (ADMM) algorithm is employed to solve the proposed optimization problems. Our comprehensive experiments demonstrate the efficiency and effectiveness of LMVSC-Sparse, offering a robust alternative to traditional MVSC methods.
基金the Research Foundation-Flanders (FWO) for a Research Project (G0B3218N)the financial support by the National Natural Science Foundation of China (22005054)+3 种基金Natural Science Foundation of Fujian Province (2021J01149)State Key Laboratory of Structural Chemistry (20200007)Sichuan Science and Technology Program (project No.: 2022ZYD0016 and 2023JDRC0013)the National Natural Science Foundation of China (project No. 21776120)。
文摘Lithium–sulfur(Li–S) batteries have received widespread attention, and lean electrolyte Li–S batteries have attracted additional interest because of their higher energy densities. This review systematically analyzes the effect of the electrolyte-to-sulfur(E/S) ratios on battery energy density and the challenges for sulfur reduction reactions(SRR) under lean electrolyte conditions. Accordingly, we review the use of various polar transition metal sulfur hosts as corresponding solutions to facilitate SRR kinetics at low E/S ratios(< 10 μL mg~(-1)), and the strengths and limitations of different transition metal compounds are presented and discussed from a fundamental perspective. Subsequently, three promising strategies for sulfur hosts that act as anchors and catalysts are proposed to boost lean electrolyte Li–S battery performance. Finally, an outlook is provided to guide future research on high energy density Li–S batteries.
基金supported in part by the National Natural Science Foundation of China(Grant No.82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)of Shenzhen Science and Technology Innovation Committee+6 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Natural Science Foundation of Jiangsu Province(No.BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038 and SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575)the Henan Province Science and Technology Research(222102310322)The Jiangsu Students’Innovation and Entrepreneurship Training Program(202110304096Y).
文摘Epilepsy is a central nervous system disorder in which brain activity becomes abnormal.Electroencephalogram(EEG)signals,as recordings of brain activity,have been widely used for epilepsy recognition.To study epilep-tic EEG signals and develop artificial intelligence(AI)-assist recognition,a multi-view transfer learning(MVTL-LSR)algorithm based on least squares regression is proposed in this study.Compared with most existing multi-view transfer learning algorithms,MVTL-LSR has two merits:(1)Since traditional transfer learning algorithms leverage knowledge from different sources,which poses a significant risk to data privacy.Therefore,we develop a knowledge transfer mechanism that can protect the security of source domain data while guaranteeing performance.(2)When utilizing multi-view data,we embed view weighting and manifold regularization into the transfer framework to measure the views’strengths and weaknesses and improve generalization ability.In the experimental studies,12 different simulated multi-view&transfer scenarios are constructed from epileptic EEG signals licensed and provided by the Uni-versity of Bonn,Germany.Extensive experimental results show that MVTL-LSR outperforms baselines.The source code will be available on https://github.com/didid5/MVTL-LSR.
基金supported in part by the Key Program of NSFC (Grant No.U1908214)Special Project of Central Government Guiding Local Science and Technology Development (Grant No.2021JH6/10500140)+3 种基金Program for the Liaoning Distinguished Professor,Program for Innovative Research Team in University of Liaoning Province (LT2020015)Dalian (2021RT06)and Dalian University (XLJ202010)the Science and Technology Innovation Fund of Dalian (Grant No.2020JJ25CY001)Dalian University Scientific Research Platform Project (No.202101YB03).
文摘Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application scenarios.With the introduction of end-to-end direct regression methods,the field has entered a new stage of development.However,the regression results of joints that are more heavily influenced by external factors are not accurate enough even for the optimal method.In this paper,we propose an effective feature recalibration module based on the channel attention mechanism and a relative optimal calibration strategy,which is applied to themulti-viewmulti-person 3D human pose estimation task to achieve improved detection accuracy for joints that are more severely affected by external factors.Specifically,it achieves relative optimal weight adjustment of joint feature information through the recalibration module and strategy,which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding joints.We call this method as the Efficient Recalibration Network(ER-Net).Finally,experiments were conducted on two benchmark datasets for this task,Campus and Shelf,in which the PCP reached 97.3% and 98.3%,respectively.
文摘In multi-view image localization task,the features of the images captured from different views should be fused properly.This paper considers the classification-based image localization problem.We propose the relational graph location network(RGLN)to perform this task.In this network,we propose a heterogeneous graph construction approach for graph classification tasks,which aims to describe the location in a more appropriate way,thereby improving the expression ability of the location representation module.Experiments show that the expression ability of the proposed graph construction approach outperforms the compared methods by a large margin.In addition,the proposed localization method outperforms the compared localization methods by around 1.7%in terms of meter-level accuracy.
基金This work was supported by the National Natural Science Foundation of China(62073087,62071132,61973090).
文摘Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.