/// Apply noise on the decision vector based on rho
void robust::inject_noise_x(decision_vector &x) const
{
// We follow the algorithm at
// http://math.stackexchange.com/questions/87230/picking-random-points-in-the-volume-of-sphere-with-uniform-probability
// 0. Define the radius
double radius = m_rho * pow(m_uniform_dist(m_drng),1.0/x.size());
// 1. Sampling N(0,1) on each dimension
std::vector<double> perturbation(x.size(), 0.0);
double c2=0;
for(size_type i = 0; i < perturbation.size(); i++){
perturbation[i] = m_normal_dist(m_drng);
c2 += perturbation[i]*perturbation[i];
}
// 2. Normalize the vector
for(size_type i = 0; i < perturbation.size(); i++){
perturbation[i] *= (radius / sqrt(c2) );
x[i] += perturbation[i];
}
// 3. Clip the variables to the valid bounds
for(base::size_type i = 0; i < x.size(); i++){
x[i] = std::max(x[i], get_lb()[i]);
x[i] = std::min(x[i], get_ub()[i]);
}
}
/// Implementation of the sparsity structure: automated detection
void earth_planet::set_sparsity(int &lenG, std::vector<int> &iGfun, std::vector<int> &jGvar) const
{
//Initial point
decision_vector x0(get_dimension());
for (pagmo::decision_vector::size_type i = 0; i<x0.size(); ++i)
{
x0[i] = get_lb()[i] + (get_ub()[i] - get_lb()[i]) / 3.12345;
}
//Numerical procedure
estimate_sparsity(x0, lenG, iGfun, jGvar);
}
double antibodies_problem::compute_distance(const decision_vector &x) const {
double distance = 0.;
// hamming distance
switch(m_method) {
case(algorithm::cstrs_immune_system::HAMMING): {
const decision_vector &lb = get_lb();
const decision_vector &ub = get_ub();
for(decision_vector::size_type i=0; i<x.size(); i++) {
std::vector<int> current_binary_gene = double_to_binary(x.at(i), lb.at(i), ub.at(i));
for(decision_vector::size_type j=0; j<m_pop_antigens.size(); j++) {
std::vector<int> antigens_binary_gene = double_to_binary((m_pop_antigens.at(j)).at(i), lb.at(i), ub.at(i));
for(std::vector<int>::size_type k=0; k<antigens_binary_gene.size(); k++) {
distance += antigens_binary_gene.at(k) && current_binary_gene.at(k);
}
}
}
// we take the inverse of the distance as the measure we need is
// how close the x is from the antigen population
// which means that we need to maximize the ressemblance
distance = - distance;
break;
}
case(algorithm::cstrs_immune_system::EUCLIDEAN): {
for(decision_vector::size_type j=0; j<m_pop_antigens.size(); j++) {
double euclid = 0.;
const decision_vector &antigen_decision = m_pop_antigens.at(j);
for(decision_vector::size_type i=0; i<x.size(); i++) {
euclid += std::pow(x.at(i) - antigen_decision.at(i),2);
}
distance += std::sqrt(euclid);
}
break;
}
}
return distance;
}
