USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors

By Mi Zhang, Alexander A. Sawchuk. Ubiquitous Computing, 2012

622 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7854760393966e63011c14eb81a29b1e5fb379cf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Nasser Kehtarnavaz
2. Roozbeh Jafari
3. Cheng Chen
4. Aimé Lay-Ekuakille
5. Jae-Young Pyun
6. Satya Prakash Singh
7. Md Abdullah Al Hafiz Khan
8. Archan Misra

In Computer Networks and Communications

1. Jae-Young Pyun
2. Vijay Janappa Reddi
3. Md Abdullah Al Hafiz Khan
4. Archan Misra
5. Abdulmajid Murad
6. Cheng Chen
7. Sreenivasan Ramasamy Ramamurthy
8. Nirmalya Roy

In Computer Vision and Pattern Recognition

1. Nasser Kehtarnavaz
2. Roozbeh Jafari
3. Cheng Chen
4. Aimé Lay-Ekuakille
5. Rocky Rhodes
6. Daniela Micucci
7. Paolo Napoletano
8. Jae-Young Pyun

Citations in the corpus

• Recent trends in machine learning for human activity recognition—A survey (2018, methodology): “The authors have evaluated the model using HAR using smart phone dataset (Anguita et al., 2013) as their source and USC-HAD dataset (Zhang & Sawchuk, 2012) as target.”
• Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation (2018, background): “, for inferring human activity and its correlation with behavioral health [11], [1], [12].”
• TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems (2020, background): “…consumer and industrial applications, including predictive maintenance (Goebel et al., 2020; Susto et al., 2014), acoustic-anomaly detection (Koizumi et al., 2019), visual object detection (Chowdhery et al., 2019), and human-activity recognition (Chavarriaga et al., 2013; Zhang & Sawchuk, 2012).”
• UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor (2015, background): “, UC Berkeley Wearable Action Recognition Database (WARD) [9], and USC Human Activity Dataset (HAD) [10]).”
• Deep Recurrent Neural Networks for Human Activity Recognition (2017, methodology): “2) USC-HAD [20]: Dataset collected by using a high performance IMU (3D accelerometer and gyroscope) sensor positioned on volunteers’ front right hips.”
• Deep ConvLSTM With Self-Attention for Human Activity Decoding Using Wearable Sensors (2020, methodology): “USC-HAD: USC-HAD dataset contains data related to 12 daily activities from 14 subjects.”
• Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks (2015, neutral): “interaction and surveillance [1][2].”
• Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “Specifically, the accuracy for the Opportunity, USC-HAD, and DSA datasets are 82.3% (1.6% improvement over traditional methods), 99.2% (13.9% improvement), and 99.1% (15.9% improvement), respectively.”
• UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones (2016, background): “This set includes, sorted by year of creation from the oldest the most recent, the following datasets: DLR v2 [32], Ugulino [33], USC HAD [34], DaLiAc [10], EvAAL [35], MHEALTH [36], UCI ARSA [27], BaSA [37], UR Fall Detection [38], MMsys [9], SisFall [39], UMA Fall 4 [18], and REALDISP [40].”