Skip to main content
Kaggle

MotionSense: Smartphone IMU Dataset for HAR and Attribute Recognition [24 Subjects, 6 Activities]

Abstract

"iPhone 6s accelerometer and gyroscope dataset from 24 subjects performing 6 activities (walking, jogging, stairs up/down, sitting, standing) at 50 Hz. CSV. Kaggle and GitHub. Used for human activity recognition (HAR) and mobile sensor privacy research. Imperial College London, 2018."

Description

Overview

MotionSense was created by Mohammad Malekzadeh and colleagues at Imperial College London. It contains IMU data collected from Apple iPhone 6s smartphones placed in subjects' front pants pockets via the SensingKit framework (CoreMotion API on iOS). Twenty-four subjects of different genders, heights, weights, and ages performed 6 activities in 15 trials under the same environmental conditions: downstairs (dws), upstairs (ups), walking (wlk), jogging (jog), sitting (sit), and standing (std). Data was sampled at 50 Hz.

The sensor data includes: attitude (roll, pitch, yaw), gravity vector (x, y, z), user acceleration (x, y, z — gravity-removed), and rotation rate (x, y, z from gyroscope). The dataset targets two research questions simultaneously: activity recognition from inertial data, and the inadvertent leakage of sensitive personal attributes (gender, weight) from smartphone sensor signals — a mobile privacy concern.

Column Schema

ColumnDescription
attitude.rollRoll angle of the device (radians).
attitude.pitchPitch angle of the device (radians).
attitude.yawYaw angle of the device (radians).
gravity.x / .y / .zGravity vector components (g).
userAcceleration.x / .y / .zBody (gravity-removed) acceleration (g).
rotationRate.x / .y / .zGyroscope rotation rate (rad/s).
subjectAnonymised subject identifier (1–24).

Key Statistics

  • Subjects: 24 (13 male, 11 female)
  • Activities: 6 (downstairs, upstairs, walking, jogging, sitting, standing)
  • Sensors: Accelerometer + Gyroscope via iPhone 6s CoreMotion (iOS)
  • Sampling Rate: 50 Hz
  • File Format: CSV (one file per activity per subject)
  • Published: 2018 — GitHub (github.com/mmalekzadeh/motion-sense) and Kaggle

Use Cases

  • Human activity recognition (HAR) from smartphone IMU data
  • User attribute inference (gender, weight) and mobile privacy research
  • Federated learning for HAR across multiple users
  • Gait and posture analysis from inertial sensors in everyday settings

View Data Structure

To explore column names, data types, and sample rows, visit the official dataset page on Kaggle.

Preview on Kaggle

Cite This Dataset

Malekzadeh, Mohammad, Clegg, Richard G., Cavallaro, Andrea, & Haddadi, Hamed (2018). MotionSense: Smartphone IMU Dataset for HAR and Attribute Recognition [24 Subjects, 6 Activities]. Proceedings of the 2nd Workshop on Privacy by Design in Distributed Systems (EuroSys 2018). [Dataset]. Kaggle. https://www.kaggle.com/datasets/malekzadeh/motionsense-dataset

Source: Kaggle (2018)

Indexed by IoTDataset.com on May 10, 2026

Ready to Start Your Research?

Download this dataset directly from the official repository and start building your next breakthrough project.

Download Dataset

Related Topics & Keywords

Share This Research

More in Accelerometer / Gyroscope / Movement Analysis

View All
Accelerometer / Gyroscope / Posture Analysis Mendeley Data

MPU6050 Gyroscope Data for Posture Tracking and Analysis [Mendeley Data, March 2025]

Real-time posture monitoring dataset from the MPU6050 6-axis sensor (3D gyroscope + 3D accelerometer) attached to the upper body, streaming wirelessly via Phyphox. Angular orientation values: Angle_X, Angle_Y, Angle_Z. Mendeley Data, March 2025 — DOI: 10.17632/ftn4rjnd6x.1. Used for LSTM-based posture classification and ergonomics.

May 10, 2026
Heart Rate / Physical Effort Monitoring UCI

PPG-DaLiA: Heart Rate from Wrist PPG + Accelerometer in Daily Life Activities [15 Subjects, UCI]

Large-scale PPG-based heart rate dataset from 15 subjects wearing wrist (Empatica E4: PPG + 3-axis ACC) and chest (RespiBAN: ECG + respiration + 3-axis ACC) devices during 8 real-life activities. ECG provides HR ground truth. UCI ML Repository. Published in MDPI Sensors 2019 — DOI: 10.3390/s19143079.

May 10, 2026
Heart Rate / Fatigue / Advanced Multi-Sensor Zenodo

Daily Activities Wearable Dataset for Cardiorespiratory Fitness — IMU + HR + SpO2 [Zenodo, July 2025]

Multi-site IMU dataset (chest, hands, knees) with heart rate and SpO2 recorded at 0.5 Hz during structured daily activities and a 3-minute step test. Raw + preprocessed IMU (accelerometer, gyroscope, quaternions) + demographic metadata. Zenodo, July 2025. Used for cardiorespiratory fitness (CRF) estimation and HAR.

May 10, 2026
Advanced Sensors / Performance & Fatigue Analysis arXiv

BasketHAR — Multimodal Basketball HAR Dataset: IMU + Heart Rate + Skin Temperature [arXiv 2025]

Novel multimodal HAR dataset for basketball training with synchronized IMU (accelerometer, gyroscope, angle, magnetic field at 200 Hz, MPU9250/WT901) + heart rate and skin surface temperature (1 Hz, Si1141 wrist sensor) across 14 activity classes. ArXiv 2025. Used for sports performance analysis and LLM-based coaching reports.

May 10, 2026