检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Nuosi Wu Zexuan Zhu Zhen Ji Shenzhen City Key Laboratory of Embedded System Design Shenzhen University Shenzhen China

This paper proposes a growing partitional clustering method based on particle swarm optimization (PSO) namely PSOGC for handling data with non-spherical or non-linearly separable distribution. Particularly, PSOGC uses PSO to optimize the cluster centers. In each iteration of PSO, the particles encoding candidate cluster centers are evolved according to their social and personal knowledge. Given the candidate cluster centers, a growing strategy increasingly absorbs nearby data samples into the corresponding cluster based on k-nearest neighbor graph. The fitness of each particle is evaluated in terms of intra-cluster connectivity and inter-cluster disconnectivity of the resultant clustering. The combination of PSO and growing strategy ensures the stability of global search and the robustness of partition on data of different non-spherical shapes. Experimental results on six synthetic and three UCI real-world data sets demonstrate the efficiency of PSOGC.

关键词： Clustering algorithms Particle swarm optimization Algorithm design and analysis Kernel Robustness Clustering methods Shape

来源：评论

学校读者我要写书评

暂无评论

CM-UNet++: A Multi-Level Information Optimized Network for Urban Water Body Extraction from High-Resolution Remote Sensing Imagery

引用

Remote Sensing 2025年第6期17卷

作者： Cai, Jiangchen Tao, Liufeng Li, Yang National Engineering Research Center of Geographic Information System China University of Geosciences Wuhan 430074 China School of Computer Science China University of Geosciences Wuhan 430074 China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural Resource Shenzhen518000 China Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Ministry of Education Wuhan 430074 China School of Geophysics and Geomatics China University of Geosciences Wuhan 430074 China Anhui Urban & Rural Planning and Design Institute Co. Ltd. Hefei230022 China

Urban water bodies are crucial in urban planning and flood detection, and they are susceptible to changes due to climate change and rapid urbanization. With the development of high-resolution remote sensing technology and the success of semantic segmentation using deep learning in computer vision, it is possible to extract urban water bodies from high-resolution remote sensing images. However, many urban water bodies are small, oddly shaped, silted, or spectrally similar to other objects, making their extraction extremely challenging. In this paper, we propose a neural network named CM-UNet++, a combination of the dense-skip module based on UNet++ and the CSMamba module to encode different levels’ information with interactions and then extract global and local information at each level. We use a size-weighted auxiliary loss function to balance feature maps of different levels. Additionally, features beyond RGB are incorporated into the input of the neural network to enhance the distinction between water bodies and other objects. We produced a labeled urban water extraction dataset, and experiments on this dataset show that CM-UNet++ attains 0.8781 on the IOU (intersection over union) metric, which indicates that this method outperforms other recent semantic segmentation methods and achieves better completeness, connectivity, and boundary accuracy. The proposed dense-skip module and CSMamba module significantly improve the extraction of small and spectrally indistinct water bodies. Furthermore, experiments on a public dataset confirm the method’s robustness. © 2025 by the authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Feature extraction based on trimmed complex network representation for metabolomic data classification

Feature extraction based on trimmed complex network represen...

引用

Congress on Evolutionary Computation

作者： Yue Chen Zexuan Zhu Zhen Ji Shenzhen City Key Laboratory of Embedded System Design Shenzhen University Shenzhen China

Over the last few decades, metabolomics has been widely used to reveal the linkages between metabolite signal levels and physiological states. Metabolomic data are naturally high dimensional and noisy, which poses computational challenges for data analysis. In this study, a novel feature extraction method based on trimmed complex network representation is proposed for metabolomic data classification. Particularly, the proposed method begins with feature selection on the original data, and then a complex network of the selected features is constructed to represent each data sample. Afterward, the network edges are trimmed and a few topological network metrics are extracted as new features for the classification of the samples. The experimental results on a real-world metabolomic data of clinical liver transplantation demonstrate the efficiency of the proposed feature extraction method.

关键词： Feature extraction Metabolomics Complex networks Accuracy Noise Tin

来源：评论

学校读者我要写书评

暂无评论

In-process density measurement for model-based process optimization of functionally graded foam microcellular structures in material extrusion additive manufacturing

引用

Additive Manufacturing 2025年 106卷

作者： Zhao, Donghua Zhou, Zhaowei Ruan, Kaicheng Xu, Xuguang Zhang, Guoquan Chen, Ziwen Wang, Kui Xiong, Yi School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China Key Laboratory of Traffic Safety on Track of Ministry of Education School of Traffic and Transportation Engineering Central South University Changsha410075 China

Additive manufacturing with in-process foaming enables the creation of complex, porous structures with graded density and porosity. However, the current process planning method, based on volume conservation principles, fails to accurately capture the nonlinear process-density relationship, thereby limiting the precision of density control. Herein, this study proposes a model-based process optimization approach that utilizes a non-contact in-process density measurement method, enabling optimization of both density and track width. First, this approach accelerates data collection and constructs a reliable process-density and process-width regression model, facilitating rapid process optimization of functionally graded foam. Then, the model captures the nonlinear effects of temperature and printing speed on thermally expandable microspheres, where high temperatures and low speeds promote foaming, and vice versa. Finally, foam samples with gradient densities, produced using optimized parameters, validate the regression model's accuracy and feasibility for customizing intralayer and interlayer density, investigating continuous density gradients, and pressure distribution-driven insoles. Generally, the results highlight the critical role of temperature and printing speed in determining foam density and microstructure, significantly advancing high-quality, controlled-density foam production via material extrusion additive manufacturing. Moreover, the study presents a framework for in-situ, in-process density measurement, aiding the rapid development of process parameter windows for density-variable novel materials based on mass conservation. © 2025 Elsevier B.V.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Mobility constraints of residents in marginal rural areas of megacities: Evidence from Beijing, China

引用

Journal of Transport Geography 2025年 127卷

作者： Zhao, Yu Yingrui, Gou Moru, Li Zhifeng, Zhao Pengjun, Zhao College of Architecture and Urban Planning Beijing University of Technology Beijing 100124 China School of Urban Planning and Design Peking University Shenzhen Graduate School Shenzhen 518055 China Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China 518055 China

The mobility of rural residents in urban fringe to permit them to access public services is an important issue in promoting urban–rural equity and contributing to sustainable development. However, marginal rural residents of fast-developing megacities, often trapped in neglected mobility disadvantages, remain conspicuously absent from mobility research and policies. This paper addresses this gap by exploring their mobility features and determinants using first-hand survey data from 40 marginal villages in Beijing. The results show that the rural-to-urban mobility of these residents is unexpectedly lower than their counterparts in more remote rural areas of China. Villagers' travel destinations are mostly confined to neighbouring villages and townships, especially for shopping and recreation. They do not have good access to public services in the city centre. Transport availability, service accessibility and household income are the most influential factors undermining the mobility of rural residents. Some institutional factors within megacities, such as restrictions on car purchase and electric vehicle usage, population and industrial dispersion, and village-level service facilities withdrawal, may exacerbate mobility challenges for those residing in marginal rural areas. These insights underscore the imperative for more policy attention on differentiated land use, transport and industrial policies in marginal rural areas to sustain inclusive transport development of megacity regions. © 2025 Elsevier Ltd

关键词： Marginal area Megacity Mobility constraints Rural mobility Transport inequity

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: The design and implementation of an integrated food monitor system

RETRACTED ARTICLE: The design and implementation of an integ...

引用

作者： Liang, Zhengping Ji, Zhen Lin, Jiali Liu, Ye Mou, Kai Shenzhen City Key Lab of Embedded System Design Shenzhen University Shenzhen China State Key Lab of Soft. Eng. Wuhan University Wuhan China Department of R and D Shenzhen UNIRICHO Co Ltd. Shenzhen China

ISBN: (纸本)9781424472369

It is important to achieve food safety using the food monitor system constructed with modern information technology. This paper firstly proposes a three-dimensional coding based on EAN·UCC to identify each phrase's information of food supply chain consistently. And then the main data model and kernel function of food monitor system are analyzed. After that, the logical structure and physical deploy of the system are introduced. The practice of the system shows it helps to achieve the whole course food safety monitor and management "from farm to fork". © 2010 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning with Region Division and Leader-Follower Communication

Multi-Agent Reinforcement Learning with Region Division and ...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Chao Xu, Xiang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798350368604

The integration of multi-agent reinforcement learning (MARL) into complex systems has paved new ways for collaborative problem-solving. However, traditional approaches to MARL frequently encounter the challenge of achieving efficient communication among agents, essential for coordinated action. This paper introduces a region division and leader-follower(RDLF) communication algrithm with the MARL framework. RDLF divides the environment into several regions, each managed by a leader agent that coordinates the actions of follower agents and handling inter-region communication. This hierarchical structure reduces unnecessary communication, enhancing learning efficiency. Experimental results in multi-particle environments demonstrate RDLF’s superiority over existing MARL algorithms, especially with increasing agent numbers. RDLF effectively addresses scalability and communication challenges in large-scale multi-agent systems, providing a robust foundation for its application in complex and dynamic environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A FPGA-based real time QRS complex detection system using adaptive lifting scheme

A FPGA-based real time QRS complex detection system using ad...

引用

International Conference on Data Engineering and Internet Technology, DEIT 2011

作者： Yu, Hang Ma, Lixiao Wang, Ru Jiang, Lai Li, Yan Ji, Zhen Pingkun, Yan Fei, Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen University Shenzhen China OPTIMAL Xi'an Institute of Optics and Precision Mechanics Xi'an China IBM Almaden Research Center San Jose CA 95120 United States

ISBN: (纸本)9783642288067

This paper presents a real time QRS wave detection system implemented using the FPGA. Based on the Adaptive Lifting Scheme, the digitized ECG sequence is directly processed in the spatial domain, thus greatly simplifies the system design and reduces the memory usage. In order to synchronize the input ECG sampling data and the FPGA based ALS system, a pipeline architecture interface is proposed. It works as a buffer and the ECG data is processed in a real time manner. The system is implemented on the XUPV5-LX110T evaluation platform, and validated by using ECG samples from the MIT-BTH Arrhythmia Database. Experimental results show that the system achieves 98.688% detection accuracy, while the dynamic power consumption is only ~20mW. © 2013 Springer-Verlag GmbH.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

design of low power CMOS band-pass Gm-C filter for 5.8 GHz RF transceiver of ETC system

Design of low power CMOS band-pass Gm-C filter for 5.8 GHz R...

引用

International Conference on Communication Technology (ICCT)

作者： Yan Li Hang Yu Lai Jiang Zhen Ji Shenzhen City Key Laboratory of Embedded System Design Shenzhen University Shenzhen China Shenzhen University Shenzhen Guangdong CN

Since electronic tolling collection (ETC) allows vehicles passing through without slowing down which improves greatly transportation efficiency, it is chosen as the basic technology for new national highway network construction. The key component of the ETC system is a 5.8 GHz RF transceiver that enables wireless communication between toll booth and vehicles. A 1-V Gm-C sixth order band pass filter is designed in a 0.18 mm CMOS process for this purpose. Based on a pseudo differential operational transconductance amplifier (OTA), a wide tuning range and large input voltage swing is achieved. A common-mode feed forward (CMFF) circuit is introduced to reduce the distortion caused by common mode signal. The filter is implemented as a cascade of three identical second-order blocks. The power consumption is about 456 μW.

关键词： CMOS technology Radio frequency CMOS integrated circuits Transportation Batteries Antennas

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Robotic Pouring Using Offline Reinforcement Learning

Multi-Level Robotic Pouring Using Offline Reinforcement Lear...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Zhang, Xiaoxiong Liu, Junwei Zhang, Wei School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen518055 China

ISBN: (纸本)9781665481090

This paper presents a novel learning-based method for a robotic manipulator to achieve liquid pouring across different liquid levels using only visual sensors. Previous works have relied on either online reinforcement learning or imitation learning, which are limited by sim-to-real gaps or data efficiency. In this paper, we propose to combine supervised learning and offline reinforcement learning, utilizing a human demonstration dataset containing only successful pouring at the highest level. Specifically, our approach employs supervised learning for a visual classifier, transforming the visual input into a categorical distribution over liquid levels. The offline reinforcement learning method is applied to a binary-conditioned control policy, which takes a binary signal and the robot's proprioception as inputs to determine the action. The binary signal indicates whether the desired liquid level has been reached based on the target liquid level. Through experiments, our method demonstrates superior effectiveness compared to a state-of-the-art imitation learning algorithm. Moreover, tests in unseen scenarios and multiple liquid level commands verify the generalization and transferability of our approach. © 2024 IEEE.

关键词： Self-supervised learning

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：