Hum Nath Bhandari

Dr. Bhandari’s primary research and teaching interests focus on scientific computing, data visualization, mathematical optimization, machine learning and data science. He is involved in several interdisciplinary research projects with faculty colleagues and students. His collaborative research work has produced a number of journal publications and conference presentations. Currently, he teaches a wide range of courses in mathematics, statistics, and computing. In addition, he has lead numerous students’ research and capstone projects, including applications of machine learning and statistical models for solving time series and computer vision problems. Besides teaching and research, Dr. Bhandari is involved in various curriculum/program development initiatives related to scientific computing, data science, and applied mathematics. Dr. Bhandari is a lead contributor to the several community shared software packages that supply open-source programs for researchers who need high performance optimization and machine learning algorithms.

Google Scholar

Research Interests:

• Scientific Computing and Data Visualization
• Mathematical Modeling, Approximation, and Optimization
• High Performance Computing and Cloud Computing
• Stochastic Processes, Machine Learning, and Data Science

Current Research Projects:

• “Comparative Study of Machine Learning Models on Predicting Real Estate Market Indices”, Ramchandra Rimal, Binod Rimal, Hum Nath Bhandari, Nawa Raj Pokhrel, Keshab R Dahal: manuscript in preparation.
• “Improving Performance of the PSO Algorithm Using the Cyclic Coordinate Descent (CCD) Local Optimizer”, Hum Nath Bhandari, Philip W. Smith: manuscript in preparation.

Current Student Research Projects:

• “Application of Machine Learning for Rotifer Lifespan Analysis”. Students: Colton Pelletier, Victoria Freitas, Ella Costigan, and Kim Quaranto.
• “Investment Portfolio Construction, Optimization, and Performance Analysis Using Machine Learning”. Students: Chris Cline, Alex Cole, Rachel Piraino, and Will Bailey.
• “Developing Efficient Model Selection and Training Strategies for Machine Learning Models”. Students: Morgan Kiely and Tyler Edwards.

Selected Publications:

• Hum Nath Bhandari, Nawa Raj Pokhrel, Ramchandra Rimal, Keshab R Dahal, Binod Rimal. “Implementation of Deep Learning Models in Predicting ESG Index Volatility”, Springer Journal of Financial Innovation (https://jfin-swufe.springeropen.com/): under second review
• Hum Nath Bhandari, Binod Rimal, Nawa Raj Pokhrel, Ramchandra Rimal, Keshab R Dahal, Rajendra KC Khatri, “Predicting stock market index using LSTM”, Elsevier Journal of Machine Learning with Applications, Volume 9, (2022), 100320, ISSN 2666-8270, DOI: https://doi.org/10.1016/j.mlwa.2022.100320, ScienceDirect: https://www.sciencedirect.com/science/article/pii/S2666827022000378
• Nawa Raj Pokhrel, Keshab Raj Dahal, Ramchandra Rimal, Hum Nath Bhandari, Rajendra K.C. Khatri, Binod Rimal, William Edward Hahn, “Predicting NEPSE index price using deep learning models”, Elsevier Journal of Machine Learning with Applications, Volume 9, (2022), 100385, ISSN 2666-8270, DOI: https://doi.org/10.1016/j.mlwa.2022.100385, ScienceDirect: https://www.sciencedirect.com/science/article/pii/S2666827022000706
• Hum Nath Bhandari, Binod Rimal, Nawa Raj Pokhrel, Ramchandra Rimal, Keshab R. Dahal, “LSTM-SDM: An integrated framework of LSTM implementation for sequential data modeling”, Elsevier Journal of Software Impacts, Volume 14, (2022), 100396, ISSN 2665-9638, DOI: https://doi.org/10.1016/j.simpa.2022.100396, ScienceDirect: https://www.sciencedirect.com/science/article/pii/S2665963822000902
• Hyunsik Kim, Hum Nath Bhandari, Subha Pratihar, William L Hase, “Chemical Dynamics Simulation of Energy Transfer: Propylbenzene Cation and N2 Collisions”, Journal of Physical Chemistry A, (2019), 123(12), pp 2301-230 DOI: https://doi.org/10.1021/acs.jpca.9b00111
• Hum Nath Bhandari, Xinyou Ma, Amit K. Paul, Philip Smith, William L. Hase, “PSO Method for Fitting an Analytic Potential Energy Function, Application to I- (H2O)”, Journal of Chemical Theory Computation, (2018), 14 (3), pp 1321-1332 DOI: https://doi.org/10.1021/acs.jctc.7b01122
• Moumita Majumder, Hum Nath Bhandari, Subha Pratihar, William L. Hase, “Chemical Dynamics Simulations of Low Energy N2 Collisions with Graphite”, Journal of Physical Chemistry C, (2017), 122 (1), pp 612-623 DOI: https://doi.org/10.1021/acs.jpcc.7b10338

Software Products:

• Lead contributor to deep learning model implementation package: “LSTM-SDM: An integrated framework of LSTM implementation for sequential data modeling”, Elsevier Journal of Software Impacts, Volume 14, (2022), 100396, ISSN 2665-9638, Code Link: https://codeocean.com/capsule/3511724/tree/v1
• Lead contributor to optimization algorithm package: “PSO CCD Method”, a hybrid global optimization algorithm developed by combining the PSO algorithm with the Cyclic Coordinate Descent local optimizer, (2018) https://github.com/humnath5/MPSO_CCD_Method
• Lead contributor of “PSO-Method”, an optimization software package for solving nonlinear least-square fitting problems in computational chemistry (fitting potential energy surfaces), (2018) https://github.com/humnath5/PSO-Method

Journal Review:

• “A stock portfolio trading system: a proposed image-based deep learning model for stock selection and a mean-variance model for portfolio optimization”, Springer journal of Financial Innovation (2022) (https://jfin-swufe.springeropen.com/)
• “Impacts of online public opinion on stock price synchronicity in China”, Elsevier Journal of Expert Systems with Applications (2022)(https://www.sciencedirect.com/journal/expert-systems-with-applications)
• “Combination of Deep Learning Models to forecast stock price of AAPL and TSLA”, Jordanian Journal of Computers and Information Technology (2022) (https://www.jjcit.org/)

Invited Talks:

• Instructor of Course 1-Data Visualization and Statistical Inference in “CIMPA Summer School in Data Visualization, Modeling and Mathematical Tools”, May 15-24, (2023), Tribhuvan University, Nepal (http://anmaweb.org/AMNS-2023/summer-school.html)
• Presenter of Talk on CDM-MMS Talk Series: “Machine Learning and Data Science Techniques for Solving Complex Real World Problems”, Central Department of Mathematics, Kirtipur, TU, Nepal, December 31, (2022).
• Presenter of Talk on MNS Seminars: “Applications of Artificial Intelligence, Machine Learning, and Big Data for Solving Complex Problems in Science, Engineering, and Business”, Division of Marine & Natural Sciences, November 30, (2022), MNS, Roger Williams University.

Organizer of Workshops and Conferences:

• Organizer of “Third International Conference on Applications of Mathematics to Nonlinear Sciences (AMNS-2023)”, May 25-28, (2023), Pokhara, Nepal http://anmaweb.org/AMNS-2023/
• Moderator of “Grant Writing Webinar” (Nov 24, 6:30 pm - 9:00 pm)”, (2020), organized by Association of Nepalese Mathematicians of America (ANMA)
• Organizer of “Workshop on Collaborative Research in Mathematical Sciences-2020”, May 17 (5:00 pm -7:00 pm), (2020)
• Organizer of “Second International Conference on Applications of Mathematics to Nonlinear Sciences (AMNS-2019)”, June 27-30, (2019), Pokhara, Nepal (http://anmaweb.org/AMNS-2019/)

Conference Presentations:

• Presented a Talk “Implementation of Deep Learning Models in Predicting ESG Index Volatility”, The Global Interdisciplinary Green Cities Conference”, June 21 – June 25, Luzern, Switzerland (2022)
• Presented a Talk ”Implementation of Deep Learning Models in Stock Market Index Prediction”, Joint Mathematics Meeting (JMM), April 6-9, (2022).
• Presented Student Poster “Implementation of LSTM Model in Financial Time Series Data Forecasting”, by research student Ian McCallum during Joint Mathematics Meeting(JMM), April 6-9, 2022
• Presented a Talk “Hybrid PSO Algorithm Models Using the Cyclic Coordinate Descent (CCD) Local Optimizer”, Joint Mathematics Meeting (JMM), Denver, CO, January 15-18, 2020
• Presented a Student’s Poster “Predicting Stock Market Volatility Using Neural Networks”, by research student Jess Messina during Joint Mathematics Meeting(JMM), Jan 15-18, 2020
• Presented a Talk “Behavior of the Particle Swarm Optimization Algorithm”, Joint Mathematics Meeting (JMM), San Diego, January 10-13, 2018
• Presented a Poster “PSO Method for Fitting an Analytic Potential Energy Function, Application to I-(H2O)”, West Texas Applied Math Graduate Mini-symposium, 28 April, 2017

Past Student Projects:

• “Regression Models of Hungarian Chickenpox Cases”. Students: Nicole Rosa, Victoria Freitas, Kimberly Quaranto, and Maeve Kenny (Fall 2022).
• “Istanbul’s Stock Exchange Prediction Study Using Regression Models”. Students: Ella Costigana, Donovan Dunningb, and Morgan Kiely (Fall 2022).
• “Prediction of Indoor Air Temperature Using Regression Models”. Students: Issa Ramaji, Thomas MacGregor, and Tyler Edwards (Fall 2022).
• “Predicting Forest Fires Using Regression Models”. Students: Alexander Yeaw, Hank Bailey, and Will Bailey (Fall 2022).
• “Predicting the Std. Deviation of the S&P 500 using Regression Models” Students: Aidan Ventresca, Alex Cole, and Chris Cline (Fall 2022).
• “Building Convolutional Neural Networks (CNN) Model for Identifying Aces in a Deck of Cards”. Students: Ella Costigan, Donovan Dunning, Morgan Kiely, and Will Bailey (Fall 2022).
• “Using Deep Learning Models to Recognize Human Pointing Gestures”. Students: Issa Ramaji, Thomas MacGregor, Tyler Edwards, and Alexander Yeaw (Fall 2022).
• “Rice Grain Identification Using Deep Neural Networks”. Students: Aidan Ventresca, Alex Cole, Chris Cline, and Hank Bailey (Fall 2022). “COVID-19 Face Mask Recognition Using Deep Neural Networks”. Students: Nicole Rosa, Victoria Freitas, Kimberly Quaranto, and Maeve Kenny (Fall 2022).
• “Predicting NASDAQ Composite Index Using Deep Learning Models”. Collaborators: Ella Costigan, Donovan Dunning, Morgan Kiely, and Will Bailey(Fall 2022).
• “Predicting PM10 Levels Using Deep Learning Models”. Students: Issa Ramaji, Thomas MacGregor, Tyler Edwards, and Alexander Yeaw (Fall 2022).
• “Predicting CBOE Volatility Index (VIX) Using Deep Learning Models”. Students: Aidan Ventresca, Alex Cole, Chris Cline, and Hank Bailey (Fall 2022).
• “Predicting Dow Jones Industry Average Index Using Deep Learning Models”. Collaborators: Nicole Rosa, Victoria Freitas, Kimberly Quaranto, and Maeve Kenny (Fall 2022).
• “Implementation of LSTM Model in Financial Time Series Data Forecasting”. Student: Ian McCallum (Spring 2022)
• “Developing Efficient Optimization Algorithm for Training Machine Learning Models”. Student: Rena Yamayashi (Spring 2022)
• “An Analysis of the Percentage of Marine and Terrestrial Protected Areas in Countries Around the World in Recent Years”. Students: Molly Matthews and George Higham (Spring 2022).
• “Analysis of Global CO2 Emissions with Historical Perspectives”. Students: Emily Valcourt and Lindsey Dreher (Spring 2022).
• “A Study of Women Participation in Parliament”. Students: Ella Costigan, Jack Darakian, and Kimberly Quaranto (Spring 2022).
• “Analysis of PM2.5 Air Pollution: Mean Annual Exposure”. Students: Brian Farrel (Spring 2022).
• “A Study of Renewable Energy Production Around the World”. Students: Oswald Burgos, Mathew Fortin, and Kyle Haner (Spring 2022).
• “Total Greenhouse Gas Emissions”. Students: David Fasolino and Travis Lajoie (Spring 2022).
• “A Study of Cause of Death by Communicable Diseases and Maternal, Prenatal and Nutrition Conditions”. Students: Colton Pelletier and Donovan Dunning (Spring 2022).
• “Analyzing the World GDP Per Capita”. Students: Victoria Freitas, Morgan Strassburg, and Seth Frohnheiser (Spring 2022).
• “Forecasting the Chicago Board Options Exchange Volatility Index Using a Long Short-Term Memory Neural Network”. Student: Misha Dubuc (Spring 2021)
• “Developing CNN model for Medical Image Classification”. Student: Ramirez Roderick (Spring 2020)
• “Application of Deep Learning Techniques in Finance”. Student: Kayle Witham and Alfred Caron (Spring 2021)
• “Predicting Stock Market Volatility Using Neural Networks”. Student: Jess Messina (Spring 2020)

Program Development Initiatives:

• Currently working on establishing interdisciplinary data science program “BS/BA in Data Science”, Department of Mathematics/ Department of Computer Science, RWU.
• “Applied Mathematics Minor”, Department of Mathematics
• RWU “MATH 355/COMSC 415-Machine Learning”, Department of Mathematics/Department of Computer Science, RWU
• “MATH 255-Scientific Computing and Data Visualization”, Department of Mathematics, RWU
• “MATH 225/COMSC 225-Introduction to Data Science”, Department of Mathematics/Department of Computer Science, RWU

Leadership Positions:

• Member, Program Organizing Committee of “Third International Conference on Applications of Mathematics to Nonlinear Sciences (AMNS-2023)”, May 25-28, 2023, Pokhara, Nepal. Conference Website: http://anmaweb.org/AMNS-2023/
• Member, Educational/Training Collaborations Committee of “Data Science/Data Analytics Initiatives in Rhode Island”, 2021-2022.
• Member, “Senate Curriculum Committee (SCC)”(2021-2023), RWU
• Co-chair, “Department of Mathematics”(Jan 2021-July 2021), RWU
• Senator, “The Faculty Senate (FS)” (2019-2021), RWU.
• Member, “Faculty Development Committee (FDC)” (2020-2021), RWU
• Member, “Academic Standards Committee (FDC)” ( 2019-2020), RWU
• Member, “Diversity Committee (DC)” (2019-2020), RWU
• Executive Committee Member, “Association of Nepalese Mathematicians of America (ANMA)”, 2019-2021
• Executive Committee Member, “Nepalese Society in Lubbock (NSL)”, 2015-2017
• Treasurer, “Nepalese Student Association Texas Tech (NSA-TTU)”, 2014-2015,

Awards:

• “Hybrid Hero Award”, 2020: Awarded by Student Senate, Roger Williams University.
• “John T. White Graduate Scholarships”, 2017: Received from Mathematics and Statistics Department, Texas Tech University (TTU).
• “SIAM Scholarships”, 2016: Awarded by SIAM TTU Chapter. Training: o “Math Workshop”, a teaching pedagogy training provided by Instructional Design, Roger Williams University, 2021
• “Virtual Workshop for Remote Instruction & Whiteboard Tools”, online and hybrid teaching pedagogy training provided by Instructional Design, Roger Williams University, 2020

Professional Societies:

• American Mathematical Society (AMS): 2012 - present
• Mathematical Association of America (MAA): 2012 - present
• Society of Industrial and Applied Mathematics (SIAM): 2012-present
• Association of Nepalese Mathematicians in America (ANMA): 2015-present
• Data Science/Data Analytics Initiatives in Rhode Island: 2019- present

Current Teaching: 

• MATH 214-Calculus II, Spring 2023 (4 credits, 1 Section)
• MATH 315-Probability and Statistics, Spring 2023 (3 credits, 1 Section)
• MATH 255-Scientific Computing and Data Visualization, Spring 2023 (3 credits, 1 Section)
• MATH 479-Senior Data Science Capstone, Spring 2023 (4 credits, 1 section)

Past Teaching: 

At Roger Williams University:

• MATH 213-Calculus I, Fall 2018, Spring 2019, Fall 2019, Spring 2020
• MATH 214-Calculus II, Sum 2020, Sum 2021, Fall 2021, WI-2022, Spring 2022, Sum 2022, Fall 2022, WI-2023
• MATH 315-Probability and Statistics , Spring 2019, Fall 2019, Spring 2020, Fall 2020, Spring 2021, Fall 2021, Sum 2022
• MATH 255-Scientific Computing and Data Visualization, Spring 2020, Spring 2021, Spring 2022
• MATH 225-Introduction to Data Science, Fall 2018, Fall 2020
• MATH 355/COMSC 415-Machine Learning, Fall 2022
• MATH 410-Mathematical Optimization, Spring 2021
• MATH 450-Research in Mathematical Sciences, Spring 2019, Fall 2019, Spring 2020, Fall 2020, Spring 2021, Fall 2021, Spring 2022

At Texas Tech University (2012 - 2018):

• MATH 3342-Statistics for Engineers and Scientists: Fall 2017
• MATH 3350-Differential Equations: Summer 2017, Spring 2017
• MATH 1452-Calculus II: Fall 2016, Spring 2016, Sum II 2015, Spring 2015
• MATH 1451-Calculus I: Fall 2014, Spring 2014, Fall 2013
• MATH 1321-Trigonometry: Summer 2016
• MATH 1550-Pre-Calculus: Spring 2013

Teaching in Nepal (2002 - 2012):

• 2009 - 2012: Lecturer of Mathematics, Xavier College
• 2008 - 2009: High School Maths and Science Teacher, Nobel Academy
• 2002 - 2005: High School Maths and Science Teacher, Oxford School