Journal of Sensors / 2016 / Article / Tab 7

Research Article

WSN-DS: A Dataset for Intrusion Detection Systems in Wireless Sensor Networks

Table 7

Parameters for MLP neural network classifier.

ParameterExplanationUsed value

LLearning rate: used for weight adjustment on each iteration. (The value should be between 0 and 1.)0.3
MMomentum: used for weight adjustment during backpropagation, in order to speed up convergence and avoid local minima. (The value should be between 0 and 1.)0.2
NThe number of epochs or passes through training data.500
VThe percentage of the validation set from the training data.20%
SSeed for random number generator. Random numbers are used for setting initial weights for the connections between nodes. (The value should be ≥0.)0
EThreshold for consecutive errors allowed during validation testing before the neural network terminates. (The value should be >0.)20
HNumber of nodes in the hidden layer which is represented as follows:
number of hidden layers (number of neurons in each layer).
1 (11)
2 (11, 5)
3 (11, 5, 2)

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.