Human gait parameters reveal a lot about physical and psychological well-being. In addition, gait impairments significantly affect daily life activities and hamper the locomotive freedom of people with neurological or musculoskeletal disorders. However, there is still a need for a portable, user-friendly, costeffective gait characterization device. Therefore, in this study, a feature engineering-based portable gait characterization module is proposed, and a shank-mounted inertial measurement unit (IMU) is utilized for gait phases and event detection. The efficiency of the developed module is estimated on ten healthy subjects for plain terrain walking. A force sensing resistor (FSR) sensorized instrumented insole has been utilised as a reference system to validate the results estimated using the developed module. The performance is estimated with three different classifiers, support vector machine (SVM), K-nearest neighbor (KNN), and linear discriminant analysis (LDA). For gait event identifications, the average classification accuracies depicted by SVM, LDA, and KNN classifiers are 95.69±5.23%, 96.64±5.02%, and 93.63±4.84% (p − value < 0.05), respectively. Furthermore, the confusion matrix demonstrated the insight illustration of predicted and misclassified events for individual classifiers. In summary, the gait events and gait temporal parameters are reliably estimated using a single IMU with SVM or LDA classifier (p − value > 0.05). Additionally, the efficacy of the proposed model for sensor location and subject variability has been evaluated. The performance of LDA and SVM classifier for gait phase prediction has been found invariant (p − value > 0.05) towards sensor location and subject variability.