This book constitutes the joint refereed proceedings of the 11th International Conference on Artificial Intelligence and Symbolic Computation, AISC 2012, 19th Symposium on the Integration of Symbolic Computation and M...
详细信息
ISBN:
(数字)9783642313745
ISBN:
(纸本)9783642313738
This book constitutes the joint refereed proceedings of the 11th International Conference on Artificial Intelligence and Symbolic Computation, AISC 2012, 19th Symposium on the Integration of Symbolic Computation and Mechanized Reasoning, Calculemus 2012, 5th International Workshop on Digital Mathematics Libraries, DML 2012, 11th International Conference on Mathematical Knowledge Management, MKM 2012, Systems and Projects, held in Bremen, Germany as CICM 2012, the Conferences on Intelligent computer Mathematics. The 13 revised full papers out of 19 submissions for MKM 2012, 6 revised full papers out of 9 submissions for Calculemus 2012, 6 revised full papers out of 8 submissions for AISC 2012, 2 revised full papers out of 3 submissions for DML 2012, and 11 revised full papers out of 12 submissions for Systems and Project track presented were carefully reviewed and selected, resulting in 38 papers from a total of 52 submissions.
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).
We are rapidly heading towards a world in which the computing infrastructure will contain billions of devices, which will interact with other computing/communications devices that are carried or worn by users as they ...
详细信息
ISBN:
(数字)9783540363897
ISBN:
(纸本)9783540003939
We are rapidly heading towards a world in which the computing infrastructure will contain billions of devices, which will interact with other computing/communications devices that are carried or worn by users as they go through their daily routines. Such devices will provide data access to mobile users as they move within buildings, cities, or across the globe. This new infrastructure presents tremendous challenges for data management technology, including: huge scale; variable and intermittent connectivity; location and context-aware applications; bandwidth, power, and devi- size limitations; and multimedia data delivery across hybrid networks and systems. Traditional data management technologies such as query processing, transaction management, workflow, business process management, and metadata management must all be reevaluated in this emerging environment. Furthermore, nontraditional issues such as the semantics of mobile data, location-dependent querying, broadcast and multicast delivery, and caching/prefetching techniques must all be addressed. The ability to track people as they move about their daily tasks raises serious issues of security and privacy. This conference is the fourth in the Mobile Data Management series, focusing on the challenges and opportunities for the management of data in mobile, pervasive, and wearable computing. MDM 2000 and 2001 were in Hong Kong and MDM 2002 was in Singapore. Eighty-seven papers were submitted to the conference from 23 countries and were subject to a rigorous review procedure. Every paper had three or four independent reviews. Twenty-one full papers and 15 short papers from both academia and industry were selected for publication in this volume of proceedings.
The Second Workshop of Blended Learning (WBL 2008), as part of the 7th Inter- tional Conference on Web-Based Learning (ICWL 2008), was held in Zhejiang N- mal University, Jinhua, Zhejiang, China during August 20–22, ...
详细信息
ISBN:
(数字)9783540899624
ISBN:
(纸本)9783540899617
The Second Workshop of Blended Learning (WBL 2008), as part of the 7th Inter- tional Conference on Web-Based Learning (ICWL 2008), was held in Zhejiang N- mal University, Jinhua, Zhejiang, China during August 20–22, 2008. WBL 2008 provided an international forum for the dissemination of original results in the design, implementation, and evaluation of blended learning systems and related areas. In particular, the aim of WBL 2008 was to bring together researchers from academia as well as commercial developers from industry to explore ideas, exchange and share experiences, and further build the blended learning research network. The inspirations and new ideas were expected to emerge from intensive discussions during formal sessions and social activities. The main focus of WBL 2008 was on the most critical areas of blended learning, namely, ‘e-Learning Platforms and Tools,’ ‘Design, Model and Framework of e- Learning Systems,’ ‘Practice and Experience Sharing,’ and ‘Pedagogical Issues.’ In total, the workshop selected 17 papers from authors of different countries for presen- tion and publication, a task which was not easy due to the high quality of the subm- ted papers. Using stringent selection criteria, submissions were rigorously reviewed based on their originality, significance, relevance, and clarity of presentation by an international Program Committee from Germany, Spain, UK, Italy, Ireland, Romania, Hong Kong, Japan, Taiwan, and Macao.
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.
th This volume is an edition of the papers selected from the 12 FIRA RoboWorld C- gress, held in Incheon, Korea, August 16–18, 2009. The Federation of International Robosoccer Association (FIRA – www. fira. net) is ...
详细信息
ISBN:
(数字)9783642039867
ISBN:
(纸本)9783642039850
th This volume is an edition of the papers selected from the 12 FIRA RoboWorld C- gress, held in Incheon, Korea, August 16–18, 2009. The Federation of International Robosoccer Association (FIRA – www. fira. net) is a non-profit organization, which organizes robotic competitions and meetings around the globe annually. The RoboSoccer competitions started in 1996 and FIRA was - tablished on June 5, 1997. The Robot Soccer competitions are aimed at promoting the spirit of science and technology to the younger generation. The congress is a forum in which to share ideas and future directions of technologies, and to enlarge the human networks in robotics area. The objectives of the FIRA Cup and Congress are to explore the technical dev- opment and achievement in the field of robotics, and provide participants with a robot festival including technical presentations, robot soccer competitions and exhibits - der the theme “Where Theory and Practice Meet. ” th Under the umbrella of the 12 FIRA RoboWorld Incheon Congress 2009, six int- national conferences were held for greater impact and scientific exchange: th • 6 International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS) th • 5 International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE) • International Conference on Social Robotics (ICSR) • International Conference on Advanced Humanoid Robotics Research (ICAHRR) • International Conference on Entertainment Robotics (ICER) • International Robotics Education Forum (IREF) This volume consists of selected quality papers from the six conferences.
The two-volume set LNCS 6987 and 6988 constitutes the refereed proceedings of the International Conference on Web Information Systems and Mining, WISM 2011, held in Taiyuan, China, in September 2011. The 112 revised f...
详细信息
ISBN:
(数字)9783642239823
ISBN:
(纸本)9783642239816
The two-volume set LNCS 6987 and 6988 constitutes the refereed proceedings of the International Conference on Web Information Systems and Mining, WISM 2011, held in Taiyuan, China, in September 2011. The 112 revised full papers presented were carefully reviewed and selected from 472 submissions. The second volume includes 56 papers organized in the following topical sections: management information systems; semantic Web and ontologies; Web content mining; Web information classification; Web information extraction; Web intelligence; Web interfaces and applications; Web services and e-learning; and XML and semi-structured data.
暂无评论