E-eyes: device-free location-oriented activity identification using fine-grained WiFi signatures

By Yan Wang, Jian Liu, Yingying Chen, Marco Gruteser, Jie Yang, Hongbo Liu. ACM/IEEE International Conference on Mobile Computing and Networking, 2014

904 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/62efd4e8913ac5c4cd3a771fdd02e5abb51afc30

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. Wen Wang
3. Gang Zhou
4. Zheng Yang
5. Yunhao Liu
6. Kun Qian
7. Chenshu Wu
8. Muhammad Shahzad

In Electrical and Electronic Engineering

1. Yunhao Liu
2. Zheng Yang
3. Kun Qian
4. Chenshu Wu
5. Gang Zhou
6. Alex X. Liu
7. Kyle Jamieson
8. Wen Wang

Citations in the corpus

• Tracking Vital Signs During Sleep Leveraging Off-the-shelf WiFi (2015, neutral): “human body [17].”
• A Survey on Behavior Recognition Using WiFi Channel State Information (2017, methodology): “[13] Y.”
• Widar3.0: Zero-Effort Cross-Domain Gesture Recognition With Wi-Fi (2021, methodology): “E-eyes [10] is a pioneer work to use strength distribution of commercial Wi-Fi signals and KNN to recognize human activities.”
• WiFall: Device-free fall detection by wireless networks (2017, methodology): “Instead of using CSI amplitude directly for activity recognition, E-eyes [20] utilizes the distribution of CSI amplitude to classify the activities in whole home environment.”
• LiFS: low human-effort, device-free localization with fine-grained subcarrier information (2016, methodology): “CSI has also been employed in gesture and activity recognition systems [36, 35, 28, 6, 19].”
• mD-Track: Leveraging Multi-Dimensionality for Passive Indoor Wi-Fi Tracking (2018, methodology): “ gesture recognition and Wi-Fi imaging in recent years. Acoustic signal based solutions [36, 41, 57] can only work within a few decimeters. Wi-Fi RSSI/CSI signature based passive localization systems [2, 6, 39, 40, 42, 46, 55] usually rely on high-density deployments which are not realistic for larg”
• Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning (2016, background): “On one hand, ubiquitous computing tasks have extensively exploited different physical sensors, including wearable sensors (Lara and Labrador 2013), GPS traces (Lin and Hsu 2014), WiFi (Wang et al. 2014), barometer, temperature, and humidity sensors (Choudhury et al.”
• RT-Fall: A Real-Time and Contactless Fall Detection System with Commodity WiFi Devices (2017, methodology): “Index Terms—Fall detection, activity recognition, channel state information (CSI), WiFi, phase difference Ç”
• Wireless Sensing for Human Activity: A Survey (2020, background): “Wang et al. [21] propose the first work, E-eyes, to explore using fine-grained CSI to recognize daily activities.”
• A Survey on Wireless Indoor Localization from the Device Perspective (2016, background): “2015], location-aware activities [Wang et al. 2014], and daily activities [Wang et al.”
• The Insecurity of Home Digital Voice Assistants - Amazon Alexa as a Case Study (2017, background): “Wang et al. [27] leverages CSI to detect fine grained human activities (e.g., walking or cooking).”
• Capturing the human figure through a wall (2015, methodology): “…that can track users without requiring them to carry a wireless transmitter, e.g., [Adib et al. 2014; Joshi et al. 2015; Adib and Katabi 2013; Wang et al. 2014b; Pu et al. 2013; Abdelnasser et al. 2015; Chetty et al. 2012; Wilson and Patwari 2011; Youssef et al. 2007; Nan-nuru et al. 2013;…”
• WiFi CSI Based Passive Human Activity Recognition Using Attention Based BLSTM (2019, background): “Wang et al. presented a location-oriented activity recognition system with CSI readings in WiFi [17].”
• Device-Free Human Activity Recognition Using Commercial WiFi Devices (2017, methodology): “Compared to existing works which use statistical features along a long period [11], [28], HMM based models utilizes the transitions within the activity that provide more details about the activity.”
• Dynamic-MUSIC: accurate device-free indoor localization (2016, neutral): “E-eyes [40] utilizes the amplitude pattern of CSI to build a fingerprint map to identify the target’s moving trajectory and accordingly determine the destination room.”