Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are less accurate across the variety of impacts that patients may undergo . In this study, we investigated the spectral characteristics of different head impact types with kinematics classification . Data was analyzed from 3262 head impacts from head model simulations, on-field data from American football and mixed martial arts (MMA) using our instrumented mouthguard, and publicly available car crash data . A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify different types of head impacts (e.g., football, MMA), reaching a median accuracy of 96% over 1000 random partitions of training and test sets . Furthermore, to test the classifier on data from different measurement devices, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards with the classifier reaching over 96% accuracy from these devices . The most important features in classification included both low-frequency and high-frequency features, both linear acceleration features and angular velocity features . It was found that different head impact types had different distributions of spectral densities in low-frequency and high-frequency ranges (e.g., the spectral densities of MMA impacts were higher in high-frequency range than in the low-frequency range). Finally, with head impact classification, type-specific, nearest-neighbor regression models were built for 95th percentile maximum principal strain , 95th percentile maximum principal strain in corpus callosum, and cumulative strain damage (15th percentile). This showed a generally higher R^2-value than baseline models without classification.