检索结果-内蒙古大学图书馆

NLOS/LOS Classification by Constructing Indirect Environment Interaction From GNSS Receiver Measurements Using a Transformer-Based Deep Learning Model

NLOS/LOS Classification by Constructing Indirect Environment...

引用

2023 International Technical Meeting of The Institute of Navigation, ITM 2023

作者： Li, Zhenni Zeng, Kungan Wang, Lujia Kan, Xie Yuan, Rong Xie, Shengli School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Software and Engineering Sun Yat-sen University Hong Kong Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Techtotop Microelectronics Technology Co. Ltd Guangzhou510006 China Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China

ISBN: (纸本)9781713871378

The blockage of the direct signal by high-rise buildings degrades the positioning performance of the global navigation satellite system (GNSS) in urban canyons. Traditional methods usually distinguish the line-of-sight (LOS), and non-line-of-sight (NLOS) signals using the satellite’s elevation angle or signal strength to mitigate the issue, which cannot obtain satisfactory classification accuracy in complex urban environments. Recently, machine learning-based methods using GNSS measurements have been developed to improve GNSS signal classification. However, dynamic changes in environments and the limited features from the measurements raise a challenge to the classification performance of algorithms. To address the above issues, a transformer-based deep learning model in this paper is proposed for LOS and NLOS signal classification. The innovation of our proposed model is using the self-attention mechanism to construct the indirect environment interaction for learning the representation of environmental information. First, the measurements of captured satellites in the same epoch will be fed into the model. The model’s feature extraction layer can learn the fundamental representation. Then, the self-attention module can construct the indirect environment interaction by computing the relevance between the satellites. Finally, the module’s output is transferred to the output layer for classification. A comparative experimental study is conducted with real-world data collected in urban canyons. The results demonstrate that our model can keep more than 90% classification accuracy while support vector machine (SVM) and multilayer perception (MLP) decline to about 80% with the sites increasing. © 2023 Proceedings of the International Technical Meeting of The Institute of Navigation, ITM.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Improving Variational Autoencoders with Density Gap-based Regularization

arXiv

引用

arXiv 2022年

作者： Zhang, Jianfei Bai, Jun Lin, Chenghua Wang, Yanmeng Rong, Wenge State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

Variational autoencoders (VAEs) are one of the most powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converging to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and the hole problem, i.e., the mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization, and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and posterior collapse. Copyright © 2022, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

3D Brain and Heart Volume Generative Models: A Survey

arXiv

引用

arXiv 2022年

作者： Liu, Yanbin Dwivedi, Girish Boussaid, Farid Bennamoun, Mohammed Harry Perkins Institute of Medical Research Department of Computer Science and Software Engineering The University of Western Australia CanberraACT2601 Australia Harry Perkins Institute of Medical Research The University of Western Australia Fiona Stanley Hospital PerthWA Australia Department of Electrical Electronic and Computer Engineering The University of Western Australia PerthWA Australia Department of Computer Science and Software Engineering The University of Western Australia PerthWA Australia

Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability. This paper provides a comprehensive survey of generative models for three-dimensional (3D) volumes, focusing on the brain and heart. A new and elaborate taxonomy of unconditional and conditional generative models is proposed to cover diverse medical tasks for the brain and heart: unconditional synthesis, classification, conditional synthesis, segmentation, denoising, detection, and registration. We provide relevant background, examine each task and also suggest potential future directions. A list of the latest publications will be updated on GitHub to keep up with the rapid influx of papers at https://***/csyanbin/*** Codes 92C55 (Primary), 68U10 (Secondary) © 2022, CC BY.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

arXiv

引用

arXiv 2023年

作者： Huang, Zhuo Zhu, Miaoxi Xia, Xiaobo Shen, Li Yu, Jun Gong, Chen Han, Bo Du, Bo Liu, Tongliang Syndey Ai Centre The University of Sydney Australia National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Jd Explore Academy China Department of Automation University of Science and Technology of China China Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

IoST: Internet of Softwarized Things Networks, Security Challenges and Future Research Directions

IoST: Internet of Softwarized Things Networks, Security Chal...

引用

IEEE Globecom Workshops

作者： Muhammad Adil Muhammad Attique Jian Wang Faisal Alrefaei Houbing Song Ahmed Farouk Computer Science & Engineering University at Buffalo New York USA Department of Software Sejong University Seoul Korea Department of Computer Science University of Tennessee Martin TN USA Electrical Engineering & Computer Science Embry Riddle Aeronautical Universit Florida USA Faculty of Computers and Artificial Intelligence South Valley University Hurghada Egypt

ISBN: (纸本)9781665459761

Internet of Softwarized Things (IoST) is a promising and dynamic programmable technology that has the capability to interconnect sensor devices with an objective to share the accumulated data in the network without the intervention of human beings. Despite its advantages, this technology suffers from numerous security vulnerability threats, which can damage the trust of clients. Therefore, it is very important to familiarize the readers, students, experts, and industry stakeholders working in this domain with the existing counteraction schemes followed by potential security threats. For redressal of identified security threats, the literature presents various schemes, but somehow they are unable to provide fool-proof security infrastructure for these networks, because the attackers work restlessly to compromise the new security countermeasure schemes. To explore this discussion and evaluate the open security challenges with future research directions, in this paper, we present a survey regarding the most recent published literature from 2020 to 2022. Following this, we have covered the architectural and interoperability literature in the context of security threats and their countermeasure techniques to identify the weak aspects of them. Based on underscored problems, we have highlighted the unresolved security challenges to set a footstep for the future research work that could be useful for all stakeholders associated with IoST technology.

关键词： Industries Performance evaluation Privacy Conferences Network security Internet Security

来源：评论

学校读者我要写书评

暂无评论

Improving variational autoencoders with density gap-based regularization 22

Improving variational autoencoders with density gap-based re...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianfei Zhang Jun Bai Chenghua Lin Yanmeng Wang Wenge Rong State Key Laboratory of Software Development Environment Beihang University China and School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

ISBN: (纸本)9781713871088

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting multivariate LSTM models with multistep price forecasting for agricultural produce in Sri Lankan context 2

Exploiting multivariate LSTM models with multistep price for...

引用

2nd International Conference on Advancements in Computing, ICAC 2020

作者： Navaratnalingam, Shriram Kodagoda, Nuwan Suriyawansa, Kushnara Srilanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781728184128

In Sri Lanka agricultural produces possess a large supply which involves various stakeholders and thus, fluctuation of the agricultural produce prices has a direct impact on the purchasing decisions of the consumer. So, the main purpose of this study is to address the problem faced by the consumer due to poor awareness of price fluctuation which consequently astonish the consumers and hinder them from making better purchasing decisions. The research study is being specially developed in a way to adapt the Sri Lankan agricultural consumer market that is mainly based on Pettah and Dambulla trade centers. As the study we exploited different types of LSTM model with multivariate inputs along with the different combination of multistep models. The result of the study reveals that better performance was obtained for the multivariate CNN LSTM model with encoder decoder multistep model which provided an average RMSE of 19.46 Sri Lankan rupees per kilogram with an average RMSPE of 14.9%. Also, study reveals a correlation between price fluctuation and standard days of the week, where a better prediction was obtained for Monday and Tuesday with an average RMSE of 17.2 and 17.7 Sri Lankan rupees per kilogram respectively with an average RMSPE of 12.2%. Based on the input timestep considered for model, though 14 days and 21 days provided a similar result with minor variation result reveals that 14 days provided a lesser standard deviation of 0.17 than 21 days standard deviation which is 0.98. © 2020 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Cross-Channel and Regional Node Relation Enhanced Hybrid Graph Convolution Transformer for Ct Segmentation

SSRN

引用

SSRN 2023年

作者： Cui, Hui Jin, Qiangguo Wu, Xixi Wang, Linlin Zhang, Tiangang Nakaguchi, Toshiya Xuan, Ping Feng, David Dagan Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Software Northwestern Polytechnical University Shaanxi China School of Computer Science and Technology Heilongjiang University Harbin China Department of Radiation Oncology Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Jinan China School of Mathematical Science Heilongjiang University Harbin China Center for Frontier Medical Engineering Chiba University Chiba Japan Department of Computer Science School of Engineering Shantou University Shantou China School of Computer Science The University of Sydney Sydney Australia

Accurate and robust organ and tumour segmentation from CT scans are critical for precision diagnosis and prognosis of cancer, and the development of personalized treatment planning. However, automatic segmentation of tumours and organs they have invaded is challenging due to significant variations, abnormalities, and unclear boundaries. While graph convolutional networks can propagate knowledge and correlations in a flexible feature space, they suffer from information saturation during deep learning which can limit their effectiveness. To overcome this issue, we proposed a hybrid graph convolution transformer (HCGT) model. The HCGT has a channel transformer (CTrans) component, which helps to learn contextual relationships across different feature channels. Furthermore, we developed a convolutional graph transformer (convG-Trans) that can simultaneously and interactively learn enhanced relationships between different parts of the image by aggregating knowledge propagation from graph convolution and cross-node similarities from the transformer. Finally, we incorporated category-level attention to understand the significance of the two representations from the CTrans and convG-Trans, which helped adjust the fusion process before generating the segmentation output. We evaluated the HCGT on kidney and tumour and lung and non-small cell lung cancer datasets. Our evaluations included comparisons with other three-dimensional (3D) medical image segmentation benchmarks, as well as graph-based and transformer-based segmentation models. The results demonstrated improved performance in abdominal and thorax organ and tumour segmentation tasks. Additionally, ablation studies showed that the major technical innovations were effective and consistent when using different 3D medical image segmentation backbones. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PEFN: A Patches Enhancement and Hierarchical Fusion Network for Robust Vehicle Re-Identification

引用

IEEE Internet of Things Journal 2025年

作者： He, Wenying Wang, Feiyu Bai, Yude Xiong, Neal N. Xu, Guangquan Guo, Fei Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Hebei University of Technology Hebei Province Key Laboratory of Big Data Calculation Tianjin300130 China Tiangong University School of Software Tianjin300387 China Northeastern State University Department of Mathematics and Computer Science TahlequahOK74464 United States Tianjin300350 China Central South University School of Computer Science and Engineering Changsha410083 China

Vehicle Re-Identification (Re-ID), which is a significant application in the Internet of Things, aims to accurately retrieve the remaining images of a given vehicle across different cameras views. The improvement in vehicle Re-ID performance largely stems from better addressing the issues of inter-class similarity and intra-class variance. Existing methods, relying solely on max or average pooling after using attention modules, fail to obtain significantly complete and pure global and local features, and neglect the false guidance that some unique individual information on images bring to re-identification. Moreover, models combining global and local features have shown good results in vehicle Re-ID, but these successes neglect the interaction between features across different convolutional layers, resulting in the loss of crucial details for vehicle Re-ID. To tackle these issues, we introduce a Patches Enhancement and hierarchical Fusion Network (PEFN) based on a multi-branch architecture, divided into a Global and Local Attention Supplement (GLAS) branch, and an Enhanced Hierarchical feature fusion (EnHi) branch. The GLAS branch, through the Identity-related Feature Remodeling (IDFR) module’s staged supplementation of spatial and channel features, has achieved the enhancement of both global and local features and effectively mitigated the negative impacts of individual information. The EnHi branch enhances the robustness of feature representation by interacting hierarchical features. Extensive experiments on two large-scale vehicle re-identification datasets demonstrate that our PEFN method outperforms state-of-the-art vehicle re-identification approaches. Specifically, without utilizing extra data and re-ranking, our model achieves 85.15% mAP on the VeRi776 dataset. © 2014 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

A Fault Forecasting Approach Using Two-Dimensional Optimization

A Fault Forecasting Approach Using Two-Dimensional Optimizat...

引用

IEEE World Forum on Internet of Things (WF-IoT)

作者： Mohsen Tajgardan Reza Khoshkangini Abbas Orand Mahdi Rabbani Faculty of Electrical and Computer Engineering Qom University of Technology Qom Iran Department of Computer Science and Media Technology Internet of Things and People (IOTAP) Malmö University Malmo Sweden Arriver Software AB Qualcomm Company Linköping Sweden Canadian Institute for Cybersecurity University of New Brunswick NB Canada

ISBN: (数字)9798350373011

ISBN: (纸本)9798350373028

Data preparation is crucial in every machine learning approach, particularly when applied to detecting claims in the automotive industry. The challenge of managing highdimensional feature spaces and imbalanced data becomes even more pronounced with the proliferation of IoT devices, which generate vast amounts of data over time. Machine learning models trained on such imbalanced datasets often yield unreliable and inaccurate predictions. Thus, addressing these issues during the data pre-processing phase is critical. In this paper, we introduce a novel two-dimensional optimization (TDO) strategy to tackle the problem of imbalanced data in fault detection, specifically in the context of IoT-enhanced automotive systems. We leverage a heuristic optimization technique known as the Genetic Algorithm to simultaneously reduce both the number of data point tuples and the feature space. Additionally, we evaluate the effectiveness of two-dimensional reduction using Particle Swarm Optimization (PSO) and Whale Optimization algorithms. Our empirical results, derived from data collected from thousands of IoT-equipped vehicles, demonstrate the promise of our proposed methods.

关键词： Industries Fault detection Machine learning Predictive models Whale optimization algorithms Internet of Things Particle swarm optimization Optimization Automotive engineering Genetic algorithms

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：