检索结果-内蒙古大学图书馆

ECA-RetinaNet: A Novel Self-Attention RetinaNet for Environmental Microorganism Image Object Detection

学校读者我要写书评

暂无评论

ECA-RetinaNet: A Novel Self-Attention RetinaNet for Environm...

IEEE International Conference on Big Data

作者： Hechen Yang Jinzhu Yang Tao Jiang Xin Zhao Jinghua Zhang Peng Zhao Ao Chen Qianqing Nie Marcin Grzegorzek Chen Li Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang Liaoning China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Institute of Robotics and Intelligent Systems Chengdu University of Information Technology Chengdu China Institute of Medical Informatics University of Luebeck Luebeck Germany

The detection of environmental microorganisms is always a difficult task, e specially when the multi-scale environment is complex. For tiny objects in microscopic images, current detection methods face the challenge of accurate identification and localization. In contrast, we propose a convolutional neural network (ECA-RetinaNet) for microscopic object detection of which underlying dataset is a high-quality EMDS-7 dataset. The accuracy of ECA-RetinaNet is high, with a high mean Average Precision (mAP) value of 81.42% in the Environmental Microorganisms (EMS) detection task. Its accuracy has been higher than that of the two-stage object detection network.

关键词：

Hierarchical Adaptive Tracking Control for Mobile Robots With Multiple Constraints

学校读者我要写书评

暂无评论

Hierarchical Adaptive Tracking Control for Mobile Robots Wit...

Chinese Automation Congress (CAC)

作者： Chenghao Zhao Shiqi Zheng Haiming Li Haitao Jian Shihao Wang School of Automation China University of Geosciences Wuhan Campus Hubei Key Laboratory of Advanced Control and Intelligent Automation fo Complex Systems Wuhan China

ISBN: (纸本)9781665426480

This paper studies the mobile robots with multiple constraints based on path planning of A-star algorithm. A hierarchical adaptive control method is presented to handle multiple constaints. On the upper layer, a Astar path planning algorithm is designed. On the lower layer, a new controller is provided. Then, we design barrier Lyapunov function and adaptive RBF neural network control method to make sure that tracking error and velocity error converges to the specified set within a finite amount of time. Compared with other existing works, this system considers multiple consraints include tracking error, constraints velocity constraints and output saturation constraint, provides guarantee for the safe operation of the mobile robot. In addition, because of the unknown conditions on the ground, system also considers the impact of slipping. Computer simulation result demonstrates the effectiveness of control method. In the experimental verification, we use A-star algorithm to generate the appropriate path as the desired trajectory of the mobile robot. The experiment proved the stability of control method.

关键词： Automation Computer simulation Neural networks Approximation algorithms Stability analysis Trajectory Planning

Model Compression Based on YOLOv3 Object Detection Algorithm from the Perspective of UAV

学校读者我要写书评

暂无评论

Model Compression Based on YOLOv3 Object Detection Algorithm...

第40届中国控制会议

作者： Bing Wu Zhijun Xue Wenjie Chen State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center

Recently,unmanned aerial vehicles are widely used in surveillance,aerial photography,power grid line inspections and other *** order to deploy the YOLOv3[1] algorithm on drones,it is necessary to adopt the YOLOv3 algorithm with fewer parameters and a simpler *** paper implements the model compression of YOLOv3 based on methods such as sparseness,pruning,and knowledge *** paper implements the sparseness of the network by adding L1 regular expressions on the convolutional *** that,redundant channels and layers are removed through channel pruning and layer *** sparse and pruning,the mAP lost a *** using knowledge distillation after pruning,it attempts to recover mAP lost in sparseness and *** this method,the YOLOv3 algorithm can be deployed on embedded platforms such as RK3399 *** evaluate the model on the visdrone2019 *** experimental results show that after model compression,YOLOv3 is more suitable for deployment on embedded platforms.

关键词： Object Detection Model Compress RK3399pro YOLOv3

Suppression of heading errors in Bell-Bloom optically pumped free-induction-decay alkali-metal atomic magnetometers

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Siqi Wang, Xueke Zhang, Xiangdong Xiao, Wei Sheng, Dong Department of Precision Machinery and Precision Instrumentation Key Laboratory of Precision Scientific Instrumentation of Anhui Higher Education Institutes University of Science and Technology of China Hefei230027 China College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China Beijing Computational Science Research Center Beijing100193 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Center for Quantum Information Technology Peking University Beijing100871 China MIIT Key Laboratory of Complex-field Intelligent Sensing Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing100081 China Hefei National Laboratory University of Science and Technology of China Hefei230088 China

Heading errors of atomic magnetometers refer to the dependence of measurement results on the sensor orientation with respect to the external magnetic field. There are three main sources of such errors: the light shift effect, the linear nuclear-spin Zeeman effect, and the nonlinear Zeeman effect. In this work, we suppress the former two effects by using the Bell-Bloom optical pumping method and probe the atomic signals while the pumping beam is off, and focus on the heading error induced by nonlinear Zeeman effect while the sensor operates in the geomagnetic field range. We demonstrate several schemes to suppress this remaining heading error within 1 nT using a single magnetometer or a comagnetometer. In the magnetometer system, two schemes are developed to average out the horizontal atomic polarization in space or in time, respectively. In the comagnetometer system, we combine the simultaneously measured Larmor frequencies of two different kinds of alkali atoms to either suppress the heading error or extract the orientation of the pumping beam relative to the bias field. © 2025, CC BY.

关键词： Blooms (metal)

Takeaway Method Based on the Crowdsensing Path Planning System: A Study on the Use of Idle Bicycle Resources for Delivery

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Xiong, Yonghua Zeng, Hongrui Yu, Anjun Hiroaki, Kurokawa She, Jinhua School of Automation China University of Geosciences Wuhan430074 China Hubei key laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Jiangxi Ganyue Expressway Co. Ltd. Jiangxi330200 China School of Engineering Tokyo University of Technology Tokyo192-0982 Japan

Due to the surge in takeaway demand, full-time delivery riders are facing challenges in completing their tasks on time. To address this issue, this study proposed a takeaway delivery method based on Crowdsensing. This strategy uses idle bicycle riders as resources to complete delivery tasks at a lower cost. To decrease the total delivery cost of merchants, the idle bicycle path planning model was established. The path planning problem of the proposed model is characterized by multiple riders, random locations, open deliveries, and pickup and delivery crossovers. Further, it belongs to the NP-hard problem. To solve this path planning model, a takeaway delivery-based genetic algorithm was designed. Order-preserving initialization was utilized to construct the initial population. The order crossover algorithm and adaptive mutation algorithm were introduced to overcome slow convergence and prevent the probability of falling into the local optimal solution of the traditional algorithm. The experimental results showed that the proposed takeaway delivery-based genetic algorithm had a fast convergence and high accuracy. Moreover, it can effectively solve the path planning model, thereby reducing merchant delivery cost and improving delivery timeliness. The method proposed in this paper has a significant application value. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

Provably Convergent Federated Trilevel Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xinshun Zhang, Wanying Wang, Can Gao, Yuan Liu, Mengyuan the National Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School China the School of Intelligent Systems Engineering Sun Yat-sen University China the Multimedia Information Processing Laboratory the Department of Computer Science Kiel University Germany Peking University China the Unit of Computing Sciences CS Faculty of Information Technology and Communication Sciences ITC Tampere University Finland

Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task. Nevertheless, how to construct a graph from a skeleton sequence and how to perform message passing on the graph are still open problems, which severely affect the performance of GCN. To solve both problems, this paper presents a Dynamic Dense Graph Convolutional Network (DD-GCN), which constructs a dense graph and implements an integrated dynamic message passing. More specifically, we construct a dense graph with 4D adjacency modeling as a comprehensive representation of motion sequence at different levels of abstraction. Based on the dense graph, we propose a dynamic message passing framework that learns dynamically from data to generate distinctive messages reflecting sample-specific relevance among nodes in the graph. Extensive experiments on benchmark Human 3.6M and CMU Mocap datasets verify the effectiveness of our DD-GCN which obviously outperforms state-of-the-art GCN-based methods, especially when using long-term and our proposed extremely long-term protocol. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

a branch-and-price approach for the nurse rostering problem with multiple units

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Wanzhe He, Xiaozhou Luo, Li Pardalos, Panos M. School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing China Business School Sichuan University Sichuan Chengdu China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China Department of Industrial and Systems Engineering Center for Applied Optimization University of Florida Gainesville United States

In this paper, we study the nurse rostering problem that considers multiple units and many soft time-related constraints. An efficient branch and price solution approach that relies on a fast algorithm to solve the pricing subproblem of the column generation process is presented. For the nurse rostering problem, its pricing subproblem can be formulated as a shortest path problem with resource constraints, which has been the backbone of several solutions for several classical problems like vehicle routing problems. However, approaches that perform well on these problems cannot be used since most constraints in the nurse rostering problem are soft. Based on ideas borrowed from global constraints in constraint programming to model rostering problems, an efficient dynamic programming algorithm with novel label definitions and dominating rules specific to soft time-related constraints is proposed. In addition, several acceleration strategies are employed to improve the branch and price algorithm. Computational results on instances of different sizes indicate that the proposed algorithm is a promising solution for the nurse rostering problem with multiple units. Copyright © 2023, The Authors. All rights reserved.

关键词： Constraint programming

Resource Allocation and Power Control Policy for Device-to-Device Communication Using Multi-Agent Reinforcement Learning

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第6期63卷 1515-1532页

作者： Yifei Wei Yinxiang Qu Min Zhao Lianping Zhang F.Richard Yu Beijing Key Laboratory of Work Safety Intelligent Monitoring Beijing University of Posts and TelecommunicationsBeijing100876China Alibaba Cloud Computing Hangzhou311121China Department of Systems and Computer Engineering Carleton UniversityOttawaK1S 5B6Canada

Device-to-Device(D2D)communication is a promising technology that can reduce the burden on cellular networks while increasing network *** this paper,we focus on the channel resource allocation and power control to improve the system resource utilization and network ***,we treat each D2D pair as an independent *** agent makes decisions based on the local channel states information observed by *** multi-agent Reinforcement Learning(RL)algorithm is proposed for our multi-user *** assume that the D2D pair do not possess any information on the availability and quality of the resource block to be selected,so the problem is modeled as a stochastic non-cooperative ***,each agent becomes a player and they make decisions together to achieve global ***,the multi-agent Q-learning algorithm based on game theory is ***,in order to accelerate the convergence rate of multi-agent Q-learning,we consider a power allocation strategy based on Fuzzy C-means(FCM)*** strategy firstly groups the D2D users by FCM,and treats each group as an agent,and then performs multi-agent Q-learning algorithm to determine the power for each group of D2D *** simulation results show that the Q-learning algorithm based on multi-agent can improve the throughput of the *** particular,FCM can greatly speed up the convergence of the multi-agent Q-learning algorithm while improving system throughput.

关键词： D2D communication resource allocation power control multi-agent Q-learning fuzzy C-means