检索结果-内蒙古大学图书馆

Interaction and combined toxicity of microplastics and per-and polyfluoroalkyl substances in aquatic environment

Frontiers of Environmental Science & engineering 2022年第10期16卷 145-161页

作者： Yanhui Dai Jian Zhao Chunxiao Sun Diying Li Xia Liu Zhenyu Wang Tongtao Yue Baoshan Xing Institute of Coastal Environmental Pollution Control Key Laboratory of Marine Environment and Ecology(Ministry of Education)Frontiers Science Center for Deep Ocean Multispheres and Earth SystemOcean University of ChinaQingdao 266100China Laboratory for Marine Ecology and Environmental Science Qingdao National Laboratory for Marine Science and TechnologyQingdao 266237China Institute of Environmental Processes and Pollution Control and School of Environmental and Civil EngineeringJiangnan UniversityWuxi 214122China Stockbridge School of Agriculture University of MassachusettsAmherstMA 01003USA

Microplastics(MPs)are recognized as vectors for the transport of organic contaminants in aquatic environments in addition to their own adverse effects on aquatic ***-and polyfluoroalkyl substances(PFASs)are widely present in aquatic environments due to their widespread applications,and thus coexist with ***,we focus on the interaction of MPs and PFASs and related combined toxicity in aquatic environments in this work The adsorption of PFASs on MPs is critically reviewed,and new mechanisms such as halogen bonding,π-πinteraction,cation-πinteractions,and micelle formation are ***,the effect of MPs on the transport and transformation of PFASs in aquatic environments is *** on four typical aquatic organisms(shellfish,Daphnia,algae,and fish),the toxicity of MPs and/or PFASs at the organismal or molecular levels is also evaluated and ***,challenges and research perspectives are proposed,and the roles of the shapes and aging process of MPs on PFAS biogeochemical processes and toxicity,especially on PFAS substitutes,are recommended for further *** review provides a better understanding of the interactions and toxic effects of coexisting MPs and PFASs in aquatic environments.

关键词： Microplastics Per-and Polyfluoroalkyl substances Adsorption Transport Transformation

来源：评论

学校读者我要写书评

暂无评论

End-to-end Flow Scheduling Optimization for Industrial 5G and TSN Integrated Networks

End-to-end Flow Scheduling Optimization for Industrial 5G an...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Houling Li, Mingyan Gu, Fuqiang Li, Qihao Zhang, Weiting Guo, Songtao Chongqing University College of Computer Science Chongqing400044 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai China Jilin University College of Communication Engineering Changchun130015 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100091 China

ISBN: (纸本)9798350351255

The integrated of the fifth generation (5G) and time-sensitive networking (TSN) is a promising approach to meet the requirements of deterministic forwarding with extremely low latency and high flexibility for the Industrial Internet of Things (IIoT). However, due to the large dissimilarity of protocol stacks, the 5G system normally serves as a logical bridge for TSN, performing hold-and-forward operations in Base Stations (BSs) under the current 5G-TSN frameworks. To provide ubiquitous and seamless connectivity for IIoT devices, this paper focuses on the integrated enhancement of 5G and TSN by optimizing the scheduling of time-sensitive flows with end-to-end latency of 5G-TSN transmission taken into consideration. Specifically, we propose a novel architecture named GF-CQF, which combines 5G Grant-free (GF) access with TSN Cyclic Queuing and Forwarding (CQF). Subsequently, the distributed flow scheduling problem based on GF-CQF architecture is established due to the high timeliness demands. To alleviate the impact of the uncertainty inherent in 5G channels on end-to-end deterministic transmission, a feature-aware decentralized real-time scheduling (FDRS) policy based on Multi-agent Reinforcement Learning is proposed. FDRS allows each agent at BS to adaptively allocate TSN injection slots for flows mainly based on dynamic 5G transmission performance and TSN network resource state so that TSN queue overflow can be avoided and flow delay constraints can be guaranteed. Simulations show that FDRS offers superior scheduling capabilities under the limited TSN queue resources. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Self-feedback LSTM regression model for real-time particle source apportionment

引用

Journal of Environmental Sciences 2022年第4期34卷 10-20页

作者： Wei Wang Weiman Xu Shuai Deng Yimeng Chai Ruoyu Ma Guoliang Shi Bo Xu Mei Li Yue Li Trusted AI System Laboratory College of Computer ScienceNankai UniversityTianjin 300350China KLMDASR Tianjin Key Laboratory of Network and Data Security TechnologyTianjin 300350China State Environmental Protection Key Laboratory of Urban Ambient Air Particulate Matter Pollution Prevention and Control College of Environmental Science and EngineeringNankai UniversityTianjin 300071China Institute of Mass Spectrometry and Atmospheric Environment Guangdong Provincial Engineering Research Center for on-line source apportionment system of air pollution Jinan UniversityGuangzhou 510632China Guangdong-Hongkong-Macao Joint Laboratory of Collaborative Innovation for Environmental Quality Guangzhou 510632China

Atmospheric particulate matter pollution has attracted much wider attention *** recent years,the development of atmospheric particle collection techniques has put forwards new demands on the real-time source apportionments *** demands are summarized,in this paper,as how to set up new restraints in apportionment and how to develop a non-linear regression model to process complicated circumstances,such as the existence of secondary source and similar *** this study,we firstly analyze the possible and potential restraints in single particle source apportionment,then propose a novel three-step self-feedback long short-term memory(SF-LSTM)network for approximating the source *** proposed deep learning neural network includes three modules,as generation,scoring and refining,and regeneration *** from the scoring modules,SF-LSTM implants four loss functions representing four restraints to be followed in the apportionment,meanwhile,the regeneration module calculates the source contribution in a non-linear *** results show that the model outperforms the conventional regression methods in the overall performance of the four evaluation indicators(residual sum of squares,stability,sparsity,negativity)for the ***,in short time-resolution analyzing,SF-LSTM provides better results under the restraint of stability.

关键词： Time series Regression Self-feedback LSTM network Particle source apportionment

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning with Min-Max Distance Approach for Few-Shot Steel Surface Defects Recognition 43

Self-Supervised Learning with Min-Max Distance Approach for ...

引用

43rd Chinese control Conference, CCC 2024

作者： Wang, Tianlei Chen, Xinyao Li, Zeliang Zhou, Zhencai Zhou, Zhiheng Wuyi University School of Electronic and Information Engineering Jiangmen China Jiangmen Key Laboratory of Kejie Semiconductor Bonding Technology and Control System Jiangmen China Wuyi University School of Mechanical and Automation Engineering Jiangmen China Guangdong Province Kejie Machinery Automation Company Technical Department Jiangmen China

ISBN: (纸本)9789887581581

Surface defects in steel are crucial for quality inspection in the manufacturing of industrial metal products. While deep learning methods have been extensively studied in this field, the lack of large-scale annotated defect samples imposes significant labeling pressure, making training fully supervised deep models challenging. In response to this issue, we employ self-supervised learning for few-shot recognition, effectively learning representations from limited unlabeled data and achieving defect recognition with a small amount of labeled samples. In particular, we construct Other encoder with multi-view information and Base encoder with single view information based on the distillation self-supervised learning framework through the multi-crops mechanism, and the Other encoders and Base encoders perform information share. Our main contribution is that, based on this framework, we propose a new regularization method to solve the problem of instances deviating from the center of self-supervised clustering by minimizing the maximum instance distance (MMD). In testing, fine-tuning the MMD pre-trained model with a small number of labeled data achieves superior recognition performance on the steel surface defect dataset NEU, significantly outperforming other testing methods. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

MA-RRT∗ Algorithm for Path Planning with Maximum Rotation Angle Constraint and Adaptive Crossing Threat Zone 42

MA-RRT∗ Algorithm for Path Planning with Maximum Rotation A...

引用

42nd Chinese control Conference, CCC 2023

作者： Luo, Jiong Heng, Yong Li, Qi Hua, Yongzhao Dong, Xiwang Ren, Zhang School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Beijing Institute of Electronic System Engineering Beijing100854 China Institute of Artificial Intelligence Beihang University Beijing100191 China

ISBN: (纸本)9789887581543

With the gradual diversification of modern application scenes, the demand for UAV path planning is becoming more and more abundant. This paper first introduces a possible battle scenario, and the problems that must be considered in path planning in this scene are analyzed: the maximum rotation angle constraint and the demand that the UAV can cross the threat zone flexibly. Maximum rotation angle and Adaptive crossing threat zone RRT∗(MA-RRT∗) algorithm is proposed to solve the above problems. The algorithm improves the reconnection process of neighbor set in RRT∗, and adds the maximum rotation angle constraint to the RRT∗ framework, so that the generated path strictly meets this constraint. In addition, the above process also reduces the time consumption of RRT∗, and the speed advantage of MA-RRT∗ becomes more and more obvious with the increase of iteration times. Then, the obstacle information is regarded as one of the components of the node cost of the path, and the original obstacle is regarded as a soft constraint. This enables the path to adaptively cross the threat zone, which is more in line with the actual situation. We compare our algorithm with RRT∗ in numerical simulation, which verifies the effectiveness and time consumption advantages of the algorithm. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Application and Practice of Smart Education Technology in Blended Teaching of engineering Drawing Course 24

Application and Practice of Smart Education Technology in Bl...

引用

9th International Conference on Distance Education and Learning, ICDEL 2024

作者： Xu, Jinyou Tian, He Wang, Xiaofei Xue, Yahong Li, Ling Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin University of Technology China School of Environmental Science and Safety Engineering Tianjin University of Technology Tianjin China

ISBN: (纸本)9798400716805

The expeditious progress of information technology has encouraged the digital enhancement of the educational sector. To remedy the issues of the traditional teaching mode, a blended teaching mode of engineering drawing course has been developed with the use of smart education technology. Based on the Outcomes-based Education ( OBE ), the teaching objectives and teaching contents of the course are reconstructed by using the method of reverse design and forward implementation. By leveraging the synergy of online and offline, virtual and real, and quantitative and qualitative evaluation, a blended teaching approach that is both student-centered and teacher-guided is realized. A course knowledge graph has been built, offering fresh concepts for accomplishing personalized learning for students. The teaching practice shows that the blended teaching mode based on intelligent education has created a multi-dimensional autonomous learning space and personalized learning path for students, which effectively improves the enthusiasm and initiative of students to participate in teaching activities, and also improves the information level of teaching process and management, and promotes the organic integration of teaching and learning. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Design and Wave Propagation Characterization of Starchiral Metamaterials

引用

Acta Mechanica Solida Sinica 2022年第2期35卷 215-227页

作者： Yajun Xin Han Wang Cong Wang Jinxin Yao Qian Ding Haoqiang Gao Shuliang Cheng Yongtao Sun Key Laboratory of Green Construction and Intelligent Maintenance for Civil Engineering of Hebei Province Yanshan UniversityQinhuangdao 060000China Hebei Province Low-Carbon and Clean Building Heating Technology Innovation Center Yanshan UniversityQinhuangdao 060000China Department of Mechanics and Tianjin Key Laboratory of Nonlinear Dynamics and Control Tianjin UniversityTianjin 300072China State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures Shijiazhuang Tiedao UniversityShijiazhuang 050043China

Metamaterials with simple artificial topological properties made from industrially produced single-phase materials have extraordinary innovation and *** this paper,we investigated wave propagation characteristics of a hexastarchiral lattice metamaterial with periodic assemblies and used the finite element(FE)method to study the band gap ***,in order to understand the mechanism of band gaps,we discussed the mode shapes of unit cells and found that the bending of the ligament and the overall rotation have a high correlation with the generation of omnidirectional band *** relationships bet ween geometric parameters and band gap properties have also been systematically studied,which demonstrated that the band gaps of the proposed metamaterial could be reasonably predicted through the evolution of geometric ***,the transmission characteristics of finite sandwich panel structures composed of periodic unit cells were calculated to verify the correctness of the band gap simulation results,which proved that the proposed artificial metastructure has potential application value in vibration and noise reduction projects.

关键词： Hexastarchiral lattice metamaterials Band gap properties Finite element method Rotational resonance

来源：评论

学校读者我要写书评

暂无评论

A public data-set for synchronous motor electrical faults diagnosis with CNN and LSTM reference classifiers

引用

Energy and AI 2023年第4期14卷 221-237页

作者： Zhenglong Sun Ram Machlev Qianchao Wang Juri Belikov Yoash Levron Dmitry Baimel Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)JilinChina The Andrew and Erna Viterbi Faculty of Electrical&Computer Engineering Technion-Israel Institute of TechnologyHaifa 3200003Israel Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing210096China Department of Software Science Tallinn University of TechnologyAkadeemia tee 15a12618 TallinnEstonia Department of Electrical and Electronics Engineering Sami Shamoon College of EngineeringBeer-Sheva84100Israel

In the last two decades,motor operation monitoring tools have become a necessity,and many studies focus on the detection and diagnosis of motor electrical ***,at present,a core obstacle that prevents the direct comparison of such classification techniques is the lack of a standard database that can be used as a *** view of this,we offer here a public experimental data-set that has beendesigned specifically for the comparison of synchronous motor electrical fault *** data-set comprises five types of motor electrical faults:open phase between inverter and motor;short circuit/leakage current between two phases;short circuit/leakage current in phase-to-neutral;rotor excitation voltage disconnection;and variation of rotor excitation *** addition,each fault has been recorded as a four-dimensional signal:three phase voltages;three phase currents;motor speed;and motor *** package includes two deep-learning reference classifiers that are based on a convolutional neural network(CNN)and long short term memory(LSTM).Due to the good performance of these classifiers,we suggest that they can be used by the community as benchmarks for the development of new and better motor electrical fault classification *** database and the reference classifiers are examined and insights regarding different combinations of features and lengths of recording points are *** developed code is available online,and is free to use.

关键词： Motor faults Synchronous motors Public data-set Classification Deep-learning CNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of Logistics Packages Based on CNN and Image Recognition Technology 4

Anomaly Detection of Logistics Packages Based on CNN and Ima...

引用

4th IEEE International Conference on Data Science and Computer Application, ICDSCA 2024

作者： Liang, Kun Zhang, Hang School of Management Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China

ISBN: (纸本)9798350368239

To address abnormal situations such as packaging damage, liquid leakage, and item displacement during logistics package transportation, this paper introduces Convolutional Neural Network (CNN) and image recognition technology to achieve real-time anomaly detection and alarm, improving the response speed and accuracy of the logistics system. First, by designing multiple layers of convolution and pooling layers, adding Batch Normalization layers and Dropout layers to prevent overfitting, a CNN deep learning model suitable for logistics package anomaly detection is constructed. Key features are extracted through image preprocessing methods such as normalization and data enhancement to ensure that the model has high recognition adaptability to various abnormal situations such as damage and leakage. Secondly, through data enhancement methods such as rotation, scaling, brightness adjustment, and transfer learning using pre-trained models, the model's adaptability in different lighting, angles, and occlusion conditions is improved. Finally, the model is applied to actual monitoring, and real-time alarms are issued for abnormalities such as damage and leakage, which are then fed back to the system closed-loop management. This method is significantly better than traditional methods in terms of detection accuracy and response speed. Under natural light environment, the model detection accuracy is as high as 98.4%, reducing false positives and false negatives. Combining CNN's anomaly detection technology effectively improves the accuracy and efficiency of logistics monitoring and provides technical support for intelligent logistics management. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel feature enhancement module for small object detection

A novel feature enhancement module for small object detectio...

引用

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Wang, Ruogu Li, Ning Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (纸本)9781728119489

Generic object detection has made great progress in recent years, yet small object detection is still facing a serious problem of missed detection. The problem is caused by two reasons: low resolution in small targets and feature loss during deep convolution downsampling. Some previous studies used feature pyramid structures and multi-scale training predictions to alleviate this problem, but still cannot efficiently utilise the feature information of small targets. In this paper, firstly we propose a novel and effective feature enhancement module to extract more features;secondly, a filter size design method is presented to extract features of matching objects and incorporate context information;finally, an adaptive fusion method is used to process outputs of our module and improve model robustness. We select YOLOv3 as base model and carry out several experiments on a special Small Object Dataset and the results show that our work can achieve an increase of about seven percentage points (35.73%) compared to 28.78% on baseline. © 2022 IEEE.

关键词： Object detection

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：