BodyScope: a wearable acoustic sensor for activity recognition

By Koji Yatani, Khai N. Truong. Ubiquitous Computing, 2012

346 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/dd5daeac78ca344cac85864efb901f4798b5ded1

How researchers see this paper

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

In Computer Networks and Communications

1. Alex X. Liu
2. Zheng Yang
3. Yunhao Liu
4. Kun Qian
5. Chenshu Wu
6. Guidong Zhang
7. Yi Zhang
8. Wen Wang

In Computer Vision and Pattern Recognition

1. Kun Qian
2. Yunhao Liu
3. Chenshu Wu
4. Zheng Yang
5. Guidong Zhang
6. Yi Zhang
7. Wen Wang
8. Alex X. Liu

In Electrical and Electronic Engineering

1. Zheng Yang
2. Yunhao Liu
3. Kun Qian
4. Chenshu Wu
5. Alex X. Liu
6. Guidong Zhang
7. Yi Zhang
8. Wen Wang

Citations in the corpus

• A Survey on Activity Detection and Classification Using Wearable Sensors (2017, background): “Fixed-sensor approaches involve acoustic [1]–[7], vibrational [8]–[11], other ambient-based sensors, or static cameras installed at fixed locations [12]–[16].”
• Understanding and Modeling of WiFi Signal Based Human Activity Recognition (2015, methodology): “Traditional approaches use cameras [6], radars [2], or wearable sensors [7, 33].”
• Widar3.0: Zero-Effort Cross-Domain Gesture Recognition With Wi-Fi (2021, neutral): “Traditional approaches use cameras [1], [2], [3], wearable devices and phones [4], [5], [6] or sonar [7], [8], [9] as the sensing module.”
• Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi (2019, methodology): “Traditional approaches use cameras [16, 24, 42], wearable devices and phones [8, 17, 36] or sonar [22, 29, 48] as the sensing module.”
• E-eyes: device-free location-oriented activity identification using fine-grained WiFi signatures (2014, methodology): “While traditional activity identification is more location independent [16, 42], our approach prioritizes device-free operation and detection of more loosely-defined daily activities involving a series of motions as opposed to gestures or basic sitting, walking, running classification.”
• A Practical Approach for Recognizing Eating Moments with Wrist-Mounted Inertial Sensing (2015, background): “2807545 reason, over the last 15 years, a large body of research has aimed at fully automating the task of food intake monitoring [11, 12, 21, 34].”
• Unintrusive eating recognition using Google Glass (2015, methodology): “From each window we generate a 180-element vector consisting of features proven useful for activity recognition ([2], [13]), specifically 5 statistical (mean, intensity, variance, skewness, kurtosis and crest-factor), 3 spectral (spectral centroid, flux, and roll-off ), and 2 temporal (delta and del”
• Recognizing Detailed Human Context in the Wild from Smartphones and Smartwatches (2016, methodology): “In Yatani et al. ’s [21] out-of-lab study, five subject wore a phone around their neck to take egocentric snapshots that were later used to label the activity.”
• Device-Free Human Activity Recognition Using Commercial WiFi Devices (2017, background): “Compared to traditional human activity recognition systems, which use cameras [2], [6], radars [17], or wearable devices [8], [35], WiFi signal based systems have the following advantages.”
• LSTM-CNN Architecture for Human Activity Recognition (2020, methodology): “The methods based on fixed sensors mean that the information is obtained from sensors mounted at a fixed position, involving acoustic sensors [7], radars [8], static cameras [9], and other ambient-based sensors.”