About

Reza Rawassizadeh is an Associate Professor of Computer Science and the Coordinator of AI and Machine Learning at Boston University. He holds a Ph.D. in Computer Science from the University of Vienna, a Master’s degree from the Vienna University of Technology, and a Bachelor’s degree from Tehran Azad University. His research focuses on ubiquitous technologies including wearables, mobile devices, and robots. He has made notable contributions in designing resource-efficient, on-device machine learning algorithms that operate on small battery-powered devices such as smartwatches and fitness trackers without requiring network connectivity. Reza serves as a senior or chief scientific advisor for several AI-based companies. His scholarly interests include on-device machine learning and artificial intelligence, ubiquitous, mobile and wearable computing, digital health, and AI democratization.

Research topics

• Medicine
• Computer Science
• Artificial Intelligence
• Environmental health
• Machine Learning
• Demography
• Internal medicine
• Political Science
• Computer network
• Virology
• Economics
• Nursing
• Gerontology
• Immunology
• Microbiology
• Radiology
• Economic growth
• Medical physics
• Business
• Psychology
• Pathology
• Intensive care medicine
• Surgery
• Embedded system

Selected publications

• NeuroViz: Real-time Interactive Visualization of Forward and Backward Passes in Neural Network Training

  ArXiv.org · 2026-05-03

  articleOpen access1st authorCorresponding

  Training neural networks is difficult to interpret, particularly for newcomers. We introduce NeuroViz, an interactive visualization tool that supports real-time exploration of fully connected neural network training. Users can configure network architecture, activation functions, learning rates, and datasets, then observe activations, weight updates, and loss progression. NeuroViz visualizes weight changes in direct correspondence with activation signals in both forward and backward passes, enabling users to distinguish pre- and post-update states within individual epochs and view dynamically updating per-neuron equations. We conduct a comparative user study with 31 participants against six established visualization tools and we achieved the highest usability score (SUS 80.97, in the 'excellent' range), with mean rankings of 2.47 for clarity and 2.23 for usefulness (lower is better). Over 70% of participants reported that the visualizations substantially increased their perception of neural network training transparency. The implemented instance is accessible at https://neuroviz.org.

  PublisherOA PDF

• Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images

  arXiv (Cornell University) · 2026-03-19

  preprintOpen accessSenior author

  Prostate cancer is a leading cause of mortality in men, yet interpretation of T2-weighted prostate MRI remains challenging due to subtle and heterogeneous lesions. We developed an interpretable framework for automatic cancer detection using a small dataset of 162 T2-weighted images (102 cancer, 60 normal), addressing data scarcity through transfer learning and augmentation. We performed a comprehensive comparison of Vision Transformers (ViT, Swin), CNNs (ResNet18), and classical methods (Logistic Regression, SVM, HOG+SVM). Transfer-learned ResNet18 achieved the best performance (90.9% accuracy, 95.2% sensitivity, AUC 0.905) with only 11M parameters, while Vision Transformers showed lower performance despite substantially higher complexity. Notably, HOG+SVM achieved comparable accuracy (AUC 0.917), highlighting the effectiveness of handcrafted features in small datasets. Unlike state-of-the-art approaches relying on biparametric MRI (T2+DWI) and large cohorts, our method achieves competitive performance using only T2-weighted images, reducing acquisition complexity and computational cost. In a reader study of 22 cases, five radiologists achieved a mean sensitivity of 67.5% (Fleiss Kappa = 0.524), compared to 95.2% for the AI model, suggesting potential for AI-assisted screening to reduce missed cancers and improve consistency. Code and data are publicly available.

  PublisherDOI

• Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images

  ArXiv.org · 2026-03-19

  articleOpen accessSenior author

  Prostate cancer is a leading cause of mortality in men, yet interpretation of T2-weighted prostate MRI remains challenging due to subtle and heterogeneous lesions. We developed an interpretable framework for automatic cancer detection using a small dataset of 162 T2-weighted images (102 cancer, 60 normal), addressing data scarcity through transfer learning and augmentation. We performed a comprehensive comparison of Vision Transformers (ViT, Swin), CNNs (ResNet18), and classical methods (Logistic Regression, SVM, HOG+SVM). Transfer-learned ResNet18 achieved the best performance (90.9% accuracy, 95.2% sensitivity, AUC 0.905) with only 11M parameters, while Vision Transformers showed lower performance despite substantially higher complexity. Notably, HOG+SVM achieved comparable accuracy (AUC 0.917), highlighting the effectiveness of handcrafted features in small datasets. Unlike state-of-the-art approaches relying on biparametric MRI (T2+DWI) and large cohorts, our method achieves competitive performance using only T2-weighted images, reducing acquisition complexity and computational cost. In a reader study of 22 cases, five radiologists achieved a mean sensitivity of 67.5% (Fleiss Kappa = 0.524), compared to 95.2% for the AI model, suggesting potential for AI-assisted screening to reduce missed cancers and improve consistency. Code and data are publicly available.

  PublisherOA PDF

• NeuroViz: Real-time Interactive Visualization of Forward and Backward Passes in Neural Network Training

  arXiv (Cornell University) · 2026-05-03

  preprintOpen access1st authorCorresponding

  Training neural networks is difficult to interpret, particularly for newcomers. We introduce NeuroViz, an interactive visualization tool that supports real-time exploration of fully connected neural network training. Users can configure network architecture, activation functions, learning rates, and datasets, then observe activations, weight updates, and loss progression. NeuroViz visualizes weight changes in direct correspondence with activation signals in both forward and backward passes, enabling users to distinguish pre- and post-update states within individual epochs and view dynamically updating per-neuron equations. We conduct a comparative user study with 31 participants against six established visualization tools and we achieved the highest usability score (SUS 80.97, in the 'excellent' range), with mean rankings of 2.47 for clarity and 2.23 for usefulness (lower is better). Over 70% of participants reported that the visualizations substantially increased their perception of neural network training transparency. The implemented instance is accessible at https://neuroviz.org.

  PublisherDOI

• From Clicks to Conversations: Evaluating the Effectiveness of Conversational Agents in Statistical Analysis

  ArXiv.org · 2025-02-12

  preprintOpen accessSenior author

  The rapid proliferation of data science forced different groups of individuals with different backgrounds to adapt to statistical analysis. We hypothesize that conversational agents are better suited for statistical analysis than traditional graphical user interfaces (GUI). In this work, we propose a novel conversational agent, StatZ, for statistical analysis. We evaluate the efficacy of StatZ relative to established statistical software:SPSS, SAS, Stata, and JMP in terms of accuracy, task completion time, user experience, and user satisfaction. We combined the proposed analysis question from state-of-the-art language models with suggestions from statistical analysis experts and tested with 51 participants from diverse backgrounds. Our experimental design assessed each participant's ability to perform statistical analysis tasks using traditional statistical analysis tools with GUI and our conversational agent. Results indicate that the proposed conversational agents significantly outperform GUI statistical software in all assessed metrics, including quantitative (task completion time, accuracy, and user experience), and qualitative (user satisfaction) metrics. Our findings underscore the potential of using conversational agents to enhance statistical analysis processes, reducing cognitive load and learning curves and thereby proliferating data analysis capabilities, to individuals with limited knowledge of statistics.

  PublisherOA PDFDOI

• Analyzing the Resource Utilization of Lambda Functions on Mobile Devices: Case Studies on Kotlin and Swift

  IEEE Pervasive Computing · 2025-04-01

  articleSenior author

  With billions of smartphones in use globally, the daily time spent on these devices contributes significantly to overall electricity consumption. Given this scale, even minor reductions in smartphone power use could result in substantial energy savings. This study explores the impact of Lambda functions on resource consumption in mobile programming. While Lambda functions are known for enhancing code readability and conciseness, their use does not add to the functional capabilities of a programming language. Our research investigates the implications of using Lambda functions in terms of battery utilization, memory usage, and execution time compared to equivalent code structures without Lambda functions. Our findings reveal that Lambda functions impose a considerable resource overhead on mobile devices without offering additional functionalities.

  PublisherDOI

• TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization

  ArXiv.org · 2025-08-31

  preprintOpen accessSenior author

  The success of the generative model has gained unprecedented attention in the music generation area. Transformer-based architectures have set new benchmarks for model performance. However, their practical adoption is hindered by some critical challenges: the demand for massive computational resources and inference time, due to their large number of parameters. These obstacles make them infeasible to deploy on edge devices, such as smartphones and wearables, with limited computational resources. In this work, we present TinyMusician, a lightweight music generation model distilled from MusicGen (a State-of-the-art music generation model). TinyMusician integrates two innovations: (i) Stage-mixed Bidirectional and Skewed KL-Divergence and (ii) Adaptive Mixed-Precision Quantization. The experimental results demonstrate that TinyMusician retains 93% of the MusicGen-Small performance with 55% less model size. TinyMusician is the first mobile-deployable music generation model that eliminates cloud dependency while maintaining high audio fidelity and efficient resource usage

  PublisherOA PDFDOI

• Analyzing the Resource Utilization of Lambda Functions on Mobile Devices: Case Studies on Kotlin and Swift

  ArXiv.org · 2025-02-07

  preprintOpen accessSenior author

  With billions of smartphones in use globally, the daily time spent on these devices contributes significantly to overall electricity consumption. Given this scale, even minor reductions in smartphone power use could result in substantial energy savings. This study explores the impact of Lambda functions on resource consumption in mobile programming. While Lambda functions are known for enhancing code readability and conciseness, their use does not add to the functional capabilities of a programming language. Our research investigates the implications of using Lambda functions in terms of battery utilization, memory usage, and execution time compared to equivalent code structures without Lambda functions. Our findings reveal that Lambda functions impose a considerable resource overhead on mobile devices without offering additional functionalities.

  PublisherOA PDFDOI

• From Clicks to Conversations: Evaluating the Effectiveness of Conversational Agents in Statistical Analysis

  International Journal of Human-Computer Interaction · 2025-10-01 · 1 citations

  articleSenior author
  PublisherDOI

• Leveraging artificial intelligence-mediated communication for cancer prevention and control and drug addiction: A systematic review

  Translational Behavioral Medicine · 2025-01-01 · 3 citations

  review

  OBJECTIVE: To conduct a systematic review on Artificial Intelligence-Mediated Communication (AIMC) behavioral interventions in cancer prevention/control and substance use. METHODS: Eight databases were searched from 2017 to 2022 using the Population Intervention Control Outcome Study (PICOS) framework. We synthesized findings of AIMC-based interventions for adult populations in cancer prevention/control or substance use, applying SIGN Methodology Checklist 2 for quality assessments and reviewing retention and engagement. RESULTS: Initial screening identified 187 studies; seven met inclusion criteria, involving 2768 participants. Females comprised 67.6% (n = 1870). Mean participant age was 42.73 years (SD = 7.00). Five studies demonstrated significant improvements in substance use recovery, physical activity, genetic testing, or dietary habits. CONCLUSIONS: AIMC shows promise in enhancing health behaviors, but further exploration is needed on privacy risks, biases, safety concerns, chatbot features, and serving underserved populations. IMPLICATIONS: There is a critical need to foster comprehensive fully powered studies and collaborations between technology developers, healthcare providers, and researchers. Policymakers can facilitate the responsible integration of AIMC technologies into healthcare systems, ensuring equitable access and maximizing their impact on public health outcomes.

  PublisherDOI

Frequent coauthors

• G Anil Kumar

  163 shared

• Simon I Hay

  125 shared

• Mehdi Hosseinzadeh

  119 shared

• Ali H. Mokdad

  115 shared

• Dan J. Stein

  South African Medical Research Council

  100 shared

• Abdollah Mohammadian-Hafshejani

  Shahrekord University of Medical Sciences

  94 shared

• Robert Ancuceanu

  Institute for Health Metrics and Evaluation

  92 shared

• Shanshan Li

  Monash University

  92 shared

Labs

• Computer Science Research TeamPI

Education

• Ph.D.

  University of Vienna

• M.S.

  Vienna University of Technology

• B.S.

  Tehran Azad University

Awards & honors

• Computer Science Research Team Wins Best Search UX Award for…