Cristin-resultat-ID: 1947658
Sist endret: 21. oktober 2021, 18:19
Resultat
Poster
2021

Recognition of Human Activities using UWB Radar and Deep Learning

Bidragsytere:
  • Farzan Majeed Noori

Presentasjon

Navn på arrangementet: Nordic Young Researchers Symposium
Sted: Norway
Dato fra: 1. november 2021
Dato til: 2. november 2022

Om resultatet

Poster
Publiseringsår: 2021

Beskrivelse Beskrivelse

Tittel

Recognition of Human Activities using UWB Radar and Deep Learning

Sammendrag

The population of older adults are increasing every day, and the trend is expected to continue. With the help of advanced assistive technologies, we can provide them better healthcare. In this work, we provide a novel sensing approach based on Ultra-wideband (UWB) sensors to recognize human activities and forecast future events. Previously, researchers focused on wearable or video sensors to detect a person’s behaviour. However, it is challenging for older people to wear devices 24/7. Similarly, vision-based sensors always carry privacy concerns. In contrast, a non-contact ambient sensor with no such privacy issues is XeThru ultra-wideband (UWB) radar. We collected the data using multiple modalities, such as UWB, depth images, thermal images, and actigraphy device, i.e. to collect heart rate (HR) for ground truth. The dataset comprised of the participants sitting on the sofa in normal situation. Afterwards, we recommended participants do some exercise for the sake of increasing HR. When the HR increased by more than 140 BPM, the users lie down on the floor in front of sensors until their HR reached a normal level. In this research, we classify normal vs abnormal situations using CNNs and LSTMs. Accuracy, precision, and recall are used as performance measures. We got 95% and 98% accuracies using CNNs and LSTMs, respectively. Furthermore, seven classes were introduced based on HR levels, as shown in Table1. We got promising results with LSTMs. A confusion matrix is shown in Figure 1. It was the first step towards classifying activities using UWB radar. In the future, we are planning to predict the future HR based only on UWB data, as it would be challenging for older people to wear actigraphy devices. Moreover, we will include other modalities which we did not include in our preliminary analysis.

Bidragsytere

Aktiv cristin-person

Farzan Majeed Noori

  • Tilknyttet:
    Forfatter
    ved Forskningsgruppe for robotikk og intelligente systemer ved Universitetet i Oslo
1 - 1 av 1