An Optimization Approach for Transcranial Direct Current Stimulation Using Nondominated Sorting Genetic Algorithm II.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Computational Neuroscience

Background:

• Transcranial direct current stimulation (tDCS) modulates brain activity using weak electrical currents.
• Current methods for tDCS optimization often yield a single solution and rely on empirical parameter tuning.
• The intensity-focality trade-off in tDCS presents a multi-objective optimization challenge.

Purpose of the Study:

• To develop and evaluate a multi-objective optimization algorithm for multi-electrode tDCS.
• To address the limitations of traditional tDCS parameter determination methods.
• To compare the proposed algorithm's solutions with existing methods like LCMV.

Main Methods:

• Implementation of the nondominated sorting genetic algorithm II (NSGA-II) for tDCS current optimization.
• Application of NSGA-II to a multi-electrode tDCS setup.
• Comparison of NSGA-II derived solutions against Linearly Constrained Minimum Variance (LCMV) solutions.

Main Results:

• The NSGA-II algorithm successfully identified a set of optimal solutions for tDCS parameters in a single run.
• Solutions obtained were close to the optimal front, indicating high efficiency.
• The method requires no prior knowledge or extensive empirical parameter setting.

Conclusions:

• NSGA-II provides an effective approach to solve the multi-objective optimization problem in multi-electrode tDCS.
• This algorithm offers a more efficient and less experience-dependent alternative to traditional tDCS optimization techniques.
• The study demonstrates the potential of advanced computational algorithms in advancing tDCS applications.