Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of am...Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of amyloidbeta(Aβ)and ta u accumulation-the molecular hallmarks of AD-structural magnetic resonance imaging(MRI),assessments of brain metabolism,and,more recently,blood-based markers),a definitive diagnosis of AD continues to be challenging.For example,Frisoni et al.展开更多
Transcranial direct current stimulation(tDCS)is a noninvasive technique that uses constant,low-intensity direct current to regulate brain activities.Clinical studies have shown that cathode-tDCS(c-tDCS)is effective in...Transcranial direct current stimulation(tDCS)is a noninvasive technique that uses constant,low-intensity direct current to regulate brain activities.Clinical studies have shown that cathode-tDCS(c-tDCS)is effective in reducing seizure frequency in patients with epilepsy.Due to the heterogeneity and patient specificity of seizures,patient-specific epilepsy networks are increasingly important in exploring the regulatory role of c-tDCS.In this study,we first set the left hippocampus,parahippocampus,and amygdala as the epileptogenic zone(EZ),and the left inferior temporal cortex and ventral temporal cortex as the initial propagation zone(PZ)to establish a large-scale epilepsy network model.Then we set tDCS cathode locations according to the maximum average energy of the simulated EEG signals and systematically study c-tDCS inhibitory effects on the propagation of epileptic activity.The results show that c-tDCS is effective in suppressing the propagation of epileptic activity.Further,to consider the patient specificity,we set specific EZ and PZ according to the clinical diagnosis of 6 patients and establish patient-specific epileptic networks.We find that c-tDCS can suppress the propagation of abnormal activity in most patient-specific epileptic networks.However,when the PZ is widely distributed in both hemispheres,the treatment effect of c-tDCS is not satisfactory.Hence,we propose dual-cathode tDCS.For epilepsy models with a wide distribution of PZ,it can inhibit the propagation of epileptiform activity in other nodes except EZ and PZ without increasing the tDCS current strength.Our results provide theoretical support for the treatment of epilepsy with tDCS.展开更多
It has been argued that the human brain,as an information-processing machine,operates near a phase transition point in a non-equilibrium state,where it violates detailed balance leading to entropy production.Thus,the ...It has been argued that the human brain,as an information-processing machine,operates near a phase transition point in a non-equilibrium state,where it violates detailed balance leading to entropy production.Thus,the assessment of irreversibility in brain networks can provide valuable insights into their non-equilibrium properties.In this study,we utilized an open-source whole-brain functional magnetic resonance imaging(fMRI)dataset from both resting and task states to evaluate the irreversibility of large-scale human brain networks.Our analysis revealed that the brain networks exhibited significant irreversibility,violating detailed balance,and generating entropy.Notably,both physical and cognitive tasks increased the extent of this violation compared to the resting state.Regardless of the state(rest or task),interactions between pairs of brain regions were the primary contributors to this irreversibility.Moreover,we observed that as global synchrony increased within brain networks,so did irreversibility.The first derivative of irreversibility with respect to synchronization peaked near the phase transition point,characterized by the moderate mean synchronization and maximized synchronization entropy of blood oxygenation level-dependent(BOLD)signals.These findings deepen our understanding of the non-equilibrium dynamics of large-scale brain networks,particularly in relation to their phase transition behaviors,and may have potential clinical applications for brain disorders.展开更多
The brain is organized as a complex network architecture, which can be mapped into structural(SC) and functional connectivity(FC) by advanced neuroimaging techniques. Achievements in brain network research have reveal...The brain is organized as a complex network architecture, which can be mapped into structural(SC) and functional connectivity(FC) by advanced neuroimaging techniques. Achievements in brain network research have revealed that modularity is a universal trait in brain networks and may be vital for cognitive segregation and integration. Large-scale brain network modeling is a promising computational approach to combine neuroimaging data with generative rules for brain dynamics. Recently, it has been proposed that chimera states, a type of dynamics referring to the coexistence of coherent and incoherent participants, have traits in common with cognitive functions like segregated and integrated brain processing. Previous studies have reported the existence of chimera-like dynamics in large-scale brain network models, whereas they did not account for the relationship between chimeralike dynamics and corresponding functional modular organizations of the brain network. By specifying qualitatively different network dynamics in an anatomically-constrained brain network model, we compare the different modular organizations of FC unfolded by network dynamics. Our simulations reveal that chimera-like dynamics support a meaningful pattern of functional modular organization, which promotes a diversity of node roles with a distributed pattern of functional cartography. The distinct node roles in modular FC are also found to occur with a spatial preference in speciflc brain regions, and, to some extent, reflect the underlying structure constraints. Our results support the view that chimera-like dynamics is a functionally meaningful scenario that may play a fundamental role in the segregation and integration of brain functioning.展开更多
A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a force...A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.展开更多
As a result of rapid development in electronics and communication technology,large-scale unmanned aerial vehicles(UAVs)are harnessed for various promising applications in a coordinated manner.Although it poses numerou...As a result of rapid development in electronics and communication technology,large-scale unmanned aerial vehicles(UAVs)are harnessed for various promising applications in a coordinated manner.Although it poses numerous advantages,resource management among various domains in large-scale UAV communication networks is the key challenge to be solved urgently.Specifically,due to the inherent requirements and future development trend,distributed resource management is suitable.In this article,we investigate the resource management problem for large-scale UAV communication networks from game-theoretic perspective which are exactly coincident with the distributed and autonomous manner.By exploring the inherent features,the distinctive challenges are discussed.Then,we explore several gametheoretic models that not only combat the challenges but also have broad application prospects.We provide the basics of each game-theoretic model and discuss the potential applications for resource management in large-scale UAV communication networks.Specifically,mean-field game,graphical game,Stackelberg game,coalition game and potential game are included.After that,we propose two innovative case studies to highlight the feasibility of such novel game-theoretic models.Finally,we give some future research directions to shed light on future opportunities and applications.展开更多
Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes.With the development of intelligent diagnosis in traditional Chinese medicine(TCM);artificial intelligence(AI)can improve ...Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes.With the development of intelligent diagnosis in traditional Chinese medicine(TCM);artificial intelligence(AI)can improve the accuracy and efficiency of eye diagnosis.However;the research on intelligent eye diagnosis still faces many challenges;including the lack of standardized and precisely labeled data;multi-modal information analysis;and artificial in-telligence models for syndrome differentiation.The widespread application of AI models in medicine provides new insights and opportunities for the research of eye diagnosis intelli-gence.This study elaborates on the three key technologies of AI models in the intelligent ap-plication of TCM eye diagnosis;and explores the implications for the research of eye diagno-sis intelligence.First;a database concerning eye diagnosis was established based on self-su-pervised learning so as to solve the issues related to the lack of standardized and precisely la-beled data.Next;the cross-modal understanding and generation of deep neural network models to address the problem of lacking multi-modal information analysis.Last;the build-ing of data-driven models for eye diagnosis to tackle the issue of the absence of syndrome dif-ferentiation models.In summary;research on intelligent eye diagnosis has great potential to be applied the surge of AI model applications.展开更多
The number of common neighbor between nodes is applied to the modeling of resting-state brain function network in order to analyze the effect of anatomical distance on the modeling of resting-state brain function netw...The number of common neighbor between nodes is applied to the modeling of resting-state brain function network in order to analyze the effect of anatomical distance on the modeling of resting-state brain function network. Three models based on anatomical distance, the number of common neighbor, or anatomical distance and the number of common neighbor are designed. Basing on residuals creates the evaluation criteria for selecting the optimal brain function model network in each class model. The model is selected to simulate the human real brain function network by comparison with real data functional magnetic resonance imaging(f MRI)network. Finally, the result shows that the best model only is based on anatomical distance.展开更多
A reduction in network energy consumption and the establishment of green networks have become key scientific problems in academic and industrial research.Existing energy efficiency schemes are based on a known traffic...A reduction in network energy consumption and the establishment of green networks have become key scientific problems in academic and industrial research.Existing energy efficiency schemes are based on a known traffic matrix,and acquiring a real-time traffic matrix in current complex networks is difficult.Therefore,this research investigates how to reduce network energy consumption without a real-time traffic matrix.In particular,this paper proposes an intra-domain energy-efficient routing scheme based on multipath routing.It analyzes the relationship between routing availability and energy-efficient routing and integrates the two mechanisms to satisfy the requirements of availability and energy efficiency.The main research focus is as follows:(1)A link criticality model is evaluated to quantitatively measure the importance of links in a network.(2)On the basis of the link criticality model,this paper analyzes an energy-efficient routing technology based on multipath routing to achieve the goals of availability and energy efficiency simultaneously.(3)An energy-efficient routing algorithm based on multipath routing in large-scale networks is proposed.(4)The proposed method does not require a real-time traffic matrix in the network and is thus easy to apply in practice.(5)The proposed algorithm is verified in several network topologies.Experimental results show that the algorithm can not only reduce network energy consumption but can also ensure routing availability.展开更多
In a large area of the east—central Asian continent there is a unified seismic network system composed of two families of large—seismic belts that intersect conjugately. Such a seismic network in the middle—upper c...In a large area of the east—central Asian continent there is a unified seismic network system composed of two families of large—seismic belts that intersect conjugately. Such a seismic network in the middle—upper crust is actually a response to the plastic flow network in the lower lithosphere including the lower crust and lithospheric mantle. The existence of the unified plastic flow system confirms that the driving force for intraplate tectonic deformation results mainly from the compression of the India plate, while the long-range transmission of the force is carried out chiefly by means of plastic flow. The plastic flow network has a control over the intraplate tectonic deformation.展开更多
Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and...Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.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
The purpose of the paper is to provide a way to model the brain functional network based on the complex networks with brain anatomical architecture. We introduce the brain structural and functional researches, and del...The purpose of the paper is to provide a way to model the brain functional network based on the complex networks with brain anatomical architecture. We introduce the brain structural and functional researches, and delineate the brain anatomical and functional networks based on complex networks, then we discuss the brain functional complex network models; at last we put forward the brain functional networks modeling process and the data processing with fMRI （functional magnetic resonance imaging） in detailed.展开更多
High-order Discontinuous Galerkin(DG) methods have been receiving more and more attentions in the area of Computational Fluid Dynamics(CFD) because of their high-accuracy property. However, it is still a challenge to ...High-order Discontinuous Galerkin(DG) methods have been receiving more and more attentions in the area of Computational Fluid Dynamics(CFD) because of their high-accuracy property. However, it is still a challenge to obtain converged solution rapidly when solving the Reynolds Averaged Navier–Stokes(RANS) equations since the turbulence models significantly increase the nonlinearity of discretization system. The overall goal of this research is to develop an Artificial Neural Networks(ANNs) model with low complexity acting as an algebraic turbulence model to estimate the turbulence eddy viscosity for RANS. The ANN turbulence model is off-line trained using the training data generated by the widely used Spalart–Allmaras(SA) turbulence model before the Optimal Brain Surgeon(OBS) is employed to determine the relevancy of input features.Using the selected relevant features, a fully connected ANN model is constructed. The performance of the developed ANN model is numerically tested in the framework of DG for RANS, where the‘‘DG+ANN' method provides robust and steady convergence compared to the ‘‘DG+SA' method. The results demonstrate the promising potential to develop a general turbulence model based on artificial intelligence in the future given the training data covering a large rang of flow conditions.展开更多
At the level of in vitro drug screening,the development of a phenotypic analysis system with highcontent screening at the core provides a strong platform to support high-throughput drug screening.There are few systema...At the level of in vitro drug screening,the development of a phenotypic analysis system with highcontent screening at the core provides a strong platform to support high-throughput drug screening.There are few systematic reports on brain organoids,as a new three-dimensional in vitro model,in terms of model stability,key phenotypic fingerprint,and drug screening schemes,and particula rly rega rding the development of screening strategies for massive numbers of traditional Chinese medicine monomers.This paper reviews the development of brain organoids and the advantages of brain organoids over induced neurons or cells in simulated diseases.The paper also highlights the prospects from model stability,induction criteria of brain organoids,and the screening schemes of brain organoids based on the characteristics of brain organoids and the application and development of a high-content screening system.展开更多
A Mechanism-Inferring method of networks exploited from machine learning theory caneffectively evaluate the predicting performance of a network model.The existing method for inferringnetwork mechanisms based on a cens...A Mechanism-Inferring method of networks exploited from machine learning theory caneffectively evaluate the predicting performance of a network model.The existing method for inferringnetwork mechanisms based on a census of subgraph numbers has some drawbacks,especially the needfor a runtime increasing strongly with network size and network density.In this paper,an improvedmethod has been proposed by introducing a census algorithm of subgraph concentrations.Networkmechanism can be quickly inferred by the new method even though the network has large scale andhigh density.Therefore,the application perspective of mechanism-inferring method has been extendedinto the wider fields of large-scale complex networks.By applying the new method to a case of proteininteraction network,the authors obtain the same inferring result as the existing method,which approvesthe effectiveness of the method.展开更多
文摘Advances in Alzheimer's disease(AD)research have deepened our understanding,yet the mechanisms driving its progression remain unclear.Although a range of in vivo biomarkers is now available(e.g.,measurements of amyloidbeta(Aβ)and ta u accumulation-the molecular hallmarks of AD-structural magnetic resonance imaging(MRI),assessments of brain metabolism,and,more recently,blood-based markers),a definitive diagnosis of AD continues to be challenging.For example,Frisoni et al.
基金supported by the National Natural Science Foundation of China (Grant Nos.12202027,11932003,12272092,11972115)the China Postdoctoral Science Foundation (Grant No.2021TQ0025)。
文摘Transcranial direct current stimulation(tDCS)is a noninvasive technique that uses constant,low-intensity direct current to regulate brain activities.Clinical studies have shown that cathode-tDCS(c-tDCS)is effective in reducing seizure frequency in patients with epilepsy.Due to the heterogeneity and patient specificity of seizures,patient-specific epilepsy networks are increasingly important in exploring the regulatory role of c-tDCS.In this study,we first set the left hippocampus,parahippocampus,and amygdala as the epileptogenic zone(EZ),and the left inferior temporal cortex and ventral temporal cortex as the initial propagation zone(PZ)to establish a large-scale epilepsy network model.Then we set tDCS cathode locations according to the maximum average energy of the simulated EEG signals and systematically study c-tDCS inhibitory effects on the propagation of epileptic activity.The results show that c-tDCS is effective in suppressing the propagation of epileptic activity.Further,to consider the patient specificity,we set specific EZ and PZ according to the clinical diagnosis of 6 patients and establish patient-specific epileptic networks.We find that c-tDCS can suppress the propagation of abnormal activity in most patient-specific epileptic networks.However,when the PZ is widely distributed in both hemispheres,the treatment effect of c-tDCS is not satisfactory.Hence,we propose dual-cathode tDCS.For epilepsy models with a wide distribution of PZ,it can inhibit the propagation of epileptiform activity in other nodes except EZ and PZ without increasing the tDCS current strength.Our results provide theoretical support for the treatment of epilepsy with tDCS.
基金supported by the Fundamental Research Funds for the Central Universities(Grant Nos.lzujbky-2021-62 and lzujbky-2024-jdzx06)the National Natural Science Foundation of China(Grant No.12247101)+1 种基金the Natural Science Foundation of Gansu Province,China(Grant Nos.22JR5RA389 and 23JRRA1740)the‘111 Center’Fund(Grant No.B20063).
文摘It has been argued that the human brain,as an information-processing machine,operates near a phase transition point in a non-equilibrium state,where it violates detailed balance leading to entropy production.Thus,the assessment of irreversibility in brain networks can provide valuable insights into their non-equilibrium properties.In this study,we utilized an open-source whole-brain functional magnetic resonance imaging(fMRI)dataset from both resting and task states to evaluate the irreversibility of large-scale human brain networks.Our analysis revealed that the brain networks exhibited significant irreversibility,violating detailed balance,and generating entropy.Notably,both physical and cognitive tasks increased the extent of this violation compared to the resting state.Regardless of the state(rest or task),interactions between pairs of brain regions were the primary contributors to this irreversibility.Moreover,we observed that as global synchrony increased within brain networks,so did irreversibility.The first derivative of irreversibility with respect to synchronization peaked near the phase transition point,characterized by the moderate mean synchronization and maximized synchronization entropy of blood oxygenation level-dependent(BOLD)signals.These findings deepen our understanding of the non-equilibrium dynamics of large-scale brain networks,particularly in relation to their phase transition behaviors,and may have potential clinical applications for brain disorders.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11932003 and 11972115)。
文摘The brain is organized as a complex network architecture, which can be mapped into structural(SC) and functional connectivity(FC) by advanced neuroimaging techniques. Achievements in brain network research have revealed that modularity is a universal trait in brain networks and may be vital for cognitive segregation and integration. Large-scale brain network modeling is a promising computational approach to combine neuroimaging data with generative rules for brain dynamics. Recently, it has been proposed that chimera states, a type of dynamics referring to the coexistence of coherent and incoherent participants, have traits in common with cognitive functions like segregated and integrated brain processing. Previous studies have reported the existence of chimera-like dynamics in large-scale brain network models, whereas they did not account for the relationship between chimeralike dynamics and corresponding functional modular organizations of the brain network. By specifying qualitatively different network dynamics in an anatomically-constrained brain network model, we compare the different modular organizations of FC unfolded by network dynamics. Our simulations reveal that chimera-like dynamics support a meaningful pattern of functional modular organization, which promotes a diversity of node roles with a distributed pattern of functional cartography. The distinct node roles in modular FC are also found to occur with a spatial preference in speciflc brain regions, and, to some extent, reflect the underlying structure constraints. Our results support the view that chimera-like dynamics is a functionally meaningful scenario that may play a fundamental role in the segregation and integration of brain functioning.
基金supported by the Ministry of Trade,Industry & Energy(MOTIE,Korea) under Industrial Technology Innovation Program (No.10063424,'development of distant speech recognition and multi-task dialog processing technologies for in-door conversational robots')
文摘A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.
基金This work was supported by National Key R&D Program of China under Grant 2018YFB1800802in part by the National Natural Science Foundation of China under Grant No.61771488,No.61631020 and No.61827801+1 种基金in part by State Key Laboratory of Air Traffic Management System and Technology under Grant No.SKLATM201808in part by Postgraduate Research and Practice Innovation Program of Jiangsu Province under No.KYCX190188.
文摘As a result of rapid development in electronics and communication technology,large-scale unmanned aerial vehicles(UAVs)are harnessed for various promising applications in a coordinated manner.Although it poses numerous advantages,resource management among various domains in large-scale UAV communication networks is the key challenge to be solved urgently.Specifically,due to the inherent requirements and future development trend,distributed resource management is suitable.In this article,we investigate the resource management problem for large-scale UAV communication networks from game-theoretic perspective which are exactly coincident with the distributed and autonomous manner.By exploring the inherent features,the distinctive challenges are discussed.Then,we explore several gametheoretic models that not only combat the challenges but also have broad application prospects.We provide the basics of each game-theoretic model and discuss the potential applications for resource management in large-scale UAV communication networks.Specifically,mean-field game,graphical game,Stackelberg game,coalition game and potential game are included.After that,we propose two innovative case studies to highlight the feasibility of such novel game-theoretic models.Finally,we give some future research directions to shed light on future opportunities and applications.
基金National Natural Science Foundation of China(82274265 and 82274588)Hunan University of Traditional Chinese Medicine Research Unveiled Marshal Programs(2022XJJB003).
文摘Eye diagnosis is a method for inspecting systemic diseases and syndromes by observing the eyes.With the development of intelligent diagnosis in traditional Chinese medicine(TCM);artificial intelligence(AI)can improve the accuracy and efficiency of eye diagnosis.However;the research on intelligent eye diagnosis still faces many challenges;including the lack of standardized and precisely labeled data;multi-modal information analysis;and artificial in-telligence models for syndrome differentiation.The widespread application of AI models in medicine provides new insights and opportunities for the research of eye diagnosis intelli-gence.This study elaborates on the three key technologies of AI models in the intelligent ap-plication of TCM eye diagnosis;and explores the implications for the research of eye diagno-sis intelligence.First;a database concerning eye diagnosis was established based on self-su-pervised learning so as to solve the issues related to the lack of standardized and precisely la-beled data.Next;the cross-modal understanding and generation of deep neural network models to address the problem of lacking multi-modal information analysis.Last;the build-ing of data-driven models for eye diagnosis to tackle the issue of the absence of syndrome dif-ferentiation models.In summary;research on intelligent eye diagnosis has great potential to be applied the surge of AI model applications.
基金the National Natural Science Foundation of China(Nos.6117013661373101+3 种基金61472270 and61402318)the Natural Science Foundation of Shanxi(No.2014021022-5)the Special/Youth Foundation of Taiyuan University of Technology(No.2012L014)the Youth Team Fund of Taiyuan University of Technology(Nos.2013T047 and 2013T048)
文摘The number of common neighbor between nodes is applied to the modeling of resting-state brain function network in order to analyze the effect of anatomical distance on the modeling of resting-state brain function network. Three models based on anatomical distance, the number of common neighbor, or anatomical distance and the number of common neighbor are designed. Basing on residuals creates the evaluation criteria for selecting the optimal brain function model network in each class model. The model is selected to simulate the human real brain function network by comparison with real data functional magnetic resonance imaging(f MRI)network. Finally, the result shows that the best model only is based on anatomical distance.
基金supported by the Program of Hainan Association for Science and Technology Plans to Youth R&D Innovation(QCXM201910)the National Natural Science Foundation of China(Nos.61702315,61802092)+1 种基金the Applied Basic Research Plan of Shanxi Province(No.2201901D211168)the Key R&D Program(International Science and Technology Cooperation Project)of Shanxi Province China(No.201903D421003).
文摘A reduction in network energy consumption and the establishment of green networks have become key scientific problems in academic and industrial research.Existing energy efficiency schemes are based on a known traffic matrix,and acquiring a real-time traffic matrix in current complex networks is difficult.Therefore,this research investigates how to reduce network energy consumption without a real-time traffic matrix.In particular,this paper proposes an intra-domain energy-efficient routing scheme based on multipath routing.It analyzes the relationship between routing availability and energy-efficient routing and integrates the two mechanisms to satisfy the requirements of availability and energy efficiency.The main research focus is as follows:(1)A link criticality model is evaluated to quantitatively measure the importance of links in a network.(2)On the basis of the link criticality model,this paper analyzes an energy-efficient routing technology based on multipath routing to achieve the goals of availability and energy efficiency simultaneously.(3)An energy-efficient routing algorithm based on multipath routing in large-scale networks is proposed.(4)The proposed method does not require a real-time traffic matrix in the network and is thus easy to apply in practice.(5)The proposed algorithm is verified in several network topologies.Experimental results show that the algorithm can not only reduce network energy consumption but can also ensure routing availability.
基金This project (No. 49070196) is funded by the National Science Foundation of China.
文摘In a large area of the east—central Asian continent there is a unified seismic network system composed of two families of large—seismic belts that intersect conjugately. Such a seismic network in the middle—upper crust is actually a response to the plastic flow network in the lower lithosphere including the lower crust and lithospheric mantle. The existence of the unified plastic flow system confirms that the driving force for intraplate tectonic deformation results mainly from the compression of the India plate, while the long-range transmission of the force is carried out chiefly by means of plastic flow. The plastic flow network has a control over the intraplate tectonic deformation.
基金This work was supported by the National Key Research and Development Program of China(2018YFC2001302)National Natural Science Foundation of China(91520202)+2 种基金Chinese Academy of Sciences Scientific Equipment Development Project(YJKYYQ20170050)Beijing Municipal Science and Technology Commission(Z181100008918010)Youth Innovation Promotion Association of Chinese Academy of Sciences,and Strategic Priority Research Program of Chinese Academy of Sciences(XDB32040200).
文摘Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.
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The authors thank the College of Information and Engineering Taishan Medical University colleagues for assistance with data collection and the manuscript comments. Special thanks to Polly and Xiaochen Xu for suggestions on writing in the English language. The authors are grateful to the anonymous referees for their valuable comments and suggestions. This research was supported by the Natural Science Foundation of Shandong （No. ZR2013FL031）, State Accident Prevention Key Technology of Work Safety Program （No. 2013-084）, Work Safety Science Technology Development Program of Shandong （No. LAJK2013-137）, High-level Training Project of Taishan Medical University （No. 2013GCC09）.
文摘The purpose of the paper is to provide a way to model the brain functional network based on the complex networks with brain anatomical architecture. We introduce the brain structural and functional researches, and delineate the brain anatomical and functional networks based on complex networks, then we discuss the brain functional complex network models; at last we put forward the brain functional networks modeling process and the data processing with fMRI （functional magnetic resonance imaging） in detailed.
基金co-supported by the Aeronautical Science Foundation of China (Nos. 20151452021and 20152752033)the National Natural Science Foundation of China (No. 61732006)
文摘High-order Discontinuous Galerkin(DG) methods have been receiving more and more attentions in the area of Computational Fluid Dynamics(CFD) because of their high-accuracy property. However, it is still a challenge to obtain converged solution rapidly when solving the Reynolds Averaged Navier–Stokes(RANS) equations since the turbulence models significantly increase the nonlinearity of discretization system. The overall goal of this research is to develop an Artificial Neural Networks(ANNs) model with low complexity acting as an algebraic turbulence model to estimate the turbulence eddy viscosity for RANS. The ANN turbulence model is off-line trained using the training data generated by the widely used Spalart–Allmaras(SA) turbulence model before the Optimal Brain Surgeon(OBS) is employed to determine the relevancy of input features.Using the selected relevant features, a fully connected ANN model is constructed. The performance of the developed ANN model is numerically tested in the framework of DG for RANS, where the‘‘DG+ANN' method provides robust and steady convergence compared to the ‘‘DG+SA' method. The results demonstrate the promising potential to develop a general turbulence model based on artificial intelligence in the future given the training data covering a large rang of flow conditions.
基金supported by the National Natural Science Foundation of China,No.32000498the Startup Funding of Zhejiang University City College,No.210000-581849 (both to CG)National College Students’Innovative Entrepreneurial Training Plan Program,No.2021 13021024 (to JQZ)。
文摘At the level of in vitro drug screening,the development of a phenotypic analysis system with highcontent screening at the core provides a strong platform to support high-throughput drug screening.There are few systematic reports on brain organoids,as a new three-dimensional in vitro model,in terms of model stability,key phenotypic fingerprint,and drug screening schemes,and particula rly rega rding the development of screening strategies for massive numbers of traditional Chinese medicine monomers.This paper reviews the development of brain organoids and the advantages of brain organoids over induced neurons or cells in simulated diseases.The paper also highlights the prospects from model stability,induction criteria of brain organoids,and the screening schemes of brain organoids based on the characteristics of brain organoids and the application and development of a high-content screening system.
基金supported by the National Natural Science Foundation of China under Grant No. 70401019
文摘A Mechanism-Inferring method of networks exploited from machine learning theory caneffectively evaluate the predicting performance of a network model.The existing method for inferringnetwork mechanisms based on a census of subgraph numbers has some drawbacks,especially the needfor a runtime increasing strongly with network size and network density.In this paper,an improvedmethod has been proposed by introducing a census algorithm of subgraph concentrations.Networkmechanism can be quickly inferred by the new method even though the network has large scale andhigh density.Therefore,the application perspective of mechanism-inferring method has been extendedinto the wider fields of large-scale complex networks.By applying the new method to a case of proteininteraction network,the authors obtain the same inferring result as the existing method,which approvesthe effectiveness of the method.
