2017, Scholarship Recipient to attend Grace Hopper Celebration (GHC).
2017, received best poster award in MobiSys Women's workshop.
2017, awarded NSF travel grant to attend MobiSys'17.
2017, received UVA Department of Computer Science Graduate Student Awards for Outstanding Service.
2017, 2nd place, Three Minute Thesis (3MT) competition at UVa.
2017, Scholarship Recipient to attend CRA-W Grad Cohort Workshop.
2016, received best presentation award in BuildSys'16.
2016, Awarded student travel grant to attend Sensys/Buildsys’16.
2016, Awarded N2-Women Young Researcher Fellowship to attend MobiCom’16.
2015, Scholarship Recipient to attend CRA-W Grad Cohort Workshop.
2011, Awarded distinguished BSc student award with honorary acceptance for the MSc program.
2011, 2nd place, B.S. in Information Technology Engineering, Amirkabir University of Technology.
2010, 2nd place, among 90 Computer Engineering B.S. students, Amirkabir University of Technology.
2007, Ranked 516th, Nationwide Universities Entrance Exam among over 450,000 participants.
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 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.