检索结果-内蒙古大学图书馆

Guidance for sharing computational models of neural stimulation: from project planning to publication

JOURNAL OF NEURAL ENGINEERING 2025年第2期22卷 021001-021001页

作者： Pelot, Nicole A. Wang, Boshuo Marshall, Daniel P. Hussain, Minhaj A. Musselman, Eric D. Yu, Gene J. Dale, Jahrane Baumgart, Ian W. Dardani, Daniel Zamani, Princess Tara Villacreses, David Chang Wagenaar, Joost B. Grill, Warren M. Duke Univ Pratt Sch Engn Dept Biomed Engn Durham NC 27708 USA Duke Univ Sch Med Dept Psychiat & Behav Sci Durham NC USA Duke Univ Off Translat & Commercializat Durham NC USA Univ Penn Perelman Sch Med Dept Biostat Epidemiol & Informat Philadelphia PA USA Duke Univ Pratt Sch Engn Dept Elect & Comp Engn Durham NC USA Duke Univ Sch Med Dept Neurobiol Durham NC USA Duke Univ Sch Med Dept Neurosurg Durham NC USA

Objective. Sharing computational models offers many benefits, including increased scientific rigor during project execution, readership of the associated paper, resource usage efficiency, replicability, and reusability. In recognition of the growing practice and requirement of sharing models, code, and data, herein, we provide guidance to facilitate sharing of computational models by providing an accessible resource for regular reference throughout a project's stages. Approach. We synthesized literature on good practices in scientific computing and on code and data sharing with our experience in developing, sharing, and using models of neural stimulation, although the guidance will also apply well to most other types of computational models. Main results. We first describe the '6 R' characteristics of shared models, leaning on prior scientific computing literature, which enforce accountability and enable advancement: re-runnability, repeatability, replicability, reproducibility, reusability, and readability. We then summarize action items associated with good practices in scientific computing, including selection of computational tools during project planning, code and documentation design during development, and user instructions for deployment. We provide a detailed checklist of the contents of shared models and associated materials, including the model itself, code for reproducing published figures, documentation, and supporting datasets. We describe code, model, and data repositories, including a list of characteristics to consider when selecting a platform for sharing. We describe intellectual property (IP) considerations to balance permissive, open-source licenses versus software patents and bespoke licenses that govern and incentivize commercialization. Finally, we exemplify these practices with our ASCENT pipeline for modeling peripheral nerve stimulation. Significance. We hope that this paper will serve as an important and actionable reference for scientist

关键词： neural engineering computational modeling model sharing data sharing open-source replicability reusability

来源：评论

学校读者我要写书评

暂无评论

Infrared Image Quality Evaluation: Benchmark Database and computational Model

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Gu, Ke Liu, Hongyan Gao, Yubin Liu, Yuchen Qiao, Junfei Zhai, Guangtao Zhang, Wenjun Hubei Univ Automot Technol Sch Automot Intelligent Mfg Shiyan 442002 Peoples R China Beijing Univ Technol Beijing Inst Artificial Intelligence Engn Res Ctr Intelligent Percept & Autonomous Cont Beijing Key Lab Computat Intelligence & Intelligen Beijing 100124 Peoples R China Beijing Univ Technol Sch Informat Sci & Technol Beijing 100124 Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Informat Proc Shanghai 200240 Peoples R China

An infrared image is the object's temperature distribution map, generated by using the infrared thermal imaging camera (ITIC) to passively receive infrared radiation emitted from the object. Infrared images play a crucial role in many fields, such as industry, medicine, transportation, and military, since they have the characteristics of broadband imaging, strong penetration, no interference from visible light, and high covertness. Nonetheless, during imaging, acquisition, transmission, and storage processes, infrared images are susceptible to the distortions (including non-uniformity noise, white noise, blur, compression, etc.) to lead to quality degradation, and this may further reduce target detection accuracy to result in some shocking incidents such as explosions and fires caused by hazardous gas leaks in petrochemical plants. To tackle such problem, we build a large-size and distortion-rich infrared image quality evaluation database (I2QED) and develop a novel infrared image quality evaluation model (I2QEM), which can be used as an optimizer to improve infrared image quality and guarantee target detection accuracy. First, we construct the I2QED by collecting 50 original infrared images and introducing abundant distortion types to create the associated 5000 distorted infrared images with subjective ratings processed based on outlier removal. Second, we devise the I2QEM by computing and fusing the gradient magnitude fidelities in multiple scales to measure the distortions on edges, contours, and foregrounds of infrared images. Experiments conducted on the large-size I2QED confirm that our proposed I2QEM achieved superior performance, far better than mainstream and state-of-the-art peers.

关键词： Image quality computational modeling Distortion Databases Distortion measurement Image edge detection Training Evaluation models Deep learning Feature extraction Benchmark database computational model gradient magnitude fidelity infrared image quality evaluation

来源：评论

学校读者我要写书评

暂无评论

Cellular computational Networks Based Hierarchical Data-Driven Dynamic State Estimation Method Considering Uncertainties

引用

PROTECTION AND CONTROL OF MODERN POWER SYSTEMS 2025年第2期10卷 150-161页

作者： Wu, Lili Wang, Yi Wang, Yaoqiang Si, Jikai Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Peoples R China

Accurate generator information is crucial for the efficient control and operation of a power system. This study proposes a hierarchical data-driven approach for dynamic state estimation (DSE) of generators using cellular computational networks (CCNs) structure. The proposed method initially divides the problem of dynamic state estimation into multiple layers through hierarchical architecture. In the prediction layer, CCNs are employed to reduce the system scale by considering only relevant generators. In the correction layer, a novel adaptive filter is utilized to increase data abundance. Simulation results demonstrate that the proposed hierarchical data-driven method can accurately estimate states using PMU data alone while maintaining high computational efficiency. Additionally, it offers easy scalability and strong robustness against uncertainties. The proposed method has potential applications in online dynamic state estimation and real-time security monitoring.

关键词： Uncertainty Accuracy computational modeling Simulation Power system dynamics Adaptive filters Generators Robustness computational efficiency State estimation Cellular computational networks data driven dynamic state estimation hierarchical model uncertainty

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation computational Offloading for Space-Air-Ground Integrated Vehicle Networks

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第5期26卷 5804-5815页

作者： Xie, Wenxuan Chen, Chen Ju, Ying Shen, Jun Pei, Qingqi Song, Houbing Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China Xidian Univ Xidian Hangzhou Inst Technol Hangzhou 311231 Peoples R China Xidian Univ Xidian Guangzhou Inst Technol Guangzhou 510555 Peoples R China China Telecom Res Inst Guangzhou 510630 Peoples R China Univ Maryland Baltimore Cty UMBC Dept Informat Syst Baltimore MD 21250 USA

In remote or disaster areas, where terrestrial networks are difficult to cover and Terrestrial Edge Computing (TEC) infrastructures are unavailable, solving the computation computational offloading for Internet of Vehicles (IoV) scenarios is challenging. Current terrestrial networks have high data rates, great connectivity, and low delay, but global coverage is limited. Space-Air-Ground Integrated Networks (SAGIN) can improve the coverage limitations of terrestrial networks and enhance disaster resistance. However, the rising complexity and heterogeneity of networks make it difficult to find a robust and intelligent computational offload strategy. Therefore, joint scheduling of space, air, and ground resources is needed to meet the growing demand for services. In light of this, we propose an integrated network framework for Space-Air Auxiliary Vehicle Computation (SA-AVC) and build a system model to support various IoV services in remote areas. Our model aims to maximize delay and fair utility and increase the utilization of satellites and Autonomous aerial vehicles (AAVs). To this end, we propose a Deep Reinforcement Learning algorithm to achieve real-time computational computational offloading decisions. We utilize the Rank-based Prioritization method in Prioritized Experience Replay (PER) to optimize our algorithm. We designed simulation experiments for validation and the results show that our proposed algorithm reduces the average system delay by 17.84%, 58.09%, and 58.32%, and the average variance of the task completion delay will be reduced by 29.41%, 48.74%, and 49.58% compared to the Deep Q Network (DQN), Q-learning and RandomChoose algorithms.

关键词： Satellites Delays Autonomous aerial vehicles computational modeling Optimization Low earth orbit satellites Disasters Space-air-ground integrated networks Resource management Processor scheduling Space-Air-Ground integrated network (SAGIN) deep reinforcement learning deep Q network (DQN) mobile edge computing (MEC)

来源：评论

学校读者我要写书评

暂无评论

computational Hydrodynamic modeling of the Vertical Axis Current Turbine

Computational Hydrodynamic Modeling of the Vertical Axis Cur...

引用

作者： Ji LI Shu YAN Meng LI Gang LIU Northeast Petroleum University Petroleum Engineering Institute Earth Sciences Institute Northeast Petroleum University

The device is designed to extract tidal energy when working in the shallow water. The turbine has a rotor with a diameter of 30 meters;three vertical blades of 3 meters span with a 1 m chord airfoil. The rotor frequency is 0.05 Hz with a wide range current speed. The analysis model based on Double Multiple Steam tube, have been developed to predict the steady and dynamic performances with fixed or self-acting variable pitch straight-blades. With the aid of Mathcad computational program, the hydrodynamic analysis of the VACT is given by using the Blade element theory and Momentum theory. In the program, a DoubleMultiple Stream tube Model is developed for analysis each stream tube. A theoretical analysis and a numerical prediction of the turbine performances as well as comparison with the experimental test results on the model turbine will be presented and discussed.

关键词： Hydrodynamic modeling Double-multiple stream tube Vertical Axis Current Turbine computational modeling

来源：评论

学校读者我要写书评

暂无评论

A DRL-Based Service Offloading Approach Using DAG for Edge computational Orchestration

引用

IEEE TRANSACTIONS ON computational SOCIAL SYSTEMS 2024年第3期11卷 3070-3078页

作者： Mekala, M. S. Dhiman, Gaurav Srivastava, Gautam Nain, Zulqar Zhang, Haolin Viriyasitavat, Wattana Varma, G. P. S. Yeungnam Univ Dept Informat & Commun Engn Gyongsan 712749 South Korea Yeungnam Univ RLRC Autonomous Vehicle Parts & Mat Innovat Gyongsan 712749 South Korea Govt Bikram Coll Commerce Dept Comp Sci Patiala 147001 Punjab India Chandigarh Univ Gharuan Dept Comp Sci & Engn Univ Ctr Res & Dev Mohali 140413 India Graph Era Deemed Univ Dept Comp Sci & Engn Dehra Dun 248002 Uttarakhand India Brandon Univ Dept Math & Comp Sci Brandon MB R7A 6A9 Canada China Med Univ Res Ctr Interneural Comp Taichung 40402 Taiwan Ohio State Univ Dept Elect & Comp Engn Columbus OH 43210 USA Chulalongkorn Univ Fac Commerce & Accountancy Dept Stat Bangkok 10330 Thailand Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vijayawada 522502 Andhra Pradesh India

Edge infrastructure and Industry 4.0 required services are offered by edge-servers (ESs) with different computation capabilities to run social application's workload based on a leased-price method. The usage of Social Internet of Things (SIoT) applications increases day-to-day, which makes social platforms very popular and simultaneously requires an effective computation system to achieve high service reliability. In this regard, offloading high required computational social service requests (SRs) in a time slot based on directed acyclic graph (DAG) is an NP-complete problem. Most state-of-art methods concentrate on the energy preservation of networks but neglect the resource sharing cost and dynamic subservice execution time (SET) during the computation and resource sharing. This article proposes a two-step deep reinforcement learning (DRL)-based service offloading (DSO) approach to diminish edge server costs through a DRL influenced resource and SET analysis (RSA) model. In the first level, the service and edge server cost is considered during service offloading. In the second level, the R-retaliation method evaluates resource factors to optimize resource sharing and SET fluctuations. The simulation results show that the proposed DSO approach achieves low execution costs by streamlining dynamic service completion and transmission time, server cost, and deadline violation rate attributes. Compared to the state-of-art approaches, our proposed method has achieved high resource usage with low energy consumption.

关键词： Costs Quality of service Servers Resource management Processor scheduling Task analysis computational modeling Adaptive quality-of-service (QoS) deep reinforcement learning (DRL) method edge computing optimal measurement analysis service offloading (SO) and scheduling

来源：评论

学校读者我要写书评

暂无评论

Slim UNETR: Scale Hybrid Transformers to Efficient 3D Medical Image Segmentation Under Limited computational Resources

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2024年第3期43卷 994-1005页

作者： Pang, Yan Liang, Jiaming Huang, Teng Chen, Hao Li, Yunhao Li, Dan Huang, Lin Wang, Qiong Guangzhou Univ Inst Artificial Intelligence & Blockchain Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Dept Chem & Biol Engn Hong Kong Peoples R China Metropolitan State Univ Denver Coll Aerosp Comp Engn & Design ACED Dept Engn & Engn Technol Denver CO 80204 USA Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Comp Vis & Virtual Real Tec Shenzhen 518057 Peoples R China

Hybrid transformer-based segmentation approaches have shown great promise in medical image analysis. However, they typically require considerable computational power and resources during both training and inference stages, posing a challenge for resource-limited medical applications common in the field. To address this issue, we present an innovative framework called Slim UNETR, designed to achieve a balance between accuracy and efficiency by leveraging the advantages of both convolutional neural networks and transformers. Our method features the Slim UNETR Block as a core component, which effectively enables information exchange through self-attention mechanism decomposition and cost-effective representation aggregation. Additionally, we utilize the throughput metric as an efficiency indicator to provide feedback on model resource consumption. Our experiments demonstrate that Slim UNETR outperforms state-of-the-art models in terms of accuracy, model size, and efficiency when deployed on resource-constrained devices. Remarkably, Slim UNETR achieves 92.44% dice accuracy on BraTS2021 while being 34.6x smaller and 13.4x faster during inference compared to Swin UNETR.

关键词： Biomedical imaging Transformers Image segmentation Task analysis computational modeling Three-dimensional displays Solid modeling 3D medical segmentation lightweight medical image analysis resource-limited application

来源：评论

学校读者我要写书评

暂无评论

Fast computational techniques for modeling RFX-mod fusion devices on hybrid CPU-GPU architectures

Fast computational techniques for modeling RFX-mod fusion de...

引用

URSI International Symposium on Electromagnetic Theory (EMTS)

作者： Domenico Abate Bruno Carpentieri Andrea G. Chiariello Giuseppe Marchiori Nicolò Marconato Stefano Mastrostefano Guglielmo Rubinacci Salvatore Ventre Fabio Villone Consorzio RFX Padova Italy DIEI Università di Cassino e del Lazio Meridionale Cassino FR Italy Nottingham Trent University School of Science and Technology Nottingham UK DIII Seconda Università di Napoli Aversa CE Italy DIETI Università di Napoli Federico II Napoli

ISBN: (纸本)9781509025039

We presents fast computational techniques applied to modelling the RFX-mod fusion device. We derive an integral equation model for estimating the current distribution in the conducting structures, and we compute the input-output transfer functions. By using hybrid CPU-GPU parallelization, speed-up factors of about 200 can be obtained against uniprocessor computation.

关键词： Plasmas computational modeling Mathematical model Coils Three-dimensional displays Transfer functions Conductors

来源：评论

学校读者我要写书评

暂无评论

Lightweight SDENet Fusing Model-Based and Learned Features for computational Histopathology

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2024年第6期18卷 1123-1137页

作者： Bao, Rina Zhao, Yunxin Srivastava, Akhil Frazier, Shellaine Palaniappan, Kannappan Univ Missouri Columbia MO 65211 USA Harvard Med Sch Boston Childrens Hosp Boston MA 02115 USA Univ Missouri Dept Elect Engn & Comp Sci Columbia MO 65211 USA Univ Missouri Sch Med Columbia MO 65211 USA

Model-based deep learning has the potential to significantly reduce the size of deep architectures while matching the competitive performance of much deeper and wider architectures. We demonstrate the advantage of combining model-based handcrafted features with learned features for AI-enabled computational pathology. Digital histopathology with whole slide image analysis using gigapixel-sized images and deep neural networks are being actively investigated for diagnosis and treatment, but require tens to hundreds of millions of learnable parameters (network weights). Additionally, using deep architectures effectively in medical applications, including pathology, has a number of challenges, including limited supervisory manual expert labels, a paucity of training data to cover clinical heterogeneity, many rare disease classes, complex anatomical structures and very large deep network architectures that have difficulty with domain adaptation along with generalization to new patient cohorts. We propose a lightweight squeeze, delineate, and excitation network (SDENet) deep learning architecture for pathology image cell and nuclei segmentation. SDENet is based on a novel hybrid network modular design, composed of a combination of model-based engineered or predefined filters for extracting salient information based on expert medical knowledge, with a learnable stack of convolution filters to capture structural relationships using complementary bottom-up data driven features. The proposed SDENetmodel-based approach learns rich feature representations of histopathology images, achieving a highly competitive performance on the MoNuSeg dataset for cell and nuclei segmentation with almost 90% fewer learnable parameters, and generalizes better to unseen image datasets, achieving about 20% higher accuracy on TNBC, compared to the widely used UNet architecture.

关键词： Image segmentation computational modeling Training Data models Deep learning Computer architecture Adaptation models Histopathology Network architecture Knowledge engineering Cell segmentation computational pathology convolution neural networks engineered features hand-crafted features histopathology medical image analysis nuclei segmentation stroma microenvironment

来源：评论

学校读者我要写书评

暂无评论

NMR and computational molecular modeling studies of mineral surfaces and interlayer galleries: A review

引用

AMERICAN MINERALOGIST 2015年第7期100卷 1341-1354页

作者： Kirkpatrick, R. James Kalinichev, Andrey G. Bowers, Geoffrey M. Yazaydin, A. Oezguer Krishnan, Marimuthu Saharay, Moumita Morrow, Christin P. Michigan State Univ Coll Nat Sci E Lansing MI 48824 USA Ecole Mines Nantes Lab SUBATECH F-44307 Nantes 3 France Alfred Univ Div Chem Alfred NY 14802 USA Alfred Univ Dept Mat Engn Alfred NY 14802 USA Michigan State Univ Dept Chem E Lansing MI 48824 USA UCL Dept Chem Engn London WC1E 7JE England Int Inst Informat Technol Ctr Computat Nat Sci & Bioinformat Hyderabad 500032 Andhra Pradesh India Osmania Univ Dept Phys Hyderabad 500007 Telengana India

This paper reviews experimental nuclear magnetic resonance (NMR) and computational molecular dynamics (MD) investigations of the structural and dynamical behavior of cations, anions, H2O, and CO2 on the surfaces and in the interlayer galleries of layer-structure minerals and their composites with polymers and natural organic matter (NOM). The interaction among mineral surfaces, charge-balancing cations or anions, H2O, CO2, and NOM are dominated by Coulombic, H-bond, and van der Waals interactions leading to statically and dynamically disordered systems and molecular-scale processes with characteristic room-temperature frequencies varying from at least as small as 10(2) to >10(12) Hz. NMR spectroscopy provides local structural information about such systems through the chemical shift and quadrupolar interactions and dynamical information at frequencies from the sub-kilohertz to gigahertz ranges through the T-1 and T-2 relaxation rates and line shape analysis. It is often difficult to associate a specific structure or dynamical process to a given NMR observation, however, and computational molecular modeling is often effective in providing a much more detailed picture in this regard. The examples discussed here illustrate these capabilities of combining experimental NMR and computational modeling in mineralogically and geochemically important systems, including clay minerals and layered double hydroxides.

关键词： Mineral surfaces mineral-fluid interactions clay minerals natural organic matter NMR molecular dynamics computational modeling layered double hydroxides Review article Invited Centennial article

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：