Each agent carries a computational unit, which runs estimation and control algorithms, and is associated with local sensors and an actuator.
Additionally, in many runs, the estimation of pmix ran into a boundary (0 or 1), thereby hindering model convergence.
Namely, we resample our data (with replacement) over and over again, 750 times, and run our estimation procedure (subsampling 10 times to get a distribution of estimates and taking the mean as the estimate λ i * b ) on each bootstrap sample to get a distribution of bootstrap estimates.
Furthermore, following Turrini et al. (2015), we run each estimation by also using the ordinary least squares (OLS) model.
In [15], authors presented two run time estimation methods named: "auto regressive moving average (ARMA)" and "Kalman Filters".
When applying the standard greedy algorithm to IM, it will repeatedly run EIS estimation (EISE) until the top k influential nodes are selected.
Likewise, we also replace W_PWi by PWi, which is a dummy indicating that the individual belongs to the post-war cohort, and run the estimation only including individuals from the pre-war and post-war cohort.
We present solutions to these issues in Section 2, and we show that gyroscopes are not needed in our context and that a simple softcore processor synthesized on a FPGA can run motion estimation algorithms.
That is, we replace W_PWi by Wi, which is a dummy indicating that the individual belongs to the war cohort, and run the estimation including only individuals from the pre-war and war cohort.
From a practical point of view, it may be suggested to run the estimation using several mutation models, check the fitness of models to data, and test the robustness of results across equally fitted models.
