检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Berto, Letícia Costa, Paula Simões, Alexandre Gudwin, Ricardo Colombini, Esther Laboratory of Robotics and Cognitive Systems Institute of Computing University of Campinas Brazil Dept. of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Brazil Dept. of Control and Automation Engineering Institute of Science and Technology São Paulo State University Sorocaba Brazil University of Campinas Brazil

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action’s perceived pleasure, which is susceptible to changes over time. This makes decision-making more complex, requiring learning to balance needs and preferences according to the context. To understand how this process works and enable the development of robots with a motivational-based learning model, we computationally model a motivation theory proposed by Hull. In this model, the agent (an abstraction of a mobile robot) is motivated to keep itself in a state of homeostasis. We added hedonic dimensions to see how preferences affect decision-making, and we employed reinforcement learning to train our motivated-based agents. We run three agents with energy decay rates representing different metabolisms in two different environments to see the impact on their strategy, movement, and behavior. The results show that the agent learned better strategies in the environment that enables choices more adequate according to its metabolism. The use of pleasure in the motivational mechanism significantly impacted behavior learning, mainly for slow metabolism agents. When survival is at risk, the agent ignores pleasure and equilibrium, hinting at how to behave in harsh scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

MDI-QKD with resource-efficient polarization compensation

MDI-QKD with resource-efficient polarization compensation

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Bedroya, Olinka Li, Chenyang Wang, Wenyuan Hu, Jianyong Lo, Hoi-Kwong Qian, Li University of Toronto Centre for Quantum Information and Quantum Control Dept. of Physics TorontoONM5S 3G4 Canada University of Toronto Centre for Quantum Information and Quantum Control Dept. of Electrical & Computer Engineering TorontoONM5S 3G4 Canada University of Hong Kong Department of Physics Pokfulam Hong Kong 100 College St TorontoON1M5G 1L5 Canada

ISBN: (纸本)9781957171180

We implemented MDI-QKD with a novel polarization compensation scheme using discarded bits without reducing the key-sharing cycle or demanding additional resources. Polarization drift was maintained below 0.13 rad over a 40 km unisolated fibre spool for four hours, and the average secret key rate generated was 7.45×10-6bits per pulse. © 2023 The Author(s).

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Feedforward control in the Presence of Input Nonlinearities: With Application to a Wirebonder

引用

IFAC-PapersOnLine 2023年第2期56卷 1895-1900页

作者： Maurice Poot Jilles van Hulst Kai Wa Yan Dragan Kostić Jim Portegies Tom Oomen CST Dept. of Mechanical Engineering Eindhoven University of Technology Eindhoven The Netherlands Center of Competency ASMPT Beuningen The Netherlands CASA Dept. of Mathematics and Computer Science Eindhoven University of Technology Eindhoven The Netherlands Delft Center for Systems and Control Delft University of Technology Delft The Netherlands

The increasing demands on throughput and accuracy of semiconductor manufacturing equipment necessitates accurate feedforward motion control that includes compensation of input nonlinearities. The aim of this paper is to develop a data-driven feedforward approach consisting of a Wiener feedforward, i.e., linear parameterization with an output nonlinearity, to achieve high tracking accuracy and task flexibility for a class of Hammerstein systems. The developed approach exploits iterative learning control to learn a feedforward signal from data that minimizes the error and utilizes a control-relevant cost function to learn the parameters of a Wiener feedforward parameterization. Experimental validation on a wirebonder shows that the developed approach enables high tracking accuracy and task flexibility.

关键词： Iterative and repetitive learning control Identification and control methods Nonlinear system identification Data-driven control Learning for control

来源：评论

学校读者我要写书评

暂无评论

Multi-layer network modelling of genomic and transcriptomic data to investigate the response to checkpoint inhibitors in NSCLC

Multi-layer network modelling of genomic and transcriptomic ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Davide Mascolo Lorenzo Farina Manuela Petti MSc Program in Data Science Sapienza University of Rome Rome Italy Dept. of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

Recent innovations and developments in molecular biology and biotechnology have made it possible to acquire and store large omics datasets. In particular genomics, transcriptomics and the study of their relationship represent the key elements to understand how genotype influences phenotype. In this work we investigate the potential of multi-layer network modeling in integrating genomic and transcriptomic data of 152 advanced non-small cell lung cancer (NSCLC) patients treated with anti-PD-(L)1 therapy. For the transcriptomic layer, we performed differential expression and differential co-expression analyses in order to identify a subset of key genes in differentiating responder patients from non-responders. Adding to the genomic-transcriptomic model other three layers related to immune, myeloid and curated immunotherapy-based literature signatures we obtained a 5-layer Patient Similarity Network. The application of Similarity Network Fusion algorithm revealed a statistically significant stratification of patients (p-value ≤ 0.05) which allows the identification of two clusters characterized by patients responding and not responding to immunotherapy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs

arXiv

引用

arXiv 2024年

作者： Gong, Junfeng Liu, Cheng Cheng, Long Li, Huawei Li, Xiaowei SKLP Institute of Computing Technology Chinese Academy of Sciences Beijing China Dept. of Computer Science University of Chinese Academy of Sciences Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China

Mixed-precision neural network (MPNN) that utilizes just enough data width for the neural network processing is an effective approach to meet the stringent resources constraints including memory and computing of MCUs. Nevertheless, there is still a lack of sub-byte and mixed-precision SIMD operations in MCU-class ISA and the limited computing capability of MCUs remains underutilized, which further aggravates the computing bound encountered in neural network processing. As a result, the benefits of MPNNs cannot be fully unleashed. In this work, we propose to pack multiple low-bitwidth arithmetic operations within a single instruction multiple data (SIMD) instructions in typical MCUs, and then develop an efficient convolution operator by exploring both the data parallelism and computing parallelism in convolution along with the proposed SIMD packing. Finally, we further leverage Neural Architecture Search (NAS) to build a HW/SW co-designed MPNN design framework, namely MCUMixQ. This framework can optimize both the MPNN quantization and MPNN implementation efficiency, striking an optimized balance between neural network performance and accuracy. According to our experiment results, MCU-MixQ achieves 2.1× and 1.4× speedup over CMix-NN and MCUNet respectively under the same resource constraints. © 2024, CC BY-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Modular Hardware, Open Source Software and Training Material for PLC Training

Modular Hardware, Open Source Software and Training Material...

引用

International Conference on control, Mechatronics and Automation (ICCMA)

作者： Harsha Priyanka Guntaka Rajesh Kushalkar Nirmala Venkat Akshay Chipkar Vishnu Easwaran Kannan Moudgalya Dept. of Systems & Control Engineering IIT Bombay Mumbai India Dept. of Computer Science & Enginering IIT Bombay Mumbai India Dept. of Chemical Engineering IIT Bombay Mumbai India

ISBN: (纸本)9781665490498

A low cost, open source, rugged, modular OpenPLC, based on ATmega16 microcontroller, has been developed for instructional purposes. Modularity permits flexible use of the OpenPLC. The open source software LDmicro, created for ladder logic operations, has been enhanced, and ported to Linux. A total of 27 Spoken Tutorials of about 10 minute duration each, suitable for self learning, are created for OpenPLC training. A pilot workshop is conducted for 16 teachers of polytechnic colleges using the Spoken Tutorials and the simulation capability of LDmicro. The feedback from the workshop is positive, and the method is suitable for a large scale training.

关键词： Training Mechatronics Costs Automation Microcontrollers Conferences Linux

来源：评论

学校读者我要写书评

暂无评论

A Multivariate Functional Analysis of Inter-Hands Spatiotemporal Coordination in Human Bimanual Tasks and its Implications for Robotics

A Multivariate Functional Analysis of Inter-Hands Spatiotemp...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Marco Baracca Andre Meixner Giuseppe Averta Paolo Salaris Tamim Asfour Matteo Bianchi Dept. of Information Engineering Research Center “E. Piaggio” University of Pisa Pisa Italy Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany Dep. of Control and Computer Engineering Politecnico di Torino Turin Italy

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

Dual-arm manipulation is a key enabler for significantly enhancing the interaction between humans and robots, and their capabilities to purposefully shape the surrounding environment. However, the spatiotemporal coordination between the motion of the hands required for this type of actions makes their planning not trivial. A proper definition of these coordination patterns moving from the human example could simplify their translation on the robot side, fostering the generation of effective bimanual tasks. In this work, we propose Multivariate functional Principal Component Analysis (MfPCA) as a mathematical tool to encode inter-hands temporal kinematic covariations in terms of principal spatiotemporal coordination patterns in the Cartesian domain. We compared these patterns extracted from a dataset of human bimanual tasks with those resulting from the usage of classical fPCA, applied independently to each hand (univariate fPCA). We found that MfPCA allows for a better classification of the tasks, with respect to a state of the art taxonomy. For what concerns motion planning, MfPCA and fPCA yield similar accuracy in the reconstruction of the motion, but with a smaller number of principal components needed in the MfPCA case. These results, although preliminary, can open interesting perspectives for the usage of MfPCA for human-like bimanual motion planning and control of robotic manipulators, as well as for action recognition, to enable a more effective human-robot interaction.

关键词： Hands Translation Shape Robot kinematics Taxonomy Human-robot interaction Functional analysis Planning Spatiotemporal phenomena Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Non-collocated Vibration Suppression using Delay-Based controllers with Multiple Fixed Delays*

引用

IFAC-PapersOnLine 2023年第2期56卷 180-185页

作者： Adrian Saldanha Wim Michiels Tomáš Vyhlídal Department of Computer Science KU Leuven Celestijnenlaan 200A 3001 Leuven Belgium Dept. Instrumentation and Control Engineering Faculty of Mechanical Engineering and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6 Czechia

The problem of non-collocated vibration absorption is targeted utilizing a multiparameter delay-based controller. The combined objective is to achieve closed-loop stability and vibration suppression at a target location, which is different from the position of the absorber. This problem can be translated into an optimization problem of shaping the poles of a closed-loop system with delays subject to zero-location constraints. The solution approach involves remodelling the closed-loop system as a system of delay-differential algebraic equations (DDAEs) which allows to systematically account for delays in the control law, thereby enabling a straightforward technique for computation of controller parameters. Finally, the proposed design method is validated by simulation on a lumped parameter model of a mass-spring-damper system.

关键词： vibration suppression time-delay systems DDAE optimization

来源：评论

学校读者我要写书评

暂无评论

Molecule Generation from Input-Attributions over Graph Convolutional Networks

arXiv

引用

arXiv 2022年

作者： Savoia, Dylan Ragno, Alessio Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

It is well known that Drug Design is often a costly process both in terms of time and economic effort. While good Quantitative Structure-Activity Relationship models (QSAR) can help predicting molecular properties without the need to synthesize them, it is still required to come up with new molecules to be tested. This is mostly done in lack of tools to determine which modifications are more promising or which aspects of a molecule are more influential for the final activity/property. Here we present an automatic process which involves Graph Convolutional Network models and input-attribution methods to generate new molecules. We also explore the problems of over-optimization and applicability, recognizing them as two important aspects in the practical use of such automatic tools. © 2022, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised GCN for learning Molecular Structure-Activity Relationships

arXiv

引用

arXiv 2022年

作者： Ragno, Alessio Savoia, Dylan Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups. In this paper, we propose to train graph-to-graph neural network using semi-supervised learning for attributing structure-property relationships. As initial case studies we apply the method to solubility and molecular acidity while checking its consistency in comparison with known experimental chemical data. As final goal, our approach could represent a valuable tool to deal with problems such as activity cliffs, lead optimization and de-novo drug design. © 2022, CC BY.

关键词： Graph neural networks

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：