Optimal Sensor Placement in Body Surface Networks using Gaussian Processes

: This paper explores a new sequential selection framework for the optimal sensor placement (OSP) in Electrocardiography imaging networks (ECGI). The proposed methodology incorporates the use a recent experimental design method for the sequential selection of landmarkings on biological objects, namely, Gaussian process landmarking (GPLMK) for better exploration of the candidate sensors. The two experimental design methods work as a source of the training and the validation locations which is fitted using a spatiotemporal Gaussian process (STGP). The STGP is fitted using the training set to predict for the current validation set generated using GPLMK, and the sensor with the largest prediction absolute error is selected from the current validation set and added to the selected sensors. Next, a new validation set is generated and predicted using the current training set. The process continues until selecting a specific number of sensor locations. The study is conducted on a dataset of body surface potential mapping (BSPM) of 352 electrodes of four human subjects. A number of 30 sensor locations is selected using the proposed algorithm. The selected sensor locations achieved average 𝑅 2 = 94.40% for estimating the whole-body QRS segment. The proposed method adds to design efforts for a more clinically practical ECGI system by improving its wearability and reduce the design cost as well. and mean absolute error (𝑀𝐴𝐸) are used to evaluate the accuracy of potential prediction in the validation locations using the selected sensors. 𝑅 2 and 𝑀𝐴𝐸 are calculated for the data of the validation locations only. Equations Error! Reference source not found. and Error! Reference source not found. show the calculations for 𝑅 2 and MAE , where 𝑓(𝑠 𝑖 , 𝑡) represent the measured potential at a specific validation location 𝑠 𝑖 at time 𝑡 𝑖 and 𝑓 ∗ (𝑠 𝑖 , 𝑡) represents the predicted potential for the same location at the same time instance. N represents the number of validation points; those not included in modeling training and equals 322 and T is the total number of time points and equal to 1000 millisecond.