检索结果-内蒙古大学图书馆

Towards an ultrafast 3D imaging scanning LiDAR system:a review

Photonics Research 2024年第8期12卷 1709-1729页

作者： ZHI LI YAQI HAN LICAN WU ZIHAN ZANG MAOLIN DAI SZE YUN SET SHINJI YAMASHITA QIAN LI H.Y.FU Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Department of Electrical Engineering and Information Systems The University of TokyoTokyo 113-8656Japan Research Center for Advanced Science and Technology The University of TokyoTokyo 153-8904Japan School of Electronic and Computer Engineering Peking UniversityShenzhen 518055China

Light detection and ranging(LiDAR),as a hot imaging technology in both industry and academia,has undergone rapid innovation and *** current mainstream direction is towards system miniaturization and *** are many metrics that can be used to evaluate the performance of a LiDAR system,such as lateral resolution,ranging accuracy,stability,size,and *** recently,with the continuous enrichment of LiDAR application scenarios,the pursuit of imaging speed has attracted tremendous research ***,for autonomous vehicles running on motorways or industrial automation applications,the imaging speed of LiDAR systems is a critical *** this review,we will focus on discussing the upper speed limit of the LiDAR *** on the working mechanism,the limitation of optical parts on the maximum imaging speed is *** beam scanner has the greatest impact on imaging *** provide the working principle of current popular beam scanners used in LiDAR systems and summarize the main constraints on the scanning ***,we highlight the spectral scanning LiDAR as a new paradigm of ultrafast ***,to further improve the imaging speed,we then review the parallel detection methods,which include multiple-detector schemes and multiplexing ***,we summarize the LiDAR systems with the fastest point acquisition rate reported *** the outlook,we address the current technical challenges for ultrafast LiDAR systems from different aspects and give a brief analysis of the feasibility of different approaches.

关键词： LiDAR scanner system

来源：评论

学校读者我要写书评

暂无评论

Gradual domain adaptation via manifold-constrained distributionally robust optimization 24

Gradual domain adaptation via manifold-constrained distribut...

引用

Proceedings of the 38th International Conference on Neural information Processing systems

作者： Amirhossein Saberi Amir Najafi Amin Behjati Ala Emrani Yasaman Zolfi Mahdi Shadrooy Abolfazl Motahari Babak H. Khalaj Department of Electrical Engineering and Sharif Center for Information Systems and Data Science Sharif University of Technology Tehran Iran Department of Computer Engineering Sharif University of Technology Tehran Iran

ISBN: (纸本)9798331314385

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of T ≥ 2 data distributions P1, ..., PT undergoing a gradual shift, where each pair of consecutive measures Pi, Pi+1 are close to each other in Wasserstein distance. We have a supervised dataset of size n sampled from P0, while for the subsequent distributions in the sequence, only unlabeled i.i.d. samples are available. Moreover, we assume that all distributions exhibit a known favorable attribute, such as (but not limited to) having intra-class soft/hard margins. In this context, we propose a methodology rooted in Distributionally Robust Optimization (DRO) with an adaptive Wasserstein radius. We theoretically show that this method guarantees the classification error across all Pis can be suitably bounded. Our bounds rely on a newly introduced compatibility measure, which fully characterizes the error propagation dynamics along the sequence. Specifically, for inadequately constrained distributions, the error can exponentially escalate as we progress through the gradual shifts. Conversely, for appropriately constrained distributions, the error can be demonstrated to be linear or even entirely eradicated. We have substantiated our theoretical findings through several experimental results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Indicator Based Multiobjective Evolutionary Algorithm Utilizing Inverse Modeling

An Indicator Based Multiobjective Evolutionary Algorithm Uti...

引用

第43届中国控制会议

作者： Tianzi Zheng Jianchang Liu Shubin Tan Honghai Wang College of Information Science and Engineering Northeastern University National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In recent years, inverse models have attracted an increasing interest in the optimization field due to their superior ability on the multiobjective optimization. Specially, inverse models can commonly be employed to approximate Pareto optimal set by sampling Pareto front, which achieve the mapping from the objective space to the decision space. In this work, we design an indicator based evolutionary algorithm(IM-IBEA), equipping with an inverse model for the multiobjective optimization. IMIBEA is evaluated on 27 WFG test problems with 30-300 decision variables, which achieves best performance in 22 out of 27 test instances. The experimental results indicate that IM-IBEA has superior performance compared than the state-of-the-art methods.

关键词： Inverse Modeling Indicator Based Evolutionary Algorithm Multiobjective Optimization

来源：评论

学校读者我要写书评

暂无评论

Social Optimization in Noncooperative Games under Central Regulation

arXiv

引用

arXiv 2025年

作者： Du, Kaixin Meng, Min Li, Xiuxian Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China Department of Control Science and Engineering College of Electronics and Information Engineering The Shanghai Research Institute for Intelligent Autonomous Systems National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai China

This paper proposes a novel optimization problem building on noncooperative games under central regulation, which can be formulated as a bilevel structure. In the low-level, each player competes to minimize its own cost function that depends not only on the strategies of all players, but also on an intervention decision of the central regulator, while the central regulator located at the high-level attempts to achieve the social optimum, that is, to minimize the sum of cost functions of all players through an adjustable intervention decision. In this setting, under the intervention of the central regulator, the low-level players perform in a noncooperative game and aim to seek the Nash equilibrium, which indeed is related with the regulator’s decision. Meanwhile, the objective of the regulator is to choose a decision such that the social cost, i.e., the sum of cost functions of all players is minimum. This formulated bilevel social optimization problem is proven to be constrained, nonconvex and nonsmooth. To address this intricate problem, an inexact zeroth-order algorithm is developed by virtue of the smoothing techniques, allowing for the Nash equilibrium of the low-level game to be computed in an inexact manner. Levering the properties of smoothing techniques, it is rigorously shown that the devised algorithm achieves a sublinear convergence rate for computing a stationary point of a related optimization problem with a smoothed objective. Moreover, the sublinear convergence rate in the scenario where the exact equilibrium of the low-level game is available is also discussed. Finally, numerical simulations are conducted to demonstrate the efficiency of theoretical findings. Copyright © 2025, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

An Image Recognition Method Based on Multi-Objective Evolutionary Learning for Material Quality Detection

An Image Recognition Method Based on Multi-Objective Evoluti...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Yang, Jiucheng Wang, Junbo Liu, Chang Northeastern University College of Information Science and Engineering Shenyang China Northeastern University National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China

ISBN: (纸本)9781665465335

In complex industrial production processes, it is generally difficult to detect product quality defects online. As the rapid development of computer vision, convolutional neural networks (CNNs) have been extensively used to solve this problem. In this paper, a multi-objective evolutionary learning method based on EfficientNet is proposed for material quality detection. Moreover, to improve the effectiveness of the model, a multi-objective differential evolution algorithm is used to optimize EfficientNet. To achieve a tradeoff between model accuracy and model complexity, a knee point mechanism is designed to obtain the model structure and hyperparameters. Steel strip surface defect datasets are used to test in computational experiments. The results verify that the proposed method has a higher precision with lower floating-point operations than other comparison methods. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Personalized music recommendation based on knowledge graphs and social circles

Personalized music recommendation based on knowledge graphs ...

引用

第43届中国控制会议

作者： Lin Li Jianchang Liu Wei Zhang Shubin Tan Yuanchao Liu The College of Information Science and Engineering Northeastern University The National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

With the rapid development of digital music services,personalized music recommendation systems have become crucial for enhancing user *** the limitations of traditional recommendation algorithms in understanding user needs and recommendation accuracy,this study proposes a knowledge-based social circle personalized music recommendation model(KSPMR).This model aims to provide more comprehensive and accurate music recommendations by deeply analyzing individual user ***,we developed a data preprocessing method to optimize embedding computation and graph construction ***,we explored the impact of social circles on user music preferences,integrating social network factors into the recommendation ***,through a series of comparative experiments,the superiority of our model in improving recommendation effectiveness was *** results show that,compared to baseline models,our model significantly improves across various performance metrics,especially in accuracy and effectiveness of recommendations after incorporating information from the user and artist social circles.

关键词： Personalized Music recommendation Knowledge graph Social circle analysis Data processing User preferences

来源：评论

学校读者我要写书评

暂无评论

Learning to Simulate Labelled Datasets with an Image-Level Content Consistent Graph Constraint

Learning to Simulate Labelled Datasets with an Image-Level C...

引用

2023 China Automation Congress, CAC 2023

作者： He, Xiling Xue, Zhenfeng Zhang, Xiongtao Liu, Yong School of Information Engineering Huzhou University Huzhou313000 China Huzhou Institute of Zhejiang University Intelligent Perception and Control Center Huzhou313098 China Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

ISBN: (纸本)9798350303759

Recent years have witnessed the explosive growth of data annotation due to the deep learning algorithm's thirst for labelled datasets. To ease the workload of data annotation, researchers begin to concentrate on automatic dataset generation, i.e. dataset synthesis via virtual engine like Unity. However, the large domain gap between the target and simulated images hinders the great potential of these methods. In this paper, we propose a novel method to simulate labelled datasets under an image-level content consistent graph constraint. A detection model is applied to extract the semantic content of target and simulated images, and the corresponding scene graphs are constructed to compare the differences between them. This method not only utilizes the high-dimensional features of the images to reduce the content gap between target and simulated datasets, but also reserves the differentiability of the whole learning pipeline. As a result, we are able to automatically simualte labelled datasts in an end-to-end manner, and the models trained on the simulated datasets behave the best against existing methods. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Support Vector Machine based Classifier for Autocoding 27

Hierarchical Support Vector Machine based Classifier for Aut...

引用

27th International Conference on Knowledge Based and Intelligent information and engineering Sytems, KES 2023

作者： Toko, Yukako Sato-Ilic, Mika National Statistics Center 19-1 Wakamatsu-cho Shinjuku-ku Tokyo162-8668 Japan Institute of Systems and Information Engineering University of Tsukuba 1-1-1 Tennodai Ibaraki Tsukuba305-8573 Japan

This paper proposes a hierarchical support vector machine based classifier for autocoding. The purpose of this method is to improve classification accuracy utilizing numerical features obtained from probability scores by support vector machine (SVM). The proposed method captures the tendency to be incorrectly predicated for each label from the probability scores obtained from SVM. Using the captured information, we train new support vector machines for each targeted label considering the feature of the targeted label to improve the classification accuracy. The numerical examples with governmental survey data show a better performance of the proposed method. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Autocoding Computational Intelligence Fuzzy c-Means Machine Learning Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge Guided Network for Video Anomaly Detection 5

Prior Knowledge Guided Network for Video Anomaly Detection

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Deng, Zhewen Chen, Dongyue Deng, Shizhuo College of Information Science and Engineering Northeastern University Shenyang China Foshan Graduate School of Innovation Northeastern University Foshan China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China

ISBN: (纸本)9798400702051

Video Anomaly Detection (VAD) involves detecting anomalous events in videos, presenting a significant and intricate task within intelligent video surveillance. Existing studies often concentrate solely on features acquired from limited normal data, disregarding the latent prior knowledge present in extensive natural image datasets. To address this constraint, we propose a Prior Knowledge Guided Network(PKG-Net) for the VAD task. First, an auto-encoder network is incorporated into a teacher-student architecture to learn two designated proxy tasks: future frame prediction and teacher network imitation, which can provide better generalization ability on unknown samples. Second, knowledge distillation on proper feature blocks is also proposed to increase the multi-scale detection ability of the model. In addition, prediction error and teacher-student feature inconsistency are combined to evaluate anomaly scores of inference samples more comprehensively. Experimental results on three public benchmarks validate the effectiveness and accuracy of our method, which surpasses recent state-of-the-arts. © 2023 Copyright held by the owner/author(s).

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

“Steric Armor”Strategy of Blue Fluorescent Emitters against Photooxidation-Induced Degradation

引用

Chinese Journal of Chemistry 2024年第11期42卷 1223-1229页

作者： Sha-Sha Wang Jing-Rui Zhang Kuan-De Wang Hao-Ran Li Peng-Hui Meng Yang Zhou Xiang Yu Ying Wei Quan-You Feng Yu-He Kan Ling-Hai Xie Centre for Molecular Systems and Organic Devices(CMSOD) State Key Laboratory of Organic Electronics and Information Displays&Institute of Advanced MaterialsJiangsu National Synergetic Innovation Center for Advanced Materials(SICAM)Nanjing University of Posts&TelecommunicationsNanjingJiangsu210023 China Jiangsu Key Laboratory for Chemistry of Low-Dimensional Materials School of Chemistry and Chemical EngineeringHuaiyin Normal UniversityHuai'anJiangsu223300 China

Stability against oxygen is an important factor affecting the performance of organic semiconductor *** photooxidation stability can prolong the service life of the device and maintain the mechanical and photoelectric properties of the ***,various encapsulation methods from molecular structure to macroscopic device level are used to improve photooxidation ***,we adopted a crystallization strategy to allow 14H-spiro[dibenzo[c,h]acridine-7,9′-fluorene](SFDBA)to pack tightly to resist fluorescence decay caused by *** this case,the inert group of SFDBA acts as a“steric armor”,protecting the photosensitive group from being attacked by ***,compared with the fluorescence quenching of SFDBA powder under 2 h of sunlight,SFDBA crystal can maintain its fluorescence emission for more than 8 h under the same ***,the photoluminescence quantum yields(PLQYs)of the crystalline film is 327%higher than that of the amorphous *** shows that the crystallization strategy is an effective method to resist oxidation.

关键词： Organic semiconductor Photooxidation Spirocyclic aromatic hydrocarbons Crystal engineering Fluorescence

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：