In this paper, source is considered as a single equivalent dipole and genetic algorithm, an efficient and robust optimization method, is proposed to estimate parameters of source. Some improvements are introduced to enhance performance of conventional genetic algorithm. | JOURNAL OF SCIENCE OF HNUE Natural Sci. 2010 Vol. 55 No. 6 pp. 101-112 ECG DIPOLE SOURCE LOCALIZATION IN 3D HUMAN MODEL Dang Thanh Trung and Nguyen The Loc Hanoi National University of Education Nguyen Thi Thanh Van and Pham Thi Mai Bao College of Technology Vietnam National University Said Elnaffar College of Information Technology UAE University UAE E-mail trungdt@ Abstract. Computing electrical source in the human heart from potentials on the body surface is an ill-posed problem of electrocardiogram ECG . It is very difficult to get an exact solution for this problem. In this paper we would like to introduce a novel method to estimate the solution. For details we use Finite Element method for the forthcoming problem in con- juction with optimization search algorithm for inverse problems. There are many optimization searches such as iterative technique Newton or Down- hill simplex etc. which can be applied to find the best source whose poten- tials best match to the observed potentials in a least square sense. Such methods however often converge to a local minimum and their results are affected by initial parameters. In this paper source is considered as a single equivalent dipole and genetic algorithm an efficient and robust optimization method is proposed to estimate parameters of source. Some improvements are introduced to enhance performance of conventional genetic algorithm. In addition a 3D volume conductor model of the human body which must be a realistic one namely accurately reflecting the internal geometrical body structure is constructed based on an anatomic atlas for numerical tests. A comparison between our approach and one using Downhill Simplex method is implemented. The results show that our approach is stable and may provide a good scheme for solving the ECG inverse problem. Keywords Bioelectric Electrocardiography ECG Inverse problem Fi- nite Element Method Genetic Algorithm. 1. Introduction The ECG inverse problem is the bioelectric
