In order to achieve a wheelchair lift function, this paper designs a tri-scissors mechanism. Through the so-called H-type transmission and L-type swing rod, the three scissors mechanisms lift in the same rate with onl...In order to achieve a wheelchair lift function, this paper designs a tri-scissors mechanism. Through the so-called H-type transmission and L-type swing rod, the three scissors mechanisms lift in the same rate with only one liner motor while ensuring the stability of the lift. Finite element analysis in ANSYS is performed to verify the material strength. The control system with Sunplus SCM achieves the voice control of wheelchair walking and lifting.展开更多
Based on the recommendation of ICTD＇09 TPC members, this Special Issue of the Journal of Electronic Science ＆ Technology of China （JESTC） contained 22 high quality papers selected from the Proceedings of 2009 IEEE...Based on the recommendation of ICTD＇09 TPC members, this Special Issue of the Journal of Electronic Science ＆ Technology of China （JESTC） contained 22 high quality papers selected from the Proceedings of 2009 IEEE Circuits and Systems International Conference on Testing and Diagnosis （ICTD ＇09） which is fully sponsored by the IEEE Circuits and Systems Society （CASS）, and is technically co-sponsored by the University of Electronic Science and Technology of China （UESTC）, the Chinese Institute of Electronics （CIE）, the China Instrument ＆ Control Society （CIS）, and organized by UESTC.展开更多
In order to reduce nursing intensity and improve freedom of the elderly and the disabled, a multi-function nursing wheelchair which can switch chair to bed and realize many kinds of posture transformation is designed....In order to reduce nursing intensity and improve freedom of the elderly and the disabled, a multi-function nursing wheelchair which can switch chair to bed and realize many kinds of posture transformation is designed. This paper introduces the mechanical structure design （position adjustment mechanism and variable wheelbase mechanism） and control design of posture transformation unit of multifunctional nursing wheelchair.展开更多
PCIM China, international conference and exhibition for power electronics, was held in Shanghai on March 21, 2006. PCIM is one of the most authoritative organizations and has won good reputation overseas for a long time.
This special issue in the Journal of Electronic Science ＆ Technology of China （JESTC） contains the selected papers presented at the 1st Asia-Pacific Optical Fiber Sensors Conference （APOS2008） organized by Univer...This special issue in the Journal of Electronic Science ＆ Technology of China （JESTC） contains the selected papers presented at the 1st Asia-Pacific Optical Fiber Sensors Conference （APOS2008） organized by University of Electronic Science and Technology of China and Chongqing University, China. This conference is supported by Ministry of Education of the People＇s Republic of China, National Nature Science Foundation of China （NSFC）, and Chinese Optics Society （COS）.展开更多
China Standardization:As I know,you have been engaged in international standardization for a long time.Last year,you got the Astin-Polk International Standards Medal in U.S.,and as the former President of the US Natio...China Standardization:As I know,you have been engaged in international standardization for a long time.Last year,you got the Astin-Polk International Standards Medal in U.S.,and as the former President of the US National Committee of IEC from 2006 to 2010,you've made great contribution to the China-US exchange and cooperation in international standardization.I believe that you have accumulated a lot of valuable experiences in international standardization.In recent years Chinese Government has been paying attention to international standardization,and being interested in participating substantially in international standardization activities;can you give us some advice about it?展开更多
Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despit...Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despite differences in the mechanisms of injury,both conditions share a high prevalence of motor and cognitive impairments.These deficits show only limited natural recovery.展开更多
In self-pollinating cereals such as rice,wheat,and barley,growing undefined mixtures of genotypes in genetic equilibrium was once standard practice when local populations(landraces)were used.The shift from landraces t...In self-pollinating cereals such as rice,wheat,and barley,growing undefined mixtures of genotypes in genetic equilibrium was once standard practice when local populations(landraces)were used.The shift from landraces to single-genotype varieties led to immediate gains in yield and quality,and over the past century,single-genotype crops have been highly successful.Nonetheless,several studies suggest that variety mixtures(i.e.,two or more consciously selected genotypes of the same crop grown together)may offer advantages over single-genotype varieties(Borg et al.,2018;Kopp et al.,2023).展开更多
The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness dimin...The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.展开更多
Physician well-being is vital to delivering high-quality emergency care.A supported and healthy emergency medicine workforce leads to better patient outcomes,fewer medical errors,and greater job satisfaction and staff...Physician well-being is vital to delivering high-quality emergency care.A supported and healthy emergency medicine workforce leads to better patient outcomes,fewer medical errors,and greater job satisfaction and staff retention.[1,2]Emergency physicians(EPs)face unique pressures,including shift work,high patient volumes and acuities,overcrowding,and systemic inefficiencies that escalate their risk of burnout.As a result,EPs have reported the highest rates of burnout among physician specialties.展开更多
The major aim of stroke therapy is to stimulate brain repair and improve behavioral recovery after cerebral ischemia.One option is to stimulate endogenous neurogenesis in the subventricular zone and direct the newly f...The major aim of stroke therapy is to stimulate brain repair and improve behavioral recovery after cerebral ischemia.One option is to stimulate endogenous neurogenesis in the subventricular zone and direct the newly formed neurons to the damaged area.However,only a small percentage of these neurons survive,and many do not reach the damaged area,possibly because the corpus callosum impedes the migration of subventricular zone-derived stem cells into the lesioned cortex.A second major obstacle to stem cell therapy is the strong inflammatory reaction induced by cerebral ischemia,whereby the associated phagocytic activity of brain macrophages removes both therapeutic cells and/or cell-based drug carriers.To address these issues,neurogenesis was electrically stimulated in the subventricular zone,followed by isolation of proliferating cells,including newly formed neurons,which were subsequently mixed with a nutritional hydrogel.This mixture was then transferred to the stroke cavity of day 14 post-stroke mice.We found that the performance of the treated animals improved in behavioral tests,including novel object,open field,hole board,grooming,and“time-to-feel”adhesive tape tests.Furthermore,immunostaining revealed that the stem cell marker nestin,the neuroepithelial marker Mash1,and the immature neuronal marker doublecortin-positive cells survived in the transplanted area for 2 weeks,possibly due to reduced phagocytic activity and supportive angiogenesis.These results clearly indicate that the transplantation of committed subventricular zone stem cells combined with a protective nutritional gel directly into the infarct cavity after the peak of stroke-induced neuroinflammation represents a feasible approach to improve neurorestoration after cerebral ischemia.展开更多
Neuronal plasticity,the brain's ability to adapt structurally and functionally,is essential for learning,memory,and recovery from injuries.In neurodegenerative diseases such as Alzheimer's disease and Parkinso...Neuronal plasticity,the brain's ability to adapt structurally and functionally,is essential for learning,memory,and recovery from injuries.In neurodegenerative diseases such as Alzheimer's disease and Parkinson's disease,this plasticity is disrupted,leading to cognitive and motor deficits.This review explores the mechanisms of neuronal plasticity and its effect on Alzheimer's disease and Parkinson's disease.Alzheimer's disease features amyloid-beta plaques and tau tangles that impair synaptic function,while Parkinson's disease involves the loss of dopaminergic neurons affecting motor control.Enhancing neuronal plasticity offers therapeutic potential for these diseases.A systematic literature review was conducted using databases such as PubMed,Scopus,and Google Scholar,focusing on studies of neuronal plasticity in Alzheimer's disease and Parkinson's disease.Data synthesis identified key themes such as synaptic mechanisms,neurogenesis,and therapeutic strategies,linking molecular insights to clinical applications.Results highlight that targeting synaptic plasticity mechanisms,such as long-term potentiation and long-term depression,shows promise.Neurotrophic factors,advanced imaging techniques,and molecular tools(e.g.,clustered regularly interspaced short palindromic repeats and optogenetics)are crucial in understanding and enhancing plasticity.Current therapies,including dopamine replacement,deep brain stimulation,and lifestyle interventions,demonstrate the potential to alleviate symptoms and improve outcomes.In conclusion,enhancing neuronal plasticity through targeted therapies holds significant promise for treating neurodegenerative diseases.Future research should integrate multidisciplinary approaches to fully harness the therapeutic potential of neuronal plasticity in Alzheimer's disease and Parkinson's disease.展开更多
Recent studies indicate that millions of individuals suffer from renal diseases,with renal carcinoma,a type of kidney cancer,emerging as both a chronic illness and a significant cause of mortality.Magnetic Resonance I...Recent studies indicate that millions of individuals suffer from renal diseases,with renal carcinoma,a type of kidney cancer,emerging as both a chronic illness and a significant cause of mortality.Magnetic Resonance Imaging(MRI)and Computed Tomography(CT)have become essential tools for diagnosing and assessing kidney disorders.However,accurate analysis of thesemedical images is critical for detecting and evaluating tumor severity.This study introduces an integrated hybrid framework that combines three complementary deep learning models for kidney tumor segmentation from MRI images.The proposed framework fuses a customized U-Net and Mask R-CNN using a weighted scheme to achieve semantic and instance-level segmentation.The fused outputs are further refined through edge detection using Stochastic FeatureMapping Neural Networks(SFMNN),while volumetric consistency is ensured through Improved Mini-Batch K-Means(IMBKM)clustering integrated with an Encoder-Decoder Convolutional Neural Network(EDCNN).The outputs of these three stages are combined through a weighted fusion mechanism,with optimal weights determined empirically.Experiments on MRI scans from the TCGA-KIRC dataset demonstrate that the proposed hybrid framework significantly outperforms standalone models,achieving a Dice Score of 92.5%,an IoU of 87.8%,a Precision of 93.1%,a Recall of 90.8%,and a Hausdorff Distance of 2.8 mm.These findings validate that the weighted integration of complementary architectures effectively overcomes key limitations in kidney tumor segmentation,leading to improved diagnostic accuracy and robustness in medical image analysis.展开更多
The present investigation inspects the unsteady,incompressible MHD-induced flow of a ternary hybrid nanofluid made of SiO_(2)(silicon dioxide),ZnO(zinc oxide),and MWCNT(multi-walled carbon nanotubes)suspended in a wat...The present investigation inspects the unsteady,incompressible MHD-induced flow of a ternary hybrid nanofluid made of SiO_(2)(silicon dioxide),ZnO(zinc oxide),and MWCNT(multi-walled carbon nanotubes)suspended in a water-ethylene glycol base fluid between two perforated squeezing Riga plates.This problem is important because it helps us understand the complicated connections between magnetic fields,nanofluid dynamics,and heat transport,all of which are critical for designing thermal management systems.These findings are especially useful for improving the design of innovative cooling technologies in electronics,energy systems,and healthcare applications.No prior study has been done on the theoretical study of the flow of ternary nanofluid(SiO_(2)+ZnO+MWCNT/Water−EthylGl ycol,(60∶40))past a pierced squeezed Riga plates using the boundary value problem solver 4th-order collocation(BVP4C)numerical approach to date.So,the current work has been carried out to fill this gap,and the core purpose of this study is to explore the aspects that enhance the heat transfer of base fluids(H_(2)O/EG)suspended with three nanomaterials SiO_(2),ZnO,and MWCNT.The Riga plates introduce electromagnetic forcing through an embedded array of magnets and electrodes,generating Lorentz forces to regulate the flow.The squeezing effect introduces dynamic boundary movement,which enhances mixing;however,permeability,due to porosity,replicates the true material limits.Similarity transformations of the Navier-Stokes and energy equations result in a highly nonlinear set of ordinary differential equations that govern momentum and thermal energy transport.The subsequent boundary value problem is solved utilizing the BVP4C numerical approach.The study observes the impact of magnetic parameters,squeezing velocity,solid volume percentages of the three nanoparticles,and porous medium factors on velocity and temperature fields.Results show that magnetic fields reduce the velocity profile by 6.75%due to increased squeezing and medium effects.Tri-hybrid nanofluids notice a 9%rise in temperature with higher thermal radiation.展开更多
近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融...近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融合,并且几乎可以求解任何偏微分方程问题,由于其融合数据的优势,相较于传统算法,其计算效率通常提升数万倍.因此,本文全面综述了AI4PDEs的研究,总结了现有AI4PDEs算法、理论,并讨论了其在固体力学中的应用,包括正问题和反问题,展望了未来研究方向,尤其是必然会出现的计算力学大模型.现有AI4PDEs算法包括基于物理信息神经网络(physicsinformed neural network,PINNs)、深度能量法(deep energy methods,DEM)、算子学习(operator learning),以及基于物理神经网络算子(physics-informed neural operator,PINO).AI4PDEs在科学计算中有许多应用,本文聚焦于固体力学,正问题包括线弹性、弹塑性,超弹性、以及断裂力学;反问题包括材料参数,本构,缺陷的识别,以及拓朴优化.AI4PDEs代表了一种全新的科学模拟方法,通过利用大量数据在特定问题上提供近似解,然后根据具体的物理方程进行微调,避免了像传统算法那样从头开始计算,因此AI4PDEs是未来计算力学大模型的雏形,能够大大加速传统数值算法.我们相信,利用人工智能助力科学计算不仅仅是计算领域的未来重要方向,同时也是计算力学的未来,即是智能计算力学。展开更多
基金Supported by Special Topic of the Ministry of Education about Humanities and Social Sciences(12JDGC007)ZheJiang Henglin Chair Industry Co.,Ltd.-Hefei University of Technology Green Seat and Intelligent House Innovate Team
文摘In order to achieve a wheelchair lift function, this paper designs a tri-scissors mechanism. Through the so-called H-type transmission and L-type swing rod, the three scissors mechanisms lift in the same rate with only one liner motor while ensuring the stability of the lift. Finite element analysis in ANSYS is performed to verify the material strength. The control system with Sunplus SCM achieves the voice control of wheelchair walking and lifting.
文摘Based on the recommendation of ICTD＇09 TPC members, this Special Issue of the Journal of Electronic Science ＆ Technology of China （JESTC） contained 22 high quality papers selected from the Proceedings of 2009 IEEE Circuits and Systems International Conference on Testing and Diagnosis （ICTD ＇09） which is fully sponsored by the IEEE Circuits and Systems Society （CASS）, and is technically co-sponsored by the University of Electronic Science and Technology of China （UESTC）, the Chinese Institute of Electronics （CIE）, the China Instrument ＆ Control Society （CIS）, and organized by UESTC.
基金Supported by NSFC(61170005)Special Topic of the Ministry of Education about Humanities and Social Sciences(12JDGC007)+2 种基金University Quality Project of Anhui Province(20100096)Graduate Education Reform Project of Hefei University of Technology(2011yjs003)National College Students' Training Project of Innovation and Entrepreneurship(201210359078)
文摘In order to reduce nursing intensity and improve freedom of the elderly and the disabled, a multi-function nursing wheelchair which can switch chair to bed and realize many kinds of posture transformation is designed. This paper introduces the mechanical structure design （position adjustment mechanism and variable wheelbase mechanism） and control design of posture transformation unit of multifunctional nursing wheelchair.
文摘PCIM China, international conference and exhibition for power electronics, was held in Shanghai on March 21, 2006. PCIM is one of the most authoritative organizations and has won good reputation overseas for a long time.
文摘This special issue in the Journal of Electronic Science ＆ Technology of China （JESTC） contains the selected papers presented at the 1st Asia-Pacific Optical Fiber Sensors Conference （APOS2008） organized by University of Electronic Science and Technology of China and Chongqing University, China. This conference is supported by Ministry of Education of the People＇s Republic of China, National Nature Science Foundation of China （NSFC）, and Chinese Optics Society （COS）.
文摘China Standardization:As I know,you have been engaged in international standardization for a long time.Last year,you got the Astin-Polk International Standards Medal in U.S.,and as the former President of the US National Committee of IEC from 2006 to 2010,you've made great contribution to the China-US exchange and cooperation in international standardization.I believe that you have accumulated a lot of valuable experiences in international standardization.In recent years Chinese Government has been paying attention to international standardization,and being interested in participating substantially in international standardization activities;can you give us some advice about it?
基金supported by the Defitech Foundation(Morges,CH)to FCHthe Bertarelli Foundation-Catalyst program(Gstaad,CH)to FCH+2 种基金the Wyss Center for Bio and Neuroengineering the Lighthouse Partnership for AI-guided Neuromodulation to FCHthe Fonds de recherche du Quebec-Sante(FRQS#342969)to CEPthe Neuro X Postdoctoral Fellowship Program to CEP。
文摘Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despite differences in the mechanisms of injury,both conditions share a high prevalence of motor and cognitive impairments.These deficits show only limited natural recovery.
基金supported by the FACCE-JPI SusCrop project RECOBAR,funded by MASAF(D.M.no.142548)the Deutsche Forschungsgemeinschaft under the Emmy Noether Programme(project no.442020478).
文摘In self-pollinating cereals such as rice,wheat,and barley,growing undefined mixtures of genotypes in genetic equilibrium was once standard practice when local populations(landraces)were used.The shift from landraces to single-genotype varieties led to immediate gains in yield and quality,and over the past century,single-genotype crops have been highly successful.Nonetheless,several studies suggest that variety mixtures(i.e.,two or more consciously selected genotypes of the same crop grown together)may offer advantages over single-genotype varieties(Borg et al.,2018;Kopp et al.,2023).
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 62276109The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through the Research Group Project number(ORF-2025-585).
文摘The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.
文摘Physician well-being is vital to delivering high-quality emergency care.A supported and healthy emergency medicine workforce leads to better patient outcomes,fewer medical errors,and greater job satisfaction and staff retention.[1,2]Emergency physicians(EPs)face unique pressures,including shift work,high patient volumes and acuities,overcrowding,and systemic inefficiencies that escalate their risk of burnout.As a result,EPs have reported the highest rates of burnout among physician specialties.
基金supported by European Union Funding Programme,PNRR,No. 760058(to DMH)the UEFISCDI Project,No. PN-III-P4-IDPCE-2020-059(to APW)
文摘The major aim of stroke therapy is to stimulate brain repair and improve behavioral recovery after cerebral ischemia.One option is to stimulate endogenous neurogenesis in the subventricular zone and direct the newly formed neurons to the damaged area.However,only a small percentage of these neurons survive,and many do not reach the damaged area,possibly because the corpus callosum impedes the migration of subventricular zone-derived stem cells into the lesioned cortex.A second major obstacle to stem cell therapy is the strong inflammatory reaction induced by cerebral ischemia,whereby the associated phagocytic activity of brain macrophages removes both therapeutic cells and/or cell-based drug carriers.To address these issues,neurogenesis was electrically stimulated in the subventricular zone,followed by isolation of proliferating cells,including newly formed neurons,which were subsequently mixed with a nutritional hydrogel.This mixture was then transferred to the stroke cavity of day 14 post-stroke mice.We found that the performance of the treated animals improved in behavioral tests,including novel object,open field,hole board,grooming,and“time-to-feel”adhesive tape tests.Furthermore,immunostaining revealed that the stem cell marker nestin,the neuroepithelial marker Mash1,and the immature neuronal marker doublecortin-positive cells survived in the transplanted area for 2 weeks,possibly due to reduced phagocytic activity and supportive angiogenesis.These results clearly indicate that the transplantation of committed subventricular zone stem cells combined with a protective nutritional gel directly into the infarct cavity after the peak of stroke-induced neuroinflammation represents a feasible approach to improve neurorestoration after cerebral ischemia.
基金financially supported by King Abdulaziz University,Deanship of Scientific Research(DSR)。
文摘Neuronal plasticity,the brain's ability to adapt structurally and functionally,is essential for learning,memory,and recovery from injuries.In neurodegenerative diseases such as Alzheimer's disease and Parkinson's disease,this plasticity is disrupted,leading to cognitive and motor deficits.This review explores the mechanisms of neuronal plasticity and its effect on Alzheimer's disease and Parkinson's disease.Alzheimer's disease features amyloid-beta plaques and tau tangles that impair synaptic function,while Parkinson's disease involves the loss of dopaminergic neurons affecting motor control.Enhancing neuronal plasticity offers therapeutic potential for these diseases.A systematic literature review was conducted using databases such as PubMed,Scopus,and Google Scholar,focusing on studies of neuronal plasticity in Alzheimer's disease and Parkinson's disease.Data synthesis identified key themes such as synaptic mechanisms,neurogenesis,and therapeutic strategies,linking molecular insights to clinical applications.Results highlight that targeting synaptic plasticity mechanisms,such as long-term potentiation and long-term depression,shows promise.Neurotrophic factors,advanced imaging techniques,and molecular tools(e.g.,clustered regularly interspaced short palindromic repeats and optogenetics)are crucial in understanding and enhancing plasticity.Current therapies,including dopamine replacement,deep brain stimulation,and lifestyle interventions,demonstrate the potential to alleviate symptoms and improve outcomes.In conclusion,enhancing neuronal plasticity through targeted therapies holds significant promise for treating neurodegenerative diseases.Future research should integrate multidisciplinary approaches to fully harness the therapeutic potential of neuronal plasticity in Alzheimer's disease and Parkinson's disease.
基金funded by the Ongoing Research Funding Program-Research Chairs(ORF-RC-2025-2400),King Saud University,Riyadh,Saudi Arabia。
文摘Recent studies indicate that millions of individuals suffer from renal diseases,with renal carcinoma,a type of kidney cancer,emerging as both a chronic illness and a significant cause of mortality.Magnetic Resonance Imaging(MRI)and Computed Tomography(CT)have become essential tools for diagnosing and assessing kidney disorders.However,accurate analysis of thesemedical images is critical for detecting and evaluating tumor severity.This study introduces an integrated hybrid framework that combines three complementary deep learning models for kidney tumor segmentation from MRI images.The proposed framework fuses a customized U-Net and Mask R-CNN using a weighted scheme to achieve semantic and instance-level segmentation.The fused outputs are further refined through edge detection using Stochastic FeatureMapping Neural Networks(SFMNN),while volumetric consistency is ensured through Improved Mini-Batch K-Means(IMBKM)clustering integrated with an Encoder-Decoder Convolutional Neural Network(EDCNN).The outputs of these three stages are combined through a weighted fusion mechanism,with optimal weights determined empirically.Experiments on MRI scans from the TCGA-KIRC dataset demonstrate that the proposed hybrid framework significantly outperforms standalone models,achieving a Dice Score of 92.5%,an IoU of 87.8%,a Precision of 93.1%,a Recall of 90.8%,and a Hausdorff Distance of 2.8 mm.These findings validate that the weighted integration of complementary architectures effectively overcomes key limitations in kidney tumor segmentation,leading to improved diagnostic accuracy and robustness in medical image analysis.
基金funded by King Saud University,Riyadh,Saudi Arabia,through the Ongo-ing Research Funding program—Research Chairs(ORF-RC-2025-0127)funded via Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R443).
文摘The present investigation inspects the unsteady,incompressible MHD-induced flow of a ternary hybrid nanofluid made of SiO_(2)(silicon dioxide),ZnO(zinc oxide),and MWCNT(multi-walled carbon nanotubes)suspended in a water-ethylene glycol base fluid between two perforated squeezing Riga plates.This problem is important because it helps us understand the complicated connections between magnetic fields,nanofluid dynamics,and heat transport,all of which are critical for designing thermal management systems.These findings are especially useful for improving the design of innovative cooling technologies in electronics,energy systems,and healthcare applications.No prior study has been done on the theoretical study of the flow of ternary nanofluid(SiO_(2)+ZnO+MWCNT/Water−EthylGl ycol,(60∶40))past a pierced squeezed Riga plates using the boundary value problem solver 4th-order collocation(BVP4C)numerical approach to date.So,the current work has been carried out to fill this gap,and the core purpose of this study is to explore the aspects that enhance the heat transfer of base fluids(H_(2)O/EG)suspended with three nanomaterials SiO_(2),ZnO,and MWCNT.The Riga plates introduce electromagnetic forcing through an embedded array of magnets and electrodes,generating Lorentz forces to regulate the flow.The squeezing effect introduces dynamic boundary movement,which enhances mixing;however,permeability,due to porosity,replicates the true material limits.Similarity transformations of the Navier-Stokes and energy equations result in a highly nonlinear set of ordinary differential equations that govern momentum and thermal energy transport.The subsequent boundary value problem is solved utilizing the BVP4C numerical approach.The study observes the impact of magnetic parameters,squeezing velocity,solid volume percentages of the three nanoparticles,and porous medium factors on velocity and temperature fields.Results show that magnetic fields reduce the velocity profile by 6.75%due to increased squeezing and medium effects.Tri-hybrid nanofluids notice a 9%rise in temperature with higher thermal radiation.
文摘近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融合,并且几乎可以求解任何偏微分方程问题,由于其融合数据的优势,相较于传统算法,其计算效率通常提升数万倍.因此,本文全面综述了AI4PDEs的研究,总结了现有AI4PDEs算法、理论,并讨论了其在固体力学中的应用,包括正问题和反问题,展望了未来研究方向,尤其是必然会出现的计算力学大模型.现有AI4PDEs算法包括基于物理信息神经网络(physicsinformed neural network,PINNs)、深度能量法(deep energy methods,DEM)、算子学习(operator learning),以及基于物理神经网络算子(physics-informed neural operator,PINO).AI4PDEs在科学计算中有许多应用,本文聚焦于固体力学,正问题包括线弹性、弹塑性,超弹性、以及断裂力学;反问题包括材料参数,本构,缺陷的识别,以及拓朴优化.AI4PDEs代表了一种全新的科学模拟方法,通过利用大量数据在特定问题上提供近似解,然后根据具体的物理方程进行微调,避免了像传统算法那样从头开始计算,因此AI4PDEs是未来计算力学大模型的雏形,能够大大加速传统数值算法.我们相信,利用人工智能助力科学计算不仅仅是计算领域的未来重要方向,同时也是计算力学的未来,即是智能计算力学。
