Effectiveness of Data Augmentation in Cellular-based Localization Using Deep Learning

Recently, deep learning-based positioning systems have gained attention due to their higher performance relative to traditional methods. However, obtaining the expected performance of deep learning-based systems requires large amounts of data to train model. Obtaining this data is usually a tedious process which hinders the utilization of such deep learning approaches. In this paper, we introduce a number of techniques for addressing the data collection problem for deep learning-based cellular localization systems. The basic idea is to generate synthetic data that reflects the typical pattern of the wireless data as observed from a small collected dataset. Evaluation of the proposed data augmentation techniques using different Android phones in a cellular localization case study shows that we can enhance the performance of the localization systems in both indoor and outdoor scenarios by 157% and 50.5%, respectively. This highlights the promise of the proposed techniques for enabling deep learning-based localization systems.

[1]  Moustafa Youssef,et al.  The Horus WLAN location determination system , 2005, MobiSys '05.

[2]  Hirozumi Yamaguchi,et al.  TransitLabel: A Crowd-Sensing System for Automatic Labeling of Transit Stations Semantics , 2016, MobiSys.

[3]  Moustafa Youssef,et al.  It's the Human that Matters: Accurate User Orientation Estimation for Mobile Computing Applications , 2014, MobiQuitous.

[4]  Eyal de Lara,et al.  GSM indoor localization , 2007, Pervasive Mob. Comput..

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[6]  Moustafa Youssef,et al.  Dejavu: an accurate energy-efficient outdoor localization system , 2013, SIGSPATIAL/GIS.

[7]  Moustafa Youssef,et al.  CellinDeep: Robust and Accurate Cellular-Based Indoor Localization via Deep Learning , 2019, IEEE Sensors Journal.

[8]  Moustafa Youssef,et al.  MonoPHY: Mono-stream-based device-free WLAN localization via physical layer information , 2013, 2013 IEEE Wireless Communications and Networking Conference (WCNC).

[9]  Shiwen Mao,et al.  DeepFi: Deep learning for indoor fingerprinting using channel state information , 2015, 2015 IEEE Wireless Communications and Networking Conference (WCNC).

[10]  Moustafa Youssef,et al.  UPTIME: Ubiquitous pedestrian tracking using mobile phones , 2012, 2012 IEEE Wireless Communications and Networking Conference (WCNC).

[11]  Moustafa Youssef,et al.  The Tale of Two Localization Technologies: Enabling Accurate Low-Overhead WiFi-based Localization for Low-end Phones , 2017, SIGSPATIAL/GIS.

[12]  Mohamed Ibrahim,et al.  A Hidden Markov Model for Localization Using Low-End GSM Cell Phones , 2011, 2011 IEEE International Conference on Communications (ICC).

[13]  Thomas Grill,et al.  Exploring Data Augmentation for Improved Singing Voice Detection with Neural Networks , 2015, ISMIR.

[14]  Moustafa Youssef,et al.  A Robust Zero-Calibration RF-Based Localization System for Realistic Environments , 2016, 2016 13th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).

[15]  Amany Sarhan,et al.  A hybrid outlier detection algorithm based on partitioning clustering and density measures , 2015, 2015 Tenth International Conference on Computer Engineering & Systems (ICCES).

[16]  Moustafa Youssef,et al.  Small-scale compensation for WLAN location determination systems , 2003, 2003 IEEE Wireless Communications and Networking, 2003. WCNC 2003..

[17]  Moustafa Youssef,et al.  Multivariate analysis for probabilistic WLAN location determination systems , 2005, The Second Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services.

[18]  Moustafa Youssef,et al.  TrueStory: Accurate and Robust RF-Based Floor Estimation for Challenging Indoor Environments , 2018, IEEE Sensors Journal.

[19]  Moustafa Youssef,et al.  LaneQuest: An accurate and energy-efficient lane detection system , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[20]  Mohamed Ibrahim,et al.  CellSense: An Accurate Energy-Efficient GSM Positioning System , 2011, IEEE Transactions on Vehicular Technology.

[21]  Moustafa Youssef,et al.  Increasing Coverage of Indoor Localization Systems for EEE112 Support , 2019 .

[22]  Moustafa Youssef,et al.  Robust WLAN Device-free Passive motion detection , 2012, 2012 IEEE Wireless Communications and Networking Conference (WCNC).

[23]  Mohamed Ibrahim,et al.  CellSense: A Probabilistic RSSI-Based GSM Positioning System , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[24]  Moustafa Youssef,et al.  Crescendo: An Infrastructure-free Ubiquitous Cellular Network-based Localization System , 2019, 2019 IEEE Wireless Communications and Networking Conference (WCNC).

[25]  Moustafa Youssef,et al.  WLAN location determination via clustering and probability distributions , 2003, Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003)..

[26]  Moustafa Youssef,et al.  CrowdInside: automatic construction of indoor floorplans , 2012, SIGSPATIAL/GIS.

[27]  Moustafa Youssef,et al.  WiDeep: WiFi-based Accurate and Robust Indoor Localization System using Deep Learning , 2019, 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom.

[28]  Moustafa Youssef,et al.  Continuous space estimation for WLAN location determination systems , 2004, Proceedings. 13th International Conference on Computer Communications and Networks (IEEE Cat. No.04EX969).

[29]  Mustafa ElNainay,et al.  CNN based Indoor Localization using RSS Time-Series , 2018, 2018 IEEE Symposium on Computers and Communications (ISCC).

[30]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[31]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[32]  James M. Joyce.  Kullback-Leibler Divergence , 2011, International Encyclopedia of Statistical Science.

[33]  Heba Aly,et al.  Map++: A Crowd-sensing System for Automatic Map Semantics Identification , 2014, SECON.

[34]  Bruce Denby,et al.  Robust indoor localization and tracking using GSM fingerprints , 2015, EURASIP J. Wirel. Commun. Netw..

[35]  Moustafa Youssef,et al.  SemanticSLAM: Using Environment Landmarks for Unsupervised Indoor Localization , 2016, IEEE Transactions on Mobile Computing.

[36]  Moustafa Youssef,et al.  CheckInside: a fine-grained indoor location-based social network , 2014, UbiComp.

[37]  Moustafa Youssef,et al.  DeepLoc: a ubiquitous accurate and low-overhead outdoor cellular localization system , 2018, SIGSPATIAL/GIS.

[38]  Ashok K. Agrawala,et al.  LOCATION-CLUSTERING TECHNIQUES FOR WLAN LOCATION DETERMINATION SYSTEMS , 2006 .

[39]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.