HARTH: A Human Activity Recognition Dataset for Machine Learning

Abstract

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.

Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition

“…In previous work, model performance has been evaluated using metrics such as accuracy, sensitivity, specificity, precision, recall, and f1-score [ 1 ]. As class imbalance is common in most publicly available HAR datasets (see Table 2 ), f1-score is used as the main performance metric since it is more robust than accuracy in these settings [ 30 ]. To be able to compare deep learning models and classic models with HC features, the f1-scores are compared in tasks across different OOD scenarios and including five public HAR datasets.…”

“…Deep learning approaches have been explored in OOD settings by testing the models on data from unseen domains [ 4 , 29 , 30 , 31 , 32 ]. Gholamiangonabadi et al.…”

“…[ 4 ] and Logacjov et al. [ 30 ] compared several deep learning models with classic ML pipelines using LOSO validation. As opposed to what was verified in the previous studies involving ID settings, in the context of OOD, classic methods were mostly on par with deep learning approaches, outperforming them in some cases.…”

Daily motionless activities: A dataset with accelerometer, magnetometer, gyroscope, environment, and GPS data

“…Most of the available datasets combine both motionless and motion activities or focus on motion activities and falls. Also, the Human Activity Recognition Trondheim dataset (HARTH) 5 is another dataset composed by accelerometer data related that combines several activities recorded during free living. The ExtraSensory 6 dataset contains a large dataset with several activities, including motion and motionless activities, composed by a lot of sensors, including accelerometer, gyroscope, magnetometer, watch accelerometer, watch compass, location, audio, audio magnitude, and others.…”

Estimation of Head Accelerations in Crashes Using Neural Networks and Sensors Embedded in the Protective Helmet

“…Most recently, Zhou [ 29 ] proposed a novel impact load identification method of non-linear structures by using deep Recurrent Neural Networks (RNNs), verifying this method in three non-linear cases: damped Duffing oscillator, non-linear three-degree-of-freedom system and non-linear composite plate. Finally, deep learning neural networks techniques were recently implemented to recognize human activities from wearable sensors [ 32 , 33 ]. To date, there is no application for the identification of a body (e.g., head) acceleration with sensors embedded in a second body (e.g., helmet), which exhibits a relative movement to the first one.…”