The statistical analysis of the evaluation are summarized in Table V, and again results are quite favorable. These results being the first of their kind in the realm of estimating the range and intensity of an explosion event from statically emplaced smartphones are quite favorable, and demonstrate the clear feasibility for improvement with more experiments, and fusing multiple sensor phenomena like acoustic and pressure sensors, along with vibration sensing, which is a part of our future work. As discussed earlier, we have used a feature-vector of size 90 in our non-linear regression model. With this feature-vector the total training took 8.8 seconds on a Windows machine with 32 Gigabytes of RAM and CPU clock speed of 4.6 GHz. A memory footprint of as little as 90 KB was taken for training data since only accelerometer readings corresponding to explosion events were used for processing