A Versatile Annotated Dataset for Multimodal Locomotion Analytics with Mobile Devices

Gjoreski, Hristijan; Ciliberto, Mathias; Morales, Francisco; Roggen, Daniel; Mekki, Sami; Valentin, Stefan

doi:10.1145/3131672.3136976

Cited by 28 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the Sussex-Huawei Locomotion (SHL) dataset [ 36 , 37 ], three subjects carried four smartphones and a camera (chest-mounted) while performing eight different transportation activities, namely: being still (no transportation), walking, running, cycling, driving a car, taking the bus, taking the train, and being in a subway (SHL dataset available at: (accessed on 22 April 2021)). Annotations were created during the data collection using one smartphone.…”

Section: Related Workmentioning

confidence: 99%

HARTH: A Human Activity Recognition Dataset for Machine Learning

Logacjov

Bach

Kongsvold

et al. 2021

Sensors

View full text Add to dashboard Cite

Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We make two contributions in this work. First, we present the publicly available Human Activity Recognition Trondheim dataset (HARTH). Twenty-two participants were recorded for 90 to 120 min during their regular working hours using two three-axial accelerometers, attached to the thigh and lower back, and a chest-mounted camera. Experts annotated the data independently using the camera’s video signal and achieved high inter-rater agreement (Fleiss’ Kappa =0.96). They labeled twelve activities. The second contribution of this paper is the training of seven different baseline machine learning models for HAR on our dataset. We used a support vector machine, k-nearest neighbor, random forest, extreme gradient boost, convolutional neural network, bidirectional long short-term memory, and convolutional neural network with multi-resolution blocks. The support vector machine achieved the best results with an F1-score of 0.81 (standard deviation: ±0.18), recall of 0.85±0.13, and precision of 0.79±0.22 in a leave-one-subject-out cross-validation. Our highly professional recordings and annotations provide a promising benchmark dataset for researchers to develop innovative machine learning approaches for precise HAR in free living.

show abstract

Section: Related Workmentioning

confidence: 99%

HARTH: A Human Activity Recognition Dataset for Machine Learning

Logacjov

Bach

Kongsvold

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We collected more than 750 hours of data from 17 different sensors for a total of 950GB of raw data [5]. The participants were asked to perform 8 activities related to different transportation modes: staying still, walking, running, cycling, driving (or being in a car as passenger), travelling on a train, a bus or in the subway.…”

Section: Reliability and Battery Lifementioning

confidence: 99%

High reliability Android application for multidevice multimodal mobile data acquisition and annotation

Ciliberto

Morales

Gjoreski

et al. 2017

Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems

Self Cite

View full text Add to dashboard Cite

We have completed the collection of one of the richest accurately annotated mobile dataset of modes of transportation and locomotion. To do this, we developed a highly reliable Android application called DataLogger capable of recording multisensor data from multiple synchronized smartphones simultaneously. The application allows real-time data annotation. We explain how we designed the app to achieve high reliability and ease of use. We also present an evaluation of the application in a big-data collection (750 hours, 950 GB of data, 17 different sensor modalities), analysing the data loss (less than 0.4% ) and battery consumption (≈ 6% on average per hour). The application is available as open source.

show abstract

“…Users can, therefore, be considered a rich source of context data. An example of a user context information dataset can be found in [49,50]. The proposed dataset structure consists of user context data and the corresponding satisfaction values.…”

Section: Features Descriptionmentioning

confidence: 99%

Big Data-Driven AI-based Wireless Network Personalization

Alkurd¹

View full text Add to dashboard Cite

A Versatile Annotated Dataset for Multimodal Locomotion Analytics with Mobile Devices

Cited by 28 publications

References 4 publications

HARTH: A Human Activity Recognition Dataset for Machine Learning

HARTH: A Human Activity Recognition Dataset for Machine Learning

High reliability Android application for multidevice multimodal mobile data acquisition and annotation

Big Data-Driven AI-based Wireless Network Personalization

Contact Info

Product

Resources

About