Wearable Sensing

Dataset for validation of a new magnetic field-based wearable breathing sensor (MAG), which uses the movement of the chest wall as a surrogate measure of respiratory activity. Based on the principle of variation in magnetic field strength with the distance from the source, this system explores Hall effect sensing, paired with a permanent magnet, embedded in a chest strap.


The data set contains raw channel-sounding data of 30 clinically relevant scenarios, captured in the university clinic of Dresden, Germany, and a script to analyze them. The measurement campaign was conducted in five environments:

  • Infirmary (Inf)
  • Emergency Room (ER)
  • Intensive Care Unit (ICU)
  • Hallway (Hall)
  • Elevator (Elev)

The patients were performing various motion sequences:


The published Surface Electromyography (sEMG) dataset was captured under the supervision of trained physiotherapists and doctors at Mayo Hospital Lahore and National University of Sciences & Technology by following two months long experimental protocol.


The dataset was generated through the execution of a Python script designed to collect a comprehensive set of data samples from six different sensors for each specific gesture. Upon launching the script, users are prompted to initiate gesture 0, Once ready, users can commence recording, with the program automatically capturing 1000 samples for that particular gesture. Subsequently, the program prompts users to perform gesture 1, and this process repeats until data for all gestures is collected.


The morphological characteristics of skeletal muscles, such as fascicle orientation, fascicle length, and muscle thickness, contain valuable mechanical information that aids in understanding muscle contractility and excitation due to commands from the central nervous system. Ultrasound (US) imaging, a non-invasive measurement technique, has been employed in clinical research to provide visualized images that capture morphological characteristics. However, accurately and efficiently detecting the fascicle in US images is challenging.


<p> The dataset is digital health data. It contains heart rate data extracted from Fitbit version 2 smartwatch worn by a healthy male Asian person of 48 years old. Data is of one-month duration. We have uploaded a zip file that contains data from different days. Data for each day has a separate file. The file name contains the date. Each file is in csv format. Each file has two columns – timestamp and heart rate. It is a continuous time-series heart rate data. Heart rate was recorded seamlessly at 5 sec interval. However, there may be missing datum.


8-channel monopolar sEMG signals were acquired using the device developed by our research group at a sampling rate of 1000 Hz. Medical gel electrodes (CH50B, Shanghai Hanjie Electronic Technology Co., LTD., Shanghai, China) were used for data collection. The position of the electrodes is shown in Fig. 2. The REF electrode was placed on the inner side of the upper big arm near the elbow and the RLD electrode was placed on the outer side of the right upper arm near the elbow. Eight monopolar electrodes were placed on the right forearm.


The project research team successfully established China's first Inertial Motion Tracking Dataset (IMTD), which can be widely used for artificial intelligence model training in fields such as satellite-free navigation, unmanned driving, and wearable devices. Based on the IMTD dataset, the motion tracking method proposed by Wang Yifeng, Zhao Yi, and others breaks through the limitations of traditional motion tracking and positioning technologies such as inertia, optics, GPS, and carrier phase.


A challenge with how the body processes sensory information is one of the most important behavioral signs of autistic people. This is usually manifested as being either overly sensitive or underly sensitive to touch. To address this anomaly, many researchers have proposed wearable sensor-based systems and applications in the field of virtual environments but have neglected to conduct a proper evaluation and proof of concept for autistic people.


Electromyography (EMG) has limitations in human machine interface due to disturbances like electrode-shift, fatigue, and subject variability. A potential solution to prevent model degradation is to combine multi-modal data such as EMG and electroencephalography (EEG). This study presents an EMG-EEG dataset for enhancing the development of upper-limb assistive rehabilitation devices. The dataset, acquired from thirty-three volunteers without neuromuscular dysfunction or disease using commercial biosensors is easily replicable and deployable.