检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Jianning Chi Changqing Ma Xingrui Wu College of Robot Science and Engineering Northeastern University College of Information Science and Engineering Northeastern University

At present,the mainstream paradigm of multi-target tracking is still tracking-by-detection,which includes two parts:the detector for locating the target and the appearance embedding model for data *** methods implement the two modules separately,without considering the relationship between ***,the biggest problem of this two-stage methods is the large amount of calculation,leading to slow running *** this paper,we build a unified online multi-object tracking *** integrating the object detector and the apparent embedding model into the same shared model,we can get the bounding box and the embedding model simultaneously,so as to reduce the network complexity and speed up the *** further improve the performance of the detector,we add an attention mechanism to weight each dimension of the output channel,so as to highlight the important foreground information and ignore the influence of the background as much as *** experimental results demonstrate that we can achieve competitive results on MOT16 dataset,and the best trade-off between accuracy and speed.

关键词： Online multi-object tracking one-shot model attention mechanism trade-off

来源：评论

学校读者我要写书评

暂无评论

The fabrication of "8"-shape microstructured optical fiber and its application in pressure/temperature sensing

引用

Journal of Lightwave Technology 2025年

作者： Xue, Pingsheng Fu, Yongqing Wu, Qiang Ng, Wai Pang Binns, Richard Liu, Qiang Northeastern University College of Information Science and Engineering Shenyang110819 China Northumbria University Faculty of Engineering and Environment Newcastle upon TyneNE1 8ST United Kingdom Northeastern University at Qinhuangdao School of Control Engineering Qinhuangdao066004 China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinhuangdao066004 China

A microstructured optical fiber was designed. The internal structure of the fiber consists of two round channels, and its cross-section resembles the shape of "8". This fiber can be applied in the fields of pressure sensing and temperature sensing. The stress induced by pressure on the core increases the birefringence due to the photo-elastic effect. When an appropriate liquid material, such as glycerol, is filled into the two round channels of the fiber, temperature sensing can be achieved based on the coupling between the fiber core and the liquid rod. Both pressure and temperature sensing characteristics were investigated in detail in experiments. By constructing a Sagnac interferometer, the pressure sensitivity reached 109.78 nm/MPa. Based on the coupling between the core and the infiltrated glycerol in the round channels, the temperature sensitivity was as high as -47.15 nm/°C. Their cross-sensitivities were also analyzed. The pressure or temperature sensors based on this fiber are highly suitable for scenarios such as the oil and gas industries. © 1983-2012 IEEE.

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Robust Visual SLAM Algorithm for Dynamic Indoor Environments

Robust Visual SLAM Algorithm for Dynamic Indoor Environments

引用

第40届中国控制会议

作者： Lijin Fang Keqi Wang Yingcai Wan School of Robot Science and Engineering Northeastern University

In real scenes,traditional visual SLAM algorithm is limited by the assumption of static *** to the influence of moving objects,the traditional visual odometry makes a large number of mismatches and makes the system unable to run statically in real *** this paper,a robust visual SLAM algorithm for indoor dynamic environment is proposed based on deep ***,the object detection network is used to detect the dynamic objects and determine the moving objects in the surrounding ***,a semantic data association method and key-frame selection strategy are proposed for the tracking thread and the local graph thread to reduce the influence of moving objects on the algorithm ***,the TUM open datasets is *** results show that the proposed method reduces the mean root mean square error（RMSE） of ORB-SLAM2 by more than 94% in dynamic scenarios compared to the previous improved *** addition,compared to other deep learning based SLAM systems,the proposed method has a better balance of speed and accuracy in dynamic environments.

关键词： simultaneous localization and mapping dynamic environment object detection motion removal

来源：评论

学校读者我要写书评

暂无评论

Breaking barriers:Smart vaccine platforms for cancer immunomodulation

引用

Cancer Communications 2025年第5期45卷 529-571页

作者： Mohammad Mahmoudi Gomari Taha Ghantabpour Nima Pourgholam Neda Rostami Stephen M.Hatfield Farzaneh Namazifar Shadi Abkhiz Seyed Sadegh Eslami Mahsa Ramezanpour Mahsa Darestanifarahani Igor Astsaturov Sidi A.Bencherif Department of Medical Biotechnology Faculty of Allied MedicineIran University of Medical SciencesTehranIran Department of Anatomy School of MedicineQazvin University of Medical SciencesQazvinIran School of Nursing and Midwifery Iran University of Medical ScienceTehranIran Department of Chemical Engineering Arak UniversityArakIran New England Inflammation and Tissue Protection Institute Department of Pharmaceutical SciencesNortheastern UniversityBostonMassachusettsUSA Department of Chemical Engineering Northeastern UniversityBostonMassachusettsUSA Department of Chemistry University of IsfahanIsfahanIran Molecular Proteomics Laboratory Baker Heart and Diabetes InstituteMelbourneVictoriaAustralia Department of Chemistry and Chemical Biology Rutgers UniversityPiscatawayNew JerseyUSA Marvin and Concetta Greenberg Pancreatic Cancer Institute Fox Chase Cancer CenterPhiladelphiaPennsylvaniaUSA Harvard John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMassachusettsUSA Polymers Biopolymers Surfaces(PBS)LaboratoryNational Center for Scientific Research(CNRS)Mixed ResearchUnit(UMR)6270University Rouen NormandieRouenFrance

Despite significant advancements in cancer treatment,current therapies often fail to completely eradicate malignant *** shortfall underscores the urgent need to explore alternative approaches such as cancer *** the immune system’s natural ability to target and kill cancer cells holds great ther-apeutic ***,the development of cancer vaccines is hindered by several challenges,including low stability,inadequate immune response activa-tion,and the immunosuppressive tumor microenvironment,which limit their *** progress in various fields,such as click chemistry,nanotechnol-ogy,exosome engineering,and neoantigen design,offer innovative solutions to these *** achievements have led to the emergence of smart vaccine platforms(SVPs),which integrate protective carriers for messenger ribonucleic acid(mRNA)with functionalization strategies to optimize targeted *** chemistry further enhances SVP performance by improving the encapsu-lation of mRNA antigens and facilitating their precise delivery to target *** review highlights the latest developments in SVP technologies for cancer therapy,exploring both their opportunities and challenges in advancing these transformative approaches.

关键词： cancer click chemistry mRNA vaccines smart vaccine platforms targeted delivery

来源：评论

学校读者我要写书评

暂无评论

Scale-free linear protocol design for global regulated state synchronization of discrete-time double-integrator multi-agent systems subject to actuator saturation

Scale-free linear protocol design for global regulated state...

引用

Chinese Control and Decision Conference, CCDC

作者： Zhenwei Liu Ali Saberi Anton A. Stoorvogel College of Information Science and Engineering Northeastern University Shenyang China School of Electrical Engineering and Computer Science Washington State University Pullman WA USA Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede The Netherlands

This paper studies global regulated state synchronization of discrete-time double-integrator multi-agent systems subject to actuator saturation by utilizing localized information exchange. We propose a scalable linear protocol that achieves global regulated state synchronization for any network with arbitrary number of agents and arbitrarily directed communication graph that has a path between each agent and exosystem which generates the reference trajectory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-person interaction action recognition based on co-occurrence graph convolutional network

Multi-person interaction action recognition based on co-occu...

引用

Chinese Control and Decision Conference, CCDC

作者： Zhongyu Bai Hongli Xu Haopeng Zhang Haitao Gu Faculty of Robot Science and Engineering Northeastern University Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665478977

Skeleton-based human action recognition has attracted more and more attention with the accessibility of depth sensors and the development of pose estimation technology. The recognition of multi-person interaction behavior with skeleton data has wide applications in real life. However, the existing skeleton-based action recognition methods mainly focus on single-person actions, and lack the research on the semantic information of the skeleton co-occurrence relationship in the spatial dimension. Here, a two-stream co-occurrence graph convolutional network (2s-CGCN) is proposed for multi-person interactive action recognition. The topological connection structure of the proposed model establishes connections between the human limbs and the head to capture the co-occurrence feature. In addition, the coordinates and co-occurrence information of the joints are simultaneously input into the model. The experiments of mutual actions in the NTU-RGB+D dataset show the effectiveness of the proposed model.

关键词： Convolution Semantics Pose estimation Data integration Skeleton Sensors Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Handling Collaborative robot System for Grasping Medical Cotton Cloth Porous with Bernoulli Gripper

Handling Collaborative Robot System for Grasping Medical Cot...

引用

IEEE International Conference on Mechatronics and Automation

作者： Kitti Suwanratchatamanee Hideyuki Sawada Shuji Hashimoto Department of Engineering Robotics Research and Development Center Golden Robot Co. Ltd Banchang Rayong Thailand Department of Applied Physics Graduate School of Advanced Science and Engineering Faculty of Science and Engineering Waseda University Tokyo Japan Waseda University Tokyo Japan

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

This paper presents the handling collaborative robot (Cobot) system for grasping the medical cotton cloth porous that were arranged in matching layers from one point to another point by arranged them in matching layers again. The important is to not grasping all layer objects together in once, but must be separately for each layer by layer. As the object to be grasped is the cotton cloth porous to be used in the medical purpose, thus the cleanness and must not leave any wrinkles or marks when handled the fabric are necessity required before packaging process. The proposed handling collaborative robot system contains the novel tooling called "Bernoulli Gripper" can achieve this handling task perfectly with 100% success rate of experiments. This gripper was developed to lifts the porous fabric sheet up in such a way that it does not grasping touch by utilizing four points Bernoulli principle elements like no other grippers that need to do the touching forces and always leave wrinkles or marks when handled the fabric, such as pneumatic suction cup, robot hand and fingers. Moreover, the research objective is to produce the handling robot system that can achieve the non-contact grasping and do collaborative tasks together with human in the same environment. As the result, our proposed system can be used for working together with human worker as the collaborative partner to arrange these medical cotton cloth porous products with about 6.5 seconds per sheet in the real production line suitably.

关键词： Mechatronics Grasping Collaborative robots Production Pneumatic systems Packaging Fabrics

来源：评论

学校读者我要写书评

暂无评论

Research on Obstacle Avoidance Planning of Serpentine Manipulator Based on Particle Swarm Optimization

Research on Obstacle Avoidance Planning of Serpentine Manipu...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Su, Haoxiang Liu, Manlu Tan, Liguo Huo, Jianwen Su, Qing Jiang, Yang Southwest University of Science and Technology School of Information Engineering Mianyang621010 China Southwest University of Science and Technology Robot Technology Used for Special Environment Key Laboratory of Sichuan Province Mianyang621010 China Southwest University of Science and Technology School of Information Engineering Robot Technology Used for Special Environment Key Laboratory of Sichuan Province Mianyang621010 China Southwest University of Science and Technology Tianfu Institute of Research and Innovation Chengdu610299 China Research Center of Basic Space Science School of Harbin Institute of Technology Harbin150000 China Southwest University of Science and Technology Manufacturing Science and Engineering Faculty Mianyang621010 China

ISBN: (纸本)9781665465335

Compared with traditional manipulators, serpentine manipulator have the advantage of high flexibility and have broad prospects in exploring confined spaces. Aiming at the problems of large amount of calculation and poor obstacle avoidance effect in motion planning of serpentine arm in complex space environment. In this paper, combined with the particle swarm algorithm, a "head traction"path tracking method is designed, so that the rope-driven serpentine manipulator can efficiently move along the planned path in complex terrain. In the method of this paper, the obstacle modeling is completed first, and then a serpentine arm path planning algorithm based on particle swarm optimization is further designed. Use the planned path as the path point tracked by the serpentine manipulator "head". As the manipulator moves forward, all joints follow the path traveled by the manipulator's "head". In the final stage, in order to ensure that the manipulator can accurately reach the target point, an end position adjustment algorithm is designed. Through the simulation experiment of the rope-driven serpentine manipulator based on 21 degrees of freedom, it is proved that the method can successfully make the serpentine manipulator move in complex space, and has high computational efficiency and high precision, which is well verified the validity of the study. © 2022 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Self-evolving Malware Detection for Cyber Security using Network Traffic and Incremental Learning 9

Self-evolving Malware Detection for Cyber Security using Net...

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Xu, Xiaohu Liang, Yifei Zhang, Xixi Wang, Yu Lin, Yun Adebisi, Bamidele Gacanin, Haris Gui, Guan College of Telecommunications and Information Engineering Njupt Nanjing China School of Mechanical Engineering and Automation Northeastern University Shenyang China College of Information and Communication Engineering Harbin Engineering University Harbin China Manchester Metropolitan University Faculty of Science and Engineering Manchester United Kingdom Institute for Communication Technologies and Embedded Systems Rwth Aachen University Aachen Germany

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Malware detection is an important step in network security. Traditional malware detection methods suffer from the ability to learn, understand, process, and apply characteristics of network traffic data accurately, and in a relatively short space of time. It also cannot learn new tasks without forgetting the old tasks. In this paper, we propose a self-evolving malware detection (SEMD) method using network traffic and incremental learning. Incremental learning (IL) method is one of the important methods in deep learning, which can learn new tasks without forgetting the old tasks. Its loss function draws lessons from the idea of knowledge distillation. Experimental results show that the proposed method can recognize both old tasks and new tasks (overcoming the problem of catastrophic network forgetting). The performance of the proposed SEMD method is also better than the general method of incremental learning without self-evolving. © 2022 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Bayesian Network Models of Hurricane Evacuation Decision Making

arXiv

引用

arXiv 2023年

作者： Wang, Hui Sophie Yongsatianchot, Nutchanon Marsella, Stacy Institute for Experiential AI Northeastern University Boston United States Faculty of Engineering Thammasat School of Engineering Thammasat University Pathum thani Thailand Khoury College of Computer Science Department of Psychology Northeastern University Boston United States

Hurricanes cause significant economic and human costs, requiring individuals to make critical evacuation decisions under uncertainty and stress. To enhance the understanding of this decision-making process, we propose using Bayesian Networks (BNs) to model evacuation decisions during hurricanes. We collected questionnaire data from two significant hurricane events: Hurricane Harvey and Hurricane Irma. We employed a data-driven approach by first conducting variable selection using mutual information, followed by BN structure learning with two constraint-based algorithms. The robustness of the learned structures was enhanced by model averaging based on bootstrap resampling. We examined and compared the learned structures of both hurricanes, revealing potential causal relationships among key predictors of evacuation, including risk perception, information received from media, suggestions from family and friends, and neighbors evacuating. Our findings highlight the significant role of social influence, providing valuable insights into the process of evacuation decision-making. Our results demonstrate the applicability and effectiveness of data-driven BN modeling. © 2023, CC BY-NC-ND.

关键词： Risk perception

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：