Graduate Exam Abstract
Luoyang FangPh.D. Final
June 10, 2019, 10:00 am - 12:00 pm
ECE Conference Room C101B
Data Mining and Spatiotemporal Modeling in Mobile Big Data
Abstract: Modern mobile network technologies
and smartphones have successfully
penetrated nearly every aspect of
human life, due to the increasing
number of mobile applications and
services. Massive mobile data
generated by mobile networks,
including timestamp and location
information of users, have been
frequently collected. Mobile data
analytics has gained remarkable
attention from various research
communities and industries since it can
largely reveal the human
spatiotemporal mobility patterns from
the individual level to an aggregated
one. Upon previous preliminary exam,
the data mining of both the individual-
level and aggregate-level
spatiotemporal modeling will be
extended and discussed in this final
First, we discuss the scalability issue of
location privacy with respect to user re-
identifiability between two mobile
datasets merely based on their
spatiotemporal traces from the
perspective of a privacy adversary,
which is aimed to reduce the
computational complexity of the
proposed ensemble framework from
O(N^3) to sublinear. Next, we finalize
the aggregated spatiotemporal traffic
demand forecasting problem across
the entire mobile network and study a
novel demand forecasting application
in mobile networks, per-cell idle time
window (ITW) prediction, formulated
as a regression problem with an ITW
presence confidence index that
facilitates direct ITW detection and
estimation. To predict the ITW, a deep-
learning-based ITW prediction model is
proposed, consisting of a
representation learning network and an
output network. A novel temporal
graph convolutional network (TGCN)
implementing representation learning
network is also proposed to effectively
capture the graph-based
spatiotemporal input features.
Adviser: Liuqing Yang
Non-ECE Member: Haonan Wang, STAT
Member 3: J. Rockey Luo, ECE
Addional Members: Anura P Jayasumana, ECE
[B1] X. Cheng, L. Fang, L. Yang and S. Cui “Mobile Big Data”, Springer Cham, 2018 Print
[J1] J. Xiao, Z. Huang, L. Fang and L. Yang, “Hybrid Neural-Mahalanobis Metric Learning” IEEE Transactions on Neural Networks and Learning Systems (Submitted)
[J2] L. Fang, X. Cheng, H. Wang and L. Yang, “Idle Time Window Prediction in Cellular Networks via Deep Spatiotemporal Modeling” IEEE Journal on Selected Areas in Communications (Accepted)
[J3] L. Fang, R. Zhang, X. Cheng and L. Yang, “Content Similarity and Popularity Based Node Sharing via Cross-Object Coding in Distributed Storage Systems” (In Preparation)
[J4] L. Fang, H. Wang, X. Cheng and L. Yang, “Mobile Privacy: User Identification via Ensemble Matching on Spatiotemporal Features,” IEEE Transactions on Information Forensics and Security , (Submitted).
[J5] B. Hu, L. Fang, X. Cheng and L. Yang, “In-Vehicle Caching (IV-Cache) via Dynamic Distributed Storage Relay (D 2 SR) in Vehicular Networks” in IEEE Transaction on Vehicular Technology, (Accepted).
[J6] X. Cheng, L. Fang and L. Yang, "Mobile Big Data based Network Intelligence," in IEEE Internet of Things Journal (Accepted)
[J7] L. Fang, X. Cheng, L. Yang and H. Wang, “Location Privacy in Mobile Big Data: User Identifiability via Habitat Region Representation,” Journal of Communications and Information Networks, vol. 3, no. 3, pp. 31-38, Oct. 2018.
[J8] L. Fang, X. Cheng, H. Wang and L. Yang, “Mobile Demand Forecasting via Deep Graph-Sequence Spatiotemporal Modeling in Cellular Networks,” IEEE Internet of Things Journal vol. 5, no. 4, pp. 3091-3101, Aug. 2018.
[J9] X. Cheng, L. Fang, L. Yang and S. Cui, "Mobile Big Data: The Fuel for Data-Driven Wireless," IEEE Internet of Things Journal, vol. 4, no. 5, pp. 1489-1516, Oct. 2017.
[J10] L. Fang, R. Zhang, X. Cheng and L. Yang, “Cooperative Content Download-and-Share (CoCoDaS): Motivating D2D in Cellular Networks”, IEEE Communications Letters, vol. 21, no. 8, pp. 1831-1834, Aug. 2017.
[J11] R. Hou, L. Fang, Y. Chang, L. Yang and F. Wang “Named Data Networking over WDM-based Optical Networks,” IEEE Network, vol. 31, no. 3, pp. 70-79, May/June 2017.
[J12] X. Cheng, L. Fang, X. Hong and L. Yang, “Exploiting Mobile Big Data: Sources, Features, and Applications,” IEEE Network vol. 31, no. 1, pp. 72-79, January/February 2017.
[C1] B. Hu, L. Fang, X. Cheng and L. Yang, “Relay-and-Repair Based In-Vehicle Storage (R 2 IVS) System in Vehicular Networks”, in Proceedings of IEEE Global Communications Conference (GlobeCom), Abu Dhabi, UAE, Dec 9-13 2018.
[C2] B. Hu, L. Fang, X. Cheng and L. Yang, “Vehicle-to-Vehicle Distributed Storage in Vehicular Networks”, in Proceedings of IEEE International Conference on Communications (ICC), Kansas City, MO, May 20-24, 2018.
[C3] L. Fang, R. Zhang, X. Cheng and L. Yang, “Cross-Object Coding and Allocation (COCA) for Distributed Storage Systems”, in Proceeding of IEEE International Conference on Communications (ICC), Paris, France, May 21-25, 2017.
[C4] L. Fang, D. Duan and L. Yang, “Energy-Based Damping Evaluation for Exciter Control in Power Systems,” in Proceeding of IEEE Global Conference on Signal and Information Processing, Orlando, FL, December, 14-16, 2015.
[C5] L. Fang, D. Duan, L. Yang, and L. L. Scharf, “Error Floor Elimination for DFT-Based Frequency Estimators,” in Proceedings of 21st European Signal Processing Conference, Marrakech, Morocco, September 9-13, 2013.
[C6] L. Fang, R. Griffin, D. Duan and L. Yang, “A Joint Frequency and Phasor Estimation Algorithm Using DFT Samples for Power Systems”, in Proceedings of IEEE Green Technologies Conference, Denver, CO, April 4-5, 2013
[C7] L. Fang, D. Duan and L. Yang, “A New DFT-Based Frequency Estimator for Single-Tone Complex Sinusoidal Signals,” in Proceedings of IEEE Military Communications Conference, Orlando, FL, October 29-November 1, 2012.
Program of Study: