As an advanced carrier of on-board sensors, connected autonomous vehicle (CAV) can be viewed as an aggregation of self-adaptive systems with monitor-analyze-plan-execute (MAPE) for vehicle-related services. Meanwhile,...
详细信息
As an advanced carrier of on-board sensors, connected autonomous vehicle (CAV) can be viewed as an aggregation of self-adaptive systems with monitor-analyze-plan-execute (MAPE) for vehicle-related services. Meanwhile, machine learning (ML) has been applied to enhance analysis and plan functions of MAPE so that self-adaptive systems have optimal adaption to changing conditions. However, most of ML-based approaches don’t utilize CAVs’ connectivity to collaboratively generate an optimal learner for MAPE, because of sensor data threatened by gradient leakage attack (GLA). In this article, we first design an intelligent architecture for MAPE-based self-adaptive systems on Web 3.0-based CAVs, in which a collaborative machine learner supports the capabilities of managing systems. Then, we observe by practical experiments that importance sampling of sparse vector technique (SVT) approaches cannot defend GLA well. Next, we propose a fine-grained SVT approach to secure the learner in MAPE-based self-adaptive systems, that uses layer and gradient sampling to select uniform and important gradients. At last, extensive experiments show that our private learner spends a slight utility cost for MAPE (e.g., \(0.77\%\) decrease in accuracy) defending GLA and outperforms the typical SVT approaches in terms of defense (increased by \(10\%\sim 14\%\) attack success rate) and utility (decreased by \(1.29\%\) accuracy loss).
This book constitutes the refereed proceedings of the 6th IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2014, held in Montreal, QC, Canada, in October 2014. The 24 revised...
详细信息
ISBN:
(数字)9783319116563
ISBN:
(纸本)9783319116556
This book constitutes the refereed proceedings of the 6th IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2014, held in Montreal, QC, Canada, in October 2014. The 24 revised full papers presented were carefully reviewed and selected from 37 submissions for inclusion in this volume. They cover a large range of topics in the field of learning algorithms and architectures and discussing the latest research, results, and ideas in these areas.
This volume contains papers selected for presentation at the 31st Annual C- ference on Current Trends in Theory and Practice of Informatics – SOFSEM 2005, held on January 22–28, 2005 in LiptovskyJ ´ an, ´ ...
详细信息
ISBN:
(数字)9783540305774
ISBN:
(纸本)9783540243021
This volume contains papers selected for presentation at the 31st Annual C- ference on Current Trends in Theory and Practice of Informatics – SOFSEM 2005, held on January 22–28, 2005 in LiptovskyJ ´ an, ´ Slovakia. The series of SOFSEM conferences, organized alternately in the Czech - public and Slovakia since 1974, has a well-established tradition. The SOFSEM conferences were originally intended to break the Iron Curtain in scienti?c - change. After the velvet revolution SOFSEM changed to a regular broad-scope international conference. Nowadays, SOFSEM is focused each year on selected aspects of informatics. This year the conference was organized into four tracks, each of them complemented by two invited talks: – Foundations of computer Science (Track Chair: Bernadette Charron-Bost) – Modeling and Searching Data in the Web-Era (Track Chair: Peter Vojt´ a? s) – softwareengineering (Track Chair: M´ aria Bielikova) ´ – Graph Drawing (Track Chair: Ondrej Syk ´ ora) The aim of SOFSEM 2005 was, as always, to promote cooperation among professionalsfromacademiaandindustryworkinginvariousareasofinformatics. Each track was complemented by two invited talks. The SOFSEM 2005 Program Committee members coming from 13 countries evaluated 144 submissions (128 contributed papers and 16 student research - rum papers). After a careful review process (counting at least 3 reviews per paper), followed by detailed discussions in the PC, and a co-chairs meeting held on October 8, 2005 in Bratislava, Slovakia, 44 papers (overall acceptance rate 34.
This book constitutes the refereed proceedings of the 25th Canadian Conference on Artificial Intelligence, Canadian AI 2012, held in Toronto, Canada, in May 2012.The 23 regular papers, 16 short papers, and 4 papers fr...
详细信息
ISBN:
(数字)9783642303531
ISBN:
(纸本)9783642303524
This book constitutes the refereed proceedings of the 25th Canadian Conference on Artificial Intelligence, Canadian AI 2012, held in Toronto, Canada, in May 2012.
The 23 regular papers, 16 short papers, and 4 papers from the Graduate Student Symposium presented were carefully reviewed and selected for inclusion in this book. The papers cover a broad range of topics presenting original work in all areas of artificial intelligence, either theoretical or applied.
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. ...
详细信息
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this paper proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.
Recent years have witnessed the increasing prevalence of smart home applications, where digital twin (DT) is popularly employed for creating virtual models that interact with physical devices in real time. Empowered b...
详细信息
Recent years have witnessed the increasing prevalence of smart home applications, where digital twin (DT) is popularly employed for creating virtual models that interact with physical devices in real time. Empowered by artificial intelligence (AI), these DT-created virtual models have more intelligent decision-making capabilities to ensure reliable performance of a smart home system. In this paper, a DT based smart home framework is investigated. It is capable of achieving intelligent control, healthcare prediction and graphical monitoring. First, the human body and device are individually modeled, and then assembled into a DT system, and the corresponding model interfaces are provided for visual monitoring. Then, an intelligent algorithm fusing VGG, LSTM and attention mechanism is developed for healthcare monitoring, i.e., the screening out of the irregular ECG rhythms. The system results are provided, including various high-fidelity interactive DT interfaces as well as the effectiveness and advantages of the intelligent algorithms for arrhythmia detection.
暂无评论