Dataset Overview This dataset provides a comprehensive collection of 172,000 pressure maps (64×160 sensors) recorded from 30 participants assuming 20 distinct driving postures. The dataset was developed to enhance Driving Posture Recognition (DPR) using pressure sensor arrays, offering a privacy-preserving, cost-effective, and accurate alternative to camera-based monitoring systems. This dataset enables sensor array optimization for real-world applications in automated vehicles, driver safety, and ergonomic research by leveraging Machine Learning and Deep Learning techniques. Key Features Participants: 30 healthy adults with different anthropometric characteristics (BMI, height, weight). Acquisition Conditions: Laboratory setup with driving simulator. Devices: XSENSOR X3 PRO pressure sensor array, ensuring high accuracy (±10%) and fine spatial resolution. Data: 172,000 labeled pressure maps (64×160 sensors) across 20 postures. Data types: Raw CSV & PNG formats for both direct analysis and visualization. Data Collection Methodology Participants were introduced to the setup and guided through familiarization with the seat. The operator instructed the participant on the posture to mimic during data collection. The participant and the operator simultaneously pressed four highlighted points on the matrix before assuming each posture. Each session lasted approximately 8 minutes per participant. Pressure maps were saved as ‘CSV’ files. A MATLAB script was used to generate grayscale images from the data. Dataset Structure 📄 README.md📁 Dataset_PNG_Postures.zip├── 📂 P1│ ├── USER_1_p1_im1.png (64×158 grayscale image)│ ├── …│ └── USER_30_p1_im255.png ├── …└──📂 P20 ├── USER_1_p20_im1.png ├── … └── USER_30_p20_im115.png📁 Dataset_CSV_Users.zip├── User1.csv├── … └── User30.csv 📄 Info_Users.csv 📄 Frame_posture_labels.csv Notes and Recommendations Data Quality All recordings have undergone rigorous quality checks to ensure reliability. General Notes Participant IDs are pseudonymized for privacy. The dataset is intended for research and algorithm validation, not clinical applications. Potential Applications 🚗 Driver Behavior Analysis & Safety Systems – Improve vehicle safety by recognizing fatigue, discomfort, or unsafe driving postures. 📊 Machine Learning & AI Models – Train classification models for real-time driving posture recognition using CNNs, Random Forest, XGBoost, and SVM. 🛋️ Ergonomic & Automotive Seat Design – Optimize seat pressure distribution for improved driver comfort and posture correction. 🔬 Human-Computer Interaction & Smart Wearables – Develop adaptive seating solutions for autonomous vehicles and smart environments.