SØG - mellem flere end 8 millioner bøger:

Søg på: Titel, forfatter, forlag - gerne i kombination.
Eller blot på isbn, hvis du kender dette.

Viser: Fog Computing, Deep Learning and Big Data Analytics-Research Directions

Fog Computing, Deep Learning and Big Data Analytics-Research Directions
Søgbar e-bog

Fog Computing, Deep Learning and Big Data Analytics-Research Directions Vital Source e-bog

C.S.R. Prabhu
(2019)
Springer Nature
1.350,00 kr.
Leveres umiddelbart efter køb
Fog Computing, Deep Learning and Big Data Analytics-Research Directions

Fog Computing, Deep Learning and Big Data Analytics-Research Directions

C. S. R. Prabhu
(2019)
Sprog: Engelsk
Springer
1.551,00 kr.
Print on demand. Leveringstid vil være ca 2-3 uger.

Detaljer om varen

  • Vital Source searchable e-book (Reflowable pages)
  • Udgiver: Springer Nature (Januar 2019)
  • ISBN: 9789811332098
This book provides a comprehensive picture of fog computing technology, including of fog architectures, latency aware application management issues with real time requirements, security and privacy issues and fog analytics, in wide ranging application scenarios such as M2M device communication, smart homes, smart vehicles, augmented reality and transportation management.   This book explores the research issues involved in the application of traditional shallow machine learning and deep learning techniques to big data analytics. It surveys global research advances in extending the conventional unsupervised or clustering algorithms, extending supervised and semi-supervised algorithms and association rule mining algorithms to big data Scenarios. Further it discusses the deep learning applications of big data analytics to fields of computer vision and speech processing, and describes applications such as semantic indexing and data tagging. Lastly it identifies 25 unsolved research problems and research directions in fog computing, as well as in the context of applying deep learning techniques to big data analytics, such as dimensionality reduction in high-dimensional data and improved formulation of data abstractions along with possible directions for their solutions.
Licens varighed:
Bookshelf online: 5 år fra købsdato.
Bookshelf appen: ubegrænset dage fra købsdato.

Udgiveren oplyser at følgende begrænsninger er gældende for dette produkt:
Print: 2 sider kan printes ad gangen
Copy: højest 2 sider i alt kan kopieres (copy/paste)

Detaljer om varen

  • Hardback
  • Udgiver: Springer (Januar 2019)
  • ISBN: 9789811332081
This book provides a comprehensive picture of fog computing technology, including of fog architectures, latency aware application management issues with real time requirements, security and privacy issues and fog analytics, in wide ranging application scenarios such as M2M device communication, smart homes, smart vehicles, augmented reality and transportation management.   This book explores the research issues involved in the application of traditional shallow machine learning and deep learning techniques to big data analytics. It surveys global research advances in extending the conventional unsupervised or clustering algorithms, extending supervised and semi-supervised algorithms and association rule mining algorithms to big data Scenarios. Further it discusses the deep learning applications of big data analytics to fields of computer vision and speech processing, and describes applications such as semantic indexing and data tagging. Lastly it identifies 25 unsolved research problems and research directions in fog computing, as well as in the context of applying deep learning techniques to big data analytics, such as dimensionality reduction in high-dimensional data and improved formulation of data abstractions along with possible directions for their solutions.
1 Introduction
1.1. A new economy based on IOT emerging by 2015
1.1.1 Emergence of IOT
1.1.2 Smart Cities and IOT
1.1.3 Stages of IOT and Stakeholders
1.1.3.1 Stages of IOT
1.1.3.2 Stakeholders
1.1.3.3 Practical Down Scaling
1.1.4 Analytics
1.1.5 Analytics from the Edge to Cloud [179]
1.1.6 Security and Privacy Issues and Challenges in Internet of Things (IOT)
1.1.7 Access
1.1.8 Cost Reduction
1.1.9 Opportunities and Business Model
1.1.10 Content and Semantics
1.1.11 Data based Business models coming out of IOT
1.1.12 Future of IOT
1.1.12.1 Technology Drivers
1.1.12.2 Future possibilities
1.1.12.3 Challenges and Concerns
1.1.13 Big Data Analytics and IOT
1.1.13.1 Infrastructure for integration of Big Date with IOT
1.2 The Technological challenges of an IOT driven Economy
1.3 Fog Computing Paradigm as a solution
1.4 Definitions of Fog Computing
1.5 Characteristics of Fog computing
1.6 Architectures of Fog computing
1.6.1 Cloudlet Architecture
1.6.2 IoX Architecture
1.6.3 Local Grid''s Fog Computing platform
1.6.4 Parstream
1.6.5 Para Drop
1.6.6 Prismatic Vortex
1.7 Designing a robust Fog computing platform
1.8 Present challenges in designing Fog Computing Platform
1.9 Platform and Applications
1.9.1 Components of Fog Computing Platform
1.9.2 Applications and case studies
1.9.2.1 Health data management and Health care
1.9.2.2 Smart village health care
1.9.2.3 Smart home
1.9.2.4 Smart vehicle and vehicular fog computing
1.9.2.5 Augmented Reality applications
2. Fog Application management
2.1 Introduction
2.2 Application Management Approaches
2.3 Performance
2.4 Latency Aware Application Management
2.5 Distributed Application Development in Fog
2.6 Distributed Data flow approach 2.7 Resource Coordination Approaches 3 Fog Analytics
3.1 Introduction
3.2 Fog Computing
3.3 Stream data processing
3.4 Stream Data Analytics and Fog computing
3.4.1 Machine Learning for Big Data Stream data and Fog Analytics
3.4.1.1 Supervised Learning
3.4.1.2 Distributed Decision Trees
3.5.1.3 Clustering Methods for Big Data
3.4.1.4 Distributed Parallel Association Rule Mining Techniques for Big Data Scenario
3.4.1.5 Dynamic Association Mining
3.4.2 Deep Learning Techniques
3.4.3 Applications of Deep Learning in Big Data Analytics
3.4.3.1 Semantic Indexing
3.4.3.2 Discriminative Tasks and Semantic Tagging
3.4.4. Deep Learning Challenges in Big Data Analytics
3.4.4.1 Incremental Learning for Non-Stationary Data
3.4.4.2 High-Dimensional Data
3.4.4.3 Large-Scale Models
3.5 Different Approaches of Fog Analytics
3.6 Comparision
3.7 Cloud Solutions for the Edge Analytics 4 Fog Security and Privary
4.1 Introduction
4.2 Secure Communications in Fog Computing
4.3 Authentication
4.4 Privacy Issues
4.5 User Behaviour Profiling
4.6 Dynamic Fog Nodes and EUs
4.7 Malicious Attacks
4.8 Malicious Insider in the Cloud
4.9 Man in the Middle Attack
4.10 Secured Multi-Tenancy
4.11 Backup and Recovery 5 Research Directions 6 CONCLUSION References

About Springer

Science, technology and medicine play an important role in our daily lives. With Springer at the top, these subjects are quite at home in our publishing houses.

 

Some of the most renowned scientists in the world are our authors. Alongside Springer, with offices in many of the world’s centers of knowledge, the Science / Technology / Medicine (STM) publishers Apress, BioMed Central, Humana, Key Curriculum Press, Spektrum Akademischer Verlag and others enjoy excellent professional reputations.

 

All in all, some 2,000 academic journals and around 6,500 new books are published each year – in Berlin, Heidelberg, Dordrecht, Vienna, Paris, London, Milan, Moscow, New York, Beijing, Tokyo and New Delhi. 90 percent of our publications appear on the market in English.