Elahe Soltanaghaei

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]


11-2019: Invited to visit Texas Instrument Kilby Innovation Technology Center Dallas site. New!!
11-2019: Invited to visit Facebook's Data Center in Fort Worth, Texas, and discussions with the networking research team (link)New!!
10-2019: Won the Research Pitch Competition at 2019 EECS Rising Stars workshop.New!!
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: 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).



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.


Unaided Localization of WiFi Devices
Multipath Triangulation is a new localization technique that uses multipath reflections to localize a target device with a single receiver. In effect, it uses multiple reflections for triangulation similar to the way older systems use multiple devices, leading led to the design of the first decimeter-level unaided localization system. With this approach, any WiFi device can localize other nearby WiFi devices without requiring to perform any coordinated actions or even establishing a two-way communication. For example, a home automation system can localize controllers such as smart thermostats or smart plugs, even if neither the controller nor the home's access point support a localization protocol. Beside localizing a target device, Multipath Triangulation localizes the reflectors with respect to the receiver, which enables new solutions for indoor mapping by stitching static localized reflectors, or device-free localization by tracking reflections from the human body without requiring the person to hold or wear a wireless device.

Object Tracking using WiFi Tags
localizing battary-free objects requires a solution that works by simply attaching a tag to every object. This project exploits the frequency-agnostic property of RFID modulation to bring WiFi capabilities to battery-free RFID tags. So, by minor modification of off-the-shelf tags, they can backscatter WiFi waves alongside the RFID signal, which enables object tracking by using Multipath Triangulation for localization.

Safety-Critical Wireless Mobile Systems
The performance of autonomous cars or aerial drones can be greatly enhanced through wireless coordination. For example, vehicles can move around blind corners at high speed by leveraging the sensing capabilities of the cars ahead of them through wireless communications. However, mobility has traditionally been a challenge for wireless networks due to rapid fluctuation of the signal quality. State-of-the-art control systems handle this challenge by slowing down the vehicle to preserve safety. This project shows that we can by characterizing multipath propagation and using the wireless medium to sense the environment, we can assess the wireless quality and control the trajectory of the mobile agent to guarantee wireless connectivity while taking a safe efficient motion path. This work creates new methods to capture the deep interdependence between mobility, wireless, and safety, and allows mobile systems to realize the performance benefits of wireless coordination while preserving the ability to provide provable safety guarantees.

RF Sensing: Human Presence Detection Using WiFi Signals
Human presence sensing has significant potential to provide monetary and environmental benefits by saving energy. Recent advances in wireless techniques such as MIMO-OFDM technology have extended its use beyond simply a communication medium to that of a device-free human sensing tool. In this project, we leverage on the ubiquity of commodity WiFi devices. The presence of several WiFi-enabled devices or plug-in modules deployed in every room of a home creates a wireless mesh, which can serve as a sensor network and provides rich information about the environment. However, in indoor environments, WiFi signals suffer from rich multipath distortions, causing the signal disturbance produced by the target movements swamped in the noise distortion subspace. To address this challenge, we resolve multipath reflections and leverage each path as a new sensor rather than a distortion to increase both the spatial coverage and sensitivity of the sensing approaches.

Walkway Sensing: A New Sensing Principle for Home Occupancy Detection
Home automation systems can save a huge amount of energy by detecting home occupancy and sleep patterns to automatically control lights, HVAC, and water heating. However, the ability to achieve these benefits is limited by a lack of sensing technology that can reliably detect zone occupancy states. We present a new concept called Walkway Sensing based on the premise that motion sensors are more reliable in walkways than occupancy zones, such as hallways, foyers, and doorways, because people are always moving and always visible in walkways. We present a methodology for deploying motion sensors and a completely automated algorithm called WalkSense to infer zone occupancy states.

Path Scheduling Methods for Advance Reservation Systems
This project proposes new routing protocols for a new type of service called Boosting Inter-Domain Scheduled Dynamic Circuit Services (SDCS) on the Internet that offers delay and rate guarantees for data transfers (e.g., e-mail and Web access) and voice/video conferencing applications (e.g., Skype), which promises to impact a wide range of high-throughput applications like telepresence, telehealth and surgery, video-conferencing, distance-learning and remote haptics applications for the handicapped and the blind. This work advances the state-of-art in path scheduling and route selection by considering multiple call classes and allowing users to provide multiple start-time options in their requests for bandwidth in advance-reservation systems.

Botnet Detection Based on DNS Traffic Analysis
Botnets are networks build up of a large number of bot computers which provide the attacker with massive resources such as bandwidth, storage, and processing power. In turn allowing the attacker to launch massive attacks such as Distributed Denial of Service (DoS) attacks, or undertake spamming or phishing campaigns. One of the main approaches for botnet detection is based on monitoring and analysing DNS query/responses in the network, where botnets make their detection more difficult by employing techniques such as fast-fluxing. Moreover, the main challenge in detecting fast-flux botnets is their similar behaviour with that of legitimate networks, such as CDNs, using a round-robin DNS technique. In this project, we proposed a technique to detect botnet-infected hosts according to the similar DNS behaviour of several bots related to a botnet. Then using a Bayesian approach, the similar infected hosts will be grouped . In the second part, we use the sequential probability testing named SPRT (Sequential Probability Ratio Test) to improve the detection module and provide incremental data analysis.

Analysis of Occupational Accidents using Data mining
Accidents involving falls and falling objects are highly frequent accidents in the construction industry, while being hit by a vehicle, electric shock, collapse in the excavation and fire or explosion accidents are much less frequent, but they make up a considerable proportion of severe accidents. In this study, Large datasets containing occupational accident records in construction and mining industries were analysed using data mining methods such as decision tree, ensembles of decision tree and association rules methods. This analysis is aimed at extraction and characterization of high risk and high severity accidents leading to industrial safety improvement. In this project, the construction accidents of Iranian Social Security Organization (SSO) and the American mining accidents were analysed using classification and association rule methods.


University of Virginia (2014 - 2019)
Ph.D in Computer Science - Advisor: Prof. Kamin Whitehouse
Dissertation: Sensing the Physical World using Pervasive Wireless Infrastructure.

Sharif University of Technology (2011-2013)
M.S. in Computer Engineering - Advisor: Prof. Mehdi Kharrazi
Thesis: Botnet C&C Channel Detection based on DNS Traffic Analysis.

Amirkabir University of Technology (2009-2013)
B.S. in Information Technology Engineering - Advisor: Prof. Babak Sadeghyan
Thesis: Botnet Detection based on Sequential Probability Ratio Test (SPRT).

Amirkabir University of Technology (2007-2011)
B.S. in Computer (Software) Engineering - Advisor: Prof. Babak Sadeghyan
Thesis: Privacy Preserving network-based intrusion detection system.


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