An algorithm to extract rules from artificial neural networks for medical diagnosis problems

Artificial neural networks (ANNs) have been successfully applied to solve a variety of classification and function approximation problems. Although ANNs can generally predict better than decision trees for pattern classification problems, ANNs are often regarded as black boxes since their predictions cannot be explained clearly like those of decision trees.

An energy efficient multichannel MAC protocol for cognitive radio ad hoc networks

This paper presents a TDMA based energy efficient cognitive radio multichannel medium access control (MAC) protocol called ECR-MAC for wireless ad hoc networks. ECRMAC requires only a single half-duplex radio transceiver on each node that integrates the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer. In addition to explicit

CR-MAC: A multichannel MAC protocol for cognitive radio ad hoc networks

This paper proposes a cross-layer based cognitive radio multichannel medium access control (MAC) protocol with TDMA, which integrate the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer, for the ad hoc wireless networks. The IEEE 802.11 standard allows for the use of multiple channels available at the PHY layer, but its MAC protocol is designed only for a single channel.

An energy efficient QoS routing protocol for cognitive radio ad hoc networks

The explosive growth in the use of real-time applications on mobile devices has resulted in new challenges to the design of routing protocols for cognitive radio ad hoc networks (CRANs). In this paper, we propose a new on-demand Quality-of-Service (QoS) routing, namely an energy efficient QoS routing (EQR) protocol for CRANs using TDMA. It can establish QoS routes with reserved bandwidth on a per flow basis in a multi-hop networks.

Spectrum and energy aware routing protocol for cognitive radio ad hoc networks

Throughput maximization is one of the core challenges in cognitive radio ad hoc networks (CRANs), where local spectrum resources are changing over time and locations. This paper proposes a spectrum and energy aware routing (SER) protocol for CRANs, which involves spectrum aware, and energy-efficient route selection, and channel-timeslot assignment. A good routing protocol should be aware of the interference as well as the end-to-end delay.

A new data mining scheme using artificial neural networks

Classification is one of the data mining problems receiving enormous attention  in the database community. Although artificial neural networks (ANNs) have been successfully applied in a wide range of machine learning applications, they are however often regarded as black boxes, i.e., their predictions cannot be explained. To enhance the explanation of ANNs, a novel algorithm to extract symbolic rules from ANNs has been proposed in this paper.

An energy efficient MAC protocol for QoS provisioning in cognitive radio ad hoc networks

The explosive growth in the use of real-time applications on mobile devices has resulted in new challenges to the design of medium access control (MAC) protocols for ad hoc networks. In this paper, we propose an energy efficient cognitive radio (CR) MAC protocol for QoS provisioning, called ECRQ-MAC, which integrates the spectrum sensing at physical (PHY) layer and the channel-timeslots allocation at MAC layer. We consider the problem of providing QoS guarantee to CR users as well as to maintain the most efficient use of scarce bandwidth resources.

An energy efficient multichannel MAC protocol for QoS provisioning in MANETs

This paper proposes a TDMA-based multichannel medium access control (MAC) protocol for QoS provisioning in mobile ad hoc networks (MANETs) that enables nodes to transmit their packets in distributed channels. The IEEE 802.11 standard supports multichannel operation at the physical (PHY) layer but its MAC protocol is designed only for a single channel. The single channel MAC protocol does not work well in multichannel environment because of the multichannel hidden terminal problem.

ERANN: An algorithm to extract symbolic rules from trained artificial neural networks

This paper presents an algorithm to extract symbolic rules from trained artificial neural networks (ANNs), called ERANN. In many applications, it is desirable to extract knowledge from ANNs for the users to gain a better understanding of how the networks solve the problems. Although ANN usually achieves high classification accuracy, the obtained results sometimes may be incomprehensible, because the knowledge embedded within them is distributed over the activation functions and the connection weights.

الصفحات

اشترك ب KSU Faculty آر.إس.إس