Recognition of Human Activities using the User’s Context and the Activity Theory for Risk Prediction

Neto, Alfredo Del Fabro; Azevedo, Bruno Romero de; Boufleuer, Rafael; Lima, João Carlos D.; Machado, Alencar; Augustin, Iara; Pasin, Márcia

doi:10.5220/0005832202820289

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human Activity Recognition (HAR) is a widely spread field that consists in determining the activity performed by a specific person along the time. There are several applications of HAR, such as daily life monitoring for activity tracking, intelligent assisting with physical exercise or incentivizing healthy lifestyle [1], elderly healthcare in smart-homes and ambient-assisted environments [2][3][4], supervising diseases with motor anomalies [5], industry manufacturing for assisting workers and reducing accident risks [6] or industrial applications that require accurate motion control [7,8]. In many applications, it is not necessary to classify the performed activity with a low granularity (in very short segments): for example, many sports do not need a high resolution (window durations above 3 s).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time Analysis in Human Activity Recognition

Gil-Martín

San-Segundo

Fernández-Martínez

et al. 2021

Neural Process Lett

View full text Add to dashboard Cite

Continuous human activity recognition from inertial signals is performed by splitting these temporal signals into time windows and identifying the activity in each window. Defining the appropriate window duration has been the target of several previous works. In most of these analyses, the recognition performance increases with the windows duration until an optimal value and decreases or saturates for longer windows. This paper evaluates several strategies to combine sub-window information inside a window, obtaining important improvements for long windows. This evaluation was performed using a state-of-the-art human activity recognition system based on Convolutional Neural Networks (CNNs). This deep neural network includes convolutional layers to learn features from signal spectra and additional fully connected layers to classify the activity at each window. All the analyses were carried out using two public datasets (PAMAP2 and USC-HAD) and a Leave-One-Subject-Out (LOSO) cross-validation. For 10-s windows, the accuracy increased from 90.1 (± 0.66) to 94.27 (± 0.46) in PAMAP2 and from 80.54 (± 0.73) to 84.46 (± 0.67) in USC-HAD. For 20-s windows, the improvements were from 92.66 (± 0.58) to 96.35 (± 0.38) (PAMAP2) and from 78.39 (± 0.76) to 86.36 (± 0.57) (USC-HAD).

show abstract