Indoor Human Activity Recognition Method Using CSI of Wireless Signals
About:
The article was published on 2017-10-11 and is currently open access. It has received 3 citations till now. The article focuses on the topics: Activity recognition.read more
Citations
More filters
Journal ArticleDOI
Device free human activity and fall recognition using WiFi channel state information (CSI)
TL;DR: It is shown that it is possible to characterize activities and/or human body presence with high accuracy and to count the number of people in a room based on the CSI-data, which is a first step towards detecting more complex social behavior and activities.
Proceedings ArticleDOI
Device Free Human Activity Recognition using WiFi Channel State Information
Neena Damodaran,Jörg Schäfer +1 more
TL;DR: It is shown that it is possible to characterize activities and / or human body presence with high accuracy and two algorithms are proposed - one using a support vector machine (SVM) for classification and another using a long short-term memory (LSTM) recurrent neural network.
Proceedings ArticleDOI
A Wi-Fi-based Approach for Recognizing Human-Human Interactions
TL;DR: In this article, a multi-class support vector machine classifier was proposed to recognize human-human interactions using the CSI metric of the Wi-Fi signals, which achieved an average recognition accuracy of 69.78% computed overall the 13 interactions.
References
More filters
Journal ArticleDOI
Tool release: gathering 802.11n traces with channel state information
TL;DR: The measurement setup comprises the customized versions of Intel's close-source firmware and open-source iwlwifi wireless driver, userspace tools to enable these measurements, access point functionality for controlling both ends of the link, and Matlab scripts for data analysis.
Proceedings ArticleDOI
Challenges: device-free passive localization for wireless environments
TL;DR: This talk gives a holistic overview of the area of contact-free ambient sensing based on RF technology, highlighting how it evolved over a decade from binary-detection in controlled environments to commercial systems for border protection and smart homes.
Journal ArticleDOI
Human Activity Recognition Process Using 3-D Posture Data
TL;DR: Experimental results show that the solution outperforms four relevant works based on RGB-D image fusion, hierarchical Maximum Entropy Markov Model, Markov Random Fields, and Eigenjoints, respectively, and the ability to recognize the activities in real time show promise for applied use.
Proceedings ArticleDOI
FIFS: Fine-Grained Indoor Fingerprinting System
TL;DR: FIFS explores a PHYlayer Channel State Information (CSI) that specifies the channel status over all the subcarriers for location fingerprinting in WLAN that leverages the CSI values including different amplitudes and phases at multiple propagation paths, known as the frequency diversity, to uniquely manifest a location.
Journal ArticleDOI
Unsupervised learning for human activity recognition using smartphone sensors
TL;DR: This paper proposes unsupervised learning methods for human activity recognition, with sensor data collected from smartphone sensors even when the number of activities is unknown, and believes that the results of the approach provide a way of automatically selecting an appropriate value of k at which the accuracy is maximized forActivity recognition, without the generation of training datasets by hand.