Match!

Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization

Published on Jan 1, 2019in IEEE Access4.098
· DOI :10.1109/ACCESS.2019.2918714
Shing-Jiuan Liu1
Estimated H-index: 1
(CIT: Center for Information Technology),
Ronald Y. Chang12
Estimated H-index: 12
(CIT: Center for Information Technology),
Feng-Tsun Chien7
Estimated H-index: 7
(NCTU: National Chiao Tung University)
Abstract
Device-free Wi-Fi indoor localization has received significant attention as a key enabling technology for many Internet of Things (IoT) applications. Machine learning-based location estimators, such as the deep neural network (DNN), carry proven potential in achieving high-precision localization performance by automatically learning discriminative features from the noisy wireless signal measurements. However, the inner workings of the DNNs are not transparent and not adequately understood, especially in the indoor localization application. In this paper, we provide quantitative and visual explanations for the DNN learning process as well as the critical features that the DNN has learned during the process. Toward this end, we propose to use several visualization techniques, including 1) dimensionality reduction visualization, to project the high-dimensional feature space to the 2D space to facilitate visualization and interpretation, and 2) visual analytics and information visualization, to quantify relative contributions of each feature with the proposed feature manipulation procedures. The results provide insightful views and plausible explanations of the DNN in device-free Wi-Fi indoor localization using the channel state information (CSI) fingerprints.
  • References (0)
  • Citations (0)
📖 Papers frequently viewed together
2015ISWC: International Symposium on Wearable Computers
4 Authors (Yang Gu, ..., Xinlong Jiang)
2 Citations
2014IJCNN: International Joint Conference on Neural Network
4 Authors (Yang Gu, ..., Xinlong Jiang)
13 Citations
2018
3 Authors (Ayush Mittal, ..., Sudeep Pasricha)
9 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References0
Newest
Dec 1, 2018 in GLOBECOM (Global Communications Conference)
#1Ronald Y. Chang (CIT: Center for Information Technology)H-Index: 12
#2Shing-Jiuan Liu (CIT: Center for Information Technology)H-Index: 1
Last. Yen-Kai Cheng (CIT: Center for Information Technology)H-Index: 2
view all 3 authors...
This paper proposes an economical, nonintrusive, and high-precision indoor localization scheme based on Wi-Fi fingerprinting that requires only a single Wi- Fi access point and a single fixed-location receiver. A deep neural network (DNN) based classification model is trained with Wi-Fi channel state information (CSI) fingerprints for localizing the target without any device attached (i.e., device-free). CSI provides finer-grained information than received signal strength (RSS). CSI pre- process...
2 CitationsSource
Sep 1, 2018 in SMC (Systems, Man and Cybernetics)
#1Zhefu Wu (Zhejiang University of Technology)H-Index: 4
#2Qiang Xu (Zhejiang University of Technology)H-Index: 1
Last. Yun Xiang (Zhejiang University of Technology)H-Index: 8
view all 6 authors...
Passive indoor localization is important. Unlike active localization techniques, it does not require for users to carry measuring devices, e.g., smart phones. Thus, it is widely used in applications such as security, smart housing, object tracking, etc. However, in real-world applications, the passive localization accuracy is limited due to the environment noises, multipath effect, etc. To address those problems, in this paper, we propose to use channel state information (CSI) instead. Specifica...
20 CitationsSource
#1Rui Zhou (University of Electronic Science and Technology of China)H-Index: 2
#2Xiang Lu (University of Electronic Science and Technology of China)H-Index: 2
Last. Jiesong Chen (University of Electronic Science and Technology of China)H-Index: 2
view all 4 authors...
Presence detection and localization are of importance to a variety of applications. Most previous approaches require the objects to carry electronic devices, while on many occasions device-free presence detection and localization are in need. This paper proposes a device-free presence detection and localization algorithm based on WiFi channel state information (CSI) and support vector machines (SVM). In the area of interest covered with WiFi, human movements may cause observable alteration of Wi...
20 CitationsSource
#1Qinhua Gao (DUT: Dalian University of Technology)H-Index: 3
#2Jie Wang (DUT: Dalian University of Technology)H-Index: 13
Last. Hongyu Wang (DUT: Dalian University of Technology)H-Index: 14
view all 5 authors...
Device-free wireless localization and activity recognition is an emerging technique, which could estimate the location and activity of a person without equipping him/her with any device. It deduces the state of a person by analyzing his/her influence on surrounding wireless signals. Therefore, how to characterize the influence of human behaviors is the key question. In this paper, we explore and exploit a radio image processing approach to better characterize the influence of human behaviors on ...
21 CitationsSource
#1Wojciech Samek (Heinrich Hertz Institute)H-Index: 21
#2Alexander Binder (SUTD: Singapore University of Technology and Design)H-Index: 16
Last. Klaus-Robert Müller (Technical University of Berlin)H-Index: 92
view all 5 authors...
Deep neural networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multilayer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision, given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and interpret the reasoning embodied in a DNN for a s...
167 CitationsSource
#1Jie Wang (DUT: Dalian University of Technology)H-Index: 13
#2Xiao Zhang (DUT: Dalian University of Technology)H-Index: 5
Last. Hongyu Wang (DUT: Dalian University of Technology)H-Index: 7
view all 5 authors...
Device-free wireless localization and activity recognition (DFLAR) is a new technique, which could estimate the location and activity of a target by analyzing its shadowing effect on surrounding wireless links. This technique neither requires the target to be equipped with any device nor involves privacy concerns, which makes it an attractive and promising technique for many emerging smart applications. The key question of DFLAR is how to characterize the influence of the target on wireless sign...
51 CitationsSource
#1Kan Zheng (Beijing University of Posts and Telecommunications)H-Index: 32
#2Huijian Wang (Beijing University of Posts and Telecommunications)H-Index: 3
Last. Xuemin Shen (UW: University of Waterloo)H-Index: 85
view all 7 authors...
Wireless sensor networks (WSNs) are effective for locating and tracking people and objects in various industrial environments. Since energy consumption is critical to prolonging the lifespan of WSNs, we propose an energy-efficient LOcalization and Tracking (eLOT) system, using low-cost and portable hardware to enable highly accurate tracking of targets. Various fingerprint based approaches for localization and tracking are implemented in eLOT. To achieve high energy efficiency, a network-level s...
24 CitationsSource
#1Paulo E. RauberH-Index: 7
#2Samuel G. Fadel (USP: University of São Paulo)H-Index: 3
Last. Alexandru Telea (UG: University of Groningen)H-Index: 32
view all 4 authors...
In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks are typically used as black-boxes, they are also widely believed to learn (high-dimensional) higher-level representations of the original observations. In this paper, we propose using dimensionality reduction for two tasks: visualizing the relationshi...
76 CitationsSource
#1Xuyu Wang (AU: Auburn University)H-Index: 12
#2Lingjun Gao (AU: Auburn University)H-Index: 5
Last. Santosh Pandey (Cisco Systems, Inc.)H-Index: 6
view all 4 authors...
With the fast-growing demand of location-based services in indoor environments, indoor positioning based on fingerprinting has attracted significant interest due to its high accuracy. In this paper, we present a novel deep-learning-based indoor fingerprinting system using channel state information (CSI), which is termed DeepFi. Based on three hypotheses on CSI, the DeepFi system architecture includes an offline training phase and an online localization phase. In the offline training phase, deep ...
221 CitationsSource
#1Zheng Wu (U of W: University of Windsor)H-Index: 3
#2Kechang FuH-Index: 1
Last. Mehrdad Saif (U of W: University of Windsor)H-Index: 31
view all 6 authors...
This paper proposes an indoor localization method using online independent support vector machine (OISVM) classification method and undersampling techniques. The system is based on the received signal strength indicator (RSSI) of Wi-Fi signals. A new undersampling algorithm is developed to address the imbalanced data problem associated with the OISVM, and a kernel function parameter selection algorithm is introduced for the training process. The time complexity of both the training process and t...
13 CitationsSource
Cited By0
Newest
The fingerprint indoor localization method based on channel state information (CSI) has gained widespread attention. However, this method fails to provide a better localization effect and higher localization accuracy due to poor fingerprint accuracy, unsatisfactory classification and matching effect, and vulnerability to environmental impacts. In order to solve the problem, this paper proposes a CSI fingerprint indoor localization method based on the Discrete Hopfield Neural Network (DHNN). The ...
Source
Dec 1, 2019 in GLOBECOM (Global Communications Conference)
#1Shing-Jiuan Liu (AS: Academia Sinica)
#1Shing-Jiuan Liu (UC Davis: University of California, Davis)H-Index: 1
Last. Feng-Tsun Chien (NCTU: National Chiao Tung University)H-Index: 7
view all 3 authors...
Device-free indoor localization is a key enabling technology for many Internet of Things (IoT) applications. Deep neural network (DNN)-based location estimators achieve high-precision localization performance by automatically learning discriminative features from noisy wireless signals without much human intervention. However, the inner workings of DNN are not transparent and not adequately understood especially in wireless localization applications. In this paper, we conduct visual analyses of ...
Source