Set the control parameters for the annealing schedule of spsann functions.
scheduleSPSANN(initial.acceptance = 0.95, initial.temperature = 0.001,
temperature.decrease = 0.95, chains = 500, chain.length = 1,
stopping = 10, x.max, x.min = 0, y.max, y.min = 0, cellsize)Numeric value between 0 and 1 defining the initial acceptance probability, i.e.
the proportion of proposed system configurations that should be accepted in the first chain. The
optimization is stopped and a warning is issued if this value is not attained. Defaults to
initial.acceptance = 0.95.
Numeric value larger than 0 defining the initial temperature of the system. A
low initial.temperature, combined with a low initial.acceptance result in the algorithm to
behave as a greedy algorithm, i.e. only better system configurations are accepted. Defaults to
initial.temperature = 0.001.
Numeric value between 0 and 1 used as a multiplying factor to decrease the
temperature at the end of each Markov chain. Defaults to temperature.decrease = 0.95.
Integer value defining the maximum number of chains, i.e. the number of cycles of jitters at
which the temperature and the size of the neighbourhood should be kept constant. Defaults to
chains = 500.
Integer value defining the length of each Markov chain relative to the number of
sample points. Defaults to chain.length = 1, i.e. one time the number of sample points.
Integer value defining the maximum allowable number of Markov chains without improvement of
the objective function value. Defaults to stopping = 10.
Numeric value defining the minimum and maximum quantity of random noise to
be added to the projected x- and y-coordinates. The units are the same as of the projected x- and
y-coordinates. If missing, they are estimated from candi, x.min and y.min being set
to zero, and x.max and y.max being set to half the maximum distance in the x- and
y-coordinates, respectively.
Vector with two numeric values defining the horizontal (x) and vertical (y) spacing
between the candidate locations in candi. A single value can be used if the spacing in the x- and
y-coordinates is the same. If cellsize = 0 then spsann understands that a finite set of
candidate locations is being used (See Details).
A list with a set of control parameters of the annealing schedule.
Aarts, E. H. L.; Korst, J. H. M. Boltzmann machines for travelling salesman problems. European Journal of Operational Research, v. 39, p. 79-95, 1989.
<U+010C>ern<U+00FD>, V. Thermodynamical approach to the travelling salesman problem: an efficient simulation algorithm. Journal of Optimization Theory and Applications, v. 45, p. 41-51, 1985.
Brus, D. J.; Heuvelink, G. B. M. Optimization of sample patterns for universal kriging of environmental variables. Geoderma, v. 138, p. 86-95, 2007.
Kirkpatrick, S.; Gelatt, C. D.; Vecchi, M. P. Optimization by simulated annealing. Science, v. 220, p. 671-680, 1983.
Metropolis, N.; Rosenbluth, A. W.; Rosenbluth, M. N.; Teller, A. H.; Teller, E. Equation of state calculations by fast computing machines. The Journal of Chemical Physics, v. 21, p. 1087-1092, 1953.
van Groenigen, J.-W.; Stein, A. Constrained optimization of spatial sampling using continuous simulated annealing. Journal of Environmental Quality. v. 27, p. 1078-1086, 1998.
Webster, R.; Lark, R. M. Field sampling for environmental science and management. London: Routledge, p. 200, 2013.
optimACDC, optimCORR,
optimDIST, optimMKV,
optimMSSD, optimPPL,
optimSPAN, optimUSER.
# NOT RUN {
schedule <- scheduleSPSANN()
# }
Run the code above in your browser using DataLab