publications

2025

1. Accepted NeurIPS

   Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

   Yifan Zhou, Sachin Grover, Mohamed El Mistiri, and 7 more authors

   2025
2. CEP

   Dynamic modeling and system identification of user engagement in mHealth interventions using a Bayesian approach for missing data imputation

   Mohamed El Mistiri, Steven De La Torre, Benjamin M. Marlin, and 4 more authors

   Control Engineering Practice, 2025

   Abs DOI

   Digital behavior change interventions (DBCIs) have been found to positively impact health behaviors and are becoming increasingly important as an emerging topic for control systems applications. However, their effectiveness is heavily dependent upon user engagement with both the digital tool (e.g., mHealth app, wearable activity tracker) and the behavior change intervention (e.g., exercise activity planning). In this paper, engagement refers to the unique interactions of a participant with either of these components resulting in digital traces (e.g., app page views). Furthermore, engagement in DBCIs will change over the course of the intervention in response to an individual’s environment, context, and psychological state. Intensive data collection enables modeling engagement in DBCIs as a dynamical system using fluid analogies, and applying prediction-error methods from system identification to estimate models. Missingness represents both a fundamental and practical concern in this application domain. This work addresses missingness using a novel Bayesian imputation method applied to data from the HeartSteps II physical activity intervention study. The benefits of this approach include the ability to impute missing data points more accurately than traditional methods and quantify uncertainty resulting from imputation and data scarcity; the latter is essential to the implementation of robust closed-loop interventions. The methods presented in this work provide insights into critical factors that impact engagement behavior over time and in context, ultimately benefiting the development of digital behavior change interventions relying on control engineering approaches.

3. Authorea

   Enhancing pH control in microalgae raceway photobioreactors using 3DoF-KF Model-on-Demand model predictive control

   Pablo Otálora, Sarasij Banerjee, Mohamed El Mistiri, and 3 more authors

   Authorea Preprints, 2025
4. I&ECR

   Data-Driven Control of Nonlinear Process Systems Using a Three-Degree-of-Freedom Model-on-Demand Model Predictive Control Framework

   Sarasij Banerjee, Owais Khan, Mohamed El Mistiri, and 3 more authors

   Industrial & Engineering Chemistry Research, 2025

   DOI
5. IJC

   Model predictive control in mHealth: a decision framework for optimised personalised physical activity interventions

   Mohamed El Mistiri, Daniel E. Rivera, Predrag Klasnja, and 2 more authors

   International Journal of Control, 2025

   DOI
6. OJ-CSYS

   Data-Driven Mobile Health: System Identification and Hybrid Model Predictive Control to Deliver Personalized Physical Activity Interventions

   Mohamed El Mistiri, Owais Khan, César A. Martin, and 2 more authors

   IEEE Open Journal of Control Systems, 2025

   DOI
7. CEP

   3DoF-KF HMPC: A Kalman filter-based Hybrid Model Predictive Control Algorithm for Mixed Logical Dynamical Systems

   Owais Khan, Mohamed El Mistiri, Sarasij Banerjee, and 2 more authors

   Control Engineering Practice, 2025

   Abs DOI

   This paper presents the formulation, design procedure, and application of a hybrid model predictive control (HMPC) scheme for hybrid systems that is embedded in a mixed logical dynamical (MLD) framework. The proposed scheme adopts a three degrees-of-freedom (3DoF) tuning method to accomplish precise setpoint tracking and ensure robustness in the face of disturbances (both measured and unmeasured) and uncertainty. Furthermore, the HMPC algorithm employs setpoint and disturbance anticipation to proactively enhance controller performance and potentially reduce control effort. Slack variables in the objective function prevent the mixed-integer quadratic problem from becoming infeasible. The effectiveness of the proposed algorithm is demonstrated through its application in three distinct case studies, which include control of production–inventory systems, time-varying behavioral interventions for physical activity, and management of epidemics/pandemic prevention. These case studies indicate that the HMPC algorithm can effectively manage hybrid dynamics, setpoint tracking and disturbance rejection in diverse and demanding circumstances, while tuned to perform well in the presence of nonlinearity and uncertainty.

2024

1. SYSID

   Control-Relevant Input Signal Design For Integrating Processes: Application to a Microalgae Raceway Reactor

   Sarasij Banerjee, Pablo Otálora, Mohamed El Mistiri, and 3 more authors

   IFAC-PapersOnLine, 2024

   20th IFAC Symposium on System Identification SYSID 2024

   Abs DOI

   Plants with integrators possess control-relevant modeling requirements that are typically ignored in the literature. Desired closed-loop speeds of response for such systems can differ significantly from their open-loop dynamics, causing conventional system identification guidelines to fail or be inaccurate. One such issue relates to experimental design. This paper presents guidelines for the design of excitation signals for system identification of plants with integrators, with application to the modeling and control of a microalgae raceway reactor. The concept is to excite the system through optimized test signals with control-relevant shaping of their power spectra. This facilitates a shift in emphasis of the identification objective from estimating a model with good open-loop performance to having a model possessing desired closed-loop characteristics. Such a consideration is particularly important when generating informative databases for estimating predictive models for closed-loop control. An illustration for this experimental design procedure is accomplished in this paper through the estimation of ARX-based models and, subsequently, model predictive control of the pH dynamics of an experimental raceway photobioreactor facility hosting sustainable microalgae production.

2. JBI

   Modeling engagement with a digital behavior change intervention (HeartSteps II): An exploratory system identification approach

   Steven A. De La Torre, Mohamed El Mistiri, Eric Hekler, and 5 more authors

   Journal of Biomedical Informatics, 2024

   Abs DOI

   Objective Digital behavior change interventions (DBCIs) are feasibly effective tools for addressing physical activity. However, in-depth understanding of participants’ long-term engagement with DBCIs remains sparse. Since the effectiveness of DBCIs to impact behavior change depends, in part, upon participant engagement, there is a need to better understand engagement as a dynamic process in response to an individual’s ever-changing biological, psychological, social, and environmental context. Methods The year-long micro-randomized trial (MRT) HeartSteps II provides an unprecedented opportunity to investigate DBCI engagement among ethnically diverse participants. We combined data streams from wearable sensors (Fitbit Versa, i.e., walking behavior), the HeartSteps II app (i.e. page views), and ecological momentary assessments (EMAs, i.e. perceived intrinsic and extrinsic motivation) to build the idiographic models. A system identification approach and a fluid analogy model were used to conduct autoregressive with exogenous input (ARX) analyses that tested hypothesized relationships between these variables inspired by Self-Determination Theory (SDT) with DBCI engagement through time. Results Data from 11 HeartSteps II participants was used to test aspects of the hypothesized SDT dynamic model. The average age was 46.33 (SD=7.4) years, and the average steps per day at baseline was 5,507 steps (SD=6,239). The hypothesized 5-input SDT-inspired ARX model for app engagement resulted in a 31.75 % weighted RMSEA (31.50 % on validation and 31.91 % on estimation), indicating that the model predicted app page views almost 32 % better relative to the mean of the data. Among Hispanic/Latino participants, the average overall model fit across inventories of the SDT fluid analogy was 34.22 % (SD=10.53) compared to 22.39 % (SD=6.36) among non-Hispanic/Latino Whites, a difference of 11.83 %. Across individuals, the number of daily notification prompts received by the participant was positively associated with increased app page views. The weekend/weekday indicator and perceived daily busyness were also found to be key predictors of the number of daily application page views. Conclusions This novel approach has significant implications for both personalized and adaptive DBCIs by identifying factors that foster or undermine engagement in an individual’s respective context. Once identified, these factors can be tailored to promote engagement and support sustained behavior change over time.

3. SYSID

   Data-Driven Control of Highly Interactive Systems using 3DoF Model-On-Demand MPC: Application to a MIMO CSTR

   Sarasij Banerjee, Owais Khan, Mohamed El Mistiri, and 2 more authors

   IFAC-PapersOnLine, 2024

   20th IFAC Symposium on System Identification SYSID 2024

   Abs DOI

   This paper presents a Three-Degree-of-Freedom Model Predictive Control (3DoF MPC) framework based on Multi-Input-Multi-Output (MIMO) “Model-on-Demand” (MoD) estimation. MoD is a data-centric weighted regression algorithm that generates local models over adaptively varying neighborhoods of changing operating conditions. The 3DoF formulation enables individualized tuning of parameters relating to setpoint tracking and measured and unmeasured disturbance rejection. Online estimation of system dynamics using MIMO MoD and augmentation with the 3DoF MPC structure allows the generation of control laws based on efficient locally linear approximations of system nonlinearities. This paper evaluates the framework through a case study involving a nonlinear MIMO Continuous Stirred Tank Reactor (CSTR) model. The MIMO CSTR system is highly interactive, making data-driven estimation and control notably more challenging than its SISO counterpart. The generation of an informative database using modified “zippered” multisines is presented. The paper concludes with a case study demonstrating the effectiveness of 3DoF MoD MPC in achieving constrained MIMO control of reactor concentration and temperature in the presence of disturbances through a flexible and intuitive approach.

4. SYSID

   Understanding “Just-in-Time” States in Behavioral Interventions using System Identification and Data Science Methods.

   Mohamed El Mistiri, Sarasij Banerjee, Daniel E. Rivera, and 3 more authors

   IFAC-PapersOnLine, 2024

   20th IFAC Symposium on System Identification SYSID 2024

   Abs DOI

   Insufficient physical activity (PA) is highly prevalent in society, despite its negative impact on personal health. Effective interventions are clearly needed. However, improvements to behavioral interventions face many challenges, from noisy and missing measurements to inadequate understanding of the dynamics of behavior change in context. In this paper, we present a comprehensive, data-driven, system identification approach aimed at overcoming challenges to better understand the dynamics of PA behavior change, which in turn can improve the efficacy of these interventions. The proposed approach consists of an innovative input signal design (aimed at providing informative data sets to study the concept of “just-in-time” dynamics), Singular Spectrum Analysis (SSA; for noise reduction and exploring the separability of the measured output signal), and Model-on-Demand (MoD) estimation, a hybrid data-driven modeling approach, which allows identifying dynamics under changing operating conditions. The proposed approach is evaluated on data for a representative participant from the JustWalk JITAI study. The results demonstrate significant potential of the methodology in enhancing the understanding of the dynamics of behavior change in context.

5. SYSID

   System Identification of User Engagement in mHealth Behavioral Interventions

   Mohamed El Mistiri, Steven De La Torre, Karine Tung, and 5 more authors

   IFAC-PapersOnLine, 2024
6. SIR Epidemic Control Using a 2DoF IMC-PID with Filter Control Strategy

   DE Rivera, S Banerjee, C Kobs, and 2 more authors

   IFAC-PapersOnLine, 2024
7. System Identification and Control Systems Engineering Approaches for Optimal and Practical Personalized mHealth Interventions for Physical Activity

   Mohamed El Mistiri

   Arizona State University, 2024

2023

1. JMIR

   Advancing understanding of just-in-time states for supporting physical activity (Project JustWalk JITAI): protocol for a System ID study of just-in-time adaptive interventions

   Junghwan Park, Meelim Kim, Mohamed El Mistiri, and 8 more authors

   JMIR Research Protocols, 2023
2. ACC

   System identification and hybrid model predictive control in personalized mHealth interventions for physical activity

   Mohamed El Mistiri, Owais Khan, Daniel E Rivera, and 1 more author

   In 2023 American Control Conference (ACC), 2023

2022

1. CDC

   A Kalman filter-based hybrid model predictive control algorithm for mixed logical dynamical systems: Application to optimized interventions for physical activity

   Owais Khan, Mohamed El Mistiri, Daniel E Rivera, and 2 more authors

   In 2022 IEEE 61st Conference on Decision and Control (CDC), 2022
2. BayesLDM: A Domain-specific Modeling Language for Probabilistic Modeling of Longitudinal Data

   Karine Tung, Steven De La Torre, Mohamed El Mistiri, and 7 more authors

   In 2022 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), 2022
3. ACC

   Model predictive control strategies for optimized mhealth interventions for physical activity

   Mohamed El Mistiri, Daniel E Rivera, Predrag Klasnja, and 2 more authors

   In 2022 American Control Conference (ACC), 2022
4. ACC

   Enhanced social cognitive theory dynamic modeling and simulation towards improving the estimation of" just-in-time" states

   Mohamed El Mistiri, Daniel E Rivera, Predrag Klasnja, and 2 more authors

   In 2022 American Control Conference (ACC), 2022
5. RIAI

   Un esquema de decisiones para intervenciones adaptativas comportamentales de actividad fı́sica basado en control predictivo por modelo hı́brido: ilustración con Just Walk

   Daniel Cevallos, César A Martı́n, Mohamed El Mistiri, and 2 more authors

   Revista iberoamericana de automatica e informatica industrial, 2022
6. Advancing behavioral intervention and theory development for mobile health: the HeartSteps II protocol

   Donna Spruijt-Metz, Benjamin M Marlin, Misha Pavel, and 8 more authors

   International journal of environmental research and public health, 2022
7. Using SIR Epidemic Modeling and Control to Teach Process Dynamics and Control to Chemical Engineers

   Daniel E. Rivera, Mohamed El Mistiri, and Z. Shi

   IFAC-PapersOnLine, 2022

   13th IFAC Symposium on Advances in Control Education ACE 2022

   Abs DOI

   The COVID-19 pandemic has brought about unprecedented opportunities to introduce control systems topics in the undergraduate engineering curriculum. This paper describes two computer modeling assignments based on MATLAB with Simulink developed for CHE 461: Process Dynamics and Control taught at Arizona State University during the fall 2020 semester. A myriad of important concepts, among these dynamic modeling using conservation and accounting principles, linearization, state-space system and transfer function model representations, PID feedback control and Internal Model Control design can be applied to the problem and explained to students in the context of a significant world event representing a unique “process” system, notably the COVID-19 pandemic.