检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Zongrui Lu, Zhan Yan, Haojie Shi, Boxin Pan, Gang Zheng, Qian Jiang, Xudong Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Natural Light Uncalibrated Photometric Stereo (NaUPS) relieves the strict environment and light assumptions in classical Uncalibrated Photometric Stereo (UPS) methods. However, due to the intrinsic ill-posedness and high-dimensional ambiguities, addressing NaUPS is still an open question. Existing works impose strong assumptions on the environment lights and objects' material, restricting the effectiveness in more general scenarios. Alternatively, some methods leverage supervised learning with intricate models while lacking interpretability, resulting in a biased estimation. In this work, we propose Spin Light Uncalibrated Photometric Stereo (Spin-UP), an unsupervised method to tackle NaUPS in various environment lights and objects. The proposed method uses a novel setup that captures the object's images on a rotatable platform, which mitigates NaUPS's ill-posedness by reducing unknowns and provides reliable priors to alleviate NaUPS's ambiguities. Leveraging neural inverse rendering and the proposed training strategies, Spin-UP recovers surface normals, environment light, and isotropic reflectance under complex natural light with low computational cost. Experiments have shown that Spin-UP outperforms other supervised/unsupervised NaUPS methods and achieves state-of-the-art performance on synthetic and real-world datasets. Codes and data are available at https://***/LMozart/CVPR2024-SpinUP. Copyright © 2024, The Authors. All rights reserved.

关键词： Photometry

来源：评论

学校读者我要写书评

暂无评论

Multi-Leader Multi-Follower Game-based Incentive Scheme for Socially-Aware Mobile Crowdsensing

Multi-Leader Multi-Follower Game-based Incentive Scheme for ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Jiangtian Nie Jun Luo Zehui Xiong Dusit Niyato Ping Wang Yang Zhang ERI@N Interdisciplinary Graduate Programme Nanyang Technological University (NTU) Singapore School of Computer Science and Engineering Nanyang Technological University (NTU) Singapore York University Canada Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology Wuhan China

ISBN: (纸本)9781728195056;9781728195063

As the paradigm of crowdsensing involves the data collection from users, the issue of designing reward to incentivize the users is fundamentally important to be addressed, thereby effectively enhancing the participation. In this paper, we revisit this issue in the context of socially-aware crowdsensing which integrates crowdsensing into social networks. For example, in crowdsensing-based healthcare services, the accuracy of diet recommendation for a certain user can be promoted by exploiting the nutritional information contributed and shared by the socially-connected friends of him/her taking similar types of food. To be more general and practical, we study the incentive schemes in presence of multiple crowdsensing service providers and multiple users. Understanding the behaviors of users and service providers in socially-aware crowdsensing is of paramount importance for incentive schemes. Considering this, we propose a multi-leader and multi-follower Stackelberg game approach to model the strategic interactions among service providers and users, where the social influence of users and the strategic interconnections of service providers are jointly and formally integrated into the game modeling. Through backward induction methods, we theoretically validate the existence and uniqueness of the Stackelberg equilibrium. Simulations are conducted to evaluate game equilibrium properties, and the results are presented to assess and demonstrate the performance effectiveness of the proposed game model.

关键词： Crowdsensing Social networking (online) System performance Conferences Games Medical services Data collection

来源：评论

学校读者我要写书评

暂无评论

Purify unlearnable examples via rate-constrained variational autoencoders 24

Purify unlearnable examples via rate-constrained variational...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yi Yu Yufei Wang Song Xia Wenhan Yang Shijian Lu Yap-Peng Tan Alex C. Kot Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme and School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (DVAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control of Five-Level Current Source Converter with Optimized Weighting Factors

Model Predictive Control of Five-Level Current Source Conver...

引用

IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES)

作者： Muyu Chen Zhige Yuan Faramarz Faraji Amer M. Y. M. Ghias Honnyong Cha Vun Chan Hua Nicholas Collab. Initiative Interdisciplinary Graduate Programme School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Energy Engineering Kyungpook National University Daegu Korea School of Computer Science and Engineering Nanyang Technological University Singapore

This paper presents the finite control set model predictive control (FCS-MPC) with improved control objectives using optimized weighting factors. The Pareto curve obtained from the Particle Swarm optimizes the weighting factors. The optimal weighting factors are then used in the FCS-MPC algorithm to enhance the control objective performance of a three-phase five-level current source converter (5L-CSC). In 5L-CSC, two identical three-level CSC (3L-CSC) modules are connected in parallel with one common current source supply to provide uniform five-level output current waveform. This CSC requires a current balance to operate the converter safely. Therefore, the control objective of the MPC is to control the output voltage and balance the internal currents. The weighting factors are optimized based on the converter's total harmonics distortion (THD) performance and inductor current ripple. The performance enhancement of 5L-CSC, utilizing optimal weighting factors, is confirmed through MATLAB simulations when compared to the model employing arbitrarily assigned weighting factors. The simulation outcomes additionally indicate that the integration of Particle Swarm Optimization (PSO) with FCS-MPC exhibits resilience across various condition settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

arXiv

引用

arXiv 2020年

作者： Liu, Yi Garg, Sahil Nie, Jiangtian Zhang, Yang Xiong, Zehui Kang, Jiawen Shamim Hossain, M. School of Data Science and Technology Heilongjiang University Harbin China Electrical Engineering Department École de technologie supérieure Uni-versité du Québec Montréal Canada Energy Research Institute Interdisciplinary Graduate Programme School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Technology Wuhan University of Technology China Alibaba-NTU Joint Research Institute School of Computer Science and Engineering NTU Singapore Singapore Energy Research Institute Nanyang Technological University Singapore Department of Software Engineering College of Computer and Information Sciences King Saud University Saudi Arabia

Since edge device failures (i.e., anomalies) seriously affect the production of industrial products in Industrial IoT (IIoT), accurately and timely detecting anomalies is becoming increasingly important. Furthermore, data collected by the edge device may contain the user’s private data, which is challenging the current detection approaches as user privacy is calling for the public concern in recent years. With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. Specifically, we first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. The AMCNN-LSTM model uses attention mechanism-based CNN units to capture important fine-grained features, thereby preventing memory loss and gradient dispersion problems. Furthermore, this model retains the advantages of LSTM unit in predicting time series data. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-k selection to improve communication efficiency. Extensive experiment studies on four real-world datasets demonstrate that the proposed framework can accurately and timely detect anomalies and also reduce the communication overhead by 50% compared to the federated learning framework that does not use gradient compression scheme. Copyright © 2020, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

arXiv

引用

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science & Engineering Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatialtemporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization

arXiv

引用

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Hu, Yongjian Kot, Alex C. The Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore The School of Computer Science & Engineering Nanyang Technological University Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore The South China University of Technology Guangzhou China

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and time-consuming to annotate. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition. We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data. We represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. Specifically, we design a two-steam pretraining network that leverages fine-grained and coarse-grained colorization to learn multi-scale spatial-temporal features. In addition, we design a Masked Skeleton Cloud Repainting task that can pretrain the designed auto-encoder framework to learn informative representations. We evaluate our skeleton cloud colorization approach with linear classifiers trained under different configurations, including unsupervised, semi-supervised, fully-supervised, and transfer learning settings. Extensive experiments on NTU RGB+D, NTU RGB+D 120, PKU-MMD, NW-UCLA, and UWA3D datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins and achieves competitive performance in supervised 3D action recognition as well. Copyright © 2023, The Authors. All rights reserved.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racing

Continual Learning for Robust Gate Detection under Dynamic L...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhongzheng Qiao Xuan Huy Pham Savitha Ramasamy Xudong Jiang Erdal Kayacan Andriy Sarabakha ERI@N Interdisciplinary Graduate Programme Nanyang Technological University Singapore Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark Institute of Infocomm Research (I2R) Agency for Science Technology and Research (A*STAR) Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Automatic Control Group (RAT) Paderborn University Paderborn Germany

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In autonomous and mobile robotics, a principal challenge is resilient real-time environmental perception, particularly in situations characterized by unknown and dynamic elements, as exemplified in the context of autonomous drone racing. This study introduces a perception technique for detecting drone racing gates under illumination variations, which is common during high-speed drone flights. The proposed technique relies upon a lightweight neural network backbone augmented with capabilities for continual learning. The envisaged approach amalgamates predictions of the gates' positional coordinates, distance, and orientation, encapsulating them into a cohesive pose tuple. A comprehensive number of tests serve to underscore the efficacy of this approach in confronting diverse and challenging scenarios, specifically those involving variable lighting conditions. The proposed methodology exhibits notable robustness in the face of illumination variations, thereby substantiating its effectiveness.

关键词： Continuing education Robot kinematics Neural networks Lighting Logic gates Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Second-Order Non-Convex Optimization for Constrained Fixed-Structure Static Output Feedback Controller Synthesis

arXiv

引用

arXiv 2019年

作者： Cheng, Zilong Ma, Jun Li, Xiaocong Tomizuka, Masayoshi Lee, Tong Heng The Integrative Sciences and Engineering Programme NUS Graduate School National University of Singapore 119077 Singapore Guangzhou China The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States The Department of Mechanical Engineering University of California BerkeleyCA94720 United States

For linear time-invariant (LTI) systems, the design of an optimal controller is a commonly encountered problem in many applications. Among all the optimization approaches available, the linear quadratic regulator (LQR) methodology certainly garners much attention and interest. As is well-known, standard numerical tools in linear algebra are readily available to determine the optimal static LQR feedback gain matrix when all the system state variables are measurable. However, in various certain scenarios where some of the system state variables are not measurable, and consequent prescribed structural constraints on the controller structure arise, the optimization problem can become intractable due to the non-convexity characteristics that can then be present. In such cases, some first-order methods have been proposed to cater to these problems, but all of these methods, if at all successful, are limited to linear convergence. To speed up the convergence, a second-order approach in the matrix space is essential, with appropriate methodology to solve the linear equality constrained static output feedback (SOF) problem with a suitably defined linear quadratic cost function. Thus in this work, an efficient method is proposed in the matrix space to calculate the Hessian matrix by solving several Lyapunov equations. Then a new optimization technique is applied to deal with the indefiniteness of the Hessian matrix. Subsequently, through Newton's method with linear equality constraints, a second-order optimization algorithm is developed to effectively solve the constrained SOF LQR problem. Finally, two numerical examples are described which demonstrate the applicability and effectiveness of the proposed method. Copyright © 2019, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid Global Flexible Power Point Tracking Algorithm for Photovoltaic Systems

Hybrid Global Flexible Power Point Tracking Algorithm for Ph...

引用

European Conference on Power Electronics and Applications

作者： Anusha Kumaresan Hossein Dehghani Tafti Glen G. Farivar Josep Pou Kai Strunz Dusit Niyato Energy Research Institute at NTU Interdisciplinary Graduate Programme Nanyang Technological University Singapore Engineering Institute of Technology (EIT) Australia Department of Electrical and Electronic Engineering The University of Melbourne Victoria Australia School of Electrical and Electronic Engineering Nanyang Technological University Singapore Chair for Sustainable Electric Networks and Sources of Energy Technische Universität Berlin Germany School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350364446

ISBN: (纸本)9798350364453

Frequency support in grid-connected photovoltaic (PV) systems is achieved by employing flexible power point tracking (FPPT) algorithms. Subsequently, according to the grid frequency requirements, the PV power is curtailed to a power reference, unlike the traditional method of operating the PV at the maximum power point. In practical cases, the PV arrays are prone to partial shading, and hence, there is a requirement to formulate the FPPT algorithms that operates effectively during such cases. Moreover, fast transient response is a necessity, which implies that the algorithms proposed in this paper is desirable. This paper proposes a hybrid global FPPT (GFPPT) algorithm based on secant and Newton’s method, to shift the PV operating point to the required power reference. The Newton’s method offers quadratic convergence rate and the secant method guarantees convergence. Hence, a hybrid algorithm consisting of these two methods will provide both fast and guaranteed convergence. Validation through simulation is presented in this paper and the proposed method is compared with the recently presented perturb and observe (P&O) GFPPT algorithm in the literature.

关键词： Photovoltaic systems Transient response Europe Voltage Hybrid power systems Convergence

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：