首页 > 最新文献

Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)最新文献

英文 中文
Improving Targeted Mass Spectrometry Data Analysis with Nested Active Machine Learning 利用嵌套主动机器学习改进目标质谱数据分析
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-05-12 DOI: 10.1002/aisy.202300773
Duran Bao, Qingbo Shu, Bo Ning, Michael Tang, Yubing Liu, Noel Wong, Zhengming Ding, Zizhan Zheng, Christopher J. Lyon, Tony Hu, Jia Fan

Targeted mass spectrometry (MS) holds promise for precise protein and protein-representative peptide identification and quantification, enhancing disease diagnosis. However, its clinical application is hindered by complex data analysis and expert review requirements. It is hypothesized that machine learning (ML) models can automate data analysis to accelerate the clinical application of MS. The approach involves an ML-driven pipeline that extracts statistical and morphological features from an MS target region and feeds these features into ML algorithms to generate and assess predictive models. The findings demonstrate ML prediction models exhibit superior performance when trained on extracted features versus raw spectra intensity data and that random forest models exhibit robust classification performance in both internal and external validation datasets. These models remain effective across varying training dataset sizes and positive sample rates and are enhanced by a nested active learning approach. This approach can thus revolutionize clinical MS applications.

靶向质谱(MS)有望实现蛋白质和蛋白质代表肽的精确鉴定和定量,从而提高疾病诊断水平。然而,复杂的数据分析和专家审查要求阻碍了其临床应用。假设机器学习(ML)模型可以自动进行数据分析,从而加快 MS 的临床应用。该方法涉及一个 ML 驱动的管道,该管道从 MS 靶区提取统计和形态特征,并将这些特征输入 ML 算法,以生成和评估预测模型。研究结果表明,ML 预测模型在提取的特征与原始光谱强度数据的对比训练中表现出更优越的性能,随机森林模型在内部和外部验证数据集中都表现出稳健的分类性能。这些模型在不同的训练数据集规模和阳性样本率下依然有效,并通过嵌套主动学习方法得到增强。因此,这种方法可以彻底改变临床 MS 应用。
{"title":"Improving Targeted Mass Spectrometry Data Analysis with Nested Active Machine Learning","authors":"Duran Bao,&nbsp;Qingbo Shu,&nbsp;Bo Ning,&nbsp;Michael Tang,&nbsp;Yubing Liu,&nbsp;Noel Wong,&nbsp;Zhengming Ding,&nbsp;Zizhan Zheng,&nbsp;Christopher J. Lyon,&nbsp;Tony Hu,&nbsp;Jia Fan","doi":"10.1002/aisy.202300773","DOIUrl":"10.1002/aisy.202300773","url":null,"abstract":"<p>Targeted mass spectrometry (MS) holds promise for precise protein and protein-representative peptide identification and quantification, enhancing disease diagnosis. However, its clinical application is hindered by complex data analysis and expert review requirements. It is hypothesized that machine learning (ML) models can automate data analysis to accelerate the clinical application of MS. The approach involves an ML-driven pipeline that extracts statistical and morphological features from an MS target region and feeds these features into ML algorithms to generate and assess predictive models. The findings demonstrate ML prediction models exhibit superior performance when trained on extracted features versus raw spectra intensity data and that random forest models exhibit robust classification performance in both internal and external validation datasets. These models remain effective across varying training dataset sizes and positive sample rates and are enhanced by a nested active learning approach. This approach can thus revolutionize clinical MS applications.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300773","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140986891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fast Exploring Literature by Language Machine Learning for Perovskite Solar Cell Materials Design 通过语言机器学习快速探索文献,设计 Perovskite 太阳能电池材料
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-05-12 DOI: 10.1002/aisy.202300678
Lei Zhang, Yiru Huang, Leiming Yan, Jinghao Ge, Xiaokang Ma, Zhike Liu, Jiaxue You, Alex K. Y. Jen, Shengzhong Frank Liu

Making computers automatically extract latent scientific knowledge from literature is highly desired for future materials and chemical research in the artificial intelligence era. Herein, the natural language processing (NLP)-based machine learning technique to build language models and automatically extract hidden information regarding perovskite solar cell (PSC) materials from 29 060 publications is employed. The concept that there are light-absorbing materials, electron-transporting materials, and hole-transporting materials in PSCs is successfully learned by the NLP-based machine learning model without a time-consuming human expert training process. The NLP model highlights a hole-transporting material that receives insufficient attention in the literature, which is then elaborated via density functional theory calculations to provide an atomistic view of the perovskite/hole-transporting layer heterostructures and their optoelectronic properties. Finally, the above results are confirmed by device experiments. The present study demonstrates the viability of NLP as a universal machine learning tool to extract useful information from existing publications.

让计算机自动从文献中提取潜在的科学知识,是人工智能时代未来材料和化学研究的殷切希望。本文采用基于自然语言处理(NLP)的机器学习技术,从 29 060 篇文献中建立语言模型并自动提取有关包晶体太阳能电池(PSC)材料的隐藏信息。基于 NLP 的机器学习模型成功地学习了 PSC 中存在光吸收材料、电子传输材料和空穴传输材料的概念,而无需耗时的人工专家培训过程。NLP 模型强调了一种在文献中未得到充分关注的空穴传输材料,然后通过密度泛函理论计算对其进行了阐述,从而提供了一种关于包晶/空穴传输层异质结构及其光电特性的原子论视图。最后,上述结果得到了器件实验的证实。本研究证明了 NLP 作为通用机器学习工具从现有出版物中提取有用信息的可行性。
{"title":"Fast Exploring Literature by Language Machine Learning for Perovskite Solar Cell Materials Design","authors":"Lei Zhang,&nbsp;Yiru Huang,&nbsp;Leiming Yan,&nbsp;Jinghao Ge,&nbsp;Xiaokang Ma,&nbsp;Zhike Liu,&nbsp;Jiaxue You,&nbsp;Alex K. Y. Jen,&nbsp;Shengzhong Frank Liu","doi":"10.1002/aisy.202300678","DOIUrl":"10.1002/aisy.202300678","url":null,"abstract":"<p>Making computers automatically extract latent scientific knowledge from literature is highly desired for future materials and chemical research in the artificial intelligence era. Herein, the natural language processing (NLP)-based machine learning technique to build language models and automatically extract hidden information regarding perovskite solar cell (PSC) materials from 29 060 publications is employed. The concept that there are light-absorbing materials, electron-transporting materials, and hole-transporting materials in PSCs is successfully learned by the NLP-based machine learning model without a time-consuming human expert training process. The NLP model highlights a hole-transporting material that receives insufficient attention in the literature, which is then elaborated via density functional theory calculations to provide an atomistic view of the perovskite/hole-transporting layer heterostructures and their optoelectronic properties. Finally, the above results are confirmed by device experiments. The present study demonstrates the viability of NLP as a universal machine learning tool to extract useful information from existing publications.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300678","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140987492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Toward Collaborative Multitarget Search and Navigation with Attention-Enhanced Local Observation 利用注意力增强型局部观察实现多目标协同搜索和导航
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-05-07 DOI: 10.1002/aisy.202300761
Jiaping Xiao, Phumrapee Pisutsin, Mir Feroskhan

Collaborative multitarget search and navigation (CMTSN) is highly demanded in complex missions such as rescue and warehouse management. Traditional centralized and decentralized approaches fall short in terms of scalability and adaptability to real-world complexities such as unknown targets and large-scale missions. This article addresses this challenging CMTSN problem in three-dimensional spaces, specifically for agents with local visual observation operating in obstacle-rich environments. To overcome these challenges, this work presents the POsthumous Mix-credit assignment with Attention (POMA) framework. POMA integrates adaptive curriculum learning and mixed individual-group credit assignments to efficiently balance individual and group contributions in a sparse reward environment. It also leverages an attention mechanism to manage variable local observations, enhancing the framework's scalability. Extensive simulations demonstrate that POMA outperforms a variety of baseline methods. Furthermore, the trained model is deployed over a physical visual drone swarm, demonstrating the effectiveness and generalization of our approach in real-world autonomous flight.

在救援和仓库管理等复杂任务中,对协作式多目标搜索和导航(CMTSN)的需求很高。传统的集中式和分散式方法在可扩展性和适应现实世界的复杂性(如未知目标和大规模任务)方面存在不足。本文探讨了三维空间中这一具有挑战性的 CMTSN 问题,特别是在障碍物丰富的环境中具有本地视觉观测能力的代理。为了克服这些挑战,本研究提出了 "注意力混合学分分配"(POMA)框架。POMA 整合了自适应课程学习和个人-小组混合学分分配,以便在奖励稀少的环境中有效平衡个人和小组的贡献。它还利用注意力机制来管理可变的局部观察,从而增强了框架的可扩展性。大量的仿真证明,POMA 优于各种基准方法。此外,经过训练的模型被部署在一个物理可视无人机群上,证明了我们的方法在现实世界自主飞行中的有效性和通用性。
{"title":"Toward Collaborative Multitarget Search and Navigation with Attention-Enhanced Local Observation","authors":"Jiaping Xiao,&nbsp;Phumrapee Pisutsin,&nbsp;Mir Feroskhan","doi":"10.1002/aisy.202300761","DOIUrl":"10.1002/aisy.202300761","url":null,"abstract":"<p>Collaborative multitarget search and navigation (CMTSN) is highly demanded in complex missions such as rescue and warehouse management. Traditional centralized and decentralized approaches fall short in terms of scalability and adaptability to real-world complexities such as unknown targets and large-scale missions. This article addresses this challenging CMTSN problem in three-dimensional spaces, specifically for agents with local visual observation operating in obstacle-rich environments. To overcome these challenges, this work presents the POsthumous Mix-credit assignment with Attention (POMA) framework. POMA integrates adaptive curriculum learning and mixed individual-group credit assignments to efficiently balance individual and group contributions in a sparse reward environment. It also leverages an attention mechanism to manage variable local observations, enhancing the framework's scalability. Extensive simulations demonstrate that POMA outperforms a variety of baseline methods. Furthermore, the trained model is deployed over a physical visual drone swarm, demonstrating the effectiveness and generalization of our approach in real-world autonomous flight.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300761","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141005291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Touch to Learn: A Review of Haptic Technology's Impact on Skill Development and Enhancing Learning Abilities for Children 触摸学习:触觉技术对儿童技能发展和提高学习能力的影响综述
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-05-07 DOI: 10.1002/aisy.202300731
Amal Hatira, Mine Sarac

Early childhood education is critical in shaping children's intellectual and motor skills as it provides a solid foundation for cognitive, social, and emotional development, which highly depends on spatial thinking. Haptic feedback can be effectively used for educational and training purposes, particularly in fields such as physics, math, and arts, offering a more interactive learning media and supporting kinesthetic learners by its nature. Herein, different ways of implementing haptic feedback on different educational scenarios from the perspective of technological development and their impact on children's learned skills and outcomes (e.g., their motivation, their analytical or spatial thinking abilities, or fine motor skills) will be examined. This article provides an overview of how haptic feedback has been implemented in different learning scenarios for children. Particularly, it is indicated that haptics can potentially improve early childhood learning outcomes and spatial reasoning skills as it can increase children's interest, participation, performance in educational activities, and analytical ability. The major drawbacks of the current studies, such as variance in participants’ learning challenges and small sample numbers are also highlighted.

幼儿教育对于塑造儿童的智力和运动技能至关重要,因为它为认知、社交和情感发展奠定了坚实的基础,而这些发展在很大程度上取决于空间思维。触觉反馈可以有效地用于教育和培训目的,尤其是在物理、数学和艺术等领域,它提供了一种更具互动性的学习媒体,并为动觉学习者提供了支持。本文将从技术发展的角度,探讨在不同教育场景中实施触觉反馈的不同方式,以及它们对儿童所学技能和成果(如学习动机、分析或空间思维能力或精细动作技能)的影响。本文概述了触觉反馈在儿童不同学习场景中的应用。文章特别指出,触觉反馈可以提高儿童对教育活动的兴趣、参与度、学习成绩和分析能力,因此有可能改善幼儿的学习成果和空间推理能力。此外,还强调了当前研究的主要缺点,如参与者的学习挑战存在差异和样本数量较少。
{"title":"Touch to Learn: A Review of Haptic Technology's Impact on Skill Development and Enhancing Learning Abilities for Children","authors":"Amal Hatira,&nbsp;Mine Sarac","doi":"10.1002/aisy.202300731","DOIUrl":"10.1002/aisy.202300731","url":null,"abstract":"<p>Early childhood education is critical in shaping children's intellectual and motor skills as it provides a solid foundation for cognitive, social, and emotional development, which highly depends on spatial thinking. Haptic feedback can be effectively used for educational and training purposes, particularly in fields such as physics, math, and arts, offering a more interactive learning media and supporting kinesthetic learners by its nature. Herein, different ways of implementing haptic feedback on different educational scenarios from the perspective of technological development and their impact on children's learned skills and outcomes (e.g., their motivation, their analytical or spatial thinking abilities, or fine motor skills) will be examined. This article provides an overview of how haptic feedback has been implemented in different learning scenarios for children. Particularly, it is indicated that haptics can potentially improve early childhood learning outcomes and spatial reasoning skills as it can increase children's interest, participation, performance in educational activities, and analytical ability. The major drawbacks of the current studies, such as variance in participants’ learning challenges and small sample numbers are also highlighted.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300731","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141005672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Real-Time Noise Source Estimation of a Camera System from an Image and Metadata 根据图像和元数据实时估计摄影系统的噪声源
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-04-26 DOI: 10.1002/aisy.202300479
Maik Wischow, Patrick Irmisch, Anko Boerner, Guillermo Gallego

Autonomous machines must self-maintain proper functionality to ensure the safety of humans and themselves. This pertains particularly to its cameras as predominant sensors to perceive the environment and support actions. A fundamental camera problem addressed in this study is noise. Solutions often focus on denoising images a posteriori, that is, fighting symptoms rather than root causes. However, tackling root causes requires identifying the noise sources, considering the limitations of mobile platforms. In this work, a real-time, memory-efficient, and reliable noise source estimator that combines data-based and physically based models is investigated. To this end, a deep neural network that examines an image with camera metadata for major camera noise sources is built and trained. In addition, it quantifies unexpected factors that impact image noise or metadata. This study investigates seven different estimators on six datasets that include synthetic noise, real-world noise from two camera systems, and real-field campaigns. For these, only the model with most metadata is capable to accurately and robustly quantify all individual noise contributions. This method outperforms total image noise estimators and can be plug-and-play deployed. It also serves as a basis to include more advanced noise sources, or as part of an automatic countermeasure feedback loop to approach fully reliable machines.

自动机器必须自我维持适当的功能,以确保人类和自身的安全。这尤其与作为感知环境和支持行动的主要传感器的摄像头有关。本研究涉及的一个基本摄像头问题是噪声。解决方案通常侧重于对图像进行事后去噪,即治标不治本。然而,考虑到移动平台的局限性,要从根本上解决问题,就必须找出噪声源。在这项工作中,我们研究了一种实时、内存效率高、可靠的噪声源估计器,它结合了基于数据的模型和基于物理的模型。为此,我们构建并训练了一个深度神经网络,该网络可检查带有相机元数据的图像,找出主要的相机噪点来源。此外,它还能量化影响图像噪点或元数据的意外因素。本研究在六个数据集上研究了七种不同的估算器,这些数据集包括合成噪点、来自两个相机系统的真实世界噪点以及真实的现场活动。在这些数据集中,只有元数据最多的模型能够准确、稳健地量化所有单独的噪声贡献。这种方法优于总体图像噪声估计方法,可以即插即用。它还可作为包括更高级噪声源的基础,或作为自动对策反馈回路的一部分,以接近完全可靠的机器。
{"title":"Real-Time Noise Source Estimation of a Camera System from an Image and Metadata","authors":"Maik Wischow,&nbsp;Patrick Irmisch,&nbsp;Anko Boerner,&nbsp;Guillermo Gallego","doi":"10.1002/aisy.202300479","DOIUrl":"https://doi.org/10.1002/aisy.202300479","url":null,"abstract":"<p>Autonomous machines must self-maintain proper functionality to ensure the safety of humans and themselves. This pertains particularly to its cameras as predominant sensors to perceive the environment and support actions. A fundamental camera problem addressed in this study is noise. Solutions often focus on denoising images a posteriori, that is, fighting symptoms rather than root causes. However, tackling root causes requires identifying the noise sources, considering the limitations of mobile platforms. In this work, a real-time, memory-efficient, and reliable noise source estimator that combines data-based and physically based models is investigated. To this end, a deep neural network that examines an image with camera metadata for major camera noise sources is built and trained. In addition, it quantifies unexpected factors that impact image noise or metadata. This study investigates seven different estimators on six datasets that include synthetic noise, real-world noise from two camera systems, and real-field campaigns. For these, only the model with most metadata is capable to accurately and robustly quantify all individual noise contributions. This method outperforms total image noise estimators and can be plug-and-play deployed. It also serves as a basis to include more advanced noise sources, or as part of an automatic countermeasure feedback loop to approach fully reliable machines.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300479","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141488378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Intelligent Structure Searching and Designs for Nanoclusters: Effective Units in Atomic Manufacturing 纳米团簇的智能结构搜索和设计:原子制造中的有效单元
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-04-26 DOI: 10.1002/aisy.202300716
Junfeng Gao, Luneng Zhao, Yuan Chang, Yanxue Zhang, Shi Qiu, Yuanyuan Zhao, Hongsheng Liu, Jijun Zhao

Clusters, an aggregation of several to thousands of atoms, molecules, or ions, are the building blocks of novel functional materials by atomic manufacturing and exhibit excellent applications in catalysis, quantum information, and nanomedicine. The evolution of cluster structures has been studied for many years. Many effective structural search methods, such as genetic algorithm, basin-hopping, and so on, have been developed. However, the efficient execution of these methods relies on precise energy calculators, such as density functional theory (DFT) calculations. Up to now, limited by computational methods and capabilities, the researches mainly focus on free-standing clusters, which are different from clusters in practical applications. Recently, the rapid development of big data-driven machine learning is expected to replace DFT for high-precision large-scale computing. In this review, the present cluster search methods and challenges currently faced have been summarized. It is proposed that the development of artificial intelligence has the potential to solve some practical problems including the structural and properties evolution of clusters in complex environment, causing revolutionary developments in the fields of catalysis, quantum information, and nanomedicine based on clusters.

原子团簇是由数个至数千个原子、分子或离子聚集而成的,是原子制造新型功能材料的基石,在催化、量子信息和纳米医学方面有着卓越的应用。多年来,人们一直在研究团簇结构的演变。目前已开发出许多有效的结构搜索方法,如遗传算法、跳盆法等。然而,这些方法的有效执行有赖于精确的能量计算器,如密度泛函理论(DFT)计算。迄今为止,受限于计算方法和能力,研究主要集中在独立的集群上,这与实际应用中的集群有所不同。近年来,大数据驱动的机器学习发展迅速,有望取代 DFT 实现高精度大规模计算。本综述总结了目前的集群搜索方法和面临的挑战。文章提出,人工智能的发展有可能解决一些实际问题,包括复杂环境中团簇的结构和性质演化,从而在基于团簇的催化、量子信息和纳米医学等领域带来革命性的发展。
{"title":"Intelligent Structure Searching and Designs for Nanoclusters: Effective Units in Atomic Manufacturing","authors":"Junfeng Gao,&nbsp;Luneng Zhao,&nbsp;Yuan Chang,&nbsp;Yanxue Zhang,&nbsp;Shi Qiu,&nbsp;Yuanyuan Zhao,&nbsp;Hongsheng Liu,&nbsp;Jijun Zhao","doi":"10.1002/aisy.202300716","DOIUrl":"https://doi.org/10.1002/aisy.202300716","url":null,"abstract":"<p>Clusters, an aggregation of several to thousands of atoms, molecules, or ions, are the building blocks of novel functional materials by atomic manufacturing and exhibit excellent applications in catalysis, quantum information, and nanomedicine. The evolution of cluster structures has been studied for many years. Many effective structural search methods, such as genetic algorithm, basin-hopping, and so on, have been developed. However, the efficient execution of these methods relies on precise energy calculators, such as density functional theory (DFT) calculations. Up to now, limited by computational methods and capabilities, the researches mainly focus on free-standing clusters, which are different from clusters in practical applications. Recently, the rapid development of big data-driven machine learning is expected to replace DFT for high-precision large-scale computing. In this review, the present cluster search methods and challenges currently faced have been summarized. It is proposed that the development of artificial intelligence has the potential to solve some practical problems including the structural and properties evolution of clusters in complex environment, causing revolutionary developments in the fields of catalysis, quantum information, and nanomedicine based on clusters.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300716","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141488465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep Reinforcement Multiagent Learning Framework for Information Gathering with Local Gaussian Processes for Water Monitoring 利用局部高斯过程收集信息的深度强化多代理学习框架,用于水监测
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-04-26 DOI: 10.1002/aisy.202300850
Samuel Yanes Luis, Dmitriy Shutin, Juan Marchal Gómez, Daniel Gutiérrez Reina, Sergio Toral Marín

The conservation of hydrological resources involves continuously monitoring their contamination. A multiagent system composed of autonomous surface vehicles is proposed herein to efficiently monitor the water quality. To achieve a safe control of the fleet, the fleet policy should be able to act based on measurements and fleet state. It is proposed to use local Gaussian processes and deep reinforcement learning to jointly obtain effective monitoring policies. Local Gaussian processes, unlike classical global Gaussian processes, can accurately model the information in a dissimilar spatial correlation which captures more accurately the water quality information. A deep convolutional policy is proposed, that bases the decisions on the observation on the mean and variance of this model, by means of an information gain reward. Using a double deep Q-learning algorithm, agents are trained to minimize the estimation error in a safe manner thanks to a Consensus-based heuristic. Simulation results indicate an improvement of up to 24% in terms of the mean absolute error with the proposed models. Also, training results with 1–3 agents indicate that our proposed approach returns 20% and 24% smaller average estimation errors for, respectively, monitoring water quality variables and monitoring algae blooms, as compared to state-of-the-art approaches.

保护水文资源需要持续监测其污染情况。本文提出了一个由自动地面车辆组成的多代理系统,用于有效监测水质。为实现对车队的安全控制,车队策略应能根据测量结果和车队状态采取行动。本文建议使用局部高斯过程和深度强化学习来共同获得有效的监控策略。与经典的全局高斯过程不同,局部高斯过程可以准确地模拟不同空间相关性的信息,从而更准确地捕捉水质信息。我们提出了一种深度卷积策略,通过信息增益奖励,将观测决策建立在该模型的均值和方差基础上。利用双深度 Q 学习算法,通过基于共识的启发式,对代理进行训练,以安全的方式最小化估计误差。模拟结果表明,使用所提出的模型,平均绝对误差最多可改善 24%。此外,1-3 个代理的训练结果表明,与最先进的方法相比,我们提出的方法在监测水质变量和监测藻类繁殖方面的平均估计误差分别减少了 20% 和 24%。
{"title":"Deep Reinforcement Multiagent Learning Framework for Information Gathering with Local Gaussian Processes for Water Monitoring","authors":"Samuel Yanes Luis,&nbsp;Dmitriy Shutin,&nbsp;Juan Marchal Gómez,&nbsp;Daniel Gutiérrez Reina,&nbsp;Sergio Toral Marín","doi":"10.1002/aisy.202300850","DOIUrl":"https://doi.org/10.1002/aisy.202300850","url":null,"abstract":"<p>The conservation of hydrological resources involves continuously monitoring their contamination. A multiagent system composed of autonomous surface vehicles is proposed herein to efficiently monitor the water quality. To achieve a safe control of the fleet, the fleet policy should be able to act based on measurements and fleet state. It is proposed to use local Gaussian processes and deep reinforcement learning to jointly obtain effective monitoring policies. Local Gaussian processes, unlike classical global Gaussian processes, can accurately model the information in a dissimilar spatial correlation which captures more accurately the water quality information. A deep convolutional policy is proposed, that bases the decisions on the observation on the mean and variance of this model, by means of an information gain reward. Using a double deep Q-learning algorithm, agents are trained to minimize the estimation error in a safe manner thanks to a Consensus-based heuristic. Simulation results indicate an improvement of up to 24% in terms of the mean absolute error with the proposed models. Also, training results with 1–3 agents indicate that our proposed approach returns 20% and 24% smaller average estimation errors for, respectively, monitoring water quality variables and monitoring algae blooms, as compared to state-of-the-art approaches.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202300850","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Volume Transfer: A New Design Concept for Fabric-Based Pneumatic Exosuits 体积转移:织物气动外衣的新设计理念
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-04-26 DOI: 10.1002/aisy.202400039
Chendong Liu, Dapeng Yang, Jiachen Chen, Yiming Dai, Li Jiang, Hong Liu

The fabric-based pneumatic exosuit is now a hot research topic because it is lighter and softer than traditional exoskeletons. Existing research focuses more on the mechanical properties of the exosuit (e.g., torque and speed), but less on its wearability (e.g., appearance and comfort). This work presents a new design concept for fabric-based pneumatic exosuits: volume transfer, which means transferring the volume of pneumatic actuators beyond the garment's profile to the inside. This allows for a concealed appearance and a larger stress area while maintaining adequate torques. In order to verify this concept, a fabric-based pneumatic exosuit is developed for knee extension assistance. Its profile is only 26 mm and its stress area wraps around almost half of the leg. A mathematical model and simulation is used to determine the parameters of the exosuit, avoiding multiple iterations of the prototype. Experiment results show that the exosuit can generate a torque of 7.6 Nm at a pressure of 90 kPa and produce a significant reduction in the electromyography activity of the knee extensor muscles. It is believed that volume transfer can be utilized prevalently in future fabric-based pneumatic exosuit designs to achieve a significant improvement in wearability.

与传统外骨骼相比,基于织物的气动外骨骼更轻、更柔软,因此是目前的热门研究课题。现有研究更多地关注外骨骼的机械性能(如扭矩和速度),而较少关注其可穿戴性(如外观和舒适度)。这项研究为基于织物的气动外衣提出了一种新的设计理念:体积转移,即把气动致动器的体积从服装的外形转移到内部。这样可以在保持足够扭矩的同时,实现隐蔽的外观和更大的受力面积。为了验证这一概念,我们开发了一种基于织物的气动外衣,用于膝关节伸展辅助。它的外形仅为 26 毫米,受力面积几乎覆盖了半条腿。通过数学模型和仿真来确定外穿衣的参数,避免了原型的多次重复。实验结果表明,在 90 kPa 的压力下,外穿衣可产生 7.6 牛米的扭矩,并显著降低膝关节伸肌的肌电图活动。相信在未来基于织物的气动外衣设计中,可以普遍利用体积转移技术来显著提高可穿戴性。
{"title":"Volume Transfer: A New Design Concept for Fabric-Based Pneumatic Exosuits","authors":"Chendong Liu,&nbsp;Dapeng Yang,&nbsp;Jiachen Chen,&nbsp;Yiming Dai,&nbsp;Li Jiang,&nbsp;Hong Liu","doi":"10.1002/aisy.202400039","DOIUrl":"https://doi.org/10.1002/aisy.202400039","url":null,"abstract":"<p>The fabric-based pneumatic exosuit is now a hot research topic because it is lighter and softer than traditional exoskeletons. Existing research focuses more on the mechanical properties of the exosuit (e.g., torque and speed), but less on its wearability (e.g., appearance and comfort). This work presents a new design concept for fabric-based pneumatic exosuits: volume transfer, which means transferring the volume of pneumatic actuators beyond the garment's profile to the inside. This allows for a concealed appearance and a larger stress area while maintaining adequate torques. In order to verify this concept, a fabric-based pneumatic exosuit is developed for knee extension assistance. Its profile is only 26 mm and its stress area wraps around almost half of the leg. A mathematical model and simulation is used to determine the parameters of the exosuit, avoiding multiple iterations of the prototype. Experiment results show that the exosuit can generate a torque of 7.6 Nm at a pressure of 90 kPa and produce a significant reduction in the electromyography activity of the knee extensor muscles. It is believed that volume transfer can be utilized prevalently in future fabric-based pneumatic exosuit designs to achieve a significant improvement in wearability.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142316935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Kirigami Multi-Stable Flexible Gripper with Energy-Free Configurations Switching 具有无能量配置切换功能的叽里呱啦多稳定柔性抓手
IF 6.8 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-04-26 DOI: 10.1002/aisy.202400038
Zhifeng Qi, Xiuting Sun, Jian Xu

Inspired by the kirigami and recombination mechanism, a kirigami flexible gripper is presented. The configuration variation behaviors are realized by recombinant kirigami segments, and thus, with only head segment actuation, the gripper slickly deforms among different configurations. Revolutionizing the conventional deployable systems, the proposed design methodology can realize configuration variation-locking integration, and reusing of multi-stability property. To realize rapid configuration switching with the lowest energy input, a nested origami actuation, called trigger structure, is given. Furthermore, advanced design for the trigger structure is carried out, broadening the bistable state to four-stable geometric configurations for enhanced reachable space of the flexible gripper. By combining the design of the advanced trigger structure, the flexible gripper enables an energy-free switching behavior between deployed and curled configurations in symmetrical and asymmetrical planes. The asymmetrical configurations, induced by the multi-stability property of the advanced trigger structure, make the flexible gripper appropriate for various moving velocities capture. The proposed kirigami multi-stable flexible gripper has significant capture capability for moving targets with different types and motion attitudes. Summarily, the proposed kirigami multi-stable flexible gripper opens a new avenue for flexible robots, with potential applications in space exploration, grippers, and beyond.

受 "叽里格米 "和重组机制的启发,我们提出了一种 "叽里格米 "柔性机械手。配置变化行为由重组的 "叽里呱啦 "片段实现,因此,只需头部片段驱动,抓手就能在不同配置之间灵活变形。所提出的设计方法颠覆了传统的可部署系统,实现了配置变化与锁定的整合,并可重复使用多稳定性特性。为了以最低的能量输入实现快速配置切换,我们给出了一种嵌套折纸致动装置,即触发结构。此外,还对触发结构进行了高级设计,将双稳态拓宽到四稳态几何构型,以增强柔性机械手的可触及空间。通过结合先进的触发结构设计,柔性机械手可以在对称和非对称平面上实现展开和卷曲配置之间的无能量切换行为。先进触发器结构的多稳定性所带来的非对称配置使柔性机械手适用于各种移动速度的捕捉。所提出的叽里神多稳柔性机械手对不同类型和运动姿态的移动目标具有显著的捕捉能力。总之,所提出的叽里神多稳柔性抓手为柔性机器人开辟了一条新的道路,有望应用于空间探索、抓手等领域。
{"title":"A Kirigami Multi-Stable Flexible Gripper with Energy-Free Configurations Switching","authors":"Zhifeng Qi,&nbsp;Xiuting Sun,&nbsp;Jian Xu","doi":"10.1002/aisy.202400038","DOIUrl":"https://doi.org/10.1002/aisy.202400038","url":null,"abstract":"<p>Inspired by the kirigami and recombination mechanism, a kirigami flexible gripper is presented. The configuration variation behaviors are realized by recombinant kirigami segments, and thus, with only head segment actuation, the gripper slickly deforms among different configurations. Revolutionizing the conventional deployable systems, the proposed design methodology can realize configuration variation-locking integration, and reusing of multi-stability property. To realize rapid configuration switching with the lowest energy input, a nested origami actuation, called trigger structure, is given. Furthermore, advanced design for the trigger structure is carried out, broadening the bistable state to four-stable geometric configurations for enhanced reachable space of the flexible gripper. By combining the design of the advanced trigger structure, the flexible gripper enables an energy-free switching behavior between deployed and curled configurations in symmetrical and asymmetrical planes. The asymmetrical configurations, induced by the multi-stability property of the advanced trigger structure, make the flexible gripper appropriate for various moving velocities capture. The proposed kirigami multi-stable flexible gripper has significant capture capability for moving targets with different types and motion attitudes. Summarily, the proposed kirigami multi-stable flexible gripper opens a new avenue for flexible robots, with potential applications in space exploration, grippers, and beyond.</p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202400038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fast-Moving and Highly Adaptable Hollow Piezoelectric Miniature Robot 移动快速、适应性强的中空压电微型机器人
Pub Date : 2024-04-22 DOI: 10.1002/aisy.202470019
Binbin Zhu, Yan Qing Wang

Hollow Piezoelectric Miniature Robot

Inspired by the locomotive gait of crocodiles, Binbin Zhu and Yan Qing Wang in article number 2300612 introduce a hollow piezoelectric miniature robot (HPMR). Based on the hollow-center design, the robot realizes multiple motion outputs with single energy input, incorporating two working modes, oscillation and rotation. The HPMR satisfies the needs of miniaturization, rapid and accurate movement, and high adaptability to a certain extent; in particular, its amphibious mobility expands the application scenarios. This design concept gives the robot an enhanced ability to multitask in constrained spaces with equal energy input and fewer external components.

受鳄鱼运动步态的启发,朱彬彬和王彦青在文章编号 2300612 中介绍了一种空心压电微型机器人(HPMR)。该机器人基于空心设计,以单一能量输入实现多种运动输出,并结合了摆动和旋转两种工作模式。HPMR 在一定程度上满足了小型化、快速精确运动和高适应性的需求,特别是其两栖移动性拓展了应用场景。这种设计理念提高了机器人在有限空间内执行多重任务的能力,只需输入相同的能量和较少的外部组件。
{"title":"Fast-Moving and Highly Adaptable Hollow Piezoelectric Miniature Robot","authors":"Binbin Zhu,&nbsp;Yan Qing Wang","doi":"10.1002/aisy.202470019","DOIUrl":"https://doi.org/10.1002/aisy.202470019","url":null,"abstract":"<p><b>Hollow Piezoelectric Miniature Robot</b>\u0000 </p><p>Inspired by the locomotive gait of crocodiles, Binbin Zhu and Yan Qing Wang in article number 2300612 introduce a hollow piezoelectric miniature robot (HPMR). Based on the hollow-center design, the robot realizes multiple motion outputs with single energy input, incorporating two working modes, oscillation and rotation. The HPMR satisfies the needs of miniaturization, rapid and accurate movement, and high adaptability to a certain extent; in particular, its amphibious mobility expands the application scenarios. This design concept gives the robot an enhanced ability to multitask in constrained spaces with equal energy input and fewer external components.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":93858,"journal":{"name":"Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aisy.202470019","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140633774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1