Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Machine Learning-Based GPU Energy Prediction for Workload Management in Datacenters
Published in 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC) , 2025
A machine learning approach to predict GPU power usage and improve workload scheduling.
Recommended citation: B. Ismalej, M. Smith, and X. Jiang. (2025). "Machine Learning-Based GPU Energy Prediction for Workload Management in Datacenters." IEEE Computing and Communication Workshop and Conference (CCWC).
Automating Large-Scale Detection and Classification of Larger Than Life Cellular Automata Patterns
Published in 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC) , 2025
An automated approach in Lua to simullate, search, and classify dynamical pattern of Larger than Life cellular automata with the Golly software.
Recommended citation: B. Ismalej and K. M. Evans. (2025). "Automating Large-Scale Detection and Classification of Larger Than Life Cellular Automata Patterns." IEEE Computing and Communication Workshop and Conference (CCWC).
Stress Detection Through Sleep-Based Physiological Signals: An Integrated Semi-Supervised and Supervised Approach
Submitted to 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS) , 2025
An ML-based approach to forecast stress from sleep pattern data gathered from wearable devices.
Evaluating Privacy and Utility of Synthetic Tabular Data with Membership Inference Attacks
Submitted to 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS) , 2025
An empirical evaluation of privacy-utility tradeoffs of synthetic tabular data, using CTGAN, TVAE, and GaussianCopula.
research
BORACLE - Intelligent Algorithms
ML-driven health prognostics using wearable sensor data. Leading a cross-disciplinary team to tackle sub-problems in stress, sleep, and physical activity monitoring.
Predictive Energy Modeling for GPU Workloads
ML-driven workload scheduling to reduce GPU energy consumption.
Discovery in Larger than Life Cellular Automata
Analyzing complex emergent behavior in Larger than Life cellular automata using Lua and Golly.
Physics-Informed Neural Networks
An empirical study of Physics-Informed Neural Networks (PINNs) for modeling the chaotic driven damped pendulum, comparing Kolmogorov-Arnold Networks (KANs), Multilayer Perceptrons (MLPs), and traditional numerical solvers.
Empirical Investigations of Synthetic Data - Privacy, Utility, and Fidelity
Evaluating the privacy and utility of synthetically generated data using membership inference attacks. Examining fidelity from an information-theoretic perspective.
talks
Poster: BORACLE Intelligent Algorithms (IA): Advancements in Health Analytics & Risk Detection
Published:
teaching
Statistics Tutor
Tutoring, Department of Mathematics, California State University, Northridge, 2021
Supplemental Instructor - UNIV60NN
Supplemental Instruction, The Learning Resource Center, California State University, Northridge, 2023
“Build with Brandon” Workshop
Workshop, CSUN GeoGebra Summer Institute, Western Regional Noyce Network, 2024
Peer Mentor
Mentorship, College of Computer Science and Engineering, California State University, Northridge, 2024