ABOUT

Zhang, R. S., & Ramesh, B. (2024). A configurational perspective on design elements and user governance engagement in blockchain platforms. Information Systems Journal, 34(4), 1264–1323. https://doi.org/10.1111/isj.12494​​

• This study contributes to the understanding of blockchain platform governance by identifying optimal configurations of design elements that facilitate decentralized governance and user engagement. Utilizing fuzzy set qualitative comparative analysis (fsQCA), the research identifies five key design elements—access to decision rights, Click here to enter text. process visibility, protocol automation, and distinct incentives for developers/miners and other stakeholders. These elements combine to form four ideal types of blockchain platforms: the centralized incentive model, the impartial incentive model, the automation-driven model (for high generative governance engagement), and the comprehensive model (for high evaluative governance engagement). The significance of this work was highlighted by the guest editors of the special issue, who recognized its contribution to developing middle-range theories in the domain. 

Ellis, C. A., Sendi, M. S. E., Zhang, R. , Carbajal, D. A., Wang, M. D., Miller, R. L., & Calhoun, V. D. (2023). Novel methods for elucidating modality importance in multimodal electrophysiology classifiers. Frontiers in Neuroinformatics, 17, Article 1123376. https://doi.org/10.3389/fninf.2023.1123376 

• This interdisciplinary study bridges neuroscience and data science by developing novel explainability methods for multimodal electrophysiology classifiers in sleep stage classification. We introduce three approaches—global ablation, local ablation, and gradient-based feature attribution—to assess the importance of EEG, EOG, and EMG modalities. These methods reveal how clinical and demographic factors, such as sex, medication, and age, influence patterns learned by deep learning classifiers, offering new insights for personalized medicine and improving AI interpretability in clinical settings. My contributions to this interdisciplinary project included assisting with model development, conducting literature review, and revising the manuscript​

Werder, K., Ramesh, B., & Zhang, R. (2022). Establishing data provenance for responsible artificial intelligence systems. ACM Transactions on Management Information Systems, 13(2), Article 1–23. https://doi.org/10.1145/3503488 

• This paper investigates the role of data provenance in enhancing fairness, accountability, transparency, and explainability (FATE) in AI systems. It identifies biases originating from data sources and pre-processing stages, provides strategies for mitigating these biases, and proposes a research agenda to advance data provenance practices. The paper contributes significantly to the responsible AI discourse by demonstrating how data Click here to enter text. provenance can improve data quality, which is crucial for ensuring FATE characteristics in AI systems. I contributed to the conceptualization, literature review, and both the draft and revision of the manuscript. This work has been well-received, with 75 citations on Google Scholar within two years of publication. 

Zhang, R. , George, A., Kim, J., Johnson, V., & Ramesh, B. (2019). Benefits of blockchain initiatives for value‑based care: Proposed framework. Journal of Medical Internet Research, 21(9), e13595. https://doi.org/10.2196/13595

• This study proposes a novel framework for evaluating the benefits of blockchain technology in delivering value-based care by extending the Balanced Scorecard (BSC) evaluation framework. It assesses blockchain applications across five perspectives: financial, customer, internal process, learning and growth, and external partnerships. The framework provides a comprehensive evaluation method for blockchain initiatives in healthcare, demonstrating its potential to improve efficiency, security, and patient outcomes. I contributed to the theorizing, drafting, and revising stages of the research. As of September 2024, this work has received 27 citations according to Google Scholar, indicating its impact and relevance in the field. ​