检索结果-内蒙古大学图书馆

Noise Tolerant Identification and Tuning Approach Using Deep Neural Networks For Visual Servoing Applications

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hay, Oussama Abdul Chehadeh, Mohamad Ayyad, Abdulla Wahbah, Mohamad Humais, Muhammad Boiko, Igor Seneviratne, Lakmal Zweiri, Yahya Center for Autonomous Robotic Systems Khalifa University Abu Dhabi United Arab Emirates Department of Electrical Engineering and Computer Science Department of Aerospace Engineering Khalifa University Abu Dhabi United Arab Emirates

Vision based control of Unmanned Aerial Vehicles (UAVs) has been adopted by a wide range of applications due to the availability of low-cost on-board sensors and computers. Tuning such systems to work properly requires extensive domain specific experience, which limits the growth of emerging applications. Moreover, obtaining performance limits of UAV based visual servoing is difficult due to the complexity of the models used. In this paper, we propose a novel noise tolerant approach for real-time identification and tuning of visual servoing systems, based on deep neural networks (DNN) classification of system response generated by the modified relay feedback test (MRFT). The proposed method, called DNN with noise protected MRFT (DNN-NP-MRFT), can be used with a multitude of vision sensors and estimation algorithms despite the high levels of sensor’s noise. Response of DNN-NP-MRFT to noise perturbations is investigated and its effect on identification and tuning performance is analyzed. The proposed DNN-NP-MRFT is able to detect performance changes due to the use of high latency vision sensors, or due to the integration of inertial measurement unit (IMU) measurements in the UAV states estimation. Experimental identification closely matches simulation results, which can be used to explain system behaviour and predict the closed loop performance limits for a given hardware and software setup. We also demonstrate the ability of DNN-NP-MRFT tuned UAVs to reject external disturbances like wind, or human push and pull. Finally, we discuss the advantages of the proposed DNN-NP-MRFT visual servoing design approach compared with other approaches in literature. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Qingquan Liu, Jialin Zhang, Zeqi Wen, Junyi Mao, Bifei Yao, Xin The Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Trustworthiness Theory Research Center Huawei Technologies Co. Ltd. Shenzhen518129 China The School of Computer Science University of Birmingham United Kingdom

In the literature of mitigating unfairness in machine learning, many fairness measures are designed to evaluate predictions of learning models and also utilised to guide the training of fair models. It has been theoretically and empirically shown that there exist conflicts and inconsistencies among accuracy and multiple fairness measures. Optimising one or several fairness measures may sacrifice or deteriorate other measures. Two key questions should be considered, how to simultaneously optimise accuracy and multiple fairness measures, and how to optimise all the considered fairness measures more effectively. In this paper, we view the mitigating unfairness problem as a multi-objective learning problem considering the conflicts among fairness measures. A multi-objective evolutionary learning framework is used to simultaneously optimise several metrics (including accuracy and multiple fairness measures) of machine learning models. Then, ensembles are constructed based on the learning models in order to automatically balance different metrics. Empirical results on eight well-known datasets demonstrate that compared with the state-of-the-art approaches for mitigating unfairness, our proposed algorithm can provide decision-makers with better tradeoffs among accuracy and multiple fairness metrics. Furthermore, the high-quality models generated by the framework can be used to construct an ensemble to automatically achieve a better tradeoff among all the considered fairness metrics than other ensemble methods. Our code is publicly available at https://***/qingquan63/FairEMOL. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

ORA3D: Overlap Region Aware Multi-view 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Roh, Wonseok Chang, Gyusam Moon, Seokha Nam, Giljoo Kim, Chanyoung Kim, Younghyun Kim, Jinkyu Kim, Sangpil Department of Artificial Intelligence Korea University Seoul Korea Republic of School of Computing KAIST Daejeon Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of Autonomous Driving Center Hyundai Motor Company R&D Division Seoul Korea Republic of

Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network. Moreover, objects in the overlap region are often largely occluded or suffer from deformation due to camera distortion, causing a domain shift. To mitigate this issue, we propose using the following two main modules: (1) Stereo Disparity Estimation for Weak Depth Supervision and (2) Adversarial Overlap Region Discriminator. The former utilizes the traditional stereo disparity estimation method to obtain reliable disparity information from the overlap region. Given the disparity estimates as supervision, we propose regularizing the network to fully utilize the geometric potential of binocular images and improve the overall detection accuracy accordingly. Further, the latter module minimizes the representational gap between non-overlap and overlapping regions. We demonstrate the effectiveness of the proposed method with the nuScenes large-scale multi-view 3D object detection data. Our experiments show that our proposed method outperforms current state-of-the-art models, i.e., DETR3D and BEVDet. © 2022, CC BY.

关键词： Object detection

Full-pose Trajectory Tracking of Overactuated Multi-Rotor Aerial Vehicles with Limited Actuation Abilities

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Hamandi, Mahmoud Al-Ali, Ismail Seneviratne, Lakmal Franchi, Antonio Zweiri, Yahya The Department of Aerospace Engineering Khalifa University of Science and Technology Abu Dhabi United Arab Emirates The Department of Mechanical Engineering Khalifa University Abu Dhabi United Arab Emirates Khalifa University of Science and Technology Abu Dhabi United Arab Emirates The Robotics and Mechatronics Lab Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands The Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy LAAS CNRS Université de Toulouse Toulouse31000 France Khalifa University Abu Dhabi United Arab Emirates Center for Artificial Intelligence and Robotics New York University Abu Dhabi Saadiyat Island Abu Dhabi129188 United Arab Emirates

This paper presents a novel optimization-based full-pose trajectory tracking method to control overactuated multirotor aerial vehicles with limited actuation abilities. The proposed method allocates feasible control inputs to track a reference trajectory, while ensuring the tracking of the reference position, and while tracking the closest feasible attitude. The optimization simultaneously searches for a feasible trajectory and corresponding feasible control inputs from the infinite possible solutions, while ensuring smooth control inputs. The proposed real-time algorithm is tested in extensive simulation on multiple platforms with fixed and actuated propellers. The simulation experiments show the ability of the proposed approach to exploit the complex set of feasible forces and moments of overactuated platforms while allocating smooth feasible control inputs. © 2023, CC BY.

关键词： Trajectories

Metabolic and oxidative responses in Helix aspersa to iron oxide nanoparticle exposure: individual and combined (Fe₂O₃/SiO₂) effects

学校读者我要写书评

暂无评论

Journal of Nanoparticle Research 2025年第6期27卷 1-14页

作者： Benamara, Amel Grara, Nedjoud Bensoltane, Samira Bouchaala, Laid Laouar, Amel Grara, Kamila Hemmami, Hadia Abdelghani, Boudjahem Aslam, Ali Abbas Ahmed, Mahmood Laboratory of Cellular Toxicology Faculty of Sciences University of Badji Mokhtar Annaba 23000 Algeria Department of Applied Biology Echahid Cheikh Larbi Tebessi University Tebessa 12400 Algeria Laboratory of Molecular and Cellular Biology Faculty of Natural and Life Sciences Earth and Universe Sciences P.O. Box 401 University 8 May 1945 Guelma Algeria Faculty of Medicine University of Badji Mokhtar Annaba 23000 Algeria Division of Environmental Innovation and Eco-Waste Management Environmental Research Center (CRE) Annaba Algeria Laboratory of Biochemistry and Environmental Toxicology Faculty of Sciences University of Badji Mokhtar Annaba 23000 Algeria Laboratory of Analysis and Control of Differential Equations Department of Mathematics P.O. Box 401 University 8 May 1945 Guelma 24000 Algeria Department of Process Engineering and Petrochemical Faculty of Technology University of El Oued P.O. Box 789 El Oued 39000 Algeria Faculty of Mathematics Computer and Materials Sciences Department of Materials Science Universityof 8 Mai Guelma 1945 Algeria Department of Chemistry Division of Science and Technology University of Education Lahore 54770 Pakistan

This study evaluates the toxicity of iron oxide nanoparticles (Fe2O3 NPs) alone and in combination with silica nanoparticles (SiO2 NPs) on Helix aspersa. Snails were exposed to escalating concentrations (0, 5000, 10,0... 详细信息

This study evaluates the toxicity of iron oxide nanoparticles (Fe₂O₃ NPs) alone and in combination with silica nanoparticles (SiO₂ NPs) on Helix aspersa. Snails were exposed to escalating concentrations (0, 5000, 10,000, 15,000 μg/g of flour) of Fe₂O₃ NPs and a mixture of Fe₂O₃ and SiO₂ NPs for 28 days to assess impacts on metabolic parameters, oxidative stress, and neurotoxicity. Fe₂O₃ NPs significantly increased protein levels;the mixture exhibited a more pronounced effect, with significantly increased protein levels, particularly in the hepatopancreas and kidneys. Lipid levels generally decreased across all treatments, suggesting significant metabolic disruption. Carbohydrate responses were tissue-specific and differed significantly between single and combined exposures, highlighting complex responses to nanoparticle treatments. Malondialdehyde (MDA), a marker of lipid peroxidation, demonstrated a significant increase in all treatments compared to the control group. The mixture treatment caused divergent MDA responses, with higher levels observed in the hepatopancreas and lower levels in the kidneys than in single NP treatments. Glutathione (GSH) levels showed complex tissue-specific changes with mixture exposure, with reductions in the hepatopancreas and increases in the kidney. Furthermore, glutathione S-transferase (GST), catalase (CAT), and glutathione peroxidase (GPx) were altered, reflecting cellular stress responses. Notably, acetylcholinesterase (AChE) activity, a marker of neurotoxicity, was significantly reduced in all treated groups. These findings demonstrate that Fe₂O₃ NPs, individually and combined with SiO₂ NPs, induce significant metabolic dysregulation, oxidative stress, and neurotoxicity in H. aspersa. This study underscores the potential ecological risks of NPs contamination and the importance of further

关键词： Helix aspersa Iron Nanoparticles Oxidative stress Silica Toxicity

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Li Ye, Junda Peng, Hao Wang, Feiyang Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Computer Science University of Illinois ChicagoIL United States

Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence. On the other hand, continual learners in the literature rely on abundant labels, but labeling graph in practice is particularly hard especially for the continuously emerging graphs on-the-fly. To address the aforementioned challenges, we propose to explore a challenging yet practical problem, the self-supervised continual graph learning in adaptive Riemannian spaces. In this paper, we propose a novel self-supervised Riemannian Graph Continual Learner (RieGrace). In RieGrace, we first design an Adaptive Riemannian GCN (AdaRGCN), a unified GCN coupled with a neural curvature adapter, so that Riemannian space is shaped by the learnt curvature adaptive to each graph. Then, we present a Label-free Lorentz Distillation approach, in which we create teacher-student AdaRGCN for the graph sequence. The student successively performs intra-distillation from itself and inter-distillation from the teacher so as to consolidate knowledge without catastrophic forgetting. In particular, we propose a theoretically grounded Generalized Lorentz Projection for the contrastive distillation in Riemannian space. Extensive experiments on the benchmark datasets show the superiority of RieGrace, and additionally, we investigate on how curvature changes over the graph sequence. © 2022, CC BY-NC-SA.

关键词： Distillation

Reconfigurable Intelligent Surface Assisted High-Speed Train Communications: Coverage Performance Analysis and Placement Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Changzhu He, Ruisi Niu, Yong Han, Zhu Ai, Bo Gao, Meilin Ma, Zhangfeng Wang, Gongpu Zhong, Zhangdui The State Key Laboratory of Advanced Rail Autonomous Operation The School of Electronics and Information Engineering The Frontiers Science Center for Smart High-speed Railway System The Beijing Engineering Research Center of High-Speed Railway Broadband Mobile Communications Beijing Jiaotong University Beijing100044 China The State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing100044 China The National Mobile Communications Research Laboratory Southeast University Nanjing211189 China The Department of Electrical and Computer Engineering The University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China The Tsinghua Space Center the Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100091 China The College of Information Engineering Shaoyang University Shaoyang422000 China The Beijing Key Lab of Transportation Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Reconfigurable intelligent surface (RIS) emerges as maximization problem is formulated to facilitate RIS discrete an efficient and promising technology for the next wireless phase design and RIS placement optimization, which is subject generation networks and has attracted a lot of attention owing to coverage probability constraint. Simulation results validate to the capability of extending wireless coverage by reflecting that better coverage performance and higher travel distance signals toward targeted receivers. In this paper, we consider can be achieved with deployment of RIS. The impacts of some a RIS-assisted high-speed train (HST) communication system key system parameters including transmission power, signal-to-to enhance wireless coverage and improve coverage probability. noise ratio threshold, number of RIS elements, number of RIS First, coverage performance of the downlink single-input-single- quantization bits, horizontal distance between base station and output system is investigated, and the closed-form expression RIS, and speed of HST on system performance are investigated. of coverage probability is derived. Moreover, travel distance In addition, it is found that RIS can well improve coverage probability with limited power consumption for HST communications. Copyright © 2023, The Authors. All rights reserved.

关键词： Railroads

Experimental verification of the steering ellipsoid zoo via two-qubit states

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Kai Liu, Lijun Wang, Ning-Ning Zhang, Chao Huang, Yun-Feng Liu, Bi-Heng Cheng, Shuming Li, Chuan-Feng Guo, Guang-Can CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China College of Mathematics and Computer Science Shanxi Normal University Taiyuan030006 China Hefei National Laboratory University of Science and Technology of China Hefei230088 China The Department of Control Science and Engineering Institute for Advanced Study Tongji University Shanghai201804 China

Quantum steering ellipsoid visualizes the set of all qubit states that can be steered by measuring on another correlated qubit in the Bloch picture. Together with local reduced states, it provides a faithful geometric characterization of the underlying two-qubit state so that almost all nonclassical state features can be reflected in its geometric properties. Consequently, the various types of quantum ellipsoids with different geometric properties form an ellipsoid zoo, which, in this work, is experimentally verified via measurements on many polarization-path photonic states. By generating two-qubit states with high fidelity, the corresponding ellipsoids are constructed to certify the presence of entanglement, one-way Einstein-Podolsky-Rosen steering, discord, and steering incompleteness. It is also experimentally verified that the steering ellipsoid can be reconstructed from using the twelve vertices of the icosahedron as measurement directions. Our results aid progress in applying the quantum steering ellipsoid to reveal nonclassical features of the multi-qubit system. Copyright © 2023, The Authors. All rights reserved.

关键词： Quantum entanglement

Thickness Dependence of Unidirectional Magnetoresistance in Co2MnGa Films

学校读者我要写书评

暂无评论

Thickness Dependence of Unidirectional Magnetoresistance in ...

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Bin Rong Lizhu Ren Hongsheng Zheng Liang Liu Yumeng Yang School of Information Science and Technology ShanghaiTech University Shanghai China Shanghai Engineering Research Center of Energy Efficient and Custom AI IC ShanghaiTech University Shanghai China Department of Electrical and Computer Engineering National University of Singapore Singapore Key Laboratory of Artificial Structures and Quantum Control (Ministry of Education) TD Lee institute School of Physics and Astronomy Shanghai Jiao Tong University Shanghai China Hefei National Laboratory Hefei China Shanghai Research Center for Quantum Sciences Shanghai China

ISBN: (数字)9798350362213

ISBN: (纸本)9798350362220

With intrinsic giant anomalous Hall and Nernst effects, Weyl ferromagnet C02MnGa stands as an ideal candidate for exploring efficient charge-to-spin conversions. In this work, by utilizing the high-quality epitaxial C02MnGa single films, we observed a sizable unidirectional magnetoresistance. Surprisingly, the isotropic crystallographic axis dependence of unidirectional magnetoresistance, together with its linear scaling to the C02MnGa thickness, neither can be explained by the conventional spin current drift-diffusion process. By employing heat equation, we analytically derived the current induced vertical temperature gradient, and unambiguously show the thickness dependence of unidirectional magnetoresistance induced by anomalous Nernst effects. Our work provides direct evidences of thermoelectric voltages in the nonlinear transport that may be extended to other material systems as well.

关键词： Magnetic films Heating systems Temperature dependence Giant magnetoresistance Epitaxial growth