The mechanistic target of rapamycin(m TOR) is a serine/threonine kinase that plays a pivotal role in cellular growth, proliferation, survival, and metabolism. In the central nervous system(CNS), the mTOR pathway regul...The mechanistic target of rapamycin(m TOR) is a serine/threonine kinase that plays a pivotal role in cellular growth, proliferation, survival, and metabolism. In the central nervous system(CNS), the mTOR pathway regulates diverse aspects of neural development and function. Genetic mutations within the m TOR pathway lead to severe neurodevelopmental disorders, collectively known as “mTORopathies”(Crino, 2020). Dysfunctions of m TOR, including both its hyperactivation and hypoactivation, have also been implicated in a wide spectrum of other neurodevelopmental and neurodegenerative conditions, highlighting its importance in CNS health.展开更多
Spinal cord injury results in permanent loss of neurological functions due to severance of neural networks.Transplantation of neural stem cells holds promise to repair disrupted connections.Yet,ensuring the survival a...Spinal cord injury results in permanent loss of neurological functions due to severance of neural networks.Transplantation of neural stem cells holds promise to repair disrupted connections.Yet,ensuring the survival and integration of neural stem cells into the host neural circuit remains a formidable challenge.Here,we investigated whether modifying the intrinsic properties of neural stem cells could enhance their integration post-transplantation.We focused on phosphatase and tensin homolog(PTEN),a well-characterized tumor suppressor known to critically regulate neuronal survival and axonal regeneration.By deleting Pten in mouse neural stem cells,we observed increased neurite outgrowth and enhanced resistance to neurotoxic environments in culture.Upon transplantation into injured spinal cords,Pten-deficient neural stem cells exhibited higher survival and more extensive rostrocaudal distribution.To examine the potential influence of partial PTEN suppression,rat neural stem cells were treated with short hairpin RNA targeting PTEN,and the PTEN knockdown resulted in significant improvements in neurite growth,survival,and neurosphere motility in vitro.Transplantation of sh PTEN-treated neural stem cells into the injured spinal cord also led to an increase in graft survival and migration to an extent similar to that of complete deletion.Moreover,PTEN suppression facilitated neurite elongation from NSC-derived neurons migrating from the lesion epicenter.These findings suggest that modifying intrinsic signaling pathways,such as PTEN,within neural stem cells could bolster their therapeutic efficacy,offering potential avenues for future regenerative strategies for spinal cord injury.展开更多
After spinal cord injury,impairment of the sensorimotor circuit can lead to dysfunction in the motor,sensory,proprioceptive,and autonomic nervous systems.Functional recovery is often hindered by constraints on the tim...After spinal cord injury,impairment of the sensorimotor circuit can lead to dysfunction in the motor,sensory,proprioceptive,and autonomic nervous systems.Functional recovery is often hindered by constraints on the timing of interventions,combined with the limitations of current methods.To address these challenges,various techniques have been developed to aid in the repair and reconstruction of neural circuits at different stages of injury.Notably,neuromodulation has garnered considerable attention for its potential to enhance nerve regeneration,provide neuroprotection,restore neurons,and regulate the neural reorganization of circuits within the cerebral cortex and corticospinal tract.To improve the effectiveness of these interventions,the implementation of multitarget early interventional neuromodulation strategies,such as electrical and magnetic stimulation,is recommended to enhance functional recovery across different phases of nerve injury.This review concisely outlines the challenges encountered following spinal cord injury,synthesizes existing neurostimulation techniques while emphasizing neuroprotection,repair,and regeneration of impaired connections,and advocates for multi-targeted,task-oriented,and timely interventions.展开更多
Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon...Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon-based readout circuits in a single step.Based on this,we propose a photodiode based on an n-i-p structure,which removes the buffer layer and further simplifies the manufacturing process of quantum dot image sensors,thus reducing manufacturing costs.Additionally,for the noise complexity in quantum dot image sensors when capturing images,traditional denoising and non-uniformity methods often do not achieve optimal denoising re⁃sults.For the noise and stripe-type non-uniformity commonly encountered in infrared quantum dot detector imag⁃es,a network architecture has been developed that incorporates multiple key modules.This network combines channel attention and spatial attention mechanisms,dynamically adjusting the importance of feature maps to en⁃hance the ability to distinguish between noise and details.Meanwhile,the residual dense feature fusion module further improves the network's ability to process complex image structures through hierarchical feature extraction and fusion.Furthermore,the pyramid pooling module effectively captures information at different scales,improv⁃ing the network's multi-scale feature representation ability.Through the collaborative effect of these modules,the network can better handle various mixed noise and image non-uniformity issues.Experimental results show that it outperforms the traditional U-Net network in denoising and image correction tasks.展开更多
Deep learning has become integral to robotics,particularly in tasks such as robotic grasping,where objects often exhibit diverse shapes,textures,and physical properties.In robotic grasping tasks,due to the diverse cha...Deep learning has become integral to robotics,particularly in tasks such as robotic grasping,where objects often exhibit diverse shapes,textures,and physical properties.In robotic grasping tasks,due to the diverse characteristics of the targets,frequent adjustments to the network architecture and parameters are required to avoid a decrease in model accuracy,which presents a significant challenge for non-experts.Neural Architecture Search(NAS)provides a compelling method through the automated generation of network architectures,enabling the discovery of models that achieve high accuracy through efficient search algorithms.Compared to manually designed networks,NAS methods can significantly reduce design costs,time expenditure,and improve model performance.However,such methods often involve complex topological connections,and these redundant structures can severely reduce computational efficiency.To overcome this challenge,this work puts forward a robotic grasp detection framework founded on NAS.The method automatically designs a lightweight network with high accuracy and low topological complexity,effectively adapting to the target object to generate the optimal grasp pose,thereby significantly improving the success rate of robotic grasping.Additionally,we use Class Activation Mapping(CAM)as an interpretability tool,which captures sensitive information during the perception process through visualized results.The searched model achieved competitive,and in some cases superior,performance on the Cornell and Jacquard public datasets,achieving accuracies of 98.3%and 96.8%,respectively,while sustaining a detection speed of 89 frames per second with only 0.41 million parameters.To further validate its effectiveness beyond benchmark evaluations,we conducted real-world grasping experiments on a UR5 robotic arm,where the model demonstrated reliable performance across diverse objects and high grasp success rates,thereby confirming its practical applicability in robotic manipulation tasks.展开更多
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
The hippocampus is part of the brain limbic system and plays an important role in learning and memory.Moreover,its ability to form,consolidate,and retrieve different types of memories makes it a central component in t...The hippocampus is part of the brain limbic system and plays an important role in learning and memory.Moreover,its ability to form,consolidate,and retrieve different types of memories makes it a central component in the cognitive functions necessary for everyday life.Understanding the role of the hippocampus helps comprehend how memories are created,stored,and recalled and sheds light on the impact of hippocampal damage in conditions such as Alzheimer’s disease and other forms of dementia.展开更多
Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving g...Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving graph learning.However,its application often diminishes data utility,especially for nodes with fewer neighbors in graph neural networks(GNNs).展开更多
Neural stem cells(NSCs)and glioblastoma stem cells(GSCs)share a complex regulatory landscape in which cholinergic signaling plays a pivotal role in both neural development and tumor progression.While acetylcholine(ACh...Neural stem cells(NSCs)and glioblastoma stem cells(GSCs)share a complex regulatory landscape in which cholinergic signaling plays a pivotal role in both neural development and tumor progression.While acetylcholine(ACh)regulates NSC quiescence and differentiation within neurogenic niches,glioblastoma cells exploit th ese pathways to enhance their adaptability and invasiveness.The involvement of muscarinic(M3)and nicotinic(α7)receptors in both cell types suggests that glioblastoma retains neural progenitor-like traits,contributing to its plasticity and resilience.This article explores the shared cholinergic mechanisms between NSCs and GSCs,highlighting their role in both neural development and glioblastoma progression.展开更多
The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a n...The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a necessary step before their practical application.As these investigations are time and resource-consuming undertakings,an effective prediction model can significantly improve the efficiency of research operations.In this work,an Artificial Neural Network(ANN)model is developed to predict the thermal conductivity of metal oxide water-based nanofluid.For this,a comprehensive set of 691 data points was collected from the literature.This dataset is split into training(70%),validation(15%),and testing(15%)and used to train the ANN model.The developed model is a backpropagation artificial neural network with a 4–12–1 architecture.The performance of the developed model shows high accuracy with R values above 0.90 and rapid convergence.It shows that the developed ANN model accurately predicts the thermal conductivity of nanofluids.展开更多
This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination me...This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.展开更多
While neural radiance field(NeRF)methods have shown promising results in generating talking faces,existing studies primarily focus on the correlation between avatars and driving sources.However,these studies often ove...While neural radiance field(NeRF)methods have shown promising results in generating talking faces,existing studies primarily focus on the correlation between avatars and driving sources.However,these studies often overlook emotion modeling,resulting in the generation of emotionless or unnatural facial animations.In response,this paper introduces an audio-driven and emotion-editing dynamic NeRF(AED-NeRF)approach,designed for the real-time generation of expressive talking face avatars driven by audio inputs.Specifically,we integrate audio features into a grid-based NeRF to compensate for the lack of a deformation channel,successfully capturing lip dynamics and enabling end-to-end generation from audio-driven sources to talking face avatars.Emotion labels,comprising emotion categories and intensity levels,guide the proposed NeRF framework to implicitly model visual emotions,allowing for explicit control and editing of facial expressions.Extensive qualitative and quantitative experiments validate the effectiveness and advantages of our proposed method,demonstrating its ability to achieve real-time,photo-realistic talking face avatar generation across different audio and emotion scenarios.展开更多
In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in...In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.展开更多
Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequ...Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequently,the academic community has devoted increasing attention to these security risks.However,conventional approaches to vulnerability detection frequently exhibit limited accuracy.To address this limitation,the present study introduces a novel vulnerability detection framework called GNNSE that integrates symbolic execution with graph neural networks(GNNs).The proposedmethod first constructs semantic graphs to comprehensively capture the control flow and data flow dependencies within smart contracts.These graphs are subsequently processed using GNNs to efficiently identify contracts with a high likelihood of vulnerabilities.For these high-risk contracts,symbolic execution is employed to perform fine-grained,path-level analysis,thereby improving overall detection precision.Experimental results on a dataset comprising 10,079 contracts demonstrate that the proposed method achieves detection precisions of 93.58% for reentrancy vulnerabilities and 92.73% for timestamp-dependent vulnerabilities.展开更多
The development of β-titanium alloys with bone-mimicking elastic moduli remains a significant challenge.Although machine learning has the potential to accelerate alloy discovery,traditional methods often face data li...The development of β-titanium alloys with bone-mimicking elastic moduli remains a significant challenge.Although machine learning has the potential to accelerate alloy discovery,traditional methods often face data limitations such as sparsity,compositional discontinuity,and feature heterogeneity,leading to overfitting and restricting the exploration of novel compositional spaces.In this study,we introduce a domain-adversarial neural network framework that balances predictive accuracy with the generalization ability of unexplored composition space through integrated feature alignment and adversarial training.Using this approach,we successfully developed a non-intuitiveβ-Ti alloy with an ultra-low elastic modulus of 28±3 GPa,providing new insights beyond conventionally designed biomedical titanium alloys.This work establishes a screening framework for materials discovery in small-sample data spaces,with broad implications for the design of biomedical and other alloy systems.展开更多
The development of non-invasive brain-computer interfaces(BCIs)relies on multidisciplinary integration across neuroscience,artificial intelligence,flexible electronics,and systems engineering.Recent advances in deep l...The development of non-invasive brain-computer interfaces(BCIs)relies on multidisciplinary integration across neuroscience,artificial intelligence,flexible electronics,and systems engineering.Recent advances in deep learning have significantly improved the accuracy and robustness of neural signal decoding.Parallel progress in electrode design—particularly through the use of flexible and stretchable materials like nanostructured conductors and novel fabrication strategies—has enhanced wearability and operational stability.Nevertheless,key challenges persist,including individual variability,biocompatibility limitations,and susceptibility to interference in complex environments.Further validation and optimization are needed to address gaps in generalization capability,long-term reliability,and real-world operational robustness.This review systematically examines the representative progress in neural decoding algorithms and flexible bioelectronic platforms over the past decade,highlighting key design principles,material innovations,and integration strategies that are poised to advance non-invasive BCI capabilities.It also discusses the importance of multimodal data fusion,hardware-software co-optimization,and closed-loop control strategies.Furthermore,the review discusses the application potential and associated engineering challenges of this technology in clinical rehabilitation and industrial translation,aiming to provide a reference for advancing non-invasive BCIs toward practical and scalable deployment.展开更多
Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(...Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(CSI)as real-valued inputs,potentially discarding useful information embedded in the original CSI.In addition,existing positioning models generally face the contradiction between computational complexity and positioning accuracy.To address these issues,we combine graph neural network(GNN)with complex-valued neural network(CVNN)to construct a lightweight indoor positioning model named CGNet.CGNet employs complexvalued convolution operation to directly process the original CSI data,fully exploiting the correlation between real and imaginary parts of CSI while extracting local features.Subsequently,the feature values are treated as nodes,and conditional position encoding(CPE)module is applied to add positional information.To reduce the number of connections in the graph structure and lower themodel complexity,feature information is mapped to an efficient graph structure through a dynamic axial graph construction(DAGC)method,with global features extracted usingmaximum relative graph convolution(MRConv).Experimental results show that,on the CTW dataset,CGNet achieves a 10%improvement in positioning accuracy compared to existing methods,while the number of model parameters is only 0.8 M.CGNet achieves excellent positioning accuracy with very few parameters.展开更多
The adult subventricular zone of the lateral ventricles and the subgranular zone in the hippocampal dentate gyrus(DG)are the two brain regions where neurogenesis occurs throughout life in the adult mammalian brain(Min...The adult subventricular zone of the lateral ventricles and the subgranular zone in the hippocampal dentate gyrus(DG)are the two brain regions where neurogenesis occurs throughout life in the adult mammalian brain(Ming and Song,2011).Adult quiescent hippocampal neural stem cells(NSCs)are bona fide stem cells and,when activated,give rise to newborn granule neurons in the adult brain,which play vital roles in learning,memory,mood,and affective cognition(Bonaguidi et al.,2011;Ming and Song,2011).展开更多
In this study,we present the development of a cryobioink designed to fabricate anisotropic scaffolds that support both neural and muscle cell-alignment.Given the critical role of cellular organization in nerve fibers ...In this study,we present the development of a cryobioink designed to fabricate anisotropic scaffolds that support both neural and muscle cell-alignment.Given the critical role of cellular organization in nerve fibers and neuromuscular junctions,we employed a vertical cryobioprinting-enabled ice-templating technique to create scaffolds with aligned microchannels.These channels facilitated cell-alignment,which is important in modeling neural and neuromuscular tissues.By integrating hyaluronic acid-methacrylate(HAMA)with gelatin methacryloyl and the necessary cryoprotective agent melezitose,we showcased that the cryobioink could preserve cell viability during freezing/thawing processes,even at low temperatures employed during cryobioprinting.We optimized HAMA concentration to enhance neural cell viability and alignment,and successfully constructed anisotropic scaffolds featuring distinct sections that contained muscle and neural cells,establishing a model for neuromuscular junctions.The resulting models provide a versatile platform for studying nerve fibers and neuromuscular dysfunctions,offering potential advancements in neural regeneration research.展开更多
基金supported by grants from Simons Foundation (SFARI 479754),CIHR (PJT-180565)the Scottish Rite Charitable Foundation of Canada (to YL)funding from the Canada Research Chairs program。
文摘The mechanistic target of rapamycin(m TOR) is a serine/threonine kinase that plays a pivotal role in cellular growth, proliferation, survival, and metabolism. In the central nervous system(CNS), the mTOR pathway regulates diverse aspects of neural development and function. Genetic mutations within the m TOR pathway lead to severe neurodevelopmental disorders, collectively known as “mTORopathies”(Crino, 2020). Dysfunctions of m TOR, including both its hyperactivation and hypoactivation, have also been implicated in a wide spectrum of other neurodevelopmental and neurodegenerative conditions, highlighting its importance in CNS health.
基金supported by the National Research Foundation of Korea,Nos.2021R1A2C2006110,2021M3E5D9021364,2019R1A5A2026045(to BGK)the Korea Initiative for Fostering University of Research and Innovation(KIURI)Program of the NRF funded by the MSIT(to HK),No.NRF2021M3H1A104892211(to HSK)。
文摘Spinal cord injury results in permanent loss of neurological functions due to severance of neural networks.Transplantation of neural stem cells holds promise to repair disrupted connections.Yet,ensuring the survival and integration of neural stem cells into the host neural circuit remains a formidable challenge.Here,we investigated whether modifying the intrinsic properties of neural stem cells could enhance their integration post-transplantation.We focused on phosphatase and tensin homolog(PTEN),a well-characterized tumor suppressor known to critically regulate neuronal survival and axonal regeneration.By deleting Pten in mouse neural stem cells,we observed increased neurite outgrowth and enhanced resistance to neurotoxic environments in culture.Upon transplantation into injured spinal cords,Pten-deficient neural stem cells exhibited higher survival and more extensive rostrocaudal distribution.To examine the potential influence of partial PTEN suppression,rat neural stem cells were treated with short hairpin RNA targeting PTEN,and the PTEN knockdown resulted in significant improvements in neurite growth,survival,and neurosphere motility in vitro.Transplantation of sh PTEN-treated neural stem cells into the injured spinal cord also led to an increase in graft survival and migration to an extent similar to that of complete deletion.Moreover,PTEN suppression facilitated neurite elongation from NSC-derived neurons migrating from the lesion epicenter.These findings suggest that modifying intrinsic signaling pathways,such as PTEN,within neural stem cells could bolster their therapeutic efficacy,offering potential avenues for future regenerative strategies for spinal cord injury.
基金supported by the National Key Research and Development Program of China,No.2023YFC3603705(to DX)the National Natural Science Foundation of China,No.82302866(to YZ).
文摘After spinal cord injury,impairment of the sensorimotor circuit can lead to dysfunction in the motor,sensory,proprioceptive,and autonomic nervous systems.Functional recovery is often hindered by constraints on the timing of interventions,combined with the limitations of current methods.To address these challenges,various techniques have been developed to aid in the repair and reconstruction of neural circuits at different stages of injury.Notably,neuromodulation has garnered considerable attention for its potential to enhance nerve regeneration,provide neuroprotection,restore neurons,and regulate the neural reorganization of circuits within the cerebral cortex and corticospinal tract.To improve the effectiveness of these interventions,the implementation of multitarget early interventional neuromodulation strategies,such as electrical and magnetic stimulation,is recommended to enhance functional recovery across different phases of nerve injury.This review concisely outlines the challenges encountered following spinal cord injury,synthesizes existing neurostimulation techniques while emphasizing neuroprotection,repair,and regeneration of impaired connections,and advocates for multi-targeted,task-oriented,and timely interventions.
基金Supported by the National key research and development program in the 14th five year plan 2021YFA1200700)the National Natural Science Foundation of China(62535018,62431025,62561160113)the Natural Science Foundation of Shanghai(23ZR1473400).
文摘Near-infrared image sensors are widely used in fields such as material identification,machine vision,and autonomous driving.Lead sulfide colloidal quantum dot-based infrared photodiodes can be integrated with sil⁃icon-based readout circuits in a single step.Based on this,we propose a photodiode based on an n-i-p structure,which removes the buffer layer and further simplifies the manufacturing process of quantum dot image sensors,thus reducing manufacturing costs.Additionally,for the noise complexity in quantum dot image sensors when capturing images,traditional denoising and non-uniformity methods often do not achieve optimal denoising re⁃sults.For the noise and stripe-type non-uniformity commonly encountered in infrared quantum dot detector imag⁃es,a network architecture has been developed that incorporates multiple key modules.This network combines channel attention and spatial attention mechanisms,dynamically adjusting the importance of feature maps to en⁃hance the ability to distinguish between noise and details.Meanwhile,the residual dense feature fusion module further improves the network's ability to process complex image structures through hierarchical feature extraction and fusion.Furthermore,the pyramid pooling module effectively captures information at different scales,improv⁃ing the network's multi-scale feature representation ability.Through the collaborative effect of these modules,the network can better handle various mixed noise and image non-uniformity issues.Experimental results show that it outperforms the traditional U-Net network in denoising and image correction tasks.
基金funded by Guangdong Basic and Applied Basic Research Foundation(2023B1515120064)National Natural Science Foundation of China(62273097).
文摘Deep learning has become integral to robotics,particularly in tasks such as robotic grasping,where objects often exhibit diverse shapes,textures,and physical properties.In robotic grasping tasks,due to the diverse characteristics of the targets,frequent adjustments to the network architecture and parameters are required to avoid a decrease in model accuracy,which presents a significant challenge for non-experts.Neural Architecture Search(NAS)provides a compelling method through the automated generation of network architectures,enabling the discovery of models that achieve high accuracy through efficient search algorithms.Compared to manually designed networks,NAS methods can significantly reduce design costs,time expenditure,and improve model performance.However,such methods often involve complex topological connections,and these redundant structures can severely reduce computational efficiency.To overcome this challenge,this work puts forward a robotic grasp detection framework founded on NAS.The method automatically designs a lightweight network with high accuracy and low topological complexity,effectively adapting to the target object to generate the optimal grasp pose,thereby significantly improving the success rate of robotic grasping.Additionally,we use Class Activation Mapping(CAM)as an interpretability tool,which captures sensitive information during the perception process through visualized results.The searched model achieved competitive,and in some cases superior,performance on the Cornell and Jacquard public datasets,achieving accuracies of 98.3%and 96.8%,respectively,while sustaining a detection speed of 89 frames per second with only 0.41 million parameters.To further validate its effectiveness beyond benchmark evaluations,we conducted real-world grasping experiments on a UR5 robotic arm,where the model demonstrated reliable performance across diverse objects and high grasp success rates,thereby confirming its practical applicability in robotic manipulation tasks.
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
基金supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (2020M3E5D9079764, RS-2024-00408736)(to KS)supported by Korea Drug Development Fund funded by Ministry of Science and ICT,Ministry of Trade,Industry,and Energy,and Ministry of Health and Welfare (RS-2024-00335752)(to KS)。
文摘The hippocampus is part of the brain limbic system and plays an important role in learning and memory.Moreover,its ability to form,consolidate,and retrieve different types of memories makes it a central component in the cognitive functions necessary for everyday life.Understanding the role of the hippocampus helps comprehend how memories are created,stored,and recalled and sheds light on the impact of hippocampal damage in conditions such as Alzheimer’s disease and other forms of dementia.
基金supported by the National Key Research and Development Program of China(2023YFF0612900,2023YFF0612902)the Natural Science Foundation of Beijing,China(4254086)+3 种基金the National Natural Science Foundation of China(62472032)the Open Project Funding of Key Laboratory of Mobile Application Innovation and Governance Technology,Ministry of Industry and Information Technology(2023IFS080601-K)the Beijing Institute of Technology Research Fund Program for Young Scholarsthe Young Elite Scientists Sponsorship Program by CAST(2023QNRC001)。
文摘Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving graph learning.However,its application often diminishes data utility,especially for nodes with fewer neighbors in graph neural networks(GNNs).
文摘Neural stem cells(NSCs)and glioblastoma stem cells(GSCs)share a complex regulatory landscape in which cholinergic signaling plays a pivotal role in both neural development and tumor progression.While acetylcholine(ACh)regulates NSC quiescence and differentiation within neurogenic niches,glioblastoma cells exploit th ese pathways to enhance their adaptability and invasiveness.The involvement of muscarinic(M3)and nicotinic(α7)receptors in both cell types suggests that glioblastoma retains neural progenitor-like traits,contributing to its plasticity and resilience.This article explores the shared cholinergic mechanisms between NSCs and GSCs,highlighting their role in both neural development and glioblastoma progression.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2021R1A6A1A10044950).
文摘The thermal conductivity of nanofluids is an important property that influences the heat transfer capabilities of nanofluids.Researchers rely on experimental investigations to explore nanofluid properties,as it is a necessary step before their practical application.As these investigations are time and resource-consuming undertakings,an effective prediction model can significantly improve the efficiency of research operations.In this work,an Artificial Neural Network(ANN)model is developed to predict the thermal conductivity of metal oxide water-based nanofluid.For this,a comprehensive set of 691 data points was collected from the literature.This dataset is split into training(70%),validation(15%),and testing(15%)and used to train the ANN model.The developed model is a backpropagation artificial neural network with a 4–12–1 architecture.The performance of the developed model shows high accuracy with R values above 0.90 and rapid convergence.It shows that the developed ANN model accurately predicts the thermal conductivity of nanofluids.
基金supported by the National Natural Science Foundation of China under Grants 61962023,61562029 and 62466019.
文摘This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.
基金supported by ZTE Industry-University-Institute Cooperation Funds under Grant No.IA20230921015。
文摘While neural radiance field(NeRF)methods have shown promising results in generating talking faces,existing studies primarily focus on the correlation between avatars and driving sources.However,these studies often overlook emotion modeling,resulting in the generation of emotionless or unnatural facial animations.In response,this paper introduces an audio-driven and emotion-editing dynamic NeRF(AED-NeRF)approach,designed for the real-time generation of expressive talking face avatars driven by audio inputs.Specifically,we integrate audio features into a grid-based NeRF to compensate for the lack of a deformation channel,successfully capturing lip dynamics and enabling end-to-end generation from audio-driven sources to talking face avatars.Emotion labels,comprising emotion categories and intensity levels,guide the proposed NeRF framework to implicitly model visual emotions,allowing for explicit control and editing of facial expressions.Extensive qualitative and quantitative experiments validate the effectiveness and advantages of our proposed method,demonstrating its ability to achieve real-time,photo-realistic talking face avatar generation across different audio and emotion scenarios.
文摘In contemporary computer vision,convolutional neural networks(CNNs)and vision transformers(ViTs)represent the two primary architectural paradigms for image recognition.While both approaches have been widely adopted in medical imaging applications,they operate based on fundamentally different computational principles.This report attempts to provide brief application notes on ViTs and CNNs,particularly focusing on scenarios that guide the selection of one architecture over the other in practical medical implementations.Generally,CNNs rely on convolutional kernels,localized receptive fields,and weight sharing,enabling efficient hierarchical feature extraction.These properties contribute to strong performance in detecting spatially constrained patterns such as textures,edges,and anatomical boundaries,while maintaining relatively low computational requirements.ViTs,on the other hand,decompose images into smaller segments referred to as tokens and employ self-attention mechanisms to model relationships across the entire image.This global modeling capability allows ViTs to capture long-range dependencies that may be difficult for convolution-based architectures to learn.However,ViTs typically achieve optimal performance when trained on extremely large datasets or when supported by extensive pretraining,as their reduced inductive bias requires greater data exposure to learn robust representations.This report briefly examines the architectural structure,underlying mathematical foundations,and relative performance characteristics of CNNs and ViTs,drawing upon recent findings from contemporary research.Emphasis is placed on understanding how differences in data availability,computational resources,and task requirements influence model effectiveness across medical imaging domains.Most importantly,the report serves as a concise application guide for practitioners seeking informed implementation decisions between these two influential deep learning frameworks.
基金supported by the National Key Research and Development Program of China(2020YFB1005704).
文摘Since the advent of smart contracts,security vulnerabilities have remained a persistent challenge,compromsing both the reliability of contract execution and the overall stability of the virtual currency market.Consequently,the academic community has devoted increasing attention to these security risks.However,conventional approaches to vulnerability detection frequently exhibit limited accuracy.To address this limitation,the present study introduces a novel vulnerability detection framework called GNNSE that integrates symbolic execution with graph neural networks(GNNs).The proposedmethod first constructs semantic graphs to comprehensively capture the control flow and data flow dependencies within smart contracts.These graphs are subsequently processed using GNNs to efficiently identify contracts with a high likelihood of vulnerabilities.For these high-risk contracts,symbolic execution is employed to perform fine-grained,path-level analysis,thereby improving overall detection precision.Experimental results on a dataset comprising 10,079 contracts demonstrate that the proposed method achieves detection precisions of 93.58% for reentrancy vulnerabilities and 92.73% for timestamp-dependent vulnerabilities.
基金supported by the Guangdong S&T Program(Grant No.2025B1111130003).
文摘The development of β-titanium alloys with bone-mimicking elastic moduli remains a significant challenge.Although machine learning has the potential to accelerate alloy discovery,traditional methods often face data limitations such as sparsity,compositional discontinuity,and feature heterogeneity,leading to overfitting and restricting the exploration of novel compositional spaces.In this study,we introduce a domain-adversarial neural network framework that balances predictive accuracy with the generalization ability of unexplored composition space through integrated feature alignment and adversarial training.Using this approach,we successfully developed a non-intuitiveβ-Ti alloy with an ultra-low elastic modulus of 28±3 GPa,providing new insights beyond conventionally designed biomedical titanium alloys.This work establishes a screening framework for materials discovery in small-sample data spaces,with broad implications for the design of biomedical and other alloy systems.
基金the National Natural Science Foundation of China for Distinguished Young Scholars(62325403)the National Natural Science Foundation of China(62504103 and 82002454)+4 种基金the Basic Research Program of Jiangsu(BK20251214)the Natural Science Foundation of Jiangsu Province(BK20230498)the China Postdoctoral Science Foundation under Grant Number 2025T180143 and 2025M770547the Medical Scientific Research Project of Jiangsu Health Commission(ZD2021011)the Jiangsu Funding Program for Excellent Postdoctoral Talent(2024ZB427)。
文摘The development of non-invasive brain-computer interfaces(BCIs)relies on multidisciplinary integration across neuroscience,artificial intelligence,flexible electronics,and systems engineering.Recent advances in deep learning have significantly improved the accuracy and robustness of neural signal decoding.Parallel progress in electrode design—particularly through the use of flexible and stretchable materials like nanostructured conductors and novel fabrication strategies—has enhanced wearability and operational stability.Nevertheless,key challenges persist,including individual variability,biocompatibility limitations,and susceptibility to interference in complex environments.Further validation and optimization are needed to address gaps in generalization capability,long-term reliability,and real-world operational robustness.This review systematically examines the representative progress in neural decoding algorithms and flexible bioelectronic platforms over the past decade,highlighting key design principles,material innovations,and integration strategies that are poised to advance non-invasive BCI capabilities.It also discusses the importance of multimodal data fusion,hardware-software co-optimization,and closed-loop control strategies.Furthermore,the review discusses the application potential and associated engineering challenges of this technology in clinical rehabilitation and industrial translation,aiming to provide a reference for advancing non-invasive BCIs toward practical and scalable deployment.
文摘Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(CSI)as real-valued inputs,potentially discarding useful information embedded in the original CSI.In addition,existing positioning models generally face the contradiction between computational complexity and positioning accuracy.To address these issues,we combine graph neural network(GNN)with complex-valued neural network(CVNN)to construct a lightweight indoor positioning model named CGNet.CGNet employs complexvalued convolution operation to directly process the original CSI data,fully exploiting the correlation between real and imaginary parts of CSI while extracting local features.Subsequently,the feature values are treated as nodes,and conditional position encoding(CPE)module is applied to add positional information.To reduce the number of connections in the graph structure and lower themodel complexity,feature information is mapped to an efficient graph structure through a dynamic axial graph construction(DAGC)method,with global features extracted usingmaximum relative graph convolution(MRConv).Experimental results show that,on the CTW dataset,CGNet achieves a 10%improvement in positioning accuracy compared to existing methods,while the number of model parameters is only 0.8 M.CGNet achieves excellent positioning accuracy with very few parameters.
基金supported by National Institutes of Health(R35NS137480,R35NS116843,and RF1AG079557)by Dr.Miriam and Sheldon G.Adelson Medical Research Foundation.
文摘The adult subventricular zone of the lateral ventricles and the subgranular zone in the hippocampal dentate gyrus(DG)are the two brain regions where neurogenesis occurs throughout life in the adult mammalian brain(Ming and Song,2011).Adult quiescent hippocampal neural stem cells(NSCs)are bona fide stem cells and,when activated,give rise to newborn granule neurons in the adult brain,which play vital roles in learning,memory,mood,and affective cognition(Bonaguidi et al.,2011;Ming and Song,2011).
基金support from the National Institutes of Technology(R21EB030257,R01EB028143,R01HL153857,R01HL166522,R01CA282451,R56EB034702)National Science Foundation(CBET-EBMS-1936105,CISE-IIS-2225698)+1 种基金Chan Zuckerberg Initiative(2022316712,2024-347836)the Brigham Research Institute.
文摘In this study,we present the development of a cryobioink designed to fabricate anisotropic scaffolds that support both neural and muscle cell-alignment.Given the critical role of cellular organization in nerve fibers and neuromuscular junctions,we employed a vertical cryobioprinting-enabled ice-templating technique to create scaffolds with aligned microchannels.These channels facilitated cell-alignment,which is important in modeling neural and neuromuscular tissues.By integrating hyaluronic acid-methacrylate(HAMA)with gelatin methacryloyl and the necessary cryoprotective agent melezitose,we showcased that the cryobioink could preserve cell viability during freezing/thawing processes,even at low temperatures employed during cryobioprinting.We optimized HAMA concentration to enhance neural cell viability and alignment,and successfully constructed anisotropic scaffolds featuring distinct sections that contained muscle and neural cells,establishing a model for neuromuscular junctions.The resulting models provide a versatile platform for studying nerve fibers and neuromuscular dysfunctions,offering potential advancements in neural regeneration research.
