Results 11 to 20 of about 411,293 (150)

基于动态自选择参数共享的合作多智能体强化学习算法

open access: yes智能科学与技术学报, 2022
在多智能体强化学习的研究中,参数共享作为学习过程中一种信息集中的方式,可以有效地缓解不稳定性导致的学习低效性。但是,在实际应用中智能体使用同样的策略往往会带来不利影响。为了解决此类过度共享的问题,提出了一种新的方法来赋予智能体自动识别可能受益于共享参数的智能体的能力,并且可以在学习过程中动态地选择共享参数的对象。具体来说,智能体需要将历史轨迹编码为可表示其潜在意图的隐信息,并通过与其余智能体隐信息的对比选择共享参数的对象。实验表明,提出的方法在多智能体系统中不仅可以提高参数共享的效率 ...
王涵, 俞扬, 姜远
doaj   +1 more source

Research on Entity Relationship Extraction Model of Food Public Opinion Based on CNN-BLSTM(基于CNN-BLSTM的食品舆情实体关系抽取模型研究) [PDF]

open access: yesShipin kexue jishu xuebao, 2021
The extraction of food public opinion entity relationship is the key technology for constructing the map of food sensation knowledge, and it is also an important research topic in the field of information extraction.
WANG Qingbang(王庆棒)   +5 more
doaj   +1 more source

Application of Migration Learning in Transfer of Oil Spectral Model(迁移学习在食用油光谱模型转移中的应用) [PDF]

open access: yesShipin kexue jishu xuebao, 2019
Models established by spectral data collected by different spectroscopy instruments have model failure problems, leading to the low utilization rate, which is not conducive to the development of the spectroscopy industry.
LIU Cuiling(刘翠玲)   +5 more
doaj   +1 more source

地铁列车驾驶技术发展综述:从人工驾驶到智能无人驾驶

open access: yes智能科学与技术学报, 2022
基于国内外地铁列车驾驶技术的发展现状,提出并阐述了地铁列车驾驶技术发展的4个阶段为人工驾驶、自动驾驶、无人驾驶、智能无人驾驶。概括了我国无人驾驶地铁列车的建设情况,针对目前基于神经网络这类机器学习方法的列车控制方法可解释性差的弊端,引入了深度模糊系统的概念,提出了基于人机混合智能的地铁智能无人驾驶基本框图,为将处理紧急情况的专家经验、人工智能算法和无人驾驶系统结合起来,实现智能无人驾驶提供了一种具有前景的解决思路。
赖文柱   +4 more
doaj   +1 more source

Study on Chicken Quality Classification Method Based on K-Means-RBF(基于K-means-RBF的鸡肉品质分类方法研究) [PDF]

open access: yesShipin kexue jishu xuebao, 2018
The chicken is easy to get spoilage during the storage and transportation. The hyperspectral imaging technology with the maps and spectral combination features was applied in this study, which could extract the spectral characteristics, texture and color
XING Suxia(邢素霞)   +3 more
doaj   +1 more source

Design and Realization of Food Safety Monitoring and Pre-Control System Based on Multi-Source and Big Data(基于多源大数据食品安全监测预控系统的设计与实现) [PDF]

open access: yesShipin kexue jishu xuebao, 2018
The traditional food safety monitoring usually adopts the manual monitoring mode,which has the characteristics of low efficiency, poor timeliness, and incomplete data.
LIU Cuiling(刘翠玲)   +3 more
doaj   +1 more source

基于CPA状态方程计算水蒸汽的热力学物性

open access: yes, 2013
水和水蒸气的热力学性质是工程中重要的基础数据,获得可靠的计算途径对于工程设计具有重要的意义。本文利用CPA方程研究了水和水蒸气热力学性质的计算,建立了基于CPA方程的热力学性质计算模型,主要研究了水的饱和状态、水和水蒸气的PVT性质以及焓值计算。通过考察研究发现,在(0~22)bar范围内,CPA方程计算的水的热力学性质与其实验数据具有良好的一致性,所计算的数据与实验数据的平均相对偏差小于1%,最大偏差不超过5%,满足工程计算的精度需要 ...
曾志勇   +3 more
core   +5 more sources

Determination of Volatile Basic Nitrogen in Pork Based on TDLAS Technique(基于TDLAS技术判定猪肉挥发性盐基氮含量) [PDF]

open access: yesShipin kexue jishu xuebao, 2018
Total volatile basic nitrogen (TVB-N) content is an important indicator for pork freshness detection. In order to detect the concentration of hydrogen sulfide gas during the deterioration of pork, tunable diode laser absorption spectroscopy (TDLAS) was ...
ZHAO Guanghua(赵广华)   +2 more
doaj   +1 more source

Study on Risk Assessment Method of Agricultural Product Quality and Safety(农产品质量安全风险评估方法探索) [PDF]

open access: yesShipin kexue jishu xuebao, 2016
The existing quality and safety risk assessment methods for agricultural products are mostly the single factor evaluation. The valuation methods of other fields could provide new ideas for agricultural product risk assessment.
LIU Cuiling(刘翠玲)   +2 more
doaj   +1 more source

Analysis on Characteristics of Urban Consumers Demand for Food Safety——Take Demand of Milk for Example(城市消费者对食品安全的需求特征分析——以牛奶需求为例) [PDF]

open access: yesShipin kexue jishu xuebao, 2017
Food safety is a global problem and developing countries are more troubled. In China, food safety incidents have often occurred in recent years. It is an important research method to study the demand characteristics of food safety from the perspective of
JIANG Tongqiang(姜同强)   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy