Optimization techniques (GA, PSO, ANN) – MCQs – EE

1. What does GA stand for in optimization techniques?
(A) General Algorithm
(B) Genetic Algorithm
(C) Gradient Adjustment
(D) Global Approximation

2. The Genetic Algorithm (GA) is inspired by which natural process?
(A) Evolution and natural selection
(B) Photosynthesis
(C) Combustion
(D) Gravity

3. In GA, each potential solution is represented as a:
(A) Chromosome
(B) Neuron
(C) Particle
(D) Node

4. What is the main objective of Particle Swarm Optimization (PSO)?
(A) To find the optimal solution by simulating the behavior of a flock of birds or school of fish
(B) To solve linear equations
(C) To analyze circuits
(D) To simulate heat transfer

5. In GA, the crossover operator is used to:
(A) Combine two parent solutions to form offspring
(B) Randomly mutate a solution
(C) Initialize the population
(D) Remove bad solutions

6. In PSO, a particle’s movement depends on:
(A) Its personal best and global best positions
(B) Random number generation only
(C) The initial random velocity
(D) Crossover rate

7. ANN stands for:
(A) Adaptive Neural Network
(B) Artificial Neural Network
(C) Analog Node Network
(D) Automated Network Node

8. Which of the following is NOT a component of GA?
(A) Selection
(B) Crossover
(C) Mutation
(D) Activation Function

9. The fitness function in GA is used to:
(A) Evaluate the quality of each solution
(B) Control mutation rate
(C) Define crossover points
(D) Select neurons

10. In PSO, each particle represents:
(A) A potential solution
(B) A neuron
(C) A population subset
(D) A chromosome pair

11. The learning in ANN is achieved by:
(A) Adjusting the weights of connections
(B) Changing crossover points
(C) Adding new chromosomes
(D) Decreasing mutation rate

12. Which of the following optimization methods is population-based?
(A) GA and PSO
(B) ANN
(C) Linear Programming
(D) Gradient Descent

13. In PSO, the term inertia weight controls:
(A) The influence of a particle’s previous velocity
(B) Mutation probability
(C) Crossover rate
(D) Learning rate

14. In GA, the mutation operator helps to:
(A) Maintain diversity in the population
(B) Reduce population size
(C) Eliminate weak chromosomes
(D) Clone parent chromosomes

15. The activation function in ANN is responsible for:
(A) Introducing non-linearity into the model
(B) Selecting chromosomes
(C) Controlling mutation
(D) Updating inertia

16. The PSO algorithm starts by:
(A) Initializing a swarm of particles randomly
(B) Defining neuron connections
(C) Selecting crossover points
(D) Generating random chromosomes

17. Which of the following is an advantage of GA?
(A) It can handle non-linear and multi-modal problems
(B) It guarantees the global optimum
(C) It is faster than all deterministic methods
(D) It does not require a fitness function

18. In PSO, the velocity update equation includes:
(A) Inertia, cognitive, and social components
(B) Only inertia
(C) Mutation rate
(D) Crossover probability

19. ANN models are trained using algorithms such as:
(A) Backpropagation
(B) Genetic crossover
(C) Random mutation
(D) Simulated annealing

20. In GA, the selection process is used to:
(A) Choose the best chromosomes for reproduction
(B) Initialize random velocities
(C) Adjust neuron weights
(D) Remove hidden layers

21. PSO is most suitable for problems that:
(A) Require continuous optimization
(B) Have discrete outcomes
(C) Are linear only
(D) Do not involve iteration

22. ANN-based optimization is effective when:
(A) The relationship between input and output is complex and non-linear
(B) The system is fully linear
(C) Random solutions are acceptable
(D) No data is available

23. Which of the following describes exploration in optimization algorithms?
(A) Searching new areas of the solution space
(B) Refining known good solutions
(C) Eliminating poor chromosomes
(D) Updating neuron weights

24. In PSO, the cognitive component represents:
(A) A particle’s personal experience
(B) Group behavior
(C) Mutation rate
(D) Fitness normalization

25. Which optimization method mimics human brain learning?
(A) Artificial Neural Network (ANN)
(B) Genetic Algorithm (GA)
(C) Particle Swarm Optimization (PSO)
(D) Simulated Annealing

26. In GA, increasing mutation rate excessively can lead to:
(A) Random search behavior and loss of good solutions
(B) Faster convergence
(C) Better stability
(D) Improved elitism

27. Which method uses neurons, weights, and biases?
(A) ANN
(B) GA
(C) PSO
(D) Differential Evolution

28. The global best (gbest) in PSO represents:
(A) The best position found by the entire swarm
(B) The current particle’s best position
(C) Randomly chosen point
(D) Fitness threshold

29. The main goal of optimization techniques like GA, PSO, and ANN is to:
(A) Find the best solution under given constraints
(B) Generate random data
(C) Reduce system accuracy
(D) Increase computational cost

30. In electrical engineering, these optimization algorithms are often used for:
(A) Optimal power flow, controller design, and fault detection
(B) Circuit drawing only
(C) Manual switching
(D) Signal distortion