检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Peng, Mai Yazdani, Delaram She, Zeneng Yazdani, Danial Luo, Wenjian Li, Changhe Branke, Juergen Nguyen, Trung Thanh Gandomi, Amir H. Yang, Shengxiang Jin, Yaochu Yao, Xin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Research Institute Faculty of Engineering and Technology Liverpool John Moores University United Kingdom School of Computer Science and Technology Harbin Institute of Technology China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Peng Cheng Laboratory China School of Artificial Intelligence Anhui University of Sciences & Technology China Information Systems Management and Analytics in Warwick Business School University of Warwick United Kingdom Faculty of Engineering & Information Technology University of Technology Sydney Australia Obuda University Hungary School of Computer Science and Informatics De Montfort University United Kingdom Department of Artificial Intelligence School of Engineering Westlake University China School of Computer Science University of Birmingham United Kingdom

Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization techniques. Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively. However, in existing literature, the reported results for a given EDOA can vary significantly. This inconsistency often arises because the source codes for many EDOAs, which are typically complex, have not been made publicly available, leading to error-prone re-implementations. To support researchers in conducting experiments and comparing their algorithms with various EDOAs, we have developed an open-source MATLAB platform called the Evolutionary Dynamic Optimization LABoratory (EDOLAB). This platform not only facilitates research but also includes an educational module designed for instructional purposes. The education module allows users to observe: a) a 2-dimensional problem space and its morphological changes following each environmental change, b) the behaviors of individuals over time, and c) how the EDOA responds to environmental changes and tracks the moving optimum. The current version of EDOLAB features 25 EDOAs and four fully parametric benchmark generators. © 2023, CC BY-NC-SA.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Grand Challenges in the Verification of Autonomous systems

arXiv

引用

arXiv 2024年

作者： Leahy, Kevin Asgari, Hamid Dennis, Louise A. Feather, Martin S. Fisher, Michael Ibanez-Guzman, Javier Logan, Brian Olszewska, Joanna I. Redfield, Signe Robotics Engineering Department Worcester Polytechnic Institute WorcesterMA United States Complex and Autonomous Systems Research Group Thales UK Research Reading United Kingdom Jet Propulsion Laboratory California Institute of Technology PasadenaCA United States Department of Computer Science University of Manchester Manchester United Kingdom Renault Guyancourt France Department of Computing Science University of Aberdeen Aberdeen United Kingdom Department of Information and Computing Sciences Utrecht University Utrecht Netherlands School of Computing and Engineering University of the West of Scotland Glasgow United Kingdom U.S. Naval Research Laboratory WashingtonDC United States

Autonomous systems use independent decisionmaking with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will find their way into an increasing number of applications in an ever wider range of settings. If we are to deploy them to perform safety-critical or mission-critical roles, it is imperative that we have justified confidence in their safe and correct operation. Verification is the process by which such confidence is established. However, autonomous systems pose challenges to existing verification practices. This paper highlights viewpoints of the Roadmap Working Group of the IEEE robotics and Automation Society Technical Committee for Verification of Autonomous systems, identifying these grand challenges, and providing a vision for future research efforts that will be needed to address them. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Patient Friendly System for Image Generation Using Bi-Lstm Based Deep Learning Model

SSRN

引用

SSRN 2024年

作者： Shoby, Abin Francis, Jerome Raju, Jini Pillai, Manu J. John, Ansamma Valakkada, Jineesh Amma, Ushadevi C. Rajan, Ginu Rajaram, Priyatharshini Department of Computer Science and Engineering Thangal Kunju Musaliar College of Engineering APJ Abdul Kalam Technological University Kerala India Department of Imaging Sciences and Interventional Radiology Sree Chitra Tirunal Institute for Medical Sciences and Technology Trivandrum India Department of Electronics and Communications Engineering Amrita Vishwa Vidyapeetham Amritapuri Campus Kerala India Centre for Engineering Research in Intelligent Sensors and Systems Cardiff School of Technologies Cardiff Metropolitan University Wales United Kingdom

IntraVoxel Incoherent Motion Imaging is preferred to conventional MRI technique as it brings out more information by the expense of scan time due to the need of multiple b-values, resulting in patient discomfort and quantification errors. The careful reduction of b-values without compromising the quality of MRI scans is the main challenge in the field of IVIM studies. To address this challenge, a novel approach is proposed to generate the unknown b-value images from minimum number of acquired b-value images by analyzing the haemodynamic properties of the tissue using a Bi-Directional Long Short Term Memory network which can explore the sequential nature and the bi-exponential property of IVIM signals. The experiment is carried out on simulated IVIM signals of brain tissue by successively reducing the b-value count in the input b-value sequence from 8 down to 3 and generating the signals corresponding to the required b-values. The results are validated using clinical images in the DIPY dataset and evaluated by comparing the generated images with their reference images in terms of performance metrics like Structural Similarity metric and radiology score, and is comparable to the image generated from the real IVIM environment. © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Evacuation Problem Under the Nuclear Leakage Accident

Evacuation Problem Under the Nuclear Leakage Accident

引用

第40届中国控制会议

作者： Canqi Yao Shibo Chen Zaiyue Yang School of Mechatronics Engineering Harbin Institute of Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineeringand the Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in UniversitiesSouthern University of Science and Technology

To handle the detrimental effects brought by leakage of radioactive gases at nuclear power station, we propose a bus based evacuation optimization problem. The proposed model incorporates the following four constraints, 1) the maximum dose of radiation per evacuee, 2) the limitation of bus capacity, 3) the number of evacuees at demand node（bus pickup stop）,4) evacuees balance at demand and shelter nodes, which is formulated as a mixed integer nonlinear programming（MINLP）problem. Then, to eliminate the difficulties of choosing a proper M value in Big-M method, a Big-M free method is employed to linearize the nonlinear terms of the MINLP problem. Finally, the resultant mixed integer linear program（MILP） problem is solvable with efficient commercial solvers such as CPLEX or Gurobi, which guarantees the optimal evacuation plan *** evaluate the effectiveness of proposed evacuation model, we test our model on two different scenarios（a random one and a practical scenario）. For both scenarios, our model attains executable evacuation plan within given 3600 seconds computation time.

关键词： Nuclear leakage accident bus evacuation problem mixed integer nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision

arXiv

引用

arXiv 2024年

作者： Mattamala, Matias Frey, Jonas Libera, Piotr Chebrolu, Nived Martius, Georg Cadena, Cesar Hutter, Marco Fallon, Maurice Dynamic Robot Systems Group University of Oxford 23 Banbury Road Oxford OxfordshireOX2 6NN United Kingdom Robotic Systems Lab ETH Zurich Leonhardstrasse 21 Zurich Zurich8092 Switzerland Autonomous Learning Group Max Planck Institute for Intelligent Systems Max-Planck-Ring 4 Tübingen Baden-Württemberg72076 Germany Computer Science Department University of Tüüingen Maria-von-Linden-Strasse 6 Tübingen Baden-Württemberg72076 Germany

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we present Wild Visual Navigation (WVN), an online self-supervised learning system for visual traversability estimation. The system is able to continuously adapt from a short human demonstration in the field, only using onboard sensing and computing. One of the key ideas to achieve this is the use of high-dimensional features from pre-trained self-supervised models, which implicitly encode semantic information that massively simplifies the learning task. Further, the development of an online scheme for supervision generator enables concurrent training and inference of the learned model in the wild. We demonstrate our approach through diverse real-world deployments in forests, parks, and grasslands. Our system is able to bootstrap the traversable terrain segmentation in less than 5 min of in-field training time, enabling the robot to navigate in complex, previously unseen outdoor terrains. © 2024, CC BY.

关键词： Parks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

arXiv

引用

arXiv 2023年

作者： Zuo, Shiyuan Fan, Rongfei Hu, Han Zhang, Ning Gong, Shimin The School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada The School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518055 China

In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks. At each user, model parameter is firstly updated by multiple steps, which is adjustable over iterations, and then pushed to the aggregation center directly. This decreases the number of interactions between the aggregation center and users, allows each user to set training parameter in a flexible way, and reduces computation burden compared with existing works that need to combine multiple historical model parameters. At the aggregation center, geometric median is leveraged to combine the received model parameters from each user. Rigorous proof shows that zero optimality gap is achieved by our proposed method with linear convergence, as long as the fraction of Byzantine attackers is below half. Numerical results verify the effectiveness of our proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Look closer to segment better: Boundary patch refinement for instance segmentation

arXiv

引用

arXiv 2021年

作者： Tang, Chufeng Chen, Hang Li, Xiao Li, Jianmin Zhang, Zhaoxiang Hu, Xiaolin State Key Laboratory of Intelligent Technology and Systems THU-Bosch JCML Center BNRist Institute for AI Department of Computer Science and Technology Tsinghua University China Institute of Automation CAS University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics HKISI CAS China

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundary-aware metrics. Moreover, by applying the BPR framework to the "PolyTransform + SegFix" baseline, we reached 1st place on the Cityscapes leaderboard. Code is available at https://***/tinyalpha/BPR. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ontology-based data interestingness: A state-of-the-art review

Natural Language Processing Journal

引用

Natural Language Processing Journal 2023年 4卷

作者： Abhilash C.B. Kavi Mahesh Department of Computer Science and Engineering Indian Institute of Information Technology Dharwad India Department of Data Science and Intelligent Systems Indian Institute of Information Technology Dharwad India

In recent years, there has been significant growth in the use of ontology-based methods to enhance data interestingness. These methods play a crucial role in knowledge management by providing explicit, shareable, and reusable knowledge descriptions. However, limited research has been conducted to explore the impact and practical benefits of employing ontologies to increase data interestingness. A comprehensive analysis of the current state-of-the-art approaches in ontology-based data interestingness is essential to identify future advancements and directions in this field. The main objective of this study is to present a clear roadmap showcasing how ontologies contribute to data interestingness and to evaluate their effectiveness in the existing literature. The findings of this research offer an integrated and comprehensive understanding of the following aspects: (1) interestingness metrics in data mining, (2) association rule mining to identify interesting patterns, (3) ontology-based methods to improve data interestingness, and (4) techniques that use ontologies to derive interestingness in data. The paper concludes with a summary of ontology-based methods for data interestingness and outlines potential avenues for future research.

关键词： Ontology Data interestingness Knowledge management Semantics Association rule mining Data mining Interestingness metrics Ontology-based methods

来源：评论

学校读者我要写书评

暂无评论

High-Precision 3D Printing by Deploying Expandable Microspheres

SSRN

引用

SSRN 2024年

作者： Xu, Yang Wang, Fucheng Zhang, Pei Lu, Chengbang Liu, Weixuan Guo, Yueying Ni, Zhipeng Wang, Jinqing Lu, Baoyang Lou, Qin Liang, Xiangyu Liu, Ji Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China Department of Metrology and Measurement Engineering China Jiliang University Hangzhou310018 China Agricultural Genomics Institute at Shenzhen Chinese Academy of Agricultural Sciences Shenzhen518120 China Institute of Bast Fiber Crops Center of Southern Economic Crops Chinese Academy of Agricultural Sciences Changsha410205 China Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China Yiwu Saiens Polymer Materials Co. Ltd Jinhua322099 China Jiangxi Key Lab of Flexible Electronics Flexible Electronics Innovation Institute Jiangxi Science & Technology Normal University Nanchang330013 China Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and Technology Shenzhen518055 China

Stereolithography-based 3D printing (3DP) technology is widely employed in various industries, including manufacturing, healthcare, energy, biomedical, art and other fields. However, the precision issues, such as dimensional shrinkage and structural warping, significantly hinder its wide applications. In this study, we present a straightforward, efficient yet general strategy to engineer the photosensitive resins with thermally expandable microspheres, thus enabling significant improvement in structural fidelity of the 3DP constructs. Our findings demonstrate that addition of expandable microspheres substantially mitigates the volume shrinkage below 3.98%, in comparison to over 10% for commercially-available photosensitive resins. An exceptionally high precision of 0.035% in dimensional deviation could be achieved, in comparison to over 0.1% for commercial one. Furthermore, due to the low filling ratio, the improvement in 3DP precision does not sacrifice the mechanical properties, thus it does not affect the applications where those photosensitive resins are originally targeting. Our method represents an effective strategy to improve the 3D printing resolution of photosensitive resins, thus opening new directions for high precision 3D printing technology. © 2024, The Authors. All rights reserved.

关键词： Shrinkage

来源：评论

学校读者我要写书评

暂无评论

High-Precision Stereo Matching with a Drone Equipped With Rtk-Gnss and a Single Camera for Plant Height Measurements

SSRN

引用

SSRN 2022年

作者： Matsuura, Yuta Heming, Zhang Nakao, Kousuke Qiong, Chang Firmansyah, Iman Kawai, Shin Yamaguchi, Yoshiki Hayashi, Hisayoshi Maruyama, Tsutomu Nobuhara, Hajime The Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan College of Engineering Systems School of Science and Engineering University of Tsukuba Japan The Department of Computer Science Graduate School of Science and Technology University of Tsukuba Japan The Faculty of Life and Environmental Sciences University of Tsukuba Japan The School of Computing Tokyo Institute of Technology Japan

We propose a high-precision plant height measurement system based on large-scale stereo images captured by a drone. In our system, the drone collects images of a field using a monocular camera and obtains the position data by a real time kinematic (RTK)-global navigation satellite system (GNSS). The heights of plants in the field are measured by stereo matching. By employing a single monocular camera rather than a binocular camera, we can obtain a sufficient baseline length for accurate height measurements, but the images must be precisely calibrated at run time. To this end, we propose a calibration algorithm with a conventional stereo matching algorithm. The proposed method requires only a pair of images and their position data (RTK-GNSS), which are more suitable for edge computing on drones than three-dimensional (3D) reconstructions by methods such as Structure from Motion. To show the effectiveness of the proposed method, we measured the plant height from photographs captured by the drone at different altitudes. Our method achieves a higher height resolution (1.6 cm) than the 3D reconstruction-based methods Pix4Dmapper and Metashape, with error-rate reductions of 62.2% and 69.4%, respectively, in the 10-20 m altitude range. When the altitude is lowered to 4.1 m , the depth resolution is improved to 1.6 mm with error reductions of 44.4% and 63.0% from those of Pix4Dmapper and Metashape, respectively. On a GTX 1080 TI graphics processing unit, stereo matching of 5472 × 3468-pixel images consumed 88 ms. This execution time is sufficiently fast for real-time measurements. Because our system uses the position data obtained by RTK-GNSS, it achieves centimeter-level accuracy during the drone flight. After the flight, the accuracy can be improved to millimeter level by comparing the results of the stereo matching with an image containing a reference plant of preobtained known height © 2022, The Authors. All rights reserved.

关键词： Global positioning system

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：