检索结果-内蒙古大学图书馆

Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sato, Rei Fukuchi, Kazuto Sakuma, Jun Akimoto, Youhei Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan RIKEN Center for Advanced Intelligence Project Japan

We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments: a simulator environment with semantics, that is, low-dimensional and essential information, as the state space, and a real-world environment with images as the state space. By learning mapping from images to semantics, we can transfer a policy, pre-trained in the simulator, to the real world, thereby eliminating real-world on-policy agent interactions to learn, which are costly and risky. In addition, using image-to-semantics mapping is advantageous in terms of the computational efficiency to train the policy and the interpretability of the obtained policy over other types of sim-to-real transfer strategies. To tackle the main difficulty in learning image-to-semantics mapping, namely the human annotation cost for producing a training dataset, we propose two techniques: pair augmentation with the transition function in the simulator environment and active learning. We observed a reduction in the annotation cost without a decline in the performance of the transfer, and the proposed approach outperformed the existing approach without annotation. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Consistent Event-Triggered Consensus on Complete Graphs

学校读者我要写书评

暂无评论

Consistent Event-Triggered Consensus on Complete Graphs

IEEE Conference on Decision and control

作者： Duarte J. Antunes David Meister Toru Namerikawa Frank Allgöwer W.P.M.H. Heemels Dep. of Mechanical Eng. Eindhoven Control Systems Technology Group University of Technology the Netherlands Institute for Systems Theory and Automatic Control University of Stuttgart Germany School of Integrated Design Engineering Graduate School of Science and Technology Keio University Japan

This paper starts by considering an optimal control formulation of the consensus problem on complete graphs with a cost capturing disagreement and agents modeled by integrators. An optimal control policy for this problem is shown to be the well-known consensus algorithm by which each agent resets its state to the average of its and other agents' state values received at every time step. The framework is extended to the case where agents can only exchange information periodically, with a period larger than one. Then an event-triggered control strategy is proposed that results in a better cost than that of the optimal periodic one with the same average transmission rate, that is, it is consistent. According to this strategy, each agent distributedly transmits its state if the error between its current state and a common consensus estimate based on previously transmitted agents' data exceeds a threshold. Simulation results are presented to illustrate the proposed strategy.

关键词：

A Parkinson's Bradykinesia Recognition System Based on Deep Learning Method 12

学校读者我要写书评

暂无评论

A Parkinson's Bradykinesia Recognition System Based on Deep ...

12th International Conference on CYBER Technology in Automation, control, and Intelligent systems, CYBER 2022

作者： Tong, Lina Liu, Daisong Zhang, Mingjia Peng, Liang Department of State Key Laboratory of Management and Control for Complex Systems Institute of Automation China Academy of Science Beijing China School of Mechanical Electronic and Information Engineering Chinese University of Mining and Technology-Beijing Beijing China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Parkinson's disease is a neurodegenerative disease common in middle-aged and elderly people, and bradykinesia is one of the most obvious symptoms. In this study, A deep learning-based Parkinson's bradykinesia recognition system is designed which has an inertial sensor-based data acquisition system. It can wirelessly collect bradykinesia kinematic information by wearing it on the wrist and ankle of Parkinson's patients. In addition, a method for identifying the symptom of Parkinson's bradykinesia based on Long Short Term Memory (LSTM) Network is proposed, with an accuracy of 98.6%. It provides a feasible method to identify Parkinson bradykinesia to assist the diagnosis and treatment. © 2022 IEEE.

关键词： Neurodegenerative diseases

Extended Adaptive Data-Rate (X-ADR) Technique for Optimal Resource Allocation in Smart City Applications

学校读者我要写书评

暂无评论

Extended Adaptive Data-Rate (X-ADR) Technique for Optimal Re...

IEEE International Symposium on World of Wireless Mobile and Multimedia Networks (WoWMoM)

作者： Nikumani Choudhury Manik Gupta Moustafa M. Nasralla Satoshi Fujita Dept. of Computer Science and Information Systems Birla Institute of Technology & Science Pilani Hyderabad India Dept. of Communications & Networks Engineering Prince Sultan University Riyadh Saudi Arabia Graduate School of Advanced Science and Engineering Hiroshima University Japan

With the rapid growth of urbanization, the need for sustainable, energy-efficient, and smart solutions for home, industry, governance, traffic, and in general, the need for improved quality of life and health has risen. As an enabling technology, the Internet of Things (IoT) must facilitate several advanced applications with varied QoS requirements for smart cities. In this regard, Long Range (LoRa) technologies can be an ideal communication protocol for resource-constrained IoT devices. The LoRa Wide Area Network (LoRaWAN) defines physical layer options and the medium access control (MAC) sub-layer protocols for facilitating low-power, low-rate communications among battery-operated wireless IoT devices. With the enormous number of IoT devices and growing QoS requirements, it is imperative to optimally allocate resources (bandwidth, spreading factor, and transmit power) to these constrained devices so that network lifetime can be improved. The Adaptive Data-Rate (ADR) technique is used by the Network Servers (NS) to adapt the transmission parameters of the devices optimally. This is based on several received parameters from the end devices as well as the network settings. In this work, we extend the ADR technique to the LoRa gateways to consider the class of LoRa devices and the frequency of transmissions further to extend the energy efficiency and lifespan of IoT devices. Additionally, there is a considerable delay in adapting to optimal settings for the end-devices resulting in excess power dissipation. Further, a novel mechanism is proposed to address the congestion issue in the network using the Spreading Factor parameter (SF).

关键词：

Increased dependence on mycorrhizal fungi for nutrient acquisition under carbon limitation by tree girdling

学校读者我要写书评

暂无评论

Plant Diversity 2025年第3期47卷 466-478页

作者： Chen, Jing Cao, Jingjing Guo, Binglin Han, Meixu Feng, Zhipei Tang, Jinqi Mo, Xiaohan Wang, Junjian Yang, Qingpei Pei, Yuxin Kuzyakov, Yakov Ding, Junxiang Makita, Naoki Yang, Xitian Zhang, Haiyang Zhao, Yong Kong, Deliang College of Forestry Henan Agricultural University Zhengzhou 450002 China College of Horticulture China Agricultural University Beijing 100193 China School of Urban Planning and Design Peking University Shenzhen Graduate School Peking University Shenzhen 518055 China State Environmental Protection Key Laboratory of Integrated Surface Water-Groundwater Pollution Control School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Department of Soil Science of Temperate Ecosystem University of Göttingen Göttingen 37077 Germany Peoples Friendship University of Russia (RUDN University) Moscow 117198 Russian Federation College of Ecology and Environment Zhengzhou University Zhengzhou 450001 China Faculty of Science Shinshu University 3-1-1 Asahi Nagano Matsumoto 390-8621 Japan Hawkesbury Institute for the Environment Western Sydney University Penrith 2751 NSW Australia College of Life Science Hebei University Baoding 071002 China

Nutrient acquisition through symbiotic ectomycorrhizal fungi is carbon (C) costly but fundamental for plant growth, community, and ecosystem functioning. Here, we examined the functions of roots and mycorrhiza with respect to nutrient uptake after artificially inducing C limitation-seven months after girdling of an ectomycorrhizal tree, Pinus taeda. Root physiological activity (measured as root nitrogen content and root exudation) declined after girdling and was accompanied with 110% and 340% increases in mycorrhizal colonization and extramatrical hyphal length, respectively. Fungi colonizing roots switched to a community characterized by higher C efficiency (lower C cost) of nutrient acquisition (CENA, the amount of nutrient acquisition per unit C cost) and lower network complexity, indicating a tradeoff between CENA and stability of the fungal community. Root transcriptome analysis suggested a shift in metabolic pathways from a tricarboxylic acid cycle decomposition of carbohydrate to lipid biosynthesis to maintain closer associations with mycorrhiza for nutrient cycling after the girdling. By integrating multi-level evidence, including root transcriptome, fungal composition, and network complexity data, we demonstrate an increased dependence on mycorrhiza for nutrient acquisition under the C limitation condition, which is likely due to a shift to fungal community with higher CENA at the cost of lower stability. © 2025 Kunming Institute of Botany, Chinese Academy of sciences

关键词： Carbon limitation Fungal network complexity Girdling effects Mycorrhizal and root strategies Plant–microbiome interaction Root transcriptome

Energy-efficient Hybrid Model Predictive Trajectory Planning for Autonomous Electric Vehicles

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ding, Fan Luo, Xuewen Li, Gaoxuan Tew, Hwa Hui Loo, Junn Yong Tong, Chor Wai Bakibillah, A.S.M. Zhao, Ziyuan Tao, Zhiyu The School of Information Technology Monash University Malaysia The School of Engineering Monash University Malaysia The Department of Systems and Control Engineering Tokyo Institute of Technology Japan The Institute for Infocomm Research A*STAR Singapore The National Science Library Chinese Academy of Sciences China

To tackle the twin challenges of limited battery life and lengthy charging durations in electric vehicles (EVs), this paper introduces an Energy-efficient Hybrid Model Predictive Planner (EHMPP), which employs an energy-saving optimization strategy. EHMPP focuses on refining the design of the motion planner to be seamlessly integrated with the existing automatic driving algorithms, without additional hardware. It has been validated through simulation experiments on the Prescan, CarSim, and Matlab platforms, demonstrating that it can increase passive recovery energy by 11.74% and effectively track motor speed and acceleration at optimal power. To sum up, EHMPP not only aids in trajectory planning but also significantly boosts energy efficiency in autonomous EVs. Copyright © 2024, The Authors. All rights reserved.

关键词： Hybrid vehicles

Separability Membrane: 3D Active Contour for Point Cloud Surface Reconstruction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pratamasunu, Gulpi Qorik Oktagalu Hao, Guoqing Fukui, Kazuhiro Department of Computer Science Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba305-0085 Japan Department of Integrated Information Technology Aoyama Gakuin University Kanagawa Sagamihara252-5258 Japan

This paper proposes Separability Membrane, a robust 3D active contour for extracting a surface from 3D point cloud object. Our approach defines the surface of a 3D object as the boundary that maximizes the separability of point features, such as intensity, color, or local density, between its inner and outer regions based on Fisher’s ratio. Separability Membrane identifies the exact surface of a 3D object by maximizing class separability while controlling the rigidity of the 3D surface model with an adaptive B-spline surface that adjusts its properties based on the local and global separability. A key advantage of our method is its ability to accurately reconstruct surface boundaries even when they are ambiguous due to noise or outliers, without requiring any training data or conversion to volumetric representation. Evaluations on a synthetic 3D point cloud dataset and the 3DNet dataset demonstrate the membrane’s effectiveness and robustness under diverse conditions. © 2025, CC BY.

关键词： 3D reconstruction

A fractional order impedance model for heterogeneous drug distribution in obese patients during general anesthesia ⁎

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第12期58卷 61-66页

作者： Amani R. Ynineb Erhan Yumuk Hamed Farbakhsh Ghada Ben Othman Dana Copot Isabela R. Birs Cristina I. Muresan Robin De Keyser Samir Ladaci Clara M. Ionescu Martine Neckebroek Ghent University Department of Electromechanics Systems and Metal Engineering Research Group on Dynamical Systems and Control Tech Lane Science Park 125 Zwijnaarde 9052 Belgium Istanbul Technical University Department of Control and Automation Engineering Maslak 34469 Istanbul Turkey Technical University of Cluj Napoca Romania Department of Automation Memorandumului Street 20 Cluj Romania National Polytechnic School Department of Automatics and Control Engineering 10 Rue des Fréres OUDEK El Harrach 16200 Algiers Algeria Ghent University Hospital Department of Anesthesia Corneel Heymanslaan 10 Ghent 9000 Belgium

Personalised pharmacokinetic models imply stepping away from the classical assumption of homogeneous drug mixing in various tissue compartments in the body, with a particular impact on obese patients. In this work, the pharmacokinetic compartmental model structure is revisited to account for non-uniform distribution of uptake/clearance time constants in patients as a nonlinear function of body mass index. Simulations are confirming expected patterns of drug distribution in the body and can account for post-anesthesia side effects up to 72 hours. We apply spectroscopy to extract the complex impedance in fat tissue samples. The data is modelled by a Cole-Cole model, where parameters of the fractional order impedance model are optimized using a genetic algorithm. The findings suggest that fat tissue will exhibit anomalous diffusion when drug uptake and clearance are present.

关键词： fractional order impedance model Cole-Cole model bioimpedance compartmental modelling general anesthesia frequency domain spectroscopy

Small-Gain Theorem Based Distributed Prescribed-Time Convex Optimization For Networked Euler-Lagrange systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zuo, Gewei Li, Mengmou Zhu, Lijun School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Imaging Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 China Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima739-0046 Japan

In this paper, we address the distributed prescribed-time convex optimization (DPTCO) for a class of networked Euler-Lagrange systems under undirected connected graphs. By utilizing position-dependent measured gradient value of local objective function and local information interactions among neighboring agents, a set of auxiliary systems is constructed to cooperatively seek the optimal solution. The DPTCO problem is then converted to the prescribed-time stabilization problem of an interconnected error system. A prescribed-time small-gain criterion is proposed to characterize prescribed-time stabilization of the system, offering a novel approach that enhances the effectiveness beyond existing asymptotic or finite-time stabilization of an interconnected system. Under the criterion and auxiliary systems, innovative adaptive prescribed-time local tracking controllers are designed for subsystems. The prescribed-time convergence lies in the introduction of time-varying gains which increase to infinity as time tends to the prescribed time. Lyapunov function together with prescribed-time mapping are used to prove the prescribed-time stability of closed-loop system as well as the boundedness of internal signals. Finally, theoretical results are verified by one numerical example. Copyright © 2024, The Authors. All rights reserved.

关键词： Lyapunov functions