Mohamed Ghalwash is an Associate Professor of Computer Science at Ain Shams University.
Ghalwash is interested in developing machine learning and AI models for discovery of interpretable spatio-temporal patterns from complex events and exploiting their utilities in practical high impact real-world applications, focusing on analytics for healthcare, health behavior, decision support, and to support the generation of real world evidence from medical data, wearable devices and instrumented environments. He also has more than ten years of expertise in the software engineering industry, developing software that are currently being deployed, where he engaged in all phases of the project life cycle for the development of large business applications.
My long-term goal is to put my footprints in the field of pattern recognition through contribution of original ideas and translating those ideas to end applications and products.
PhD in Computer Science, 2009-2013
Temple University, USA
BSc in Pure Mathematics and Computer Science, 1994-1998
Ain Shams University, Egypt
Synergetic Activities to the Research Community
Undergraduate and graduate courses I taught
COMP 104
COMP 303
COMP 304
COMP 402
COMP 603
COMP 612
Technical and Academic Positions
Courses:
Dissertation: “Interpretable Early Classification of Multivariate Time Series”, August 2013.
Allied Soft was created in direct response to provide, effectively and professionally, comprehensive services and support in the field of Information Technology.
List of projects either related to research (mainly in academia or in IBM research center) or in software industry
Develop and test patient and disease representations for clinical models. Jointly learning embedding for different domains and further fine tuning or enhancing embeddings for some domains when limited amounts of data is available present significant AI challenges that will force us to produce methodological innovations. We build a comprehensive library for representation learning methods and develop novel methods to address these presented issues. These representation algorithms will be assessed based on their sensitivity to data characteristics including fairness.
Role I technically lead the task force for patient representation for developing novel fair AI models.
IBM Research. Oct 2020 - Present .
Develop novel computational disease models that could be used to identify factors that impact the rapid/slow progression of Type 1 Diabetes (“T1D”) in infants and young children who are genetically pre-disposed and may be pre-symptomatic clinically. Such methodologies and models may
(1) incorporate heterogeneous features coming from multiple sites and assessments covering multiple aspects of T1D.
(2) leverage diverse data sets to accommodate noise and uncertainty in study data.
(3) provide comprehensive view of risk factors that impact the onset of T1D in different time horizons.
Role I lead the efforts of developing AI models for disease progression modeling, which lead to publications in high-impact journals such as Lancet D&E (IF 45), Lancet C&A (IF 38), Diabetes Care (IF 19), etc.
IBM Research. May 2017 - May 2022 .
This work is focused on identifying correlates of individual pain, defining objective pain metrics, and determining changes to the device parameters that provide the user with the greatest impression of relief. A number of data streams will be studied to identify pain correlates from physiological signals, environmental stresses, and individual behavioral responses. These correlates will be used to identify pain metrics, understand the individual patient’s pain experience and how the device parameters can be changed to optimize the sense of change in a manner that is adaptive to the varying needs of the patient.
Role I am the technical leader for developing AI algorithms to define and build an objective pain metric and identifies pain correlates.
IBM Research. Oct 2016 - Oct 2019.
Integrating context, domain knowledge, and data-driven modeling of complex phenomena based on observations that are highly structured and interdependent is a very challenging task. In this project we address this problem by using the structured predictive modeling framework based on a probabilistic exponential graphical model instead of relying on traditional statistical approaches that assume independent and identically distributed random variables. Current state-of-the-art predictive modeling techniques usually cannot deal with such large and complex networks; thus we provide knowledge-based compression techniques for complexity reduction. We use multiple kinds of domain knowledge and context to capture additional information that might be missing from the observed data. We also directly constrain the model optimization based on domain constraints and embed other problem-specific qualitative knowledge directly into the framework. The main innovation of this project is extending our structured learning models to explore in detail the hypothesis that a unified approach of integrating big data with sources of high-level knowledge (ontologies, domain-based constraints etc.) is beneficial for predictive modeling of complex phenomena.
Role I have developed predictive models for BIG temporal graphs, which resulted in publications in IEEE Big Data conference.
Temple University. ONR (N00014-15-1-2729). Jun 2015 - May 2016 .
The analysis of social networks often assumes a time invariant scenario, while in practice actor attributes and links in such networks evolve over time and are inextricably dependent on each other. In addition, the temporal graph is just partially observed, multiple kinds of links exist among actors, various actors have different temporal dynamics and environmental influence can be both positive and negative. This project is closely examining the hypothesis that a unified approach of jointly modeling these and related problems is beneficial for prospective analysis of large-scale partially observed temporal hypergraphs. Novel methods for analyzing large and evolving graphs developed on the project are evaluated on high impact applications related to predictive modeling of information networks, climate and human health.
Role I have mentored students and participated in developing predictive models for temporal graphs, which resulted in publications in top-tier AI conferences such as AAAI.
Temple University. DARPA (AFOSR award number FA 9550-12-1-0406). Aug 2012 - Jul 2016 .
This project develops and validates effective predictive modeling technology to achieve the following sepsis treatment related aims on high dimensional and noisy data at a clinically relevant scale
AIM 1 - Personalized sepsis therapy optimization for an individual patient’s state improvement.
AIM 2 - Early diagnosis of sepsis and accurate detection of change in the state of sepsis., and
AIM 3 - Gene expression analysis for sepsis biomarkers identification.
Role I was leading the first and second aims where I developed novel ideas for early detection of sepsis, which resulted in publication in high prestigious conferences such as KDD and SDM.
Temple University. DARPA (DARPA-N66001-11-1-4183). Aug 2011 - Aug 2015 .
Role Technical Team Lead.
Technologies/Tools J2EE, OracleDB10g, WebShpere Rational Developer.
Description Vodafone Egypt (VFE) has established agreements with indirect sales business partners (Agents) and 3rd party (Exclusive Dealers, Trade Key Accounts and Dealers) all over Egypt to address all country markets to ensure Vodafone projects and services availability nationwide. Vodafone Egypt sells its products to agents; agents in turn sell Vodafone products to exclusive dealers and dealers who eventually sell to end customers. The current number of agents is 7 with around 50 branches; the number of exclusive dealers is around 150 shops and the number of main normal dealers is around 7000. Vodafone Distribution Department would like to track VFE products’ sales movement performed by distribution channels in order to produce accurate incentive calculations and to be able to generate and view analytical reports on dealers’ sales patterns in order to study the market behavior versus various parameters (e.g. time, cities, zones, etc…). This project affects VFE, Agents, Trade Key Accounts, dealers and end customers and it is an online web-based application be accessed by VFE Sales staff and Agents for stock management, transactions recording and serialized products tracking. The application also enables VFE sales staff to view agents and dealers information and to evaluate their performance in order to manage their incentives. There are as well integrations with other 3rd party systems like Billing System, TIBCO, etc.
Asset Technology Group. Feb 2008 – Aug 2009 .
Role Technical Team Lead.
Technologies/Tools J2EE, OracleDB10g, WebShpere Rational Developer.
Description Vodafone sales representatives use a handheld device to make their sales out transactions at the dealer branch. This project is responsible for providing the extranet functionality to the handheld application through HTTP. The handheld application sends an HTPP request to the extranet application to perform some task and the extranet application responds back the results but compressed using HTTP compression. Using the handheld application, the sales agent may conduct sales out transactions and check their stock.
Asset Technology Group. Feb 2008 – Aug 2009 .
Role Technical Team Lead.
Technologies/Tools OracleUCM (Universal Content Management).
Description Implementing pilots with Oracle UCM and making certain adjustments to the workflow, security, fragmentation, etc. to meet our demands. The website can be published to an external web server using the publishing tool.
Asset Technology Group. Feb 2008 – Aug 2009 .
Role Analysis of requirements and Implementation.
Technologies/Tools Java, OracleJDeveloper10g.
Description Implementing multi threading technology on the AWB (Al Watany Bank) middleware and apply some needed modifications.
Raya Software. Jul 2005 – Jan 2008 .
Role Senior Software Expert.
Technologies/Tools SOA, BPEL, J2EE, TopLink, OracleJDeveloper10g.
Description Designing the framework for one of the biggest project in the company Ministry of Civil Aviation MOCA.
Raya Software. Jul 2005 – Jan 2008 .
Role Technical and Managerial Team Lead.
Technologies/Tools Java, XML, OracleDB, TCP/IP Listener, Threading, Connection Pooling, Caching, Encryption, WebServices, JDBC to call stored procedures, and OracleJDeveloper10g.
Description The construction of a new middleware for NSGB, an intermediary tier that shields legacy systems from being transparent to retail and customer-serving delivery channels, was part of this project. The main responsibility of the middleware is to receive requests from the frontend, parse the information from these requests, send inquiries to the backend, receive replies back, process the replies and apply some logic, and finally return the results to the requester. Along with managing the project (resource management, mission planning, logistics, status reports, financial control, etc.), participating in the feasibility study to design the project, and participating in the technical design of the required software changes (specifications and programming support), I was also implementing the middleware’s core functionality.
Raya Software. Jul 2005 – Jan 2008 .
Role Technical and Managerial Team Lead.
Technologies/Tools J2EE, Struts, Hibernate, XML, OracleJdeveloper10g.
Description Designing and implementing with a team of 4 members the NSGB admin web tool. The tool consists of 4 modules.
(1) Subscription module is responsible for the subscriptions of a customer to some products or services.
(2) Administration module is responsible for maintaining the user profile that uses the system.
(3) Reporting module is responsible for generating reports for all channels and these reports could be exported to excel sheets and PDF.
(4) Security module assigns the roles and the privileges for the users.
Raya Software. Jul 2005 – Jan 2008 .
Role Technical Consultant.
Technologies/Tools Jasper Reports, J2EE, Java, Oracle JDeveloper 10g.
Description As a Technical Consultant, I was in charge of training a team of four members on Java, Jasper Report, and J2EE, and directing the group responsible for developing the Duravit Company’s invoicing system and arabization of the inventory items.
Nile Soft. Jan 2002 – May 2005 .
Role Technical Team Leader.
Technologies/Tools J2EE, Struts, EJB2, OracleJDeveloper10g.
Description Working as a Team Leader, leading a team of 4 members responsible for producing UML class diagrams and detailed sequence diagrams for an automated web-based integration system (ERP) of the Credit Guarantee Company (CGC). CGC was mainly established to provide small businesses with loan guarantees. The system is composed of 8 subsystems (Finance/Accounting, Payroll, Fixed Assets, Credit Guarantees, Micro Credit Unit, Access Rights, Deposits, and Investment) and was created in accordance with UML standards. The system’s architecture is multi-tiered, built on J2EE standard and the MVC paradigm, and uses Oracle Database Server for the persistent layer with EJB, Struts for the control layer, and JSP for the presentation layer.
Nile Soft. Jan 2002 – May 2005 .
Technologies/Tools Java, J2EE, UML, XML, OOAD.
Description
Nile Soft
- Teaching Java, J2EE, UML, OOAD (Object Oriented Analysis and Design), and XML as a part-time instructor.
- Supervising several capstone projects, including online apps that use the three-tier architecture as well as desktop and networking applications.
Allied Soft
- Working as an Instructor (Part Time), teaching Java, J2EE, UML, and OOAD (Object Oriented analysis and Design).
- Supervisor of more than one graduation projects ranging from desktop applications, networking applications to web applications implementing the 3 tiers architecture.
Nile Soft. Jan 2002 – May 2005 .
Allied Soft. Jan 2001 – Aug 2001 .
Places I visited in my life.