检索结果-内蒙古大学图书馆

A Visual-Cortex-Mimetic Tiny Neuromorphic Vision Processor Based on Reconfigurable Cortical Neuron Unit

IEEE Transactions on Circuits and Systems II: Express Briefs 2025年

作者： Chen, Mingju He, Junxian Wang, Haibing Wang, Tengxiao Gao, Haoran Liu, Liyuan Wang, Ying Shi, Cong Sichuan University of Science and Engineering Artificial Intelligence Key Laboratory of Sichuan Province Sichuan Yibin643000 China Chongqing University School of Microelectronics and Communication Engineering Chongqing400044 China Chinese Academy of Sciences State Key Laboratory for Superlattices and Microstructures Institute of Semiconductors Beijing100083 China Chinese Academy of Sciences State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing100190 China

Edge visual systems demand high energy-efficiency vision processors like neuromorphic hardware leveraging spikebased computations. But their disability of directly interacting with non-spike information in the real world requests additional components to execute image pre-processing, spike encoding and decoding, severely increasing overall system cost, energy and latency. To overcome such drawback, this brief proposes a tiny neuromorphic vision processor which emulates functional regions along the ventral pathway in the visual cortex. It performs image pre-processing, spike encoding, spike-based feature extraction and classification, spike decoding as well as decision making on a single chip. To reduce hardware resources, our processor builds on a reconfigurable cortical neuron (RCN) unit, which runs different neuron models for different visual cortex regions in a timemultiplexing fashion. It also embeds biological learning circuits to better adapt the processor to dynamic edge scenarios. Our neuromorphic processor was prototyped on a very-low-cost Xilinx Zynq-7010 device. On the MNIST dataset, it exhibited a real-time inference speed of 696 frame/s covering image pre-processing to final decision and a high on-chip learning accuracy of 97.12%, while only delivering a power consumption as low as 118 mW. © 2004-2012 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

arXiv

引用

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Proposing thematic mapping for integrated risk communication: A study of British & Japanese perspectives in flood-prone communities” [Int. J. Disaster Risk Reduc., 107 (2024) 104472]

引用

International Journal of Disaster Risk Reduction 2024年 109卷

作者： Maciej Pawlik Kaori Kitagawa Hideyuki Shiroshita Ravindra Jayaratne Soma Nomoto Yoshihiro Okumura Kazuhiro Kono University of East London School of Architecture Computing and Engineering UK University College London Institute of Education UK Kansai University Graduate School of Societal Safety Sciences Japan

来源：评论

学校读者我要写书评

暂无评论

Inverse learning of black-box aggregator for robust Nash equilibrium

arXiv

引用

arXiv 2024年

作者： Chen, Guanpu Xu, Gehui He, Fengxiang Tao, Dacheng Parisini, Thomas Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Digital Futures Stockholm100 44 Sweden Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh EdinburghEH8 9AB United Kingdom College of Computing & Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an aggregative game given a known aggregator. When the coupling parameters are affected by uncertainty, robust NE need to be computed. We consider a scenario where players' weight in the aggregator is unknown, making the aggregator kind of "a black box". We pursue a suitable learning approach to estimate the unknown aggregator by proposing an inverse variational inequality-based relationship. We then utilize the counterpart to reconstruct the game and obtain first-order conditions for robust NE in the worst case. Furthermore, we characterize the generalization property of the learning methodology via an upper bound on the violation probability. Simulation experiments show the effectiveness of the proposed inverse learning approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Removal of cadmium and zinc from water using sewage sludge-derived biochar

Sustainable Chemistry for the Environment

引用

Sustainable Chemistry for the Environment 2024年 6卷

作者： Shah, Ahsan Zakharova, Julia Batool, Maryam Coley, Matthew P. Arjunan, Arun Hawkins, Alisha J. Bolarinwa, Timothy Devi, Shreah Thumma, Anusha Williams, Craig School of Engineering Computing and Mathematical Sciences University of Wolverhampton WV1 1LY United Kingdom School of Architecture and Built Environment University of Wolverhampton WV1 1LY United Kingdom Department of Chemistry University of Sahiwal Sahiwal Pakistan Faculty of Science and Engineering University of Wolverhampton WV1 1LY United Kingdom Department of Pharmaceutical Sciences College of Pharmacy Nova Southeastern University FL United States

This research reveals the adsorption of cadmium (Cd2+) and zinc (Zn+2) from water using sewage sludge-derived biochar pyrolysed at 700 °C (SSB). The morphology and particle characteristics of SSB were characteris... 详细信息

This research reveals the adsorption of cadmium (Cd²⁺) and zinc (Zn⁺²) from water using sewage sludge-derived biochar pyrolysed at 700 °C (SSB). The morphology and particle characteristics of SSB were characterised through scanning electron microscopy (SEM), particle size distribution (PSD), fourier transform infrared (FTIR), X-ray diffraction (XRD), and X-ray fluorescence (XRF). The adsorption study showed that the optimum contact times for removing Zn²⁺ and Cd²⁺ were 80 and 140 minutes, respectively. 95.51% Zn²⁺ and 97.54% Cd²⁺ could be removed from spiked solutions featuring 50 mg/L of Zn²⁺ and 50 mg/L Cd²⁺, each treated with 25 g/L biochar. The optimum pH of the solutions was 8–9 at a temperature of 40°C, indicating some precipitation of the metal ions at an alkaline pH. The highest adsorption capacity of SSB for Cd²⁺ and Zn²⁺ was found to be 3.02 and 2.51 mg/g, respectively, which compares favourably with other adsorbents. The isotherm studies confirmed experimental data to closely follow the Langmuir isotherm model at an R² value of 0.9846 and 0.9816 for Cd²⁺ and Zn²⁺, respectively. The kinetic study confirmed the physical interaction between the adsorbents and the adsorbate. The spontaneous and exothermic nature of the process was confirmed by negative values of change in Gibbs free energy (ΔG) and enthalpy (ΔH). SSB could be regenerated for 6 cycles. Overall, this study explores sustainability, recycling, and waste management by offering SSB as a potentially cost-effective and environment-friendly solution to remove Cd²⁺ and Zn²⁺ from water. © 2024 The Authors

关键词： Adsorption Biochar Cadmium Isotherms and kinetics Regeneration Thermodynamics Zinc

来源：评论

学校读者我要写书评

暂无评论

Peak emission path of rural carbon emission in Chongqing based on optimization neural network and genetic algorithm

Journal of Biotech Research

引用

Journal of Biotech Research 2024年 19卷 269-280页

作者： Quan, Feng Liu, Peng Quan, Kai Zhang, Xingxing Jiang, Wenjie Chongqing Water Resources and Electric Engineering College Chongqing Yongchuan China Art and Media College Chongqing Metropolitan College of Science and Technology Chongqing Yongchuan China Bangkok Thailand Science Multimedia Journalism School of Multimedia Technology & Communication Awang Had Salleh Graduate School of Arts and Sciences Universiti Utara Malaysia Kedah Sintok Malaysia School of Computing Awang Had Salleh Graduate School of Arts and Sciences Universiti Utara Malaysia Kedah Sintok Malaysia College of Landscape Architecture and Arts Northwest A&F University Shaanxi Yangling China

The growth of industrialized agriculture has caused the problem of excessive carbon emission (CE) in animal husbandry and rural agriculture. To maintain energy conservation and carbon reduction in rural economic development, this study explored the peak carbon emission path in Chongqing, China through the optimization model of back-propagation neural network and genetic algorithm. The research analyzed the optimization direction of energy structure through the carbon emission of rural industrial composition with the aim of projecting energy use efficiency, which was achieved by weighing the financial gains from energy use against the associated carbon emissions. This study extended the direction of industrial optimization by combining the cross-variance model of genetic algorithm to explore the global optimal path through population simulation. The study also improved the adaptability of the model by iterative training method with the help of the learning process of back propagation neural network adaptive data. The results revealed that the loss function of the proposed model basically converged after 30 iterations in the test set, and the prediction accuracy of the model could reach more than 80% after 60 iterations. The fitness value of the proposed model was reduced to 0.22 × 10-3 after 120 iterations, while the lowest fitness value of other algorithms could only be reduced to 0.38 × 10-3, which indicated that the optimization effect of the proposed model was significantly better than other methods and could effectively avoid the local optimal solution problem. The proposed model could provide an effective planning path for exploring the peak carbon emissions in the rural area of Chongqing, China. © (2024), (Bio Tech System). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the periodic solutions of the three-body problem

引用

National Science Review 2019年第6期6卷 1070-1071页

作者： Shijun Liao Xiaoming Li Advanced Center of Computing School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong University School of Physics and Astronomy Shanghai Jiao Tong University MOE Key Laboratory of Disaster Forecast and Control in Engineering School of Mechanics and Construction Engineering Jinan University

The motion of three bodies that attract each other by universal gravitation was first investigated by Newton [1] and was reconsidered by many great mathematicians and scientists, including Euler, Lagrange, Poincaré [2] and Hilbert. The famous three-body problem has had a great influence on physics, mathematics and non-linear dynamics. It has led to a new

关键词： On the periodic solutions of the three-body problem

来源：评论

学校读者我要写书评

暂无评论

The effect of dose, settling time, shelf life, storage temperature and extractant on Moringa oleifera Lam. protein coagulation efficiency

引用

Environmental Nanotechnology, Monitoring and Management 2024年 21卷

作者： Shah, Ahsan Arjunan, Arun Manning, Georgina Zakharova, Julia Andraulaki, Ioanna Batool, Maryam School of Engineering Computing and Mathematical Sciences University of Wolverhampton WV1 1LY United Kingdom Department of Biology Chemistry and Forensic Science University of Wolverhampton WV1 1LY United Kingdom School of Architecture and Built Environment University of Wolverhampton WV1 1LY United Kingdom Department of Chemistry University of Sahiwal Sahiwal Pakistan

The study explores green chemistry to purify drinking water using Moringa oleifera (MO) Lam. seeds. This is done by investigating the coagulation efficiency of MO seed extracts for treating moderately turbid water. The research reveals the influence of various factors such as dose, settling time, shelf life, storage temperature, and extractant (water and 1 M NaCl solution) on the coagulation efficiency of MO Lam. protein. The MO seed protein extracts (MOPE) dissolved in tap water, and 1 M NaCl solution was characterised for their performance at ambient temperature and 4 ℃. Within 3 h of MOPE treatment, the turbidity reduced by 90–93 % without significantly altering pH and total dissolved solids (TDS) or electrical conductivity (EC) of the treated water samples. Although the dose rate was found to increase with the storage time, the optimum Moringa oleifera dose was 30–50 mg/l. Overall, the refrigerated MOPE in NaCl offered an extended shelf life, exhibiting good coagulation for up to 7 days compared to 3–4 days for the non-refrigerated variant. © 2024 The Author(s)

关键词： Moringa Seed extract Turbid water Water treatment Zeta potential

来源：评论

学校读者我要写书评

暂无评论

Viscous Effects on the Added Mass and Damping Forces During Free Heave Decay of a Floating Cylinder with a Hemispherical Bottom

SSRN

引用

SSRN 2022年

作者： Chen, Hao Xu, Qianlong Zheng, Xiaobo Bennetts, Luke G. Xie, Bin Lin, Zhiliang Lin, Zaibin Li, Ye School of Engineering University of Glasgow Glasgow United Kingdom Multiple Function Towing Tank Laboratory State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University 200240 China School of Naval Architecture Ocean and Civil Engineering Shanghai Jiao Tong University 200240 China School of Mathematical Sciences University of Adelaide AdelaideSA5005 Australia School of Computing Mathematics and Digital Technology Manchester Metropolitan University Manchester United Kingdom Lanzhou University of Technology China

This paper presents an analysis of viscous effects on the added mass and damping forces during free heave decay of a cylinder with a hemispherical bottom. Results from unsteady Reynolds-averaged Navier-Stokes (URANS) simulations and linear potential-flow solutions are compared. Expressions for the time-varying viscous added mass and damping coefficients are derived based on first-order Fourier analysis of the URANS results. Therefore, viscous effects are extracted by comparing the URANS results and linear potential-flow solutions, as nonlinear effects in this case are demonstrated to be negligible. It is observed that viscous effects on the added mass coefficient are minor during heave decay, such that the linear potential-flow model can predict the value of the added mass coefficient to within 5% deviations. In contrast, the viscous damping coefficient exhibits strong time-dependent variations. A parametric study of the effects of initial displacement, cylinder diameter and draft shows that viscous damping forces can play an important role when the cylinder has a relatively small diameter and large draft. Further, the damping coefficient is transformed to the nondimensional drag force coefficient, and its dependence on the Reynolds number Re is investigated, for Keulegan–Carpenter numbers in the range KC =1.5–2.5. It is found that the drag force coefficient is likely to be unrelated to Re and KC during the first cycle. From the second cycle to the fourth cycle, the drag force coefficient rapidly decreases with increasing Re , up to Re ≈ 3 × 10 5 . © 2022, The Authors. All rights reserved.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

Obstacle Detection and Avoidance in Self-Driving Carsusing LIDAR and Vision-Based Algorithms

Obstacle Detection and Avoidance in Self-Driving Carsusing L...

引用

Frontier Technologies and Solutions (ICFTS), International Conference on

作者： A. Sujin Jose Mohammad Bdair Preetish Kakkar T Praveena S. Thenappan S Lalitha Department of Automobile Engg New Horizon College of Engineering Bangalore India School of Architecture Computing & Engineering University of East London London UK IEEE Senior Member Delhi India Department of Mechatronics Engineering SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331502768

ISBN: (纸本)9798331502775

Existing algorithms do not generalize well to the Light Detection and Ranging (LIDAR) and camera modality when trained to detect cars with a vision-based algorithm, or vice versa when LIDAR is used as a separate sensor. These systems would fail in severe conditions such as low lighting and inclement weather. Itpresents a system that combines Lidar and vision-based data utilizing sensor fusion to enable Lidar's depth perception capabilities and vision-based algorithms for encompassing object recognition tasks. Such technology increases obstacle detection, object classification, and real-time decision making to provide a safer autonomous navigation system. It combines Kalman Filtering, convolutional neural network (CNN) for object detection, density-based spatial clustering of applications with noise (DBSCAN) for LIDAR data clustering, support vector machine (SVM) for classification, and predictive path planning. The results demonstrate the following improvements: 96.5% detection accuracy, 1.5% false positive rate, and 0.2% collision rate. It is more robust and outperforms existing systems in real-world situations such as bad illumination, severe weather, and complex traffic scenarios.

关键词： Support vector machines Laser radar Decision making Lighting Sensor fusion Real-time systems Path planning Classification algorithms Convolutional neural networks Meteorology

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：