As a key mode of transportation, urban metro networks have significantly enhanced urban traffic environments and travel efficiency, making the identification of critical stations within these networks increasingly ess...As a key mode of transportation, urban metro networks have significantly enhanced urban traffic environments and travel efficiency, making the identification of critical stations within these networks increasingly essential. This study presents a novel integrated topological-functional(ITF) algorithm for identifying critical nodes, combining topological metrics such as K-shell decomposition, node information entropy, and neighbor overlapping interaction with the functional attributes of passenger flow operations, while also considering the coupling effects between metro and bus networks. Using the Chengdu metro network as a case study, the effectiveness of the algorithm under different conditions is validated.The results indicate significant differences in passenger flow patterns between working and non-working days, leading to varying sets of critical nodes across these scenarios. Moreover, the ITF algorithm demonstrates a marked improvement in the accuracy of critical node identification compared to existing methods. This conclusion is supported by the analysis of changes in the overall network structure and relative global operational efficiency following targeted attacks on the identified critical nodes. The findings provide valuable insight into urban transportation planning, offering theoretical and practical guidance for improving metro network safety and resilience.展开更多
Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types o...Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics.To address the limitations of existing methods,we propose a fault diagnosis method based on graph neural networks(GNNs)embedded with multirelationships of intrinsic mode functions(MIMF).The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions(IMFs)of monitored signals and their multirelationships.Additionally,a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices.Experimental validation with datasets including independent vibration signals for gear fault detection,mixed vibration signals for concurrent gear and bearing faults,and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.展开更多
Patients with mild traumatic brain injury have a diverse clinical presentation,and the underlying pathophysiology remains poorly understood.Magnetic resonance imaging is a non-invasive technique that has been widely u...Patients with mild traumatic brain injury have a diverse clinical presentation,and the underlying pathophysiology remains poorly understood.Magnetic resonance imaging is a non-invasive technique that has been widely utilized to investigate neuro biological markers after mild traumatic brain injury.This approach has emerged as a promising tool for investigating the pathogenesis of mild traumatic brain injury.G raph theory is a quantitative method of analyzing complex networks that has been widely used to study changes in brain structure and function.However,most previous mild traumatic brain injury studies using graph theory have focused on specific populations,with limited exploration of simultaneous abnormalities in structural and functional connectivity.Given that mild traumatic brain injury is the most common type of traumatic brain injury encounte red in clinical practice,further investigation of the patient characteristics and evolution of structural and functional connectivity is critical.In the present study,we explored whether abnormal structural and functional connectivity in the acute phase could serve as indicators of longitudinal changes in imaging data and cognitive function in patients with mild traumatic brain injury.In this longitudinal study,we enrolled 46 patients with mild traumatic brain injury who were assessed within 2 wee ks of injury,as well as 36 healthy controls.Resting-state functional magnetic resonance imaging and diffusion-weighted imaging data were acquired for graph theoretical network analysis.In the acute phase,patients with mild traumatic brain injury demonstrated reduced structural connectivity in the dorsal attention network.More than 3 months of followup data revealed signs of recovery in structural and functional connectivity,as well as cognitive function,in 22 out of the 46 patients.Furthermore,better cognitive function was associated with more efficient networks.Finally,our data indicated that small-worldness in the acute stage could serve as a predictor of longitudinal changes in connectivity in patients with mild traumatic brain injury.These findings highlight the importance of integrating structural and functional connectivity in unde rstanding the occurrence and evolution of mild traumatic brain injury.Additionally,exploratory analysis based on subnetworks could serve a predictive function in the prognosis of patients with mild traumatic brain injury.展开更多
This paper presents the variational physics-informed neural network(VPINN)as an effective tool for static structural analyses.One key innovation includes the construction of the neural network solution as an admissibl...This paper presents the variational physics-informed neural network(VPINN)as an effective tool for static structural analyses.One key innovation includes the construction of the neural network solution as an admissible function of the boundary-value problem(BVP),which satisfies all geometrical boundary conditions.We then prove that the admissible neural network solution also satisfies natural boundary conditions,and therefore all boundary conditions,when the stationarity condition of the variational principle is met.Numerical examples are presented to show the advantages and effectiveness of the VPINN in comparison with the physics-informed neural network(PINN).Another contribution of the work is the introduction of Gaussian approximation of the Dirac delta function,which significantly enhances the ability of neural networks to handle singularities,as demonstrated by the examples with concentrated support conditions and loadings.It is hoped that these structural examples are so convincing that engineers would adopt the VPINN method in their structural design practice.展开更多
Rotating Space Slender Flexible Structures(RSSFS)are extensively utilized in space operations because of their light weight,mobility,and low energy consumption.To realize the accurate space operation of the RSSFS,it i...Rotating Space Slender Flexible Structures(RSSFS)are extensively utilized in space operations because of their light weight,mobility,and low energy consumption.To realize the accurate space operation of the RSSFS,it is necessary to establish a precise mechanical model and develop a control algorithm with high precision.However,with the application of traditional control strategies,the RSSFS often suffers from the chattering phenomenon,which will aggravate structure vibration.In this paper,novel deformation description is put forward to balance modeling accuracy and computational efficiency of the RSSFS,which is better appropriate for real-time control.Besides,the Neural Network Sliding Mode Control(NNSMC)strategy modified by the hyperbolic tangent(tanh)function is put forward to compensate for modeling errors and reduce the chattering phenomenon,thereby improving the trajectory tracking accuracy of the RSSFS.Firstly,a mathematical model for the RSSFS is developed according to the novel deformation description and the vibration theory of flexible structure.Comparison of the deformation accuracy between different models proves that the novel modeling method proposed has high modeling accuracy.Next,the universal approximation property of the Radial Basis Function(RBF)neural network is put forward to determine and compensate for modeling errors,which consist of higher-order modes and the uncertainties of external disturbances.In addition,the tanh function is proposed as the reaching law in the conventional NNSMC strategy to suppress driving torque oscillation.The control law of modified NNSMC strategy and the adaptive law of weight coefficients are developed according to the Lyapunov theorem to guarantee the RSSFS stability.Finally,the simulation and physical experimental tests of the RSSFS with different control strategies are conducted.Experimental results show that the control law according to the novel deformation description and the modified NNSMC strategy can obtain accurate tracking of the rotation and reduce the vibration of the RSSFS simultaneously.展开更多
<div style="text-align:justify;"> <span style="font-family:Verdana;">Sensitivity analysis of neural networks to input variation is an important research area as it goes some way to addr...<div style="text-align:justify;"> <span style="font-family:Verdana;">Sensitivity analysis of neural networks to input variation is an important research area as it goes some way to addressing the criticisms of their black-box behaviour. Such analysis of RBFNs for hydrological modelling has previously been limited to exploring perturbations to both inputs and connecting weights. In this paper, the backward chaining rule that has been used for sensitivity analysis of MLPs, is applied to RBFNs and it is shown how such analysis can provide insight into physical relationships. A trigonometric example is first presented to show the effectiveness and accuracy of this approach for first order derivatives alongside a comparison of the results with an equivalent MLP. The paper presents a real-world application in the modelling of river stage shows the importance of such approaches helping to justify and select such models.</span> </div>展开更多
Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal d...Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal discharges.Gaining more detailed information on brain network alterations can help us to further understand the mechanisms of epilepsy and pave the way for brain network-based precise therapeutic approaches in clinical practice.An increasing number of advanced neuroimaging techniques and electrophysiological techniques such as diffusion tensor imaging-based fiber tra ctography,diffusion kurtosis imaging-based fiber tractography,fiber ball imagingbased tra ctography,electroencephalography,functional magnetic resonance imaging,magnetoencephalography,positron emission tomography,molecular imaging,and functional ultrasound imaging have been extensively used to delineate epileptic networks.In this review,we summarize the relevant neuroimaging and neuroelectrophysiological techniques for assessing structural and functional brain networks in patients with epilepsy,and extensively analyze the imaging mechanisms,advantages,limitations,and clinical application ranges of each technique.A greater focus on emerging advanced technologies,new data analysis software,a combination of multiple techniques,and the construction of personalized virtual epilepsy models can provide a theoretical basis to better understand the brain network mechanisms of epilepsy and make surgical decisions.展开更多
Under the guide of system theory, taking the oasis in the Sangong River watershed as a case study, this paper analyzes the oasis structure and function from 4 aspects including oasis spatial structure, water resources...Under the guide of system theory, taking the oasis in the Sangong River watershed as a case study, this paper analyzes the oasis structure and function from 4 aspects including oasis spatial structure, water resources structure, vegetation structure, economic structure and their corresponding functions. The results indicate that as a typical small-scale watershed, Sangong River watershed has the relatively complete mountain-basin structure, and ecological and productive function. Because of human drastic activity the utilization rate of water resources was as high as 98.7%, and the utilization of groundwater was not reasonable, which resulted in an average annual decline of 0.353m in the water table of alluvial-diluvial-fan oasis, and an average annual increase of 0.047m in the alluvial-plain. The layout of crop and shelter forest benefits to the utilization of water and land resources. The development of oasis economy is at low level, and its eco-economic function is weak.展开更多
Many networks exhibit the core/periphery structure.Core/periphery structure is a type of meso-scale structure that consists of densely connected core nodes and sparsely connected peripheral nodes.Core nodes tend to be...Many networks exhibit the core/periphery structure.Core/periphery structure is a type of meso-scale structure that consists of densely connected core nodes and sparsely connected peripheral nodes.Core nodes tend to be well-connected,both among themselves and to peripheral nodes,which tend not to be well-connected to other nodes.In this brief report,we propose a new method to detect the core of a network by the centrality of each node.It is discovered that such nodes with non-negative centralities often consist in the core of the networks.The simulation is carried out on different real networks.The results are checked by the objective function.The checked results may show the effectiveness of the simulation results by the centralities of the nodes on the real networks.Furthermore,we discuss the characters of networks with the single core/periphery structure and point out the scope of the application of our method at the end of this paper.展开更多
Objective Using graph theory analysis,this study compares the topological and node attributes of the brain network to explore the differences in gray matter structural and functional network topological properties bet...Objective Using graph theory analysis,this study compares the topological and node attributes of the brain network to explore the differences in gray matter structural and functional network topological properties between bipolar depression(BD)patients with and without obsessive-compulsive symptoms(OCS).Methods A total of 90 BD patients(27 males,63 females;median age 19.0(22.0,25.0)years)were recruited from the psychiatric outpatient and inpatient departments of the First Affiliated Hospital of Jinan University between March 2018 and December 2022.Fifty healthy controls(19 males,31 females;median age:23.0(20.0,27.0)years)were also enrolled.The BD patients were divided into two groups based on the presence of OCS:53 with OCS(OCS group)and 37 without OCS(NOCS group).Resting-state structural and functional MRI data were collected for all participants to construct gray matter structural and functional networks.Graph therory analysis was aapplied to calculate network topological metrics such as small-world properties.The structural and functional network topological properties were compared among the BD-OCS,BD-nOCS,and control groups.Partial correlation analysis was conducted to examine the association between network topological metrics with significant group differences and Yale-Brown Obsessive-Compulsive Scale(Y-BOCS)scores.Support vector machines(SVM)were used with these metrics as classificationfeaturevalues toimproveediagnostic accuracy through pairwise group classification.Results Structural network analysis of gray matter:compared to HC group,both OCS group and NOCS group showed increasedshortesttpathlengthand standardized characteristic path length(shortest path length:0.78 and 0.80 vs.0.69;normalized characteristic path length:0.48 and 0.49 vs.0.43),and decreased global efficiency(0.21 and 0.21 vs.0.24)compared to the HC group(permutation test,all P<0.05).Compared to NOCS and HC groups,the OCS group showed increased nodal centrality and betweenness centrality in the right rolandic operculum and left superior occipital gyrus(permutation test,all P<0.05).Functional network analysis of gray matter:compared to the NOCS group,the OCS group showed increased node efficiency and decreased betweenness centrality in the cerebellum(t=2.15,-3.04;all P<0.05);compared to HC groups,the OCS group showed decreased betweenness centrality in the cerebellum and left inferior frontal gyrus,along with increased node centrality and nodal efficiency in the right transverse temporal gyrus(t=-2.99,-3.61,3.06,3.10;all P<0.05).In the 0CS group,betweenness centrality in the left inferior frontal gyrus positively correlated with Y-BOCS scale obsessive thinking score(r=0.303,P=0.034).Nodal centrality and node efficiency of the right transverse temporal gyrus negatively correlated with Y-BOCS total score(r=-0.301,-0.311)and Y-BOCS obsessional thinking scores(r=-0.385,-0.380)separately(all P<0.05).SVM classification:the combined network features achieved an area under the curve of 0.80 in distinguising OCS from NOCS patients.Conclusion BDOCS and BD-nOCS patients both exhibit consistent changes in gray matter structural network topology,with theOCSSgroup displaying more pronounced nodal topological abnormalities.Multi-network feature integration demostrates potential for diagnostic classfication.展开更多
This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to imp...This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.展开更多
The Wuding River Basin,situated in the Loess Plateau of northern China,is an ecologically fragile region facing severe soil erosion and imbalanced ecosystem service(ES)functions.However,the mechanisms driving the spat...The Wuding River Basin,situated in the Loess Plateau of northern China,is an ecologically fragile region facing severe soil erosion and imbalanced ecosystem service(ES)functions.However,the mechanisms driving the spatiotemporal evolution of ES functions,as well as the trade-offs and synergies among these functions,remain poorly understood,constraining effective watershed-scale management.To address this challenge,this study quantified four ES functions,i.e.,water yield(WY),carbon storage(CS),habitat quality(HQ),and soil conservation(SC)in the Wuding River Basin from 1990 to 2020 using the Integrated Valuation of Ecosystem Services and Tradeoff(InVEST)model,and proposed an innovative integration of InVEST with a Bayesian Belief Network(BBN)to nonlinearly identify trade-off and synergy relationships among ES functions through probabilistic inference.A trade-off and synergy index(TSI)was developed to assess the spatial interaction intensity among ES functions,while sensitivity and scenario analyses were employed to determine key driving factors,followed by spatial optimization to delineate functional zones.Results revealed distinct spatiotemporal variations:WY increased from 98.69 to 120.52 mm;SC rose to an average of 3.05×104 t/hm2;CS remained relatively stable(about 15.50 t/km2);and HQ averaged 0.51 with localized declines.The BBN achieved a high accuracy of 81.9%and effectively identified strong synergies between WY and SC,as well as between CS and HQ,while clear trade-offs were observed between WY and SC versus CS and HQ.Sensitivity analysis indicated precipitation(variance reduction of 9.4%),land use(9.8%),and vegetation cover(9.1%)as key driving factors.Spatial optimization further showed that core supply and ecological regulation zones are concentrated in the central-southern and southeastern basin,while ecological strengthening and optimization core zones dominate the central-northern and southeastern margins,highlighting strong spatial heterogeneity.Overall,this study advances ES research by combining process-based quantification with probabilistic modeling,offering a robust framework for studying nonlinear interactions,driving mechanisms,and optimization strategies,and providing a transferable paradigm for watershed-scale ES management and ecological planning in arid and semi-arid areas.展开更多
In this study, we simulated water flow in a water conservancy project consisting of various hydraulic structures, such as sluices, pumping stations, hydropower stations, ship locks, and culverts, and developed a multi...In this study, we simulated water flow in a water conservancy project consisting of various hydraulic structures, such as sluices, pumping stations, hydropower stations, ship locks, and culverts, and developed a multi-period and multi-variable joint optimization scheduling model for flood control, drainage, and irrigation. In this model, the number of sluice holes, pump units, and hydropower station units to be opened were used as decision variables, and different optimization objectives and constraints were considered. This model was solved with improved genetic algorithms and verified using the Huaian Water Conservancy Project as an example. The results show that the use of the joint optimization scheduling led to a 10% increase in the power generation capacity and a 15% reduction in the total energy consumption. The change in the water level was reduced by 0.25 m upstream of the Yundong Sluice, and by 50% downstream of pumping stations No. 1, No. 2, and No. 4. It is clear that the joint optimization scheduling proposed in this study can effectively improve power generation capacity of the project, minimize operating costs and energy consumption, and enable more stable operation of various hydraulic structures. The results may provide references for the management of water conservancy projects in complex river networks.展开更多
Brain plasticity, including anatomical changes and functional reorganization, is the physiological basis of functional recovery after spinal cord injury（SCI）. The correlation between brain anatomical changes and fun...Brain plasticity, including anatomical changes and functional reorganization, is the physiological basis of functional recovery after spinal cord injury（SCI）. The correlation between brain anatomical changes and functional reorganization after SCI is unclear. This study aimed to explore whether alterations of cortical structure and network function are concomitant in sensorimotor areas after incomplete SCI. Eighteen patients with incomplete SCI（mean age 40.94 ± 14.10 years old; male：female, 7：11） and 18 healthy subjects（37.33 ± 11.79 years old; male：female, 7：11） were studied by resting state functional magnetic resonance imaging. Gray matter volume（GMV） and functional connectivity were used to evaluate cortical structure and network function, respectively. There was no significant alteration of GMV in sensorimotor areas in patients with incomplete SCI compared with healthy subjects. Intra-hemispheric functional connectivity between left primary somatosensory cortex（BA1） and left primary motor cortex（BA4）, and left BA1 and left somatosensory association cortex（BA5） was decreased, as well as inter-hemispheric functional connectivity between left BA1 and right BA4, left BA1 and right BA5, and left BA4 and right BA5 in patients with SCI. Functional connectivity between both BA4 areas was also decreased. The decreased functional connectivity between the left BA1 and the right BA4 positively correlated with American Spinal Injury Association sensory score in SCI patients. The results indicate that alterations of cortical anatomical structure and network functional connectivity in sensorimotor areas were non-concomitant in patients with incomplete SCI, indicating the network functional changes in sensorimotor areas may not be dependent on anatomic structure. The strength of functional connectivity within sensorimotor areas could serve as a potential imaging biomarker for assessment and prediction of sensory function in patients with incomplete SCI. This trial was registered with the Chinese Clinical Trial Registry（registration number： Chi CTR-ROC-17013566）.展开更多
The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas...The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.展开更多
Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patien...Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patients have been established,the mechanisms that drive these alterations remain incompletely understood.This study,which was conducted in 2018 at Northeastern University in China,included data from 97 participants of the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset covering genetics,imaging,and clinical data.All participants were divided into two groups:normal control(n=52;20 males and 32 females;mean age 73.90±4.72 years)and Alzheimer’s disease(n=45,23 males and 22 females;mean age 74.85±5.66).To uncover the wiring mechanisms that shaped changes in the topology of human brain networks of Alzheimer’s disease patients,we proposed a local naive Bayes brain network model based on graph theory.Our results showed that the proposed model provided an excellent fit to observe networks in all properties examined,including clustering coefficient,modularity,characteristic path length,network efficiency,betweenness,and degree distribution compared with empirical methods.This proposed model simulated the wiring changes in human brain networks between controls and Alzheimer’s disease patients.Our results demonstrate its utility in understanding relationships between brain tissue structure and cognitive or behavioral functions.The ADNI was performed in accordance with the Good Clinical Practice guidelines,US 21 CFR Part 50-Protection of Human Subjects,and Part 56-Institutional Review Boards(IRBs)/Research Good Clinical Practice guidelines Institutional Review Boards(IRBs)/Research Ethics Boards(REBs).展开更多
The structural and functional connectomes interact and depend on each other to jointly maintain the functioning of the brain and further support cognitive processing.Elucidating the complex interplay between the struc...The structural and functional connectomes interact and depend on each other to jointly maintain the functioning of the brain and further support cognitive processing.Elucidating the complex interplay between the structural connectome(SC)and functional connectome(FC)is one of the central challenges in network neuroscience.While previous studies have consistently reported SC-FC coupling or SC constraints on FC[1],[2],[3],they typically analyzed these networks in isolation.展开更多
RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and f...RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and facilitating the design of new RNAs.Machine learning(ML)techniques have made tremendous progress in many fields in the past few years.Although their usage in protein-related fields has a long history,the use of ML methods in predicting RNA tertiary structures is new and rare.Here,we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation,the difficulties and potentials of these approaches when applied in the field.展开更多
In this paper,an improved cut-based recursive decomposition algorithm is proposed for lifeline networks.First,a complementary structural function is established and three theorems are presented as a premise of the pro...In this paper,an improved cut-based recursive decomposition algorithm is proposed for lifeline networks.First,a complementary structural function is established and three theorems are presented as a premise of the proposed algorithm.Taking the minimal cut of a network as decomposition policy,the proposed algorithm constructs a recursive decomposition process.During the decomposition,both the disjoint minimal cut set and the disjoint minimal path set are simultaneously enumerated.Therefore,in addition to obtaining an accurate value after decomposing all disjoint minimal cuts and disjoint minimal paths,the algorithm provides approximate results which satisfy a prescribed error bound using a probabilistic inequality.Two example networks,including a large urban gas system,are analyzed using the proposed algorithm.Meanwhile,a part of the results are compared with the results obtained by a path-based recursive decomposition algorithm.These results show that the proposed algorithm provides a useful probabilistic analysis method for the reliability evaluation of lifeline networks and may be more suitable for networks where the edges have low reliabilities.展开更多
To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership functi...To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.展开更多
基金Project supported by the National Natural Science Foundation of China (Grant No. 71971150)the Project of Research Center for System Sciences and Enterprise Development (Grant No. Xq16B05)the Fundamental Research Funds for the Central Universities of China (Grant No. SXYPY202313)。
文摘As a key mode of transportation, urban metro networks have significantly enhanced urban traffic environments and travel efficiency, making the identification of critical stations within these networks increasingly essential. This study presents a novel integrated topological-functional(ITF) algorithm for identifying critical nodes, combining topological metrics such as K-shell decomposition, node information entropy, and neighbor overlapping interaction with the functional attributes of passenger flow operations, while also considering the coupling effects between metro and bus networks. Using the Chengdu metro network as a case study, the effectiveness of the algorithm under different conditions is validated.The results indicate significant differences in passenger flow patterns between working and non-working days, leading to varying sets of critical nodes across these scenarios. Moreover, the ITF algorithm demonstrates a marked improvement in the accuracy of critical node identification compared to existing methods. This conclusion is supported by the analysis of changes in the overall network structure and relative global operational efficiency following targeted attacks on the identified critical nodes. The findings provide valuable insight into urban transportation planning, offering theoretical and practical guidance for improving metro network safety and resilience.
文摘Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics.To address the limitations of existing methods,we propose a fault diagnosis method based on graph neural networks(GNNs)embedded with multirelationships of intrinsic mode functions(MIMF).The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions(IMFs)of monitored signals and their multirelationships.Additionally,a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices.Experimental validation with datasets including independent vibration signals for gear fault detection,mixed vibration signals for concurrent gear and bearing faults,and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.
基金supported by the National Natural Science Foundation of China,Nos.81671671(to JL),61971451(to JL),U22A2034(to XK),62177047(to XK)the National Defense Science and Technology Collaborative Innovation Major Project of Central South University,No.2021gfcx05(to JL)+6 种基金Clinical Research Cen terfor Medical Imaging of Hunan Province,No.2020SK4001(to JL)Key Emergency Project of Pneumonia Epidemic of Novel Coronavirus Infection of Hu nan Province,No.2020SK3006(to JL)Innovative Special Construction Foundation of Hunan Province,No.2019SK2131(to JL)the Science and Technology lnnovation Program of Hunan Province,Nos.2021RC4016(to JL),2021SK53503(to ML)Scientific Research Program of Hunan Commission of Health,No.202209044797(to JL)Central South University Research Program of Advanced Interdisciplinary Studies,No.2023Q YJC020(to XK)the Natural Science Foundation of Hunan Province,No.2022JJ30814(to ML)。
文摘Patients with mild traumatic brain injury have a diverse clinical presentation,and the underlying pathophysiology remains poorly understood.Magnetic resonance imaging is a non-invasive technique that has been widely utilized to investigate neuro biological markers after mild traumatic brain injury.This approach has emerged as a promising tool for investigating the pathogenesis of mild traumatic brain injury.G raph theory is a quantitative method of analyzing complex networks that has been widely used to study changes in brain structure and function.However,most previous mild traumatic brain injury studies using graph theory have focused on specific populations,with limited exploration of simultaneous abnormalities in structural and functional connectivity.Given that mild traumatic brain injury is the most common type of traumatic brain injury encounte red in clinical practice,further investigation of the patient characteristics and evolution of structural and functional connectivity is critical.In the present study,we explored whether abnormal structural and functional connectivity in the acute phase could serve as indicators of longitudinal changes in imaging data and cognitive function in patients with mild traumatic brain injury.In this longitudinal study,we enrolled 46 patients with mild traumatic brain injury who were assessed within 2 wee ks of injury,as well as 36 healthy controls.Resting-state functional magnetic resonance imaging and diffusion-weighted imaging data were acquired for graph theoretical network analysis.In the acute phase,patients with mild traumatic brain injury demonstrated reduced structural connectivity in the dorsal attention network.More than 3 months of followup data revealed signs of recovery in structural and functional connectivity,as well as cognitive function,in 22 out of the 46 patients.Furthermore,better cognitive function was associated with more efficient networks.Finally,our data indicated that small-worldness in the acute stage could serve as a predictor of longitudinal changes in connectivity in patients with mild traumatic brain injury.These findings highlight the importance of integrating structural and functional connectivity in unde rstanding the occurrence and evolution of mild traumatic brain injury.Additionally,exploratory analysis based on subnetworks could serve a predictive function in the prognosis of patients with mild traumatic brain injury.
基金supported by the National Natural Science Foundation of China(Nos.12072118 and12372029)。
文摘This paper presents the variational physics-informed neural network(VPINN)as an effective tool for static structural analyses.One key innovation includes the construction of the neural network solution as an admissible function of the boundary-value problem(BVP),which satisfies all geometrical boundary conditions.We then prove that the admissible neural network solution also satisfies natural boundary conditions,and therefore all boundary conditions,when the stationarity condition of the variational principle is met.Numerical examples are presented to show the advantages and effectiveness of the VPINN in comparison with the physics-informed neural network(PINN).Another contribution of the work is the introduction of Gaussian approximation of the Dirac delta function,which significantly enhances the ability of neural networks to handle singularities,as demonstrated by the examples with concentrated support conditions and loadings.It is hoped that these structural examples are so convincing that engineers would adopt the VPINN method in their structural design practice.
基金Supported by the Applied Basic Research Program of Liaoning Province,China(No.2023JH2/101300159)the National Natural Science Foundation of China(No.52275090).
文摘Rotating Space Slender Flexible Structures(RSSFS)are extensively utilized in space operations because of their light weight,mobility,and low energy consumption.To realize the accurate space operation of the RSSFS,it is necessary to establish a precise mechanical model and develop a control algorithm with high precision.However,with the application of traditional control strategies,the RSSFS often suffers from the chattering phenomenon,which will aggravate structure vibration.In this paper,novel deformation description is put forward to balance modeling accuracy and computational efficiency of the RSSFS,which is better appropriate for real-time control.Besides,the Neural Network Sliding Mode Control(NNSMC)strategy modified by the hyperbolic tangent(tanh)function is put forward to compensate for modeling errors and reduce the chattering phenomenon,thereby improving the trajectory tracking accuracy of the RSSFS.Firstly,a mathematical model for the RSSFS is developed according to the novel deformation description and the vibration theory of flexible structure.Comparison of the deformation accuracy between different models proves that the novel modeling method proposed has high modeling accuracy.Next,the universal approximation property of the Radial Basis Function(RBF)neural network is put forward to determine and compensate for modeling errors,which consist of higher-order modes and the uncertainties of external disturbances.In addition,the tanh function is proposed as the reaching law in the conventional NNSMC strategy to suppress driving torque oscillation.The control law of modified NNSMC strategy and the adaptive law of weight coefficients are developed according to the Lyapunov theorem to guarantee the RSSFS stability.Finally,the simulation and physical experimental tests of the RSSFS with different control strategies are conducted.Experimental results show that the control law according to the novel deformation description and the modified NNSMC strategy can obtain accurate tracking of the rotation and reduce the vibration of the RSSFS simultaneously.
文摘<div style="text-align:justify;"> <span style="font-family:Verdana;">Sensitivity analysis of neural networks to input variation is an important research area as it goes some way to addressing the criticisms of their black-box behaviour. Such analysis of RBFNs for hydrological modelling has previously been limited to exploring perturbations to both inputs and connecting weights. In this paper, the backward chaining rule that has been used for sensitivity analysis of MLPs, is applied to RBFNs and it is shown how such analysis can provide insight into physical relationships. A trigonometric example is first presented to show the effectiveness and accuracy of this approach for first order derivatives alongside a comparison of the results with an equivalent MLP. The paper presents a real-world application in the modelling of river stage shows the importance of such approaches helping to justify and select such models.</span> </div>
基金supported by the Natural Science Foundation of Sichuan Province of China,Nos.2022NSFSC1545 (to YG),2022NSFSC1387 (to ZF)the Natural Science Foundation of Chongqing of China,Nos.CSTB2022NSCQ-LZX0038,cstc2021ycjh-bgzxm0035 (both to XT)+3 种基金the National Natural Science Foundation of China,No.82001378 (to XT)the Joint Project of Chongqing Health Commission and Science and Technology Bureau,No.2023QNXM009 (to XT)the Science and Technology Research Program of Chongqing Education Commission of China,No.KJQN202200435 (to XT)the Chongqing Talents:Exceptional Young Talents Project,No.CQYC202005014 (to XT)。
文摘Epilepsy can be defined as a dysfunction of the brain network,and each type of epilepsy involves different brain-network changes that are implicated diffe rently in the control and propagation of interictal or ictal discharges.Gaining more detailed information on brain network alterations can help us to further understand the mechanisms of epilepsy and pave the way for brain network-based precise therapeutic approaches in clinical practice.An increasing number of advanced neuroimaging techniques and electrophysiological techniques such as diffusion tensor imaging-based fiber tra ctography,diffusion kurtosis imaging-based fiber tractography,fiber ball imagingbased tra ctography,electroencephalography,functional magnetic resonance imaging,magnetoencephalography,positron emission tomography,molecular imaging,and functional ultrasound imaging have been extensively used to delineate epileptic networks.In this review,we summarize the relevant neuroimaging and neuroelectrophysiological techniques for assessing structural and functional brain networks in patients with epilepsy,and extensively analyze the imaging mechanisms,advantages,limitations,and clinical application ranges of each technique.A greater focus on emerging advanced technologies,new data analysis software,a combination of multiple techniques,and the construction of personalized virtual epilepsy models can provide a theoretical basis to better understand the brain network mechanisms of epilepsy and make surgical decisions.
基金Under the auspices of Project of Western Light Related to Eastern Scholar, the National Natural Science Foundation of China (No. 40471134)
文摘Under the guide of system theory, taking the oasis in the Sangong River watershed as a case study, this paper analyzes the oasis structure and function from 4 aspects including oasis spatial structure, water resources structure, vegetation structure, economic structure and their corresponding functions. The results indicate that as a typical small-scale watershed, Sangong River watershed has the relatively complete mountain-basin structure, and ecological and productive function. Because of human drastic activity the utilization rate of water resources was as high as 98.7%, and the utilization of groundwater was not reasonable, which resulted in an average annual decline of 0.353m in the water table of alluvial-diluvial-fan oasis, and an average annual increase of 0.047m in the alluvial-plain. The layout of crop and shelter forest benefits to the utilization of water and land resources. The development of oasis economy is at low level, and its eco-economic function is weak.
基金Project supported by the National Natural Science Foundation of China (Gant No.11872323)。
文摘Many networks exhibit the core/periphery structure.Core/periphery structure is a type of meso-scale structure that consists of densely connected core nodes and sparsely connected peripheral nodes.Core nodes tend to be well-connected,both among themselves and to peripheral nodes,which tend not to be well-connected to other nodes.In this brief report,we propose a new method to detect the core of a network by the centrality of each node.It is discovered that such nodes with non-negative centralities often consist in the core of the networks.The simulation is carried out on different real networks.The results are checked by the objective function.The checked results may show the effectiveness of the simulation results by the centralities of the nodes on the real networks.Furthermore,we discuss the characters of networks with the single core/periphery structure and point out the scope of the application of our method at the end of this paper.
文摘Objective Using graph theory analysis,this study compares the topological and node attributes of the brain network to explore the differences in gray matter structural and functional network topological properties between bipolar depression(BD)patients with and without obsessive-compulsive symptoms(OCS).Methods A total of 90 BD patients(27 males,63 females;median age 19.0(22.0,25.0)years)were recruited from the psychiatric outpatient and inpatient departments of the First Affiliated Hospital of Jinan University between March 2018 and December 2022.Fifty healthy controls(19 males,31 females;median age:23.0(20.0,27.0)years)were also enrolled.The BD patients were divided into two groups based on the presence of OCS:53 with OCS(OCS group)and 37 without OCS(NOCS group).Resting-state structural and functional MRI data were collected for all participants to construct gray matter structural and functional networks.Graph therory analysis was aapplied to calculate network topological metrics such as small-world properties.The structural and functional network topological properties were compared among the BD-OCS,BD-nOCS,and control groups.Partial correlation analysis was conducted to examine the association between network topological metrics with significant group differences and Yale-Brown Obsessive-Compulsive Scale(Y-BOCS)scores.Support vector machines(SVM)were used with these metrics as classificationfeaturevalues toimproveediagnostic accuracy through pairwise group classification.Results Structural network analysis of gray matter:compared to HC group,both OCS group and NOCS group showed increasedshortesttpathlengthand standardized characteristic path length(shortest path length:0.78 and 0.80 vs.0.69;normalized characteristic path length:0.48 and 0.49 vs.0.43),and decreased global efficiency(0.21 and 0.21 vs.0.24)compared to the HC group(permutation test,all P<0.05).Compared to NOCS and HC groups,the OCS group showed increased nodal centrality and betweenness centrality in the right rolandic operculum and left superior occipital gyrus(permutation test,all P<0.05).Functional network analysis of gray matter:compared to the NOCS group,the OCS group showed increased node efficiency and decreased betweenness centrality in the cerebellum(t=2.15,-3.04;all P<0.05);compared to HC groups,the OCS group showed decreased betweenness centrality in the cerebellum and left inferior frontal gyrus,along with increased node centrality and nodal efficiency in the right transverse temporal gyrus(t=-2.99,-3.61,3.06,3.10;all P<0.05).In the 0CS group,betweenness centrality in the left inferior frontal gyrus positively correlated with Y-BOCS scale obsessive thinking score(r=0.303,P=0.034).Nodal centrality and node efficiency of the right transverse temporal gyrus negatively correlated with Y-BOCS total score(r=-0.301,-0.311)and Y-BOCS obsessional thinking scores(r=-0.385,-0.380)separately(all P<0.05).SVM classification:the combined network features achieved an area under the curve of 0.80 in distinguising OCS from NOCS patients.Conclusion BDOCS and BD-nOCS patients both exhibit consistent changes in gray matter structural network topology,with theOCSSgroup displaying more pronounced nodal topological abnormalities.Multi-network feature integration demostrates potential for diagnostic classfication.
基金support from the following institutional grant.Internal Grant Agency of the Faculty of Economics and Management,Czech University of Life Sciences Prague,grant no.2023A0004(https://iga.pef.czu.cz/,accessed on 6 June 2025).
文摘This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.
基金supported by the Science and Technology Project of Shaanxi Province Water Conservancy,China(2025slkj-10)the Natural Science Basic Research Program of Shaanxi Province,China(S2025-JC-QN-2416).
文摘The Wuding River Basin,situated in the Loess Plateau of northern China,is an ecologically fragile region facing severe soil erosion and imbalanced ecosystem service(ES)functions.However,the mechanisms driving the spatiotemporal evolution of ES functions,as well as the trade-offs and synergies among these functions,remain poorly understood,constraining effective watershed-scale management.To address this challenge,this study quantified four ES functions,i.e.,water yield(WY),carbon storage(CS),habitat quality(HQ),and soil conservation(SC)in the Wuding River Basin from 1990 to 2020 using the Integrated Valuation of Ecosystem Services and Tradeoff(InVEST)model,and proposed an innovative integration of InVEST with a Bayesian Belief Network(BBN)to nonlinearly identify trade-off and synergy relationships among ES functions through probabilistic inference.A trade-off and synergy index(TSI)was developed to assess the spatial interaction intensity among ES functions,while sensitivity and scenario analyses were employed to determine key driving factors,followed by spatial optimization to delineate functional zones.Results revealed distinct spatiotemporal variations:WY increased from 98.69 to 120.52 mm;SC rose to an average of 3.05×104 t/hm2;CS remained relatively stable(about 15.50 t/km2);and HQ averaged 0.51 with localized declines.The BBN achieved a high accuracy of 81.9%and effectively identified strong synergies between WY and SC,as well as between CS and HQ,while clear trade-offs were observed between WY and SC versus CS and HQ.Sensitivity analysis indicated precipitation(variance reduction of 9.4%),land use(9.8%),and vegetation cover(9.1%)as key driving factors.Spatial optimization further showed that core supply and ecological regulation zones are concentrated in the central-southern and southeastern basin,while ecological strengthening and optimization core zones dominate the central-northern and southeastern margins,highlighting strong spatial heterogeneity.Overall,this study advances ES research by combining process-based quantification with probabilistic modeling,offering a robust framework for studying nonlinear interactions,driving mechanisms,and optimization strategies,and providing a transferable paradigm for watershed-scale ES management and ecological planning in arid and semi-arid areas.
基金supported by the Water Conservancy Science and Technology Project of Jiangsu Province(Grant No.2012041)the Jiangsu Province Ordinary University Graduate Student Research Innovation Project(Grant No.CXZZ13_0256)
文摘In this study, we simulated water flow in a water conservancy project consisting of various hydraulic structures, such as sluices, pumping stations, hydropower stations, ship locks, and culverts, and developed a multi-period and multi-variable joint optimization scheduling model for flood control, drainage, and irrigation. In this model, the number of sluice holes, pump units, and hydropower station units to be opened were used as decision variables, and different optimization objectives and constraints were considered. This model was solved with improved genetic algorithms and verified using the Huaian Water Conservancy Project as an example. The results show that the use of the joint optimization scheduling led to a 10% increase in the power generation capacity and a 15% reduction in the total energy consumption. The change in the water level was reduced by 0.25 m upstream of the Yundong Sluice, and by 50% downstream of pumping stations No. 1, No. 2, and No. 4. It is clear that the joint optimization scheduling proposed in this study can effectively improve power generation capacity of the project, minimize operating costs and energy consumption, and enable more stable operation of various hydraulic structures. The results may provide references for the management of water conservancy projects in complex river networks.
基金supported by a grant from Tsinghua University Initiative Scientific Research Program,No.2014081266,20131089382the National Natural Science Foundation of China,No.61171002,60372023
文摘Brain plasticity, including anatomical changes and functional reorganization, is the physiological basis of functional recovery after spinal cord injury（SCI）. The correlation between brain anatomical changes and functional reorganization after SCI is unclear. This study aimed to explore whether alterations of cortical structure and network function are concomitant in sensorimotor areas after incomplete SCI. Eighteen patients with incomplete SCI（mean age 40.94 ± 14.10 years old; male：female, 7：11） and 18 healthy subjects（37.33 ± 11.79 years old; male：female, 7：11） were studied by resting state functional magnetic resonance imaging. Gray matter volume（GMV） and functional connectivity were used to evaluate cortical structure and network function, respectively. There was no significant alteration of GMV in sensorimotor areas in patients with incomplete SCI compared with healthy subjects. Intra-hemispheric functional connectivity between left primary somatosensory cortex（BA1） and left primary motor cortex（BA4）, and left BA1 and left somatosensory association cortex（BA5） was decreased, as well as inter-hemispheric functional connectivity between left BA1 and right BA4, left BA1 and right BA5, and left BA4 and right BA5 in patients with SCI. Functional connectivity between both BA4 areas was also decreased. The decreased functional connectivity between the left BA1 and the right BA4 positively correlated with American Spinal Injury Association sensory score in SCI patients. The results indicate that alterations of cortical anatomical structure and network functional connectivity in sensorimotor areas were non-concomitant in patients with incomplete SCI, indicating the network functional changes in sensorimotor areas may not be dependent on anatomic structure. The strength of functional connectivity within sensorimotor areas could serve as a potential imaging biomarker for assessment and prediction of sensory function in patients with incomplete SCI. This trial was registered with the Chinese Clinical Trial Registry（registration number： Chi CTR-ROC-17013566）.
基金supported by the National Natural Science Fundation of China (6097408261075055)the Fundamental Research Funds for the Central Universities (K50510700004)
文摘The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.
基金Fundamental Research Funds for the Central Universities in China,No.N161608001 and No.N171903002
文摘Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patients have been established,the mechanisms that drive these alterations remain incompletely understood.This study,which was conducted in 2018 at Northeastern University in China,included data from 97 participants of the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset covering genetics,imaging,and clinical data.All participants were divided into two groups:normal control(n=52;20 males and 32 females;mean age 73.90±4.72 years)and Alzheimer’s disease(n=45,23 males and 22 females;mean age 74.85±5.66).To uncover the wiring mechanisms that shaped changes in the topology of human brain networks of Alzheimer’s disease patients,we proposed a local naive Bayes brain network model based on graph theory.Our results showed that the proposed model provided an excellent fit to observe networks in all properties examined,including clustering coefficient,modularity,characteristic path length,network efficiency,betweenness,and degree distribution compared with empirical methods.This proposed model simulated the wiring changes in human brain networks between controls and Alzheimer’s disease patients.Our results demonstrate its utility in understanding relationships between brain tissue structure and cognitive or behavioral functions.The ADNI was performed in accordance with the Good Clinical Practice guidelines,US 21 CFR Part 50-Protection of Human Subjects,and Part 56-Institutional Review Boards(IRBs)/Research Good Clinical Practice guidelines Institutional Review Boards(IRBs)/Research Ethics Boards(REBs).
基金supported by the National Natural Science Foundation of China(82021004,82327807,and T24B2012)the Beijing Natural Science Foundation(JQ23033)the Fundamental Research Funds for the Central Universities(2233100018 and 2233300002).
文摘The structural and functional connectomes interact and depend on each other to jointly maintain the functioning of the brain and further support cognitive processing.Elucidating the complex interplay between the structural connectome(SC)and functional connectome(FC)is one of the central challenges in network neuroscience.While previous studies have consistently reported SC-FC coupling or SC constraints on FC[1],[2],[3],they typically analyzed these networks in isolation.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11774158,11974173,11774157,and 11934008)。
文摘RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and facilitating the design of new RNAs.Machine learning(ML)techniques have made tremendous progress in many fields in the past few years.Although their usage in protein-related fields has a long history,the use of ML methods in predicting RNA tertiary structures is new and rare.Here,we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation,the difficulties and potentials of these approaches when applied in the field.
基金Ministry of Science and Technology of China Under Grant No.SLDRCE09-B-12Natural Science Funds for Young Scholars of China Under Grant No.50808144
文摘In this paper,an improved cut-based recursive decomposition algorithm is proposed for lifeline networks.First,a complementary structural function is established and three theorems are presented as a premise of the proposed algorithm.Taking the minimal cut of a network as decomposition policy,the proposed algorithm constructs a recursive decomposition process.During the decomposition,both the disjoint minimal cut set and the disjoint minimal path set are simultaneously enumerated.Therefore,in addition to obtaining an accurate value after decomposing all disjoint minimal cuts and disjoint minimal paths,the algorithm provides approximate results which satisfy a prescribed error bound using a probabilistic inequality.Two example networks,including a large urban gas system,are analyzed using the proposed algorithm.Meanwhile,a part of the results are compared with the results obtained by a path-based recursive decomposition algorithm.These results show that the proposed algorithm provides a useful probabilistic analysis method for the reliability evaluation of lifeline networks and may be more suitable for networks where the edges have low reliabilities.
文摘To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.
