SE Current PhD Students

Waleed Aslam
Advisor: Roberto Tron

Mahroo Bahreinian
Advisor: Sean Andersson

Rui Chen
I work with Professor Cassandras in the CODES lab. My research interests lie in Control of Hybrid System and Perturbation Analysis.  In my recent project, I focus on developing hybrid models which use Infinitesimal Perturbation Analysis (IPA) to obtain gradient-based near optimal solutions of traffic light control. Consequently,  the traffic congestion can be reduced.  In addition to the project described above, I am also a member of robot team in the CODES lab and use robots to simulate real traffic system.
Advisor: Christos Cassandras

Ruidi Chen
I work with Professor Ioannis Paschalidis in the network and optimization lab. My research interests lie in the fields of data science and optimization. I am now working on two topics, one of which is outlier detection with its application on CT radiation overdose detection. We aim to develop a rigorous and automated procedure to identify all CT scans with an abnormally high exposure given the characteristics of the patient. The other topic is related to solving the bidding strategies for producers in the electricity market using an inverse equilibrium approach.
Advisor: Ioannis Paschalidis

Jessica Covington
Advisor: Sean Andersson

Aditya Gangrade
Advisor: Bobak Nazer

Kasra Ghasemi
Advisor: Sean Andersson

Iman Haghighi
I work in the Hybrid and Networked Systems (HyNeSs) lab with Calin Belta. My research interests lie in the fields of control theory and formal methods. Specifically, my current research focuses on using tools and ideas in machine learning, information theory, and control theory in order to learn formal formulae that are able to identify, quantify and ultimately synthesize patterns in distributed and networked systems. We study and develop formal spatial logics that are able to describe static patterns and spatiotemporal logics that deal with dynamic patterns. these logics are further utilized to synthesize system parameters that guarantee emergence of desired patterns. Applications include and are not limited to emergent behaviors in biological networks, patterns produced by swarms of robots, and smart city power management.
Advisor: Calin Belta

Majid Heidarifar
Advisor: Roberto Tron

Arian Houshmand
I work with Professor Cassandras in the CODES Lab. My research is focused on optimization and control of hybrid systems with the application to Smart Cities. My research is focused on optimal routing of vehicles in traffic networks. Primarily, we are interested in solving this problem for Plug-In Hybrid Electric Vehicles (PHEV), and the objective is to minimize the energy costs of traveling through the network. We use the Eastern Massachusetts traffic data set as the input to our models. We also use traffic simulator software such as SUMO to model the uncertainties in the system and to implement our routing algorithms to achieve the social optima.
Advisor: Christos Cassandras

Arman Karimian
Infinitesimal bearing rigidity is a favorable trait in frameworks, which has applications in localization or formation control. Whenever a node in the framework goes down for whatever reason or some of the links are lost, the graph becomes flexible and we loose rigidity. My research focuses on distributed or central algorithms for restoring bearing rigidity.
Advisor: Roberto Tron

Christy Lin
I work with Professor Prakash Ishwar in the Information and Data Sciences research group. I am interested in large-scale supervised and unsupervised learning and inference problems for graph-structured data. Graphs provide a canonical representation of relationships between a set of interacting entities. They are ubiquitous in the physical, chemical, biological, computational, and social sciences. I am currently developing new statistical and computational tools for discovering latent community structure in large real-world networks. My focus is on developing statistically and computationally efficient and scalable algorithms with mathematically provable performance guarantees based on mixed-membership latent variable models and node embeddings.
Advisor: Prakash Ishwar

Ye Lin
Advisor: Alex Olshevsky

Rui Liu
Advisor: Alex Olshevsky

Yufan Luo
My research interests are compressive sensing and its application in the atomic force microscopy (AFM). AFM is a powerful tool for exploring systems with nanometer-scale features. the data acquisition rate of a conventional AFM, however, is typically on the order of minutes, severely limiting the ability of AFM to study dynamics in systems My current work focuses on reducing AFM imaging time with non-raster scanning and accurate image reconstruction with compressive sensing theory.
Advisor: Sean Andersson

Noushin Mehdipour
Advisor: Roberto Tron

Trent Montgomery
I work as part of the Information and Data Sciences group (IDS) under Professor David Castañón. Our current work focuses on improving the performance of detection systems used to identify hazardous materials through analysis of CT scan images.  The practical application for this is in the field of security screening, where the definition of what is ‘hazardous’ may evolve rapidly.  As such, our goal is to develop image processing and classification algorithms that not only improve classification accuracy generally, but that can adjust to a wide variety of input conditions or parameters without any reworking of the core process.  This will allow for end-users to focus classification tasks to specific threats and to achieve better detection performance.
Advisor: David Castañón.

Feng Nan
I’m interested in supervised machine learning under budget constraint. As machine learning algorithms become increasingly pervasive in big data analytics, computation and feature acquisition costs begin to play critical roles in real life applications. My research focuses on designing efficient algorithms that reduce such costs. An application area is active sensing, where the aim is to balance classification accuracy and the cost of taking sensor measurements.
Advisor: Ioannis Paschalidis and Venkatesh Saligrama

Francisco Penedo Alvarez
My research is focused on using computer science tools, such as formal methods and machine learning, to analyze and control dynamical systems. Some of my current work involves solving path planning problems under nonlinear dynamics using satisfiability modulo theories methods, or learning signal temporal logic formulas that describe the behavior of a system from sampled trajectories. I am working in the Hybrid and Networked Systems lab under the direction of professor Calin Belta.
Advisor: Calin Belta

Athar Roshandelpoor
I work with Professor Ioannis Paschalidis in the Structural Bioinformatics Lab. My research is focused on Protein Docking. The ultimate goal of docking is the prediction of the three dimensional structure of the Protein-protein complexes. I am now working on using supervised and unsupervised learning algorithms on the Protein docking benchmarks. In particular, we are applying clustering and classification methods in order to improve the scoring functions used in the protein docking for different types of complexes.
Advisor: Ioannis Paschalidis

Mehrnoosh Sarmashghi
Advisor: Roberto Tron

Ali Siahkamari
I work with Professor Kulis. My general interest is making the programs more intelligent and moving toward a human-like AI. I work on continual learning, which is the ability of a machine to learn successively from data. Currently, if we are using a typical learning algorithm, we need to feed the training data all at once, or the algorithm forgets what it has previously learned. I am also working on kernel density estimation with sparse data.
Advisor: Brian Kulis

Adam Sonnenberg
My research aims to analyze the effectiveness of aerosolized medication delivery and improve on commonly used strategies. Particle deposition research is focused on the interplay between the fluid mechanics of the lung and the physics of particles moving in said flow. Often, to better understand biological systems, a simplified model is analyzed to gain insight into a more complex problem. This research proposes a strategy to efficiently move particle through a symmetric bifurcating structure.
Advisor:  Bela Suki

Artin Spiridonoff
I work with Professor Paschalidis and Professor Olshevsky. My research interests are optimization algorithms in general. Currently, I’m working on Distributed Private Optimization Algorithms, which are used when many agents want to collaboratively solve an optimization problem while protecting their private data. The goal is to develop algorithms with minimal restrictive assumptions and broad applicability at the same time with high accuracy and privacy.
Advisors:  Ioannis Paschalidis and Alex Olshevsky

Xinmiao Sun
I am working with Professor Cassandras in the CODES Lab and our research interests are coverage control and optimization problems. We seek to use distributed algorithms to control the deployment of sensor nodes to maximize the coverage quality in a mission cluttered with obstacles. Currently, we are focusing on finding efficient algorithms to escape a local optimum in the coverage control problem. We test our algorithm by java simulation now and will do it with real robots in the lab.
Advisor: Christos Cassandras

Rebecca Swaszek
I work in the CODES (Control of Discrete Event Systems) Laboratory under the supervision of Professor Christos Cassandras. My research is focused on the simulation and control of shared resource systems subject to temporal demand patterns. I am interested in urban shared vehicle systems, such as car or bike shares, and how fleet inventory may be managed to respond to the current and expected daily commuter demand.
Advisor: Christos Cassandras

Shuai Wang
I work in the Intelligent Mechatronics Lab with Professor John Baillieul on developing bio-inspired autonomous systems. We seek to develop new principles for perceptual-based control of autonomous air vehicles around complex and unstructured terrains based on studies of animal flight behavior. More specifically, we focus on understanding of the flight behavior of bats, especially how they navigate inside their habitat and how they integrate heterogeneous sensory information. the tools we are using are control theory, linear and non-linear optimization, stochastic process and digital signal processing.
Advisor: John Baillieul

Taiyao Wang
I am working with Professor Ioannis Paschalidis in the Network Optimization and Control Lab. My research interest focuses on improving the health care system using machine learning, statistics, and optimization methods. In the project “SURGERY”, we try to predict the 30-day hospital re-admissions after general surgery procedures using surgery data from Boston Medical Center. At the same time, we aim to identify vital factors that lead to the re-admissions, which allow us to provide to the medical community some interpretation of the outcomes of the classification models.
Advisor: Ioannis Paschalidis

Xiao Wang
I am working on exciting machine learning problems with Professor Peter Chin, who is the principal investigator of LISP lab in the department of Computer Science. My research interests lie in the areas of deep learning, reinforcement learning and control theory. And my recent works focus on generative models where I am trying to make the computer generate images with certain specifics through learning.
Advisor: Peter Chin

Yuping Wang
Advisor: David Starobinski

W. Ralahamilage Chelaka Bhagya Welikala

Advisor: Sean Andersson

Salomon Wollenstein Betech
Advisor: Sean Andersson

Wei Xiao
Advisor: Calin Belta

Liangxiao Xin
I work with Prof. David Starobinski in the NISLAB. My research interests are evaluation and analysis of collection protocols, data dissemination, and cybersecurity in wireless networks. My current research is to exploit the vulnerabilities of Wi-Fi networks.  Such vulnerabilities can be utilized by attackers to achieve a global denial of service attack, through an interference coupling phenomenon whereby collisions induced by a hidden node lead other hidden nodes to retransmit and congest the channel.
Advisor: David Starobinski

Tingting Xu
I am working with Professor Yannis Paschalidis in the Network Optimization and Control Lab. My research interests lie in the fields of optimization, machine learning and decision theory. Specifically, my study is to develop prediction models with machine learning and optimization techniques to assess hospitalization risk of patients, based on their electronic medical records. Currently, our work is to design a joint clustering and classification framework that discovers hidden patient groups while making predictions, which guarantees both prediction quality as well as the ability to interpret prediction results in the medical setting.
Advisor: Ioannis Paschalidis

Guang Yang
I work with Professor Calin Belta and Professor Roberto Tron in BU Robotics lab. I am particularly interested in multi-agents control in surveillance applications. By utilizing Formal Methods, the idea is to synthesize controller in a setting where groups of robots are deployed to monitor an environment over time, while satisfying a mission specification. I also build and work with quadcopters that are capable of doing demanding on-board computation for experiments.
Advisors: Calin Belta and Roberto Tron

Ziqi Yang
Advisor: Alex Olshevsky

Fatma Yanikara
I work with Dr. Caramanis on participation of flexible loads in ancillary energy services. the focus is given on electric vehicles, as they can be regarded as energy storage devices. Electric vehicles can contribute to power system reliability through providing regulation service reserves. While ensuring real time matching of demand and supply, provision of reserves gives the EV owners opportunity to make profit. However, provision of reserves leads to certain trade-offs regarding battery health, due to highly variable charging powers. Besides, batteries that power such vehicles exhibit highly nonlinear and complex behaviors that need to be incorporated in the decision model through mathematical approximations. To this end, we propose a model where charging schedule of EVs are optimized considering the trade-offs among energy cost, battery degradation, and utility from charging.
Advisor: Michael Caramanis

Jing Zhang
I am working with Professor Paschalidis. My research lies in two-fold. One is using applied probability, stochastic processes, and optimization theory to deal with modelling and algorithms development. In particular, currently we are working on a problem regarding an anomaly detection algorithm, which aims to improve the accuracy of the threshold needed by the generalized Hoeffding test. To outperform the existing methods (typically using the large deviations theory), we are trying to establish weak convergence results for certain quantities of interest. the other is using machine learning approaches to tackle health care problems, making predictions of the necessity of hospitalization for people in the US.
Advisor: Ioannis Paschalidis

Yue Zhang
I am working with Professor Christos Cassandras in the CODES Lab. Our research interests cover different areas related to Smart Cities. As an example, the “Street Bump” project is related to machine learning and is carried out in collaboration with the Mayor’s Office of New Urban Mechanics of the City of Boston. It aims to automatically identify roadway obstacles (referred to as “street bumps”) which need immediate repair based on data provided by the smartphone application ‘Street Bump’ developed by the City of Boston. Any driver simply has to turn on the ‘Street Bump’ app before starting a trip. During the trip, data are automatically uploaded as the phone’s accelerometer detects a “bump” and GPS records its location. Our work is focused on transforming these data into information used to train a classifier to differentiate among different bumps and identify those in need of most attention. Apart from this, I also started to do research on traffic light control, another problem related to Smart Cities, using perturbation analysis techniques from the theory of discrete event systems, and performing modeling and testing through the VISSIM simulation tool.
Advisor: Christos Cassandras

Nan Zhou
I am working with Professor Cassandras in the CODES Lab. Our research interests lie in dynamics system, optimal control, and perturbation analysis. My current project topic is detection and tracking of multiple dynamic targets with cooperating networked agents. In this project, I focus on developing mathematical models which use Infinitesimal Perturbation Analysis (IPA) to obtain gradient-based near optimal solutions of multi-agent scheduling. In practice, this result can be applied in target tracking, data collecting and persistent monitoring using multi-agent. In addition to the project described above, I am also a passionate fan of robotics, sensor network, and computer vision. I am currently responsible for building and maintaining the robot team in our CODES Lab.
Advisor: Christos Cassandras

Henghui Zhu
I work with Professor Ioannis Paschalidis in the Network Optimization and Control Lab. My research interests include reinforcement learning and neural networks. I am currently working on an interdisciplinary project on investigating the mechanisms of symbolic processes under both neocortical circuits models and engineering neural network models. We aim to develop and test new models that would explain brains’ mechanisms and validate or disprove some existing hypotheses. Also, our goals include developing some computational reinforcement learning models from neuroscience, which may shed some light on real-world engineering problems.
Advisor: Ioannis Paschalidis