Elahé Soltanaghai

I am a postdoctoral researcher at Carnegie Mellon University in the Wireless, Sensing and Embedded Systems (WiSE) lab working with Anthony Rowe. I received my PhD in computer science from the University of Virginia in 2019 working with my advisor Kamin Whitehouse. I also received my M.S. in computer engineering from Sharif University of Technology in 2013.

My research interests span the areas of cyber-physical systems, wireless sensing, Internet of Things, and computer networking. I create the next generation of intelligent wireless systems that are faster, lower power, pervasive, and can even sense the physical environment. You can learn more about my Ph.D research here.

[CV] [LinkedIn] [Google Scholar]

I will be joining University of Illinois - Urbana Champaign as an assistant professor of Computer Science in Fall 2021.
Prospective students: feel free to reach out to me!


03-2021: Serving at MobiCom 2021 as N2Women Co-Chair.New!!
02-2021: Our MobiCom paper is available at this link, introducing an RF retro-reflective marker for immersive machine perception. New!!
01-2021: Our paper on WiFi backscatter localization is accepted in IMWUT-UbiComp 2021 .
11-2020: Our mmWave Retro-reflector paper is accepted at Mobicom 2021 .
10-2020: Our paper on On-device WiFi Human Sensing with Domain Adaptive Models is accepted at BuildSys 2020.
10-2020: Invited to give a talk at SRC-CONIX annual event on emerging application os millimeter-wave wireless systems.
06-2020: Presented our research on MMWave Backscattering at SRC e-workshop .
06-2020: Received the ACM SIGMOBILE Doctoral Dissertation Award runner-up.
11-2019: Invited to visit Texas Instrument Kilby Innovation Technology Center Dallas site.
11-2019: Invited to visit Facebook's Data Center in Fort Worth, Texas, and discussions with the networking research team (link)
10-2019: Won the Research Pitch Competition at 2019 EECS Rising Stars workshop.
09-2019: Successfully defended my PhD on "Sensing the Physical World by Using Pervasive Wireless Infrastructure".
08-2019: Selected as 2019 EECS Rising Stars, which will be held at the University of Illinois at Urbana-Champaign in October.
07-2019: Our poster on "Characterizing Uncertainties of Wireless Channels in Connected Vehicles" is accepted for presentation in MobiCom, 2019.
05-2019: Invited to give a talk at ETH Zurich on sensing the physical world with pervasive wireless infrastructure.
05-2019: MonoLoco's source code is publicly available at this link for any researcher to use.
02-2019: I'm co-chairing ACM S3 workshop 2019 that will be hold in conjunction with ACM MobiCom 2019.
01-2019: Our poster titled "Object Tracking with Battery-free WiFi-RFID Tags" is accepted for presentation in NSDI, 2019 in Boston.
12-2018: Our paper on "Doorpler: A Radar-based System for Low Power, Real-time Zone Occupancy Sensing" is accepted to RTAS, 2019.
02-2019: I'm serving on the organizing committee of the Bosch Device-Free Localization Competition that will be hold at CPS-IoT week.
10-2018: Served as the Technical Program Committee member in ACM 2018 S3 Workshop (co-located with MobiCom'18).
09-2018: Completed my research internship at Microsoft Research, Redmond, working with Dr. Bodhi Priyantha.
08-2018: Presented our research on "Single-shot Tag Localization" at Microsoft's Immersion day.
02-2018: MonoLoco's paper is accepted to ACM MobiSys 2018.
02-2018: Served as expert panelist for the energy-efficient homes competition at Charlottesville High School.
10-2017: Served as scribe in the NSF visioning workshop on extreme networking (co-located with MobiCom'17).
10-2017: Won second place in ACM Student Research Competition (SRC) at MobiCom'17.
09-2017: Walkway Sensing's paper is accepted to Applied Energy (impact factor=7.9)..
06-2017: Forma Track's paper is accepted to UbiComp'17 .
06-2017: Won best poster award in Women's workshop at MobiSys'17.
05-2017: Peripheral WiFi Vision's paper is accepted to WPA'17 .
05-2017: Received CS Graduate Student Award for Outstanding Service at UVa.
04-2017: Successfully proposed my Ph.D dissertation titled "Wireless Multipath: From a Challenge to an Opportunity for Sensing and Localization".
03-2017: Won 2nd place in Three Minute Thesis competition (3MT) at UVa.
02-2017: Received Microsoft Scholarship to attend Grace Hopper Celebration (GHC).


Millimetro: mmWave Retro-Reflective Tags for Accurate, Long Range Localization
E. Soltanaghaei, A. Prabhakara, A. Balanuta, M. Anderson, J. Rabaey, S. Kumar, A. Rowe
27th Annual International Conference on Mobile Computing and networking (MobiCom), 2021. [Paper]

TagFi: Locating Ultra-Low Power WiFi Tags Using Unmodified WiFi Infrastructure
E. Soltanaghaei, A. Dongare, A. Prabhakara, S. Kumar, A. Rowe, K. Whitehouse
ACM Proceedings on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp), 2021. [Paper] [Demo]

Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model
E. Soltanaghaei, R. Sharma, Z. Wang, A. Chittilappilly, A. Luong, E. Giler, K. Hall, S. Elias, and A. Rowe
7th Annual International Conference on Systems for Energy-Efficient Built Environments (BuildSys), 2020. [Paper] [Presentation] [Teaser]

Characterizing Uncertainties of Wireless Channels in Connected Vehicles
E. Soltanaghaei, M. Elnaggar, K. Kleeman, K. Whitehouse, C. Fleming
25th Annual International Conference on Mobile Computing and Networking (MobiCom), 2019. [Paper]

Doorpler : a radar-based system for low power, real-time zone occupancy sensing
A. Kalyanaraman, E. Soltanaghaei, K. Whitehouse
25th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2019. [Paper]

Multipath Triangulation: Decimeter-level WiFi Localization and Orientation with a Single Unaided Receiver
E. Soltanaghaei, A. Kalyanaraman, K. Whitehouse
16th international conference on mobile systems, application, and services (MobiSys), 2018. [Paper] [Presentation] [Code]

Forma Track: Tracking People based on Body Shape
A. Kalyanaraman, D. Hong, E. Soltanaghaei, K. Whitehouse.
The ACM international joint conference on pervasive and ubiquitous computing (UbiComp), 2017. [Paper]

Practical occupancy detection for programmable and smart thermostats
E. Soltanaghaei, K. Whitehouse
Elsevier Journal of Applied Energy, 2017. [Paper]

Improving Multipath Resolution Using MIMO Smoothing: Poster (2nd place winner of ACM Student Research Competition)
E. Soltanaghaei, A. Kalyanaraman, K. Whitehouse
The 23rd Annual International Conference on Mobile Computing and Networking (MobiCom), 2017. [Paper]

Peripheral WiFi Vision: Exploiting Multipath Reflections for More Sensitive Human Sensing
E. Soltanaghaei, A. Kalyanaraman, K. Whitehouse
4th Workshop on Physical Analytics (WPA), 2017. [Paper] [Data]

Occupancy State Detection using WiFi Signals: Poster (Best Poster Award in MobiSys Women's Workshop)
E. Soltanaghaei, A. Kalyanaraman, K. Whitehouse
15th international conference on mobile systems, application, and services (MobiSys), 2017. [Paper]

WalkSense: Classifying Home Occupancy States Using Walkway Sensing (Best Presentation Award)
E. Soltanaghaei, K. Whitehouse
3rd ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys'16). [Paper] [PPT] [Data]

Multi-Option, Multi-Class Path Scheduling Methods for Advance Reservation Systems
E. Soltanaghaei, M. Veeraraghavan
16th International conference on High Performance Switching and Routing (HPSR'15). [Paper]

Detection of Fast-Flux Botnets Based on DNS Analysis
E. Soltanaghaei, M. Kharrazi
International Journal of Science and Technology (Scientia Iranica'14). [Paper]

Pattern Extraction for High-Risk Accidents in the Construction Industry: A Data Mining Approach
M. Amiri, A. Ardeshir, E. Soltanaghaei
International Journal of Injury Control and Safety Promotion, 2014. [Paper]

Analysis of high risk occupational accidents in construction industry using data mining methods
M. Amiri, A. Ardeshir, E. Soltanaghaei
Journal of Iranian occupational health, Tehran university of medical sciences, 2013 [in Persian]. [Paper]

Multipath Triangulation: Decimeter-level WiFi localization and orientation estimation with a single access point
E. Soltanaghaei, K. Whitehouse
U.S. Patent Application 62/628,526, filed February 2018. Patent Pending.

Active Projects

Millimeter-wave Retro-reflectors
Vehicles need to quickly and accurately localize lane markers, road signs and other roadside infrastructure overlong distances. Even as today’s autonomous driving technology relies primarily on both visual sensing systems (e.g. cameras, LIDARs) and visual road-side infrastructure, such systems are vulnerable to obstructions such as dirt or debris and weather events such as rain and fog.This project shows how wireless reflections can enable an RF-equivalent of optical retro-reflectors in the millimeter-wave frequency range, enabling identification and localization of roadside infrastructure such as digital lane markers and road signs, even if obscured from the view, where visual sensing fails.

WiFi backscatter Tags for Object Localization
This project presents a WiFi-based localization system that can identify and locate “things” that do not have a WiFi radio or are not even powered, using commodity WiFi devices such as smart phones and laptops. RFID technology enables low-cost battery-free tags, however, the cost and complexity of covering a space with RFID infrastructure limit its practical adoption. We develop a WiFi tag that is ultra-low power and passively reflects ongoing WiFi packets, while piggybacking a code using simple modulation techniques.

Human Detection Using WiFi Signals
The ubiquity of WiFi devices combined with the ability to cover large areas, pass through walls makes WiFi signals an ideal medium for sensing occupancy. Existing WiFi sensing solutions have not been rigorously tested outside of lab environments and don't often consider real-world constraints associated with non-expert installers, cost-effective platforms and long-term changes in the environment. This project presents a user-in-the-loop self-tuning framework for WiFi-based human presence detection with on-device learning and domain adaption capabilities that operates entirely on an embedded platform.

Multi-User Augmented Reality with Collaborative Localization
Multi-user Augmented Reality (AR) could someday empower first responders with the ability to see team members around corners and through walls. For this vision of people tracking in dynamic environments to be practical, we need a localization system that is nearly instantly available across wide-areas without existing infrastructure or complex setup. In this project, we present an infrastructure-free 6-degrees-of-freedom (6DOF) localization system for AR applications that uses motion estimates and UWB range measurements between users to establish an accurate relative coordinate system.

Identifying and Locating Hidden IoT Devices in Untrusted Environments
Hidden IoT devices are increasingly used to snoop on users in hotel rooms or AirBnBs. We envision empowering users entering such an unfamiliar environment to identify and locate diverse set of IoT devices hidden behind plants or in corners using only their personal handhelds. This project presents an ML-based systematic framework for identifying a broad spectrum of IoT devices using only coarse-grained wireless layer features and locating the identified IoT devices with respect to the user using only phone sensors and wireless signal strength measurements.


Personal Interests

Aside from research, I love to do photography, gardening, cooking, and solving jigsaw puzzles!


2204 collaborative innovation center
4720 Forbes Ave
Pittsburgh, PA, 15213