Recently, human activity recognition (HAR) techniques have made remarkable developments in the field of machine learning. In this paper, we classify human gestures using data collected from a curved piezoelectric sensor, including elbow movement, wrist turning, wrist bending, coughing, and neck bending. The classification process relies on data collected from a sensor. Machine learning algorithms enabled with K-mer are developed and optimized to perform human gesture recognition (HGR) from the acquired data to achieve the best results. Three machine learning algorithms, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN), are performed and analyzed with K-mer. The input parameters such as subsequence length (K), number of cuts, penalty parameter (C), number of trees (n_estimators), maximum depth of the tree (max_depth), and nearest neighbors (k) for the three machine learning algorithms are modified and analyzed for classification accuracy. The proposed model was evaluated using its accuracy percentage, recall score, precision score, and F-score value. We achieve promising results with accuracy of 94.11 ± 0.3%, 97.18 ± 0.4%, and 96.90 ± 0.5% for SVM, RF, and k-NN, respectively. The execution time to run the program with optimal parameters is 19.395 ± 1 s, 5.941 ± 1 s, and 3.832 ± 1 s for SVM, RF, and k-NN, respectively.