C4.5: programs for machine learning
C4.5: programs for machine learning
Highly dynamic Destination-Sequenced Distance-Vector routing (DSDV) for mobile computers
SIGCOMM '94 Proceedings of the conference on Communications architectures, protocols and applications
Composing crosscutting concerns using composition filters
Communications of the ACM
A delay-tolerant network architecture for challenged internets
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
Ad hoc Networking
Spray and wait: an efficient routing scheme for intermittently connected mobile networks
Proceedings of the 2005 ACM SIGCOMM workshop on Delay-tolerant networking
Middleware: Middleware Challenges and Approaches for Wireless Sensor Networks
IEEE Distributed Systems Online
Guide to Wireless Ad Hoc Networks
Guide to Wireless Ad Hoc Networks
Algorithms and Protocols for Wireless, Mobile Ad Hoc Networks
Algorithms and Protocols for Wireless, Mobile Ad Hoc Networks
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
Software Engineering
The Internet of Things: A survey
Computer Networks: The International Journal of Computer and Telecommunications Networking
Ontologies for the internet of things
Proceedings of the 8th Middleware Doctoral Symposium
Delay Tolerant Networks: Protocols and Applications
Delay Tolerant Networks: Protocols and Applications
IEEE Communications Surveys & Tutorials
| Hi-index | 0.00 |
The realization of wireless communication in rural environments suffers from long distances, unknown node mobility and discontinuous communication paths. Combination of delay-tolerant mobile ad-hoc networks and infrastructure-based mobile communications results in an increased number of communication opportunities in many usage scenarios. However, efficient exploitation of communication opportunities remains a challenging task. This article introduces a novel middleware approach specialized for consistent and efficient wireless communication in rural environments. An important part of communication optimization is realized by processing on-hand information of the current application scenario. The middleware autonomously links scenario information to network states and applies machine-learning-based analyses to derive meaningful communication predictions. Cooperation of infrastructure-based and ad-hoc communication is implemented by a gateway component. The gateway collects connectivity information of mobile nodes, enhances communication predictions and distributes predictions across the network. Evaluation of local communication layer and application layer information as well as sharing of communication predictions using an application level API ensure efficient use of communication opportunities.