Name: Evans Etrue Howard
Pronouns: He/Him
Institution: The University of Texas at El Paso
Department: Mathematical Sciences
Biography:
Evans Etrue Howard is a PhD student in Data Science at the University of Texas, El Paso. He holds a bachelor degree in Mathematics, masters in Mathematical Engineering and a PhD in Operations Research. His research activities mainly concentrate on methods for finding provably good solutions (exact or heuristics) to pedestrian emergency evacuation planning for pre/post disasters using social force models and reinforcement learning. In the past he has worked on modeling and solving large-scale optimization problems specifically in Network Optimization using graph models to build macroscopic models and algorithms for city-wise pedestrian evacuation. His research interests are not limited to: Dynamic Evacuation Models, Network Optimization, Combinatorial Optimization, Social Network Analysis, Social Force Model for contact diseases, Reinforcement learning, Graph Models and Scheduling. His current research involves suing machine learning and techniques and Social Force Model for contact and communicable disease.
Academic Status: PhD Student
Year in program: 2nd
Research Area/Department: Applied Mathematics; Data Science; Machine Learning/AI
Other, specify:
Major/Specialty: PhD in Data Science
Degrees Earned or in Progress: PhD in Data Science / Data Science / 2025 PhD in Operations Research / Information and Communication Technology / 2022 MSc in Mathematical Engineering / 2016 BSc in Mathematics / 2011
What courses or academic preparation have you completed to prepare for a summer internship experience?
Mathematical Statistics – Data Mining – Data Science Collaborations – Data Visualization – Database Management – Linear Models – Numerical Analysis – Combinatorial optimization – optimization of machine scheduling – Network optimization – Graph Theory – Probability and Statistics – Social Network Analysis
Have you published any research or worked on research/technical projects? Yes
Where has your research been published or where have you conducted research/technical projects? – Recommendation systems – Large Scale Pedestrian Evacuation Models – Network Optimization (Graph Theory) 1. Mudassir, Ghulam, Evans Etrue Howard, Lorenza Pasquini, Claudio Arbib, Eliseo Clementini, Antinisca Di Marco, and Giovanni Stilo. “”Toward Effective Response to Natural Disasters: A Data Science Approach.”” IEEE Access 9 (2021): 167827-167844. 2. Howard, Evans Etrue, Lorenza Pasquini, Claudio Arbib, Antinisca Di Marco, and Eliseo Clementini. “”Definition of an Enriched GIS Network for Evacuation Planning.”” In GISTAM, pp. 241-252. 2021. 3. MUDASSIR, G., HOWARD, E.E., PASQUINI, L., ARBIB, C., CLEMENTINI, E., DI MARCO, A.N.T.I.N.I.S.C.A. and STILO, G., Effective Response to Natural Disasters: a Data Science Approach. 4. Gentile, Claudio, Shuai Li, Purushottam Kar, Alexandros Karatzoglou, Giovanni Zappella, and Evans Etrue. “”On context-dependent clustering of bandits.”” In International Conference on machine learning, pp. 1253-1262. PMLR, 2017.
Please describe your research/academic interests:
My research and academic interests span a diverse range of topics within the fields of computational science, optimization, and data analysis (Data science and Data Visualisation). Here is a more detailed description of my interests in each of the areas you’ve mentioned: – Dynamic Evacuation Models: I am fascinated by the development of models and algorithms for dynamic evacuation scenarios. This includes understanding how individuals and groups move during emergencies, optimizing evacuation routes, and accounting for real-time factors such as traffic conditions and crowd behavior. – Network Optimization: Network optimization involves finding the most efficient ways to allocate resources or route flows through complex networks. I am interested in applying optimization techniques to solve problems in transportation, logistics, communication, and beyond. – Combinatorial Optimization: Combinatorial optimization deals with finding the best solution from a finite set of possibilities. This field has a wide range of applications, from scheduling and routing problems to resource allocation and facility location. – Social Network Analysis: Social network analysis focuses on understanding the structure and dynamics of social relationships and interactions. I find this area intriguing because it provides insights into information diffusion, influence propagation, and community detection in various social contexts. – Social Force Model: The Social Force Model is used to simulate pedestrian movement and crowd behavior. I am particularly interested in its applications for emergency evacuation planning and studying how individuals interact in crowded spaces, which has implications for urban design and safety. – Reinforcement Learning: Reinforcement learning is a powerful machine learning paradigm that involves learning optimal decision-making policies through trial and error. I am excited about its potential to solve complex problems in autonomous systems, robotics, and game theory. – Graph Models: Graph theory is a fundamental mathematical framework for representing and analyzing relationships between entities. I am interested in using graph models to solve problems related to network analysis, data representation, and algorithm design. – Scheduling: Scheduling involves the efficient allocation of resources over time. Whether it’s scheduling tasks in manufacturing, optimizing job assignments, or managing project timelines, I find the challenges of scheduling problems intriguing. – Knowledge/Semantic graphs – Machine Learning
Computational and Data Science Areas:
Applied Mathematics; Computational Science Applications, i.e., Bioscience, Cosmology, Chemistry, Environmental Science, Nanotechnology, Climate, etc.; Data Analytics and Visualization; Machine Learning and AI
Research Synergy:
I am extremely interested in computational, AI/machine learning, and data sciences research, particularly in the context of emergency evacuation planning and communicable disease modeling. My background as a PhD student in Data Science, with a strong foundation in Mathematics and Operations Research, has equipped me with the necessary skills and expertise to contribute significantly to these areas. My research activities have primarily revolved around developing methods to find provably good solutions, whether exact or heuristic, for pedestrian emergency evacuation planning in pre and post-disaster scenarios. I’ve employed social force models and reinforcement learning techniques to tackle these challenges. This research aligns well with the DOE labs’ objectives as it involves complex data analysis and optimization, which are fundamental in various scientific domains. Furthermore, my previous work in modeling and solving large-scale optimization problems using graph models for city-wide pedestrian evacuation underscores my capability to address real-world challenges with computational techniques. This experience can be leveraged in collaborations with DOE lab staff to improve simulation methods and optimize energy and resource efficiency, which are crucial areas of interest for the DOE. Currently, my research involves employing machine learning techniques and the Social Force Model to address issues related to communicable diseases. This research is particularly relevant in today’s context, given the global emphasis on public health and pandemic preparedness. My expertise in this area can contribute to the DOE’s efforts in safeguarding national interests and enhancing our understanding of disease dynamics. In conclusion, my academic background, research experiences, and current research focus align perfectly with the computational, AI/machine learning, and data sciences research areas relevant to DOE labs. I am enthusiastic about the prospect of collaborating with DOE lab staff to apply my skills and knowledge to advance their research objectives, particularly in the context of emergency evacuation management and public health.
Motivation:
I am highly motivated to participate in this program because it offers a unique and unparalleled opportunity to apply my expertise and experiences to address real-world challenges in collaboration with the Department of Energy (DOE) laboratories. My motivation stems from several key factors: – Collaborative Potential: The program emphasizes collaborative efforts between students and DOE lab staff. This collaborative aspect excites me, as I see it as an opportunity to work alongside leading experts in various scientific domains, exchange knowledge, and leverage their domain-specific insights to enhance the quality and relevance of my research. – Access to Resources: DOE labs offer state-of-the-art facilities, data, and computational resources that are essential for conducting advanced research. Being part of this program would grant me access to these valuable resources, allowing me to conduct experiments and simulations at a scale that may not be possible in an academic setting. – Addressing Critical Challenges: The DOE labs are involved in addressing some of the most critical challenges facing our society, from advancing clean energy technologies to ensuring national security. Contributing to these efforts through my research in AI/machine learning and data sciences is a significant source of motivation, as it allows me to work on projects with a strong societal and scientific relevance. – Learning and Growth: I am eager to learn from DOE lab staff who have deep expertise in their respective fields. Engaging with them on complex problems will undoubtedly expand my knowledge and skills, helping me grow both as a researcher and as an individual. – Alignment with Research Interests: The program’s focus on cutting-edge research in computational and data-driven fields closely aligns with my own research interests. It provides a platform for me to work on challenging projects that are not only intellectually stimulating but also have the potential for significant real-world impact. – Making a Difference: Ultimately, my motivation lies in the potential to make a positive difference. By participating in this program, I hope to contribute to scientific advancements, improve emergency management strategies, and enhance our understanding of critical issues such as contact and communicable diseases. Knowing that my work may contribute to the betterment of society is a powerful driving force for me.
Lightning Talk Title: Exploring Diverse Horizons: A Journey through Computational Data Science and Operations Research