Results 21 to 30 of about 4,352,186 (159)
Gaoya dianqi, 2022 穿柜套管是开关柜中的关键绝缘件之一，在高湿环境下容易产生凝露导致运行过程中出现沿面放电现象，给配电网的安全运行带来了隐患。文中基于三维卷积搭建了C3D和MiCT时空网络研究平台，理论分析了紫外视频时空特征的提取方法。分别研究了学习率、批处理尺寸、网络深度对MiCT网络性能的影响，并根据研究结果优化了网络模型。结果表明：MiCT网络相较于C3D网络使用了更少的三维卷积，在减少计算参量的同时获得了更强的泛化能力，具有时空不对称特性的MiCT模块比三维卷积模块能更有效地获取紫外视频的时空特征 ...
李岩 +4 more
doaj
智能科学与技术学报, 2022 群体行为往往能产生远超个体行为的价值和复杂度。为了在个体智能的基础上更有效地衍生出群体智能，需要基于群体熵来科学地衡量群体智能水平，并以群体熵为引导目标，推动群体智能的增强和演进。针对这个重要的科学问题，以无人小车群体为研究对象，提出基于参数共享和群体策略熵的多智能体soft Q learning算法，通过共享智能体的观测信息，并结合最大熵强化学习方法，实现探索型任务中群体策略的持续学习更新。同时，通过将群体熵定义为度量工具，刻画群体学习中熵变化模式，实现对群智汇聚过程的定量分析。
冯埔 +4 more
doaj +1 more source
Emerging applications of large language models in ecology and conservation science
Conservation Biology, EarlyView.Abstract Large language models (LLMs) mark a major development in artificial intelligence, with potentially transformative implications for ecology and conservation science. Built on advanced deep‐learning architectures, these models can support a wide range of tasks. We reviewed emerging applications of LLMs, drawing on the wider scientific literature
Christos Mammides +5 more
wiley +1 more source
, 2021 本发明涉及工业无线网络技术，具体地说，是一种基于多智能体深度强化学习的工业无线网络资源分配方法，包括以下步骤：建立端边协同的工业无线网络；确立工业无线网络端边资源分配的优化问题；建立马尔科夫决策模型；采用多智能体深度强化学习方法，构建资源分配神经网络模型；离线训练神经网络模型，直至奖励收敛到稳定值；基于离线训练结果，工业无线网络在线执行资源分配，处理工业任务。本发明能够实时、高能效地对工业无线网络进行端边协同的资源分配，在满足有限能量、计算资源约束下 ...
夏长清 +5 more
core
Attainment Pairing Effects on Cognitive Conflict in Technology‐enhanced EFL Cooperative Tasks
International Journal of Applied Linguistics, Volume 36, Issue 2, Page 1594-1605, May 2026.ABSTRACT This study examines how attainment pairing (high‐high versus high‐low versus low‐low attainment) impacts English as a Foreign Language (EFL) learner engagement during technology‐enhanced cooperative writing tasks. Seventy‐eight Chinese university learners formed 39 dyads (13 pairs per group) via Tencent Meeting.
Ying Liu, Allen Thurston
wiley +1 more source
Rare Metals, Volume 45, Issue 2, February 2026.ABSTRACT The high accuracy in surface‐enhanced Raman scattering‐lateral flow immunoassays (SERS–LFIAs) is critical for reliable point‐of‐care testing (POCT) in clinical diagnostics. Conventional approaches are often affected by sampling variability and uneven distribution of immunoprobes, leading to unreliable signal fluctuations.
Shuai Zhao +9 more
wiley +1 more source
Research progress of causal inference in reinforcement learning framework(强化学习框架中因果推断研究进展)
Zhejiang Daxue xuebao. Lixue banCausal reasoning has been extensively studied in all fields of science. In recent decades, there have been a number of innovations in the development and implementation of methods aimed at determining causality.
刘华玲(LIU Hualing) +2 more
doaj +1 more source
Rare Metals, Volume 45, Issue 1, January 2026.ABSTRACT High‐entropy alloys (HEAs) have emerged as a transformative class of materials distinguished by their complex chemical compositions, unique microstructures, and remarkable mechanical and functional properties. Traditionally, the discovery and optimization of HEAs have relied on conventional methods, including trial‐and‐error experimentation ...
Chrispin Ouko Zamzu +2 more
wiley +1 more source
Dianxin kexue现有基于深度学习的调制识别在训练阶段需要大量IQ信号样本，而复杂电磁环境中很难获取大量样本，导致基于深度学习的调制识别算法泛化性能下降。针对网络泛化能力差的问题，提出了一种基于信号增强的调制识别（signal enhancement based modulation recognition，SEBMR）算法。首先，设计了捕获IQ信号全局特征的特征提取及重构模块；其次，提出了基于辅助分类生成对抗网络（auxiliary classifier generative adversarial network ...
程风云, 周金
doaj +1 more source
智能科学与技术学报, 2022 当代系统认知、管理与控制的核心理论、方法与技术已经转移到大数据和人工智能技术上，这导致当前人工智能技术条件局限与复杂系统认知、管理、控制的需求之间形成了一道鸿沟。因此，现实的需求催生了人工智能的一种新型形态——人机混合增强智能形态，即人类智能与机器智能协同贯穿于系统认知、管理、控制等过程的始终，人类的认知和机器智能认知互相混合，形成增强型的智能形态，这种形态是人工智能或机器智能可行的、重要的成长模式。提出了一种物理-数据-知识混合驱动的人机混合增强智能系统管控方法。从可信分布式数据、计算和算法 ...
张俊 +12 more
doaj