| Input: DFILE ⟵ Dataset file for the simulation |
| Output:IDS-Net ⟵ Final Route from VS to VD in VANET CP ← Classification Parameters |
(1) | Final Record = [] |
(2) | Count = 1 |
(3) | For I in range (Normalized Data, Col) |
(4) | Current Feature Col = Normalized Data (All Row, I) |
(5) | All Grouped Bee Records = [] |
(6) | For J in range (5) |
(7) | Ebee = [Current Feature Col (1), Other five Current Feature Col (Randomly)] |
(8) | |
(9) | Define fitness function of G-ABC |
| (i) All Fit Record = [] |
| (ii) Fit Status = 0 |
| (iii) For K in range (Ebee) |
| (iv) If Ebee (K) > Obee |
| (v) Fit Status = 1 |
| (vi) Else |
| (vii) Fit Status = 0 |
| (viii) End–If |
| (b) All Fit Record (K) = Fit Status |
| (c) End–For |
(10) | End–For |
(11) | All Fit = fitness function (Ebee, Obee) |
(12) | If count of non-zeros in All Fit >1 |
(13) | Bee Status = 1 |
(14) | Else |
(15) | Bee Status = 0 |
(16) | End–If |
(17) | All Bee Record (J) = Bee Status |
(18) | End–For |
(19) | If count of non-zeros in All Bee Record > Average (All Bee Record) |
(20) | Final Record (count) = I |
(21) | Count = Count + 1 |
(22) | End–If |
(23) | End–For |
(24) | Select Data from Normalized Data according to selected index by G-ABC |
(25) | Selected Normalized Data = Normalized Data(All Row, Final Record) |
(26) | Create Target for Model Training |
(27) | Target = []//Create an empty variable to store Target |
(28) | For I in range (Selected Normalized Data, Row) |
(29) | If ε 1st Unique Label |
(30) | Target (1, I) = 1 |
(31) | Else if ε 2nd Unique Label |
(32) | Target (2, I) = 2 |
(33) | Else if ε 3rd Unique Label |
(34) | Target (3, I) = 3 |
(35) | Else if ε 4th Unique Label |
(36) | Target (4, I) = 4 |
(37) | Else if ε 5th Unique Label |
(38) | Target (5, I) = 5 |
(39) | End–If |
(40) | End–For |
(41) | Call Deep Neural Network with 10 Hidden Layers |
(42) | IDS-Net = pattern net (10) |
(43) | IDS-Net = train (IDS-Net, Selected Normalized Data, Target); |
(44) | Test Model using IDS-Net |
(45) | Result = sim (IDS-Net, Test Data) |
(46) | CP = Calculate Parameters (Result, Unique Label) |
(47) | Return: CP as Classification Parameters |
(48) | End–Algorithm |