Research
Ongoing Projects
Computer Aided Diagnosis from Medical Images
Dr. Reza Rawassizadeh, Dr. Guanglan Zhang, Dr. Lou Chitkushev
With the assistance of biologists and physicians, we develop algorithms to assist physicians in analyzing medical images and extracting relevant information. Most of our work focused on image analysis, including computed tomography (CT scans), MRI and histopathology images. Some of our work such as CovidCTNet has published and won awards as well.
Data Science/Machine Learning
Dr. Eugene Pinsky
A collaborative project in data science/machine learning with the Center for Neural Imaging (CNI) at Brigham and Women’s Hospital. The project focus is on analysis of images for Multiple Sclerosis (MS) patients and on building classifiers to automatically predict and classify different stages of the disease.
Health Informatics
Dr. Guanglan Zhang, Dr. Lou Chitkushev
The Health Informatics Research Lab (HILab) contributes to the improvement of healthcare by pursuing research and development in health informatics, bioinformatics, and clinical research. Our work involves standardization and cataloging of medical algorithms, development of classification algorithms for bioinformatics, and implementation of knowledge-based systems for biomedicine.
Cybersecurity
Dr. Yuting Zhang, Dr. Shengzhi Zhang, Dr. Tanya Zlateva, Dr. Lou Chitkushev
The BUMET CyberSec Lab studies various aspects of cybersecurity, including mobile security, forensics, AI security, IoT security etc. Our lab supports both education and research in cybersecurity by engaging the faculty and students in the research projects and by the provision of educational and research resources.
On-Device Machine Learning
Dr. Reza Rawassizadeh
Due to emergence of extremely complex machine learning algorithms such as deep learning, their execution requires a complex computational infrastructure. On the other hand, there is a continuous trend of computer device miniaturization. In this project, students are developing resource efficient machine learning and information retrieval algorithms that perform clustering, classification, indexing and search on small battery-powered devices, such as wearables (smartwatches), without any connection to the cloud or edge devices.
Revolutionizing Flow, Heat and Dispersion Predictions over Complex Urban Environments
Dr. Dan Li (CAS), Dr. Kia Teymourian
Research in conjunction with Hariri Institute. As more and more of the population lives in the city, it is more and more challenging to understand and make predictions of heat transfer and dispersion of air pollutants over urban environments. The team will use and develop the machine learning models to execute the project. It is less computationally expensive and much faster, and may better capture the small-scale variabilities. The new model could help to identify key locations for sensor deployment. The investigators aim to submit full-blown proposals to the Army Research Office at the Department of Defense and/or the Environmental Sustainability Program at the National Science Foundation.
Software Development
Dr. Eric Braude
Multiple ongoing projects including using neural nets for post-failover system operation, PREXEL: Rapid UML class modeling for agile development, GEOPAR: Automatically creating and proving theorems in 2-dimensional geometry and new methods for large, real-world UML class models.
Computer Science & Education in Computer Science Conference (CSECS) Boston University Metropolitan College is a sponsor of CSECS and hosts the conference every three years in Boston, MA. The next conference will be hosted in 2021. The conference features papers in a wide range of Computer Science research areas ranging from Software Engineering to Information Systems Security are considered for presentation and publication in the conference proceedings. Computer Science Education topics range from introduction and evaluation of computing programs, curricula, and online courses, to syllabus, laboratories, teaching, and pedagogy.
Faculty & Student Publications
-
A bi-directional adversarial explainability for decision support
Abstract: In this paper we present an approach to creating Bi-directional Decision Support System (DSS) as an intermediary between an expert... Read more »
-
Live Processing of a Distributed Camera Network
Abstract: The shark crisis in the island of La Reunion requires innovative measures to secure sensible surfing and recreation shores. The CRA research... Read more »
-
Generalizing Morley’s and Other Theorems with Automated Realization | SpringerLink
A new approach is shown that mechanically proves various theorems in plane geometry by recasting them in terms of constraint... Read more »
-
Protein responsible for leukemia’s aggressiveness identified — ScienceDaily
Researchers have identified a protein critical for the aggressiveness of T-cell leukemia, a subtype of leukemia that afflicts children and... Read more »
-
Identification and characterization of HLA-A24-specific XBP1, CD138 (Syndecan-1) and CS1 (SLAMF7) peptides inducing antigens-specific memory cytotoxic T lymphocytes targeting multiple myeloma | Leukemia
X-box binding protein 1 (XBP1), CD138 (Syndecan-1) and CS1 (SLAMF7) are highly expressed antigens in cancers including multiple myeloma (MM). Read more »
-
How Distributed is Distributed Management or Can Too Many Cooks Spoil the Broth? by John Day | Pouzin society
The need for network management has always been recognized. At the same time, it recognized as overhead to selling equipment... Read more »
-
Applying Data Mining Techniques Over Big Data
Source: Applying Data Mining Techniques Over Big Data With rapid development of information technology, data flows in different variety of formats... Read more »
-
Factorization in the Cloud: Integer Factorization Using F# and Windows Azure
Source: Factorization in the Cloud: Integer Factorization Using F# and Windows Azure Implementations are presented of two common algorithms for integer... Read more »
-
CK2 inhibitor CX-4945 destabilizes NOTCH1 and synergizes with JQ1 against human T-acute lymphoblastic leukemic cells.
T-cell acute lymphoblastic leukemia (T-ALL) is an aggressive cancer of developing thymocytes, and remains fatal in 20% of pediatric and... Read more »
-
HPVdb: a data mining system for knowledge discovery in human papillomavirus with applications in T cell immunology and vaccinology
High-risk human papillomaviruses (HPVs) are the causes of many cancers, including cervical, anal, vulvar, vaginal, penile and oropharyngeal. To facilitate... Read more »
-
Data analytics based positioning of health informatics programs
The Master of Science in Computer Information Systems (CIS) with concentration in Health Informatics (HI) at Metropolitan College (MET), Boston... Read more »
-
Big data analytics in immunology: a knowledge-based approach
With the vast amount of immunological data available, immunology research is entering the big data era. These data vary in... Read more »
Master’s Thesis Publications
-
Patterns in network security: an analysis of architectural complexity in securing recursive inter-network architecture networks
Recursive Inter-Network Architecture (RINA) networks have a shorter protocol stack than the current architecture (the Internet) and rely instead upon... Read more »
-
Security analysis of finance and healthcare android applications
Android is a major mobile operating system pre-installed and shipped with more than 60% of smart-phones in the market. The... Read more »
-
Applying data mining techniques over big data
Source: Applying data mining techniques over big data The rapid development of information technology in recent decades means that data appear... Read more »
-
DR BACA: dynamic role based access control for Android
Source: DR BACA: dynamic role based access control for Android Android, as an open platform, dominates the booming mobile market. However, Read more »
-
Elliptic curve cryptography, zero-knowledge proof, and Lamport’s hash chain in a distributed authentication system
This paper proposes a novel distributed authentication system that uses robust alternatives in cryptographic algorithms to grant a third-party access... Read more »
-
Android application evolution and malware detection
Android has dominated the mobile market for a few years now, and continues to increase its market share. Meanwhile, Android... Read more »
-
Building an application for the writing process
Source: Building an application for the writing process The idea that writing is a process and not a product is now... Read more »
-
A clinical decision support system for the treatment of common toxin overdose
Source: A clinical decision support system for the treatment of common toxin overdose Poisonings account for 0.8% of emergency room visits... Read more »