检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Christos N. Mavridis George P. Kontoudis John S. Baras Department of Electrical and Computer Engineering Institute for Systems Research University of Maryland College Park USA Dept. of Aerospace Engineering Maryland Robotics Center Inst. of Systems Research University of Maryland College Park MD USA

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

We present a new sparse Gaussian process regression model whose covariance function is parameterized by the locations of a progressively growing set of pseudo-inputs generated by an online deterministic annealing optimization algorithm. A series of entropy-regularized optimization problems is solved sequentially, introducing a bifurcation phenomenon, according to which, pseudo-inputs are gradually generated. This results in an active learning approach, which, in contrast to most existing works, can modify already selected pseudo-inputs and is trained using a recursive gradient-free stochastic approximation algorithm. Finally, the proposed algorithm is able to incorporate prior knowledge in the form of a probability density, according to which new observations are sampled. Experimental results showcase the efficacy and potential advantages of the proposed methodology.

关键词： Annealing Gaussian processes Bifurcation Approximation algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Modelling the Dependence of Chlorophyll Leaf-Clip Measures on Vegetation Indices Derived from Multispectral UAS Images in Vineyards Parcels

Modelling the Dependence of Chlorophyll Leaf-Clip Measures o...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Gil Gonçalves Umberto Andriolo Lúcio Paiva Cristiano Premebida António Ferraz Department of Mathematics University of Coimbra Coimbra Portugal Department of Electrical and Computer Engineering INESC Coimbra Coimbra Portugal Research Centre for Natural Resources Environment and Society Polytechnic Institute of Coimbra Coimbra Agrarian Technical School Coimbra Portugal Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal NASA Jet Propulsion Laboratory Pasadena United States

Multispectral images and leaf-clip measurements were used for evaluating the Chlorophyll (Chl) content on grapevine leaves through the use of vegetation indices. The multispectral leaf images were taken by a sensor onboard an UAS, which was placed over a table at a height of 70 cm. Images were radiometrically and geometrically processed to obtain accurate coregistered five band image stacks. Using a Kmeans segmentation, each leaf imaged in a multispectral image was automatically detected and the mean leaf reflectance values were used to compute three vegetation indices: NDVI, NDRE, and GLI. When compared to leaf-clip measurements, the results indicated that the NDRE index was the best predictor of Chl leaf content (R2=0.81). The obtained NDRE regression model can be used in UAS-based multispectral orthomosaics to generate canopy Chl maps at vine-row scale, which can assist vine growers in monitoring the spatial and temporal variability of grapevine vigor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vertical Federated Learning with Missing Features During Training and Inference

arXiv

引用

arXiv 2024年

作者： Valdeira, Pedro Wang, Shiqiang Chi, Yuejie CMU IST United States IBM Research United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Systems and Robotics Instituto Superior Técnico Portugal IBM T. J. Watson Research Center United States

Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume that all feature partitions are available during both training and inference. Yet, in practice, this assumption rarely holds, as for many samples only a subset of the clients observe their partition. However, not utilizing incomplete samples during training harms generalization, and not supporting them during inference limits the utility of the model. Moreover, if any client leaves the federation after training, its partition becomes unavailable, rendering the learned model unusable. Missing feature blocks are therefore a key challenge limiting the applicability of vertical federated learning in real-world scenarios. To address this, we propose LASER-VFL, a vertical federated learning method for efficient training and inference of split neural network-based models that is capable of handling arbitrary sets of partitions. Our approach is simple yet effective, relying on the strategic sharing of model parameters and on task-sampling to train a family of predictors. We show that LASER-VFL achieves a O(1/√T) convergence rate for nonconvex objectives in general, O(1/T) for sufficiently large batch sizes, and linear convergence under the Polyak-Lojasiewicz inequality. Numerical experiments show improved performance of LASER-VFL over the baselines. Remarkably, this is the case even in the absence of missing features. For example, for CIFAR-100, we see an improvement in accuracy of 21.4% when each of four feature blocks is observed with a probability of 0.5 and of 12.2% when all features are observed. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Towards Connecting Control to Perception: High-Performance Whole-Body Collision Avoidance Using Control-Compatible Obstacles

Towards Connecting Control to Perception: High-Performance W...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Moritz Eckhoff Dennis Knobbe Henning Zwirnmann Abdalla Swikir Sami Haddadin Technical University of Munich Germany Department of Computer Engineering Chair of Robotics and Systems Intelligence TUM School of Computation Information and Technology Centre for Tactile Internet with Human-in-the-Loop (CeTI) of Technische Universität Dresden Germany Department of Electrical and Electronic Engineering Omar Al-Mukhtar University Albaida Libya

One of the most important aspects of autonomous systems is safety. This includes ensuring safe human-robot and safe robot-environment interaction when autonomously performing complex tasks or in collaborative scenarios. Al-though several methods have been introduced to tackle this, most are unsuitable for real-time applications and require carefully handcrafted obstacle descriptions. In this work, we propose a method combining high-frequency and real-time self and environment collision avoidance of a robotic manipulator with low-frequency, multimodal, and high-resolution environmental perceptions accumulated in a digital twin system. Our method is based on geometric primitives, so-called primitive skeletons. These, in turn, are information-compressed and real-time compatible digital representations of the robot's body and environment, automatically generated from ultra-realistic virtual replicas of the real world provided by the digital twin. Our approach is a key enabler for closing the loop between environment perception and robot control by providing the millisecond real-time control stage with a current and accurate world description, empowering it to react to environmental changes. We evaluate our whole-body collision avoidance on a 9-DOFs robot system through five experiments, demonstrating the functionality and efficiency of our framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Prediction of Subsurface Oil Reservoir Pressure Using Spatio-Temporal Data

Deep Learning-Based Prediction of Subsurface Oil Reservoir P...

引用

Annual Conference of Industrial Electronics Society

作者： Haibo Cheng Yunpeng He Peng Zeng Shichao Li Valeriy Vyatkin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Automation Aalto University Helsinki Finland

Prediction of subsurface oil reservoir pressure are critical to hydrocarbon production. However, the accurate pressure estimation faces great challenges due to the complexity and uncertainty of reservoir. The underground seepage flow and petrophysical parameters (permeability and porosity) are important but difficult to measure in oilfield. Deep learning methods have been successfully used in reservoir engineering and oil & gas production process. In this study, the effective but inaccessible subsurface seepage fields are not used, only the spatial coordinates and temporal information are selected as model input to predict reservoir pressure. A stacked GRU-based deep learning model is proposed to map the relationship between spatio-temporal data and reservoir pressure. The proposed deep learning method is verified by using a three-dimensional reservoir model, and compared with commonly-used methods. The results show that the stacked GRU model has a better performance and higher accuracy than other deep learning or machine learning methods in pressure prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical study on the flow field for deep-sea hydrothermal plume tracking simulation

Numerical study on the flow field for deep-sea hydrothermal ...

引用

17th Asian Congress of Fluid Mechanics (ACFM 2023)

作者： X. -H. Xu J. -C. Liu H. -R. Hou Q. -H. Meng Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin 300072 People's Republic of China Laboratory for High-speed Aerodynamics Department of Mechanics Tianjin University Tianjin 300072 People's Republic of China

In this paper, the distribution of hydrothermal buoyancy plume in the deep-sea environment is studied numerically. Submarine hydrothermal vents are prominent manifestations of hydrothermal activities and are of great scientific and engineering importance. It is an important basis to obtain the temporal and spatial distribution information of different hydrothermal plumes for tracking and locating the source of hydrothermal plumes. Based on Reynolds-averaged Navier-Stokes equations and Realizable k- ε turbulence model, the plumes of hydrothermal vents at depths of 800 m, 1200 m, and 1400 m were calculated and studied to obtain the spatial distribution of variables such as velocity field, temperature field and turbulent kinetic energy. The research results of this paper provide an important basis for the simulation of deep-sea hydrothermal plume tracking based on autonomous underwater vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new structure of end-effector traction upper limb rehabilitation robot

A new structure of end-effector traction upper limb rehabili...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Li, Liaoyuan Han, Jianhai Li, Xiangpan Guo, Bingjing Xia, Pengpeng Du, Ganqin Henan University of Science and Technology Key Laboratory of Robotics and Intelligent Systems School of Mechanical and Electrical Engineering Luoyang471000 China First Affiliated Hospital of Henan University of Science and Technology Department of Neurology Luoyang471000 China

ISBN: (纸本)9781665436786

Among the rehabilitation therapies for patients with stroke or paralysis, robot-assisted rehabilitation is a research hotspot now. However, there are not many cases of clinical application, mainly because of the complex structure, single function, or high cost. This research proposes a new type of 3-DOF (degrees of freedom) upper limb rehabilitation robot in series structure of with an end-effector, which has 2 degrees of freedom in horizontal rotation and 1 degree of freedom in the vertical movement. It has a compact structure, saves space, is easy to be moved and can realize rehabilitation training in three-dimensional space. It is mainly used for rehabilitation training of the shoulder and elbow joints of the upper limbs. The first two rotary joints are driven by AC servo motors, and the prismatic joint is driven by a single-acting cylinder, which increases the passive compliance of the robot. In addition, a three-dimensional force sensor is added to expand the human-machine interaction channel and increase the active safety of the robot. Through the trajectory tracking and force control test of the robot, it is proved that the device can meet the demand of passive and active upper limb rehabilitation. © 2021 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Point-Based 3D Virtual Fixture Generating for Image-Guided and Robot-Assisted Surgery in Orthopedics*

Point-Based 3D Virtual Fixture Generating for Image-Guided a...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Teng Li Armin Badre Hamid D. Taghirad Mahdi Tavakoli Department of Electrical and Computer Engineering Faculty of Engineering University of Alberta Edmonton Canada Western Upper Limb Facility Sturgeon Hospital St. Albert Canada Division of Orthopaedic Surgery Department of Surgery Faculty of Medicine & Dentistry University of Alberta Edmonton Canada Advanced Robotics and Automated Systems (ARAS) Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran

Virtual fixture (VF) has been playing a vital role in robot-assisted surgeries, such as guiding surgical tools’ movement and protecting a beating heart. In orthopedic surgery, preplanned images are often used in the operating room, on which planning curves might be drawn, for instance, to mark out the boundaries for osteophytes to be removed. These curves can be used to generate VF to assist in removing osteophytes during the operation. A challenge is that the hand-drawn curves usually have a random shape and cannot be mathematically represented by equations, thus most of the existing algorithms will not work in this scenario. In this paper, an algorithm of VF generating based on point clouds is presented, with which VF can be generated directly from cloud points, for example, point clouds of hand-drawn curves extracted from an image. The effectiveness of the VF algorithm is evaluated by a series of simulations and experiments. The VF algorithm is also tested in an image-based scenario and its effectiveness is demonstrated. The presented point-based VF algorithm is promising to be used in various applications in image-guided surgery to generate VF for objects with various shapes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extraction Algorithm for Morphologically Preserved Non-Invasive Multi-Channel Fetal ECG

Extraction Algorithm for Morphologically Preserved Non-Invas...

引用

Computers in Cardiology (CinC)

作者： Giulia Baldazzi Danilo Pani Hau-Tieng Wu Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) University of Genova Genova Italy Department of Electrical and Electronic Engineering (DIEE) University of Cagliari Cagliari Italy Department of Mathematics and Department of Statistical Science Duke University Durham NC USA

Non-invasive fetal ECG (fECG) is a promising technique that could allow low-cost and risk-free diagnosis, and long-term monitoring of fetal cardiac wellbeing. However, the low quality of the fECG extracted from non-invasive abdominal recordings hampers its adoption in clinical practice. In this work, a new algorithm for the recovery of clean and morphologically preserved fECG signals from multi-channel trans-abdominal recordings is presented. The proposed method exploits optimal shrinkage and nonlocal median algorithms, along with a de-shape short-time Fourier transform-based detection, to recover high-quality fECG traces from a morphological perspective, while ensuring very high performance also in terms of fetal QRS detection. On a small dataset, composed of three real 20 min-long four-channel abdominal ECG recordings, a preliminary performance assessment of the proposed fECG extraction method in terms of fetal QRS detection capabilities revealed a median accuracy of 95.8% and F1 score of 97.9%. The obtained results suggest the possibility of successfully applying this approach for an effective non-invasive fECG extraction, deserving further investigations on larger real and synthetic datasets.

关键词： Performance evaluation Fetal heart rate Electrocardiography Recording Noise measurement Cardiology Monitoring

来源：评论

学校读者我要写书评

暂无评论

deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques

arXiv

引用

arXiv 2022年

作者： Sa, Inkyu Lim, JongYoon Ahn, Ho Seok MacDonald, Bruce CSIRO Data61 Robotics and Autonomous Systems Group Robot Perception Team Switzerland CARES Department of Electrical Computer and Software Engineering University of Auckland New Zealand

This paper presents datasets utilised for synthetic near-infrared (NIR) image generation and bounding-box level fruit detection systems. A high-quality dataset is one of the essential building blocks that can lead to success in model generalisation and the deployment of data-driven deep neural networks. In particular, synthetic data generation tasks often require more training samples than other supervised approaches. Therefore, in this paper, we share the NIR+RGB datasets that are re-processed from two public datasets (i.e., nirscene and SEN12MS), expanded our previous study, deepFruits, and our novel NIR+RGB sweet pepper(capsicum) dataset. We oversampled from the original nirscene dataset at 10, 100, 200, and 400 ratios that yielded a total of 127 k pairs of images. From the SEN12MS satellite multispectral dataset, we selected Summer (45 k) and All seasons (180 k) subsets and applied a simple yet important conversion;digital number (DN) to pixel value conversion followed by image standardisation. Our sweet pepper dataset consists of 1615 pairs of NIR+RGB images that were collected from commercial farms. We quantitatively and qualitatively demonstrate that these NIR+RGB datasets are sufficient to be used for synthetic NIR image generation. We achieved Frechet Inception Distance (FID) of 11.36, 26.53, and 40.15 for nirscene1, SEN12MS, and sweet pepper datasets respectively. In addition, we release manual annotations of 11 fruit bounding boxes that can be exported as various formats using cloud service. Four newly added fruits [blueberry, cherry, kiwi, and wheat] compound 11 novel bounding box datasets on top of our previous work presented in the deepFruits project [apple, avocado, capsicum, mango, orange, rockmelon, strawberry]. The total number of bounding box instances of the dataset is 162 k and it is ready to use from cloud service. For the evaluation of the dataset, Yolov5 single stage detector is exploited and reported impressive mean-average-precision, mAP[0.

关键词： Generative adversarial 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：