publications

2026

1. ACM PDC

   DDialogue: A Collaborative Framework for Cross-Sectoral Dialogue through Data

   Alessandro Fornaroli, Ravinithesh Annapureddy, and Daniel Gatica-Perez

   In Proceedings of the 19th Participatory Design Conference 2026, Vol. 1: Full Papers, , 2026

   Abs DOI

   

   In tackling complex societal issues, cross-sector collaboration within interdisciplinary teams can leverage the diverse expertise of individuals from various organizations. Concurrently, data-driven methods are increasingly central to effective decision-making. However, there is a notable gap in research at the intersection of cross-boundary collaboration and participatory data analysis. To address this, we propose DDialogue, a conceptual framework designed to facilitate collaborative data analysis within cross-sector partnerships, while simultaneously enhancing data literacy skills among stakeholders. The DDialogue framework is instantiated as a workshop composed of nine sessions, each with a specific purpose, leading to the co-creation of outputs aimed at tackling complex issues. The framework was tested through a pilot workshop and a fully implemented workshop addressing the problem of juvenile delinquency in Turin, Italy. These activities yielded formative evidence suggesting that DDialogue can be a useful tool for researchers or practitioners who seek to engage diverse stakeholders from different sectors and with varying levels of data literacy in data-driven projects. Participant feedback highlighted the framework’s adaptability and its potential to support data-informed collaboration.

2. ACM DIS

   Building A Civic Tool for Community-Police Engagement to Adapt Neighborhood Policing

   Ravinithesh Reddy Annapureddy, Staundefinedislavs Šeiko, Natalie Higham-James, and 5 more authors

   In Proceedings of the 2026 Designing Interactive Systems Conference, , 2026

   Abs DOI

   

   Data-driven policing often prioritizes incident records over residents’ lived experiences. In the Baltic city of Riga, with a history of distrust and limited community-police engagement, this can further alienate the public. To bridge this gap, we propose a Research through Design (RtD) inquiry into the development of Par drošu Rundefinedgu, a civic tool for community-data-integrated policing. With municipal police, NGOs, and city staff, we ask how RtD enables stakeholder negotiation and which interaction qualities support trust and the use of combined community and incident data. The co-design process included workshops that surfaced divergent notions of safety; material probes designed as boundary objects to negotiate among stakeholders; and a pilot deployment showing how combining quantitative and qualitative data reshapes engagement and trust. Mixed-methods evaluation suggests increased officer-citizen interaction, but frictions in sustaining stakeholder collaboration. We contribute (i) an empirical RtD inquiry with public institutions, (ii) an artifact combining physical and dashboard interactions, and (iii) reflections on interaction design as a boundary-spanning practice for trust and infrastructuring.

2025

1. ACM C&T

   Co-Designing with Multiple Stakeholders and Datasets: A Community-Centered Process to Understand Youth Deviance in the Italian City of Turin

   Ravinithesh Annapureddy, Alessandro Fornaroli, Massimo Fattori, and 7 more authors

   In Proceedings of the 12th International Conference on Communities & Technologies, , 2025

   Abs DOI

   

   This paper presents the co-design and design evaluation of Sbocciamo Torino civic tool, which helps understand and act upon the issues of youth deviance in the Italian city of Turin through multi-stakeholder collaboration and collaborative data analysis. Rooted in research through design and participatory design methodologies, the civic tool integrates a data dashboard, stakeholder committee, and structured co-design sessions to facilitate collaborative analysis and intervention planning. The civic tool was developed in partnership with municipal authorities, law enforcement, NGOs, and social services, and reflects their institutional priorities while centering community knowledge. We describe the iterative co-design process, including stakeholder workshops for design, validation, training, and evaluation. The civic tool’s impact on stakeholder trust, collaboration, and decision-making was assessed through surveys and open-ended questionnaires. Our findings show that stakeholders valued the inclusive design approach and data-driven collaboration while revealing barriers in communication, data literacy, and operational coordination. Furthermore, political and institutional support was identified as critical to the civic tool’s success. This paper contributes to research on community technologies by demonstrating how civic tools can be collaboratively developed to navigate wicked social problems through participatory design.

2024

1. ACM DGOV

   Generative AI Literacy: Twelve Defining Competencies

   Ravinithesh Annapureddy, Alessandro Fornaroli, and Daniel Gatica-Perez

   Digit. Gov.: Res. Pract., Aug 2024

   Abs DOI HTML PDF

   

   This paper introduces a competency-based model for generative artificial intelligence (AI) literacy covering essential skills and knowledge areas necessary to interact with generative AI. The competencies range from foundational AI literacy to prompt engineering and programming skills, including ethical and legal considerations. These twelve competencies offer a framework for individuals, policymakers, government officials, and educators looking to navigate and take advantage of the potential of generative AI responsibly. Embedding these competencies into educational programs and professional training initiatives can equip individuals to become responsible and informed users and creators of generative AI. The competencies follow a logical progression and serve as a roadmap for individuals seeking to get familiar with generative AI and for researchers and policymakers to develop assessments, educational programs, guidelines, and regulations.

2. Design thinking in European security research - An empirical evaluation

   Caroline Davey, Andrew Wootton, Dagmar Heinrich, and 2 more authors

   2024

   Abs

   

   This output presents a substantial, empirically grounded research contribution arising from the EU-funded IcARUS project, focusing on the application and critical evaluation of design-led and social innovation methodologies within European security research and innovation. Drawing on multi-site qualitative research conducted across six European cities, the report synthesises interview research, observational studies, participatory workshops, and reflexive project analysis to examine how design thinking and social innovation approaches perform in complex, real-world security contexts. The primary contribution to knowledge made by this output is a critical, evidence-based evaluation of design thinking and social innovation as applied research methodologies in the security domain. Rather than treating these approaches as neutral or inherently beneficial, the report identifies structural and methodological limitations, particularly in relation to problem framing, requirements capture, power dynamics between stakeholders, and the translation of participatory processes into implementable outcomes. This represents an original contribution to debates that are often dominated by normative or promotional accounts of design thinking and social innovation. The research advances understanding of how design-led approaches interact with institutional, organisational, and cultural conditions in public security contexts. By comparing practice across multiple national and municipal settings, the report demonstrates that methodological effectiveness is highly contingent on governance structures, stakeholder capability, and the distribution of design competence. These findings challenge simplified or decontextualised models of participatory innovation and provide a more nuanced, empirically informed account of how such approaches function in practice. While the report also documents the development of tools and project activities, these are analytically subordinate to the report’s methodological and conceptual insights. The output’s originality lies not in the tools themselves, but in the critical synthesis of evidence regarding how and why certain design and social innovation approaches succeed or fail in security research and innovation. The report was independently reviewed by European Commission-appointed experts and made publicly available via CORDIS in January 2024, ensuring effective dissemination. It constitutes a coherent, stand-alone research output that contributes new empirical and conceptual insight into applied design research and innovation practice within European security studies.

2022

1. Master Thesis

   Searching for visual patterns in a children’s drawings collection

   Ravinithesh Annapureddy

   2022

   Abs HTML

   The success of large-scale digitization projects at museums, archives, and libraries is pushing other cultural institutions to embrace digitization to preserve their collections. By juxtaposing digital tools with digitized collections, it is now possible to study these cultural objects at a previously unknown scale. This thesis is the first attempt to explore a recently digitized children’s drawings collection while developing a system to identify patterns in them linked with popular cultural objects. Artists, as young as three and as old as 25, created nearly 90,000 drawings in the span of three decades from most countries in the world. The preliminary examination unveils that these drawings mirror a solid cultural ethos by using specific iconographic subjects, objects, and colors, and the distinction between children of different parts of the globe is visible in their works. These factors not only make the dataset distinct from other sketch datasets but place it distantly from them in terms of size and multifariousness of creations and the creators. The essential and another dimension of the project is matching the drawings and the popular cultural objects they represent. A deep learning model that learns a metric to rank the visual similarity between the images is used to identify the drawing-artwork pairs. Though the networks developed for image classification perform inadequately for the matching task, networks used for pattern matching in paintings show good performance. Fine-tuning the models increases the performance drastically. The primary outcomes of this work are (1) systems trained with a few methodically chosen examples perform comparably to the systems trained on thousands of generic samples and (2) using drawings enriched by adding generic effects of watercolor, oil painting, pencil sketch, and texturizing mitigates the situation of network learning examples by heart.

2018

1. IEEE SSCI

   Adaptive Critic Design for Extreme Learning Machines applied to noisy and drifting industrial processes

   Ravinithesh Annapureddy, Arya K. Bhattacharya, and Niranjan R. Masapeta

   In 2018 IEEE Symposium Series on Computational Intelligence (SSCI), 2018

   Abs DOI HTML

   

   Natural and manmade continuous-time dynamic systems are susceptible to adverse digressions, i.e. periods of rapid deterioration of performance. Conceptually, digressions of a given type are engendered when specific parameters of the system get into definitive combinatorial relationships. Machine Learning (ML) techniques can in principle identify in real time the acquisition (formation) of such relationships and release warnings that consequently command actions that can return the system to normality. Here a manufacturing system, namely the continuous casting process of steel making, is the object of study and both Artificial Neural Networks (ANNs) and Extreme Learning Machines (ELMs) have been shown to perform the above function. A specific characteristic of industrial systems isprocess drift; in such processes the drift is induced into the inter-parameter data relationship learnt by the ML mechanism and the latter has to adapt to the evolving relationship else lose out on accuracy. Adaptive-Critic techniques can function as enablers for the ML mechanism to adapt to this drift. In this work two such Adaptive-Critic techniques are developed, the first for ANNs and then for ELMs, which are demonstrated to work successfully for the industrial process of interest. Importantly, this is the first development in public domain of an Adaptive-Critic technique using ELMs for adaptation to industrial drift. The techniques are generic and amenable for drifting processes in any industrial environment.

2. ACODS

   Advance Predictions of critical digressions in a noisy industrial process- performance of Extreme Learning Machines versus Artificial Neural Networks

   Arya K. Annapureddy and Rishita Guduru

   IFAC-PapersOnLine, 2018

   5th IFAC Conference on Advances in Control and Optimization of Dynamical Systems ACODS 2018

   Abs DOI HTML

   

   Manmade continuous-time systems like vehicles, grids and industrial processes are susceptible to adverse digressions in performance which can result in losses to severe breakdowns. Traditionally, emergence of faults in systems was detected by algorithms based on specific sensory signals responding to the incipience of the fault. However, the fault itself is engendered by the fact that certain specific system state parameters acquire a specific combinatorial relationship preceding the fault, thus if the acquisition of this relationship can be detected immediately on formation, neutralization of the fault can be effected early - something particularly relevant to critical systems. The advent of the industrial IoT has made real time systemic data (state parameters) across a chain of processes available at computing platforms, and potentially enabled data-based algorithms - specifically Artificial Neural Networks - to predict such adverse digressions before actual initiation. However, most manmade systems are subject to drift, due to which ANNs trained on data acquired over a certain operational period lose accuracy going forward. Adaptive Critic systems are designed to enable ANNs to neutralize this drift effect, but these need frequent retraining hitting the constraint on computational time. Extreme Learning Machines have emerged as alternatives to ANNs with training times less by orders of magnitude, but their accuracy has to be tested against real noisy industrial data. This work investigates the accuracy of ELM performance versus that of ANNs for such data, and synthesizes ensembles of ELMs to provide accuracy at similar levels as ANNs. This facilitates the incorporation of ELM ensembles into Adaptive Critic frameworks for accurate pre-initiation prediction of faults and related control functions.

2017

1. IEEEINDICON

   Extreme Learning Machines with frequency based noise filtering for prediction of critical digressions in a noisy industrial process

   Aditya Gupta, PLN Manikumar, Ravinithesh Annapureddy, and 1 more author

   In 2017 14th IEEE India Council International Conference (INDICON), Dec 2017

   Abs DOI HTML

   

   Many systems that are continuous in time are also susceptible to adverse digressions that can result in severe losses. Conventional algorithms tend to use signals from sensors and detect faults after incipience, consequent to which corrective measures can be taken for mitigation. From an alternate perspective, it may be visualized that when some of the state parameters of the system combine to form specific relationships, such adverse digressions are engendered. Therefore, identifying these combinatorial relationships immediately upon formation can help in mitigation of such adverse effects. The advent of IoT in industry helped bring real time data to computing platforms where Machine Learning techniques can potentially be developed to detect formation of such relationships. Traditional Neural Networks (NN) can be used as a Machine Learning tool, but they require lot of time for training, and moreover, because the industrial data comes with a significant noise component, further processing of the NN outputs are needed before they can be used for such prediction purposes. Extreme Learning Machines (ELM) require about two orders of magnitude less training time, but are even more susceptible to noise corruption than NN due to reasons discussed in this paper. In this work, a method is developed to first filter out noise from industrial sensory data in real time from its spectral content, and then its downstream use in ELMs designed in ensemble pattern is found to generate outputs for predicting adverse digressions that are at least as accurate as traditional neural networks but with significantly reduced training time.

2016

1. IOP Science

   Magnetic Metamaterials: A comparative study of resonator geometry and metal conductivity

   Shashank Rangu, Sreekar Kamireddy, Ravinithesh Annapureddy, and 3 more authors

   Journal of Physics: Conference Series, Oct 2016

   Abs DOI HTML

   

   In this work, split ring resonators based metamaterials are studied for microwave, terahertz and infrared frequency regimes. Two different geometries, circular and rectangular split ring resonators based metamaterials are investigated numerically for different frequency regimes. Our study indicates that the effect of metal conductivity and resonator geometry shows very little impact on the fundamental resonance mode. However the higher order modes go through significant frequency tuning because of the change in resonator geometry. We have further shown that the metal conductivity is an important parameter for the metamaterials employed in infrared domains.