This study explores Human Activity Recognition (HAR) using smartphone sensors to address the challenges posed by position-dependent datasets. We propose a position-independent system that leverages data from accelerometers, gyroscopes, linear accelerometers, and gravity sensors collected from smartphones placed either on the chest or in the left/right leg pocket. The performance of traditional machine learning algorithms (Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Classifier (SVC), and XGBoost) is compared against deep learning models (Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer models) under two sensor configurations. Our findings highlight that the Temporal Convolutional Network (TCN) model consistently outperforms other models, particularly in the four-sensor non-overlapping configuration, achieving the highest accuracy of 97.70%. Deep learning models such as LSTM, GRU, and Transformer also demonstrate strong performance, showcasing their effectiveness in capturing temporal dependencies in HAR tasks. Traditional machine learning models, including RF and XGBoost, provide reasonable performance but do not match the accuracy of deep learning models. Additionally, incorporating data from linear accelerometers and gravity sensors led to slight improvements over using accelerometer and gyroscope data alone. This research enhances the recognition of passenger behaviors for intelligent transportation systems, contributing to more efficient congestion management and emergency response strategies.

Rapid urbanization in developing regions often outpaces the capacity of traditional public transport infrastructure, resulting in severe congestion and inefficient fleet management. This study introduces TransitSense, a cost-effective intelligent transportation framework designed to modernize urban mobility through sensor fusion. The system uniquely integrates Global Navigation Satellite Systems (GNSS) for geospatial positioning, Bluetooth Low Energy (BLE) beacons for vehicle identification, and smartphone accelerometers for context-aware Human Activity Recognition (HAR). Unlike conventional Automated Passenger Counting (APC) systems that require expensive hardware retrofitting, TransitSense leverages the passenger's own device as a sensing node. A mobile-centric HAR algorithm was implemented using the Flutter Activity Recognition framework to classify passenger states into four distinct categories (Stationary, Walking, Running, In-Vehicle) with high precision. Field deployments within a university campus environment yielded a System Usability Scale (SUS) score of 71.75, indicating a high level of user acceptance. The results indicate that TransitSense significantly enhances operational visibility and passenger satisfaction, offering a scalable solution for smart city ecosystems.