Artificial Neural Networks for Cognitive Radio: A Preliminary Survey

Pattanayak, Sandhya; Venkateswaran, P.; Nandi, R.

doi:10.1109/wicom.2012.6478438

Cited by 17 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A very important aspect concerning the design of an ANN is the choice of the weights and of the activation functions; in principle, a proper choice allows the resolution of very different kind of problems (61,62). The simplest artificial neuron is based on the McCulloch-Pitts scheme, which has a threshold activation function.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Maximum Power Point Tracking Techniques

Balato

Costanzo

Vitelli

2016

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

An essential objective for many photovoltaic (PV) applications is represented by the so‐called maximum power point tracking (MPPT). Under uniform irradiance and ambient temperature conditions, the power versus voltage characteristic of a PV array is characterized by the presence of a unique point, termed maximum power point (MPP), where the power provided by the array itself attains its maximum value. Any other operating point leads to the extraction of a smaller PV energy. Therefore, in order to avoid the waste of PV energy, the working of the array in its MPP is mandatory. Since the position of the MPP continuously changes in time as a function of irradiance and temperature, it is necessary to continuously track it. Such an objective can be obtained by using proper MPPT control techniques. A large number of papers have appeared in the scientific literature during the last 15 years on the issue of MPPT, and as a result it may be difficult to decide the best technique for a given application. Therefore, this survey may hopefully be beneficial to students, researchers, and practitioners in PV systems. The article overviews the representative PV MPPT algorithms, organized into four main groups. The first group contains the so‐called “hill climbing” techniques, the second group contains the “curve fitting” techniques, the third group contains the “dynamical” techniques, and the fourth group includes all the techniques that do not belong to the first three groups.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Maximum Power Point Tracking Techniques

Balato

Costanzo

Vitelli

2016

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

show abstract

“…In [43], the author discussed the different work with the combination of Cognitive Radio and Artificial Neural Network for the prediction of Spectrum and then predicted spectrum assigned to the Cognitive user without causing any interference, reduces sensing time of entire band again and again and also increases Quality of Service (QoS). Further author suggested that the Cognitive Radio can be applied in different areas like disaster management and aeronautical air ground interference.…”

Section: Machine Learning Models/techniques Proposed For Implementatimentioning

confidence: 99%

A Survey on Cognitive Radio Network using Artificial Neural Network

Waqar

Khadim²,

Zeb³

et al. 2017

IJFGCN

View full text Add to dashboard Cite

show abstract

“…In [12], the author proposed the Artificial Neural Network for the prediction of unused spectrum and then predicted spectrum assigned to the Secondary user which reduces sensing time of whole band again and again and increases Quality of services (QoS) without causing any interference to the primary user Moreover author proposed that the Cognitive radio can be apply in different domain and Cognitive radio is a promising solution of fixed spectrum allocation In [13], author used ANN model for the prediction of channel capacity whether it is occupied by the primary user or not cause channel capacity is an important parameter to detect the channel status also author designed the three ANN model with different layers and multiple number of neurons and from the simulation results author concluded that the ANN model 3 is slightly better than model 1 and 2…”

Section: Literature Reviewmentioning

confidence: 99%