Invited Paper: Hierarchical Activity Recognition with Smartwatch IMU

Alevizaki, Ada; Pham, Nhat; Trigoni, Niki

doi:10.1145/3571306.3571390

Cited by 3 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pancholi et al [12] develop a cost-effective Electromyography (EMG) system with eight channels for accurate arm movement recognition, utilizing machine learning for enhanced performance. To minimize the discomfort and inconvenience experienced by users due to the deployment of sensors, Alevizaki et al [13] introduce a hierarchical framework using smartwatch IMU data to learn daily living activities at varying granularity levels, employing CNN-LSTM classifiers for improved accuracy and efficiency. Jing et al [14] design a compact wireless ring, named Magic Ring, equipped with a tri-axial accelerometer, to be worn on the finger for interac-tion with surrounding electronic devices, further simplifying HAR wearable devices.…”

Section: Introductionmentioning

confidence: 99%

Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning

Guo,

Yamagishi,

Jing

2024

IEEE Access

View full text Add to dashboard Cite

Human activity recognition (HAR) plays a crucial role in human-computer interaction, smart home, health monitoring and elderly care. However, existing methods typically utilize camera, radio frequency (RF) signals or wearable devices for activity recognition. Each single-sensor modality has its inherent limitations, like camera-based methods having blind spots, Wi-Fi-based methods depending on the environment and the inconvenience of wearing Inertial Measurement Unit (IMU) devices. In this paper, we propose a HAR system that leverages three types of sensor combinations: Wi-Fi, IMU and a hybrid of Wi-Fi+IMU. We utilize the Channel State Information (CSI) provided by Wi-Fi and the accelerometer and gyroscope data from IMU devices to capture activity characteristics. Then, we employ six machine learning algorithms to recognize eight types of daily activities. These algorithms include Support Vector Machine (SVM), Multi-layer Perceptron (MLP), Decision Tree, Random Forest, Logistic Regression and k-Nearest Neighbors (kNN). Additionally, we investigate the accuracy of hand gesture recognition using different sensor combinations and analyze the calculation speed of each combination. We conduct a survey to collect user feedback on the performance of various sensor combinations in our HAR system. The results show that the combination of CSI+IMU yields the best HAR recognition accuracy, with a accuracy of 89.38%. The SVM algorithm consistently performs well across all systems, especially excelling in the CSI+IMU system supported by energy and average Fast Fourier Transform (FFT) features. However, we also find that the success of sensor fusion depends on specific algorithms and features. Fusion of CSI and IMU does not universally enhance recognition accuracy for all features and algorithms and can, in some cases, actually reduce accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%