Though it had been hoped that the constriction coefficient would eliminate the need for velocity clamping, standard PSO with velocity clamping (i.e. “E&S”) performed more consistently than both Type 1 and Type 1” without velocity clamping.  Approaches other than Type 1", Type 1, and E&S were highly inconsistent and therefore are not worth mentioning.  Standard PSO with velocity clamping provided more consistent performance than the constriction models. (more info)

Frequently Asked Questions (FAQ’s)

After experimenting with various FIPS topologies, Mendes, Kennedy, and Neves wrote, "The very worst FIPS conditions in the study were the UAll and All topologies, where the particle is truly fully informed, gathering information from every single member of the population. The best were the Ring and Square versions, where the particle has three and five neighbors (counting itself), respectively, plus their U-versions, which subtract one" [1]. Therefore, using a literally fully informed model would probably not be the best approach unless more recent research suggests doing so. (more info)

Question 1: Does the PSO Research Toolbox implement FIPS?

Q2: Why doesn’t the PSO Research Toolbox implement the constriction models?

No, people who outsource their graduate work degrade the quality of the PhD degree—watering down the accomplishments of those who earned their degrees the meaningful way.

Researchers who have their own ideas may purchase consulting time, and I will serve as a sounding board, analytically finding flaws in their ideas before valuable time is invested to implement them.  This can save considerable time for the researcher who aims to optimize his or her productivity.

If you hire me specifically to point out flaws in your research approach but I fail to find one, you will receive a full refund and be more confident of your approach; hence, you have nothing to lose—only time to gain (i.e. time that would have been wasted on a flawed idea).  Why sail blindly when you could use a compass?  Hire an independent consultant today!

Q3: Will you do some of my graduate research for a price?

George Evers, MSE

Electrical Engineer

To contact me:
george [at] georgeevers.org

(@ removed to avoid email harvesters)