检索结果-内蒙古大学图书馆

Spatio-Temporal Correlation-Based Surface Solar Irradiance Retrieval Approach Using Satellite Data Under Different Weather Conditions

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Li, Na Zhen, Zhao Wang, Fei Department of Electrical Engineering North China Electric Power University Baoding071003 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing102206 China Hebei Key Laboratory of Distributed Energy Storage and Microgrid North China Electric Power University Baoding071003 China Department of Automation Taiyuan Institute of Technology Taiyuan030008 China

Wide-area, high temporal-spatial resolution surface solar irradiance data (SSI) is critical for solar energy resource assessment, PV power station site selection, and PV power forecasting. However, it is evidently impractical to obtain the aforementioned irradiance data by deploying a large number of high-density observation devices on the ground. Satellite remote sensing, with global coverage and high spatio-temporal resolution, provides detailed surface information, widely applied in the retrieval of meteorological parameters and surface irradiance studies. Currently, most satellite data-based SSI retrieval studies only consider satellite cloud images as a representation of cloud cover, without fully utilizing the multi-channel spectral information from satellite. Furthermore, these studies not only overlook the impact of satellite cloud image spatial scale under different weather conditions on SSI retrieval but also neglect the correlation between pixels of satellite cloud images. To solve the above problems, this study proposes a spatio-temporal correlation-based SSI retrieval approach using satellite data under different weather conditions. The SSI retrieval approach mainly consists of three parts: weather classification and feature selection, SSI retrieval based on satellite single-pixel data, and SSI retrieval based on spatial correlation. The experiments not only confirm the feasibility of the proposed satellite single-pixel data-based SSI retrieval in this study but also validate the necessity of considering weather types in establishing spatio-temporal correlations for SSI retrieval. © 2024, The Authors. All rights reserved.

关键词： Solar energy

A Approach of Evaluation the Lettuce Height Based on Convolutional Neural Network

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Guo, Xiyue Zhong, Yong Feng, Yarong Zhao, Ming Zhang, Man Wang, Minjuan Key Laboratory of Modern Precision Agriculture System Integration Research Ministry of Education China Agricultural University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China College of Information and Electrical Engineering China Agricultural University China

Lettuce height is one of the important lettuce phenotypic parameters, plant height can not only reflect the basic growth of lettuce, but also provide data support for the monitoring and early warning of external environmental variables. Therefore, the real-time acquisition of lettuce plant height has certain significance. The traditional method of measuring the height of lettuce is to use an instrument for manual measurement, but this is greatly affected by human error. However, the automatic methods mainly rely on expensive sensors such as unmanned aerial vehicle LiDAR and binocular stereo cameras. Moreover, since the process of obtaining plant height may work with multiple sensors at the same time, its operation has a certain degree of complexity. At present, it is the most convenient and quickest ways to evaluate plant height information based on RGB images. However, these tasks usually require complex camera calibration operation or a reference object with a known height, which is somewhat restrictive. Therefore, we try to exploit deep neural networks to solve this problem, using its powerful ability to feature extraction and expression, without camera calibration and reference objects, directly obtain the height of lettuce © 2022, The Authors. All rights reserved.

关键词： Lettuce

Energy Efficiency Optimization for Full-Duplex D2D Communications Underlaying Distributed Antenna systems

学校读者我要写书评

暂无评论

IEEE Transactions on Green Communications and Networking

IEEE Transactions on Green Communications and Networking 2024年

作者： Liu, Zhan Liao, Zhiyuan Li, Chunquan Zhang, Zhijun Yu, Junzhi Liu, P.X. Hunan University of Humanities Science and Technology School of Information Loudi417000 China Nanchang University School of Information Engineering Nanchang330031 China Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang330031 China South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

In this paper, we investigate the total system energy efficiency (EE) of full-duplex (FD) device-to-device (D2D) communications underlaying distributed antenna systems (DAS), where remote access units (RAUs), D2D users (DUs), and cellular users (CUs) are all capable of FD operation. Specifically, we jointly optimize subcarrier assignment and power allocation under the quality of service (QoS) requirements of CUs and DUs and the maximum power constraints of RAUs, CUs, and DUs. In addition, we propose a novel spectrum sharing strategy that allows each subcarrier to be assigned to multiple CUs and/or multiple D2D pairs (DPs) for flexibility. To solve the formulated non-convex optimization problem, we first employ fractional programming to transform the objective function in the optimization problem from the fractional form into the equivalent subtractive form. Then, an efficient iterative resource allocation algorithm is proposed, which needs to solve an inner problem in each iteration. After relaxing the variables and introducing penalty factors, the non-convex inner problem is transformed into a convex problem through the successive convex approximation (SCA) method and solved by iterative algorithm. Simulation results demonstrate that the proposed algorithm can considerably improve the system EE compared to other benchmark schemes. Furthermore, the proposed spectrum sharing strategy is superior to the existing sharing strategies. © 2017 IEEE.

关键词： Convex optimization

Exploring Event-based Human Pose Estimation with 3D Event Representations

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Yin, Xiaoting Shi, Hao Chen, Jiaan Wang, Ze Ye, Yaozu Yang, Kailun Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China School of Robotics Hunan University Changsha410012 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd. Shanghai201210 China

Human pose estimation is a fundamental and appealing task in computer vision. Although traditional cameras are commonly applied, their reliability decreases in scenarios under high dynamic range or heavy motion blur, where event cameras offer a robust solution. Predominant event-based methods accumulate events into frames, ignoring the asynchronous and high temporal resolution that is crucial for distinguishing distinct actions. To address this issue and to unlock the 3D potential of event information, we introduce two 3D event representations: the Rasterized Event Point Cloud (RasEPC) and the Decoupled Event Voxel (DEV). The RasEPC aggregates events within concise temporal slices at identical positions, preserving their 3D attributes along with statistical information, thereby significantly reducing memory and computational demands. Meanwhile, the DEV representation discretizes events into voxels and projects them across three orthogonal planes, utilizing decoupled event attention to retrieve 3D cues from the 2D planes. Furthermore, we develop and release EV-3DPW, a synthetic event-based dataset crafted to facilitate training and quantitative analysis in outdoor scenes. Our methods are tested on the DHP19 public dataset, MMHPSD dataset, and our EV-3DPW dataset, with further qualitative validation via a derived driving scene dataset EV–JAAD and an outdoor collection vehicle. Our code and dataset have been made publicly available at https://***/MasterHow/EventPointPose. Copyright © 2023, The Authors. All rights reserved.

关键词： 3D modeling

Simultaneously Calibration of Multi Hand-Eye Robot system Based on Graph

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Zhou, Zishun Ma, Liping Liu, Xilong Cao, Zhiqiang Yu, Junzhi The Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Electrical Engineering and Computer Science Australian National University Canberra2601 Australia The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The State Key Laboratory for Turbulence and Complex System Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

Precise calibration is the basis for the vision-guided robot system to achieve high-precision operations. systems with multiple eyes (cameras) and multiple hands (robots) are particularly sensitive to calibration errors, such as micro-assembly systems. Most existing methods focus on the calibration of a single unit of the whole system, such as poses between hand and eye, or between two hands. These methods can be used to determine the relative pose between each unit, but the serialized incremental calibration strategy cannot avoid the problem of error accumulation in a large-scale system. Instead of focusing on a single unit, this paper models the multi-eye and multi-hand system calibration problem as a graph and proposes a method based on the minimum spanning tree and graph optimization. This method can automatically plan the serialized optimal calibration strategy in accordance with the system settings to get coarse calibration results initially. Then, with these initial values, the closed-loop constraints are introduced to carry out global optimization. Simulation experiments demonstrate the performance of the proposed algorithm under different noises and various hand-eye configurations. In addition, experiments on real robot systems are presented to further verify the proposed method. © 2023, CC BY-SA.

关键词： Multipurpose robots

Hybrid6D: A Dual-Stream Transformer-CNN Approach for 6D Object Pose Estimation from RGB-D Images *

学校读者我要写书评

暂无评论

Hybrid6D: A Dual-Stream Transformer-CNN Approach for 6D Obje...

IEEE International Conference on robotics and Biomimetics

作者： Songhao Fu Qiang Zhang Xueying Sun Mingmin Liu Zhiwei Fan College of Automation Jiangsu University of Science and Technology Zhenjiang China Central Research Institute SIASUN Robot & Automation CO. Ltd. Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation 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

Estimating the 6D pose presents a formidable challenge due to the intricate nature of world objects and the myriad of issues encountered when acquiring data from real-world scenes. This task is compounded by occlusions, fluctuating lighting conditions, and data noise. The conventional CNN or Transformer architectures primarily focus on either local or global information, and relying solely on RGB or depth maps proves inadequate for extracting the most robust features. To address these challenges, we introduce Hybird6D, a dual-stream fusion deep learning approach that leverages a Transformer-CNN structure and attention mechanism to regress the 6D pose of objects using RGB-D images as input. Our methodology capitalizes on the strengths of both Transformers and CNNs, incorporating global attention and local attention, while simultaneously harnessing both appearance and geometric information. This comprehensive approach enhances robustness to noise and occlusions. Experimental evaluation on the YCB-Video dataset demonstrates that our method outperforms existing Transformer-based approaches and surpasses advanced CNN-based methods. Moreover, our approach exhibits superior performance on symmetry objects, textureless objects, and small objects.

关键词：

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Liu, Zongxin Zhao, Zhe Song, Fu Sun, Jun Yang, Pengfei Huang, Xiaowei Zhang, Lijun Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China RealAI Beijing China Nanjing Institute of Software Technology Nanjing China Singapore Management University Singapore College of Computer and Information Science Software College Southwest University Chongqing China The University of Liverpool Liverpool United Kingdom

Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks, which are robust, easy to verify, and relatively accurate. Our method integrates neuron behavior consistency into the training process, making neuron activation states consistent across different inputs in a local neighborhood, reducing the number of unstable neurons and tightening the bounds of neurons thereby enhancing neural network verifiability. We evaluated our method using the MNIST, Fashion-MNIST, and CIFAR-10 datasets across various network architectures. The results of the experiment demonstrate that networks trained using our method are verification-friendly across different radii and different model architectures, whereas other tools fail to maintain verifiability as the radius increases. We also show that our method can be combined with existing methods to further improve the verifiability of networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Neurons

Composition and Distribution Characteristics of Nutrients and Environmental Capacity in Dapeng Bay, Northern South China Sea

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Wu, Kangyue Xiu, Bin Cui, Dandan Lu, Dongliang Yang, Bin Liang, Shengkang Zhou, Jiaodi Huang, Haifang Peng, Shiqiu Guangxi Key Laboratory of Marine Environmental Change and Disaster in Beibu Gulf Beibu Gulf University Qinzhou535011 China Shenzhen Marine Environment Monitoring Center State Oceanic Administration of China Shenzhen518067 China Department of Basic Courses Army Logistics Academy Chongqing401331 China Jiangsu Key Laboratory of Marine Bioresources and Environment Jiangsu Ocean University Lianyungang222005 China Key Laboratory of Marine Chemistry Theory and Technology Frontiers Science Center for Deep Ocean Multiphases and Earth System Ministry of Education Ocean University of China Qingdao266100 China State Key Laboratory of Tropical Oceanography South China Sea Institute of Oceanology Chinese Academy of Sciences Guangzhou510301 China

The distribution characteristics of nutrient, water quality status, environmental capacity, and the impact of ecological environment of DPB were discussed based on two voyage investigations In September 2021(wet season) and March 2022(dry season). Results showed that NH4-N and NO3-N were the main form of DIN during the wet and dry season, concentrations ranging from 5.89 to 109.12 μg/L and 2.27 to 111.22 μg/L, accounting for ~53% and ~50%of DIN, respectively. TO4-P concentration ranged 2.02 ~17.90 μg/L, accounting for ~51% and 31% of TDP in the wet and dry seasons, respectively. The distributions of NH4-N, NO3-N, NO2-N, and PO4-P were relatively similar, showing a decreasing trend from the inner bay to the outer bay. COD, DIN, and DIP remaining environmental capacities in the DPB were 3,742, 1,418, and 141 tons, respectively. This study will provide a scientific basis for the protection of marine ecological environment and sustainable development of the DPB. © 2024, The Authors. All rights reserved.

关键词： Eutrophication

Novel Sandwich Structured Glass Fiber Cloth/Poly(Ethylene Oxide)-Mxene Composite Electrolyte

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Mao, Yu-Qin Dong, Guang-He Zhu, Wei-Bin Li, Yuan-Qing Huang, Pei Fu, Shao-Yun College of Aerospace Engineering Chongqing University Chongqing400044 China State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing University Chongqing400044 China

Recently, poly(ethylene oxide) (PEO)-based solid polymer electrolytes have been attracting great attention and efforts are currently underway to develop PEO-based composite electrolytes for next generation high performance all-solid-state lithium metal batteries. In this article, a novel sandwich structured solid-state PEO composite electrolyte is developed for high performance all-solid-state lithium metal batteries. The PEO-based composite electrolyte is fabricated by hot-pressing PEO, LiTFSI and Ti3C2T x MXene nanosheets into glass fiber cloth (GFC). The as-prepared GFC@PEO-MXene electrolyte shows high mechanical properties, good electrochemical stability, and high lithium-ion migration number, which indicates an obvious synergistic effect from the microscale GFC and the nanoscale MXene. Such as, the GFC@PEO-1 wt% MXene electrolyte shows a high tensile strength of 43.43 MPa and an impressive Young’s modulus of 496 MPa, which are increased by 1205 % and 6048 % over those of PEO. Meanwhile, the ionic conductivity of GFC@PEO-1 wt% MXene at 60 ℃ reaches 5.01×10-2 S m-1, which is increased by around 200% compared with that of GFC@PEO electrolyte. In addition, the Li/Li symmetric battery based on GFC@PEO-1 wt% MXene electrolyte shows an excellent cycling stability over 800 h (0.3 mA cm-2, 0.3 mAh cm-2), which is obviously longer than that based on PEO and GFC@PEO electrolytes due to the better compatibility of GFC@PEO-1 wt% MXene electrolyte with Li anode. Furthermore, the solid-state Li/LiFePO4 battery with GFC@PEO-1 wt% MXene as electrolyte demonstrates a high capacity of 110.2-166.1 mAh g-1 in a wide temperature range of 25-60 ℃, and an excellent capacity retention rate. The developed sandwich structured GFC@PEO-1 wt% MXene electrolyte with the excellent overall performance is promising for next generation high performance all-solid-state lithium metal ***, poly(ethylene oxide) (PEO)-based solid polymer electrolytes have been attracting great attentio

关键词： Polyethylene oxides