About

Vikram Iyer is an assistant professor in the Paul G. Allen School of Computer Science and Engineering at the University of Washington and co-director of the CS for Environment Initiative. He also holds an adjunct appointment in Mechanical Engineering. His research group adopts an interdisciplinary approach to connect ideas across different engineering domains to develop end-to-end systems that advance technology with a strong emphasis on environmental sustainability. Their work includes innovations such as biodegradable and recyclable circuit boards, battery-free robots, batteryless sensors capable of dispersing in the wind and changing shape mid-air, streaming cameras small enough to be carried by live insects, and design tools to assess the environmental impact of these devices. A notable project involved collaboration with the Washington Department of Agriculture to wirelessly track invasive "murder" hornets, contributing to the destruction of the first nest in the United States, an effort featured on Discovery Channel.

Research topics

• Computer Science
• Artificial Intelligence
• Telecommunications
• Geography
• Embedded system
• Physics
• Operating system
• Biology
• Data Mining
• Meteorology
• Computer vision
• Engineering
• World Wide Web
• Environmental science
• Data science
• Genetics
• Computer network
• Computational biology
• Pharmacology
• Ecology
• Bioinformatics
• Pathology
• Cartography
• Electrical engineering

Selected publications

• Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-site Wearables

  ArXiv.org · 2026-05-18

  articleOpen access

  Wearables are widely used for mobile health monitoring, and photoplethysmography (PPG) is a key sensing modality for heart rate and related physiological measurements. However, public in-the-wild PPG datasets remain largely wrist-centric or limited to short, controlled studies, constraining research on emerging wearable form factors. We present Multi-site PPG, an in-the-wild physiological dataset collected from four custom-developed unobtrusive wearables: a smart earring, ring, watch, and necklace. Each device records green and infrared reflective PPG, 3-axis acceleration, and temperature with timestamps for cross-device alignment, while a Polar H10 chest strap provides reference electrocardiogram (ECG). Participants wore the devices for multiple days during daytime activities while continuing their normal routines. The dataset contains over 350 hours of raw data and 230-290 hours of modeling-ready 8-second windows per wearable. We benchmark heuristic, supervised, and self-supervised heart-rate estimation methods, showing substantial body-site differences: the best methods achieve mean absolute errors (MAEs) of 2.30 bpm on the earring, 5.13 bpm on the ring, 8.37 bpm on the watch, and 8.68 bpm on the necklace. We further analyze motion effects and evaluate multi-site and PPG-accelerometer fusion, demonstrating the dataset's value for robust physiological sensing across emerging wearable form factors.

  PublisherOA PDF

• Open Set Pedestrian Re Identification through Uncertainty Calibrated Vision Language Similarity

  Global Media and Social Sciences Research Journal · 2026-02-01

  articleOpen accessSenior author

  Single-frame pedestrian re-identification is often unstable in traffic scenes due to motion blur and partial visibility, whereas short video clips provide complementary cues. Building on uncertainty-aware CLIP-style modal representations, this work proposes an uncertainty-guided temporal aggregation module that assigns lower weights to unreliable frames and aligns clip-level visual features with text-derived semantic prompts. The model is evaluated on video-based autonomous driving benchmarks containing 52,000 tracklets and 1.1 million frames, with clip lengths ranging from 8 to 32 frames. Comparisons are conducted against video ReID baselines such as temporal pooling, recurrent aggregation, and transformer-based sequence models, as well as frame-level TransReID and CLIP-based methods. The proposed approach improves clip-level mAP by 3.6%–5.4% and rank-1 accuracy by 2.8%–4.1%, with additional gains in fast-motion segments where frame uncertainty is high.

  PublisherOA PDFDOI

• Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-site Wearables

  arXiv (Cornell University) · 2026-05-18

  preprintOpen access

  Wearables are widely used for mobile health monitoring, and photoplethysmography (PPG) is a key sensing modality for heart rate and related physiological measurements. However, public in-the-wild PPG datasets remain largely wrist-centric or limited to short, controlled studies, constraining research on emerging wearable form factors. We present Multi-site PPG, an in-the-wild physiological dataset collected from four custom-developed unobtrusive wearables: a smart earring, ring, watch, and necklace. Each device records green and infrared reflective PPG, 3-axis acceleration, and temperature with timestamps for cross-device alignment, while a Polar H10 chest strap provides reference electrocardiogram (ECG). Participants wore the devices for multiple days during daytime activities while continuing their normal routines. The dataset contains over 350 hours of raw data and 230-290 hours of modeling-ready 8-second windows per wearable. We benchmark heuristic, supervised, and self-supervised heart-rate estimation methods, showing substantial body-site differences: the best methods achieve mean absolute errors (MAEs) of 2.30 bpm on the earring, 5.13 bpm on the ring, 8.37 bpm on the watch, and 8.68 bpm on the necklace. We further analyze motion effects and evaluate multi-site and PPG-accelerometer fusion, demonstrating the dataset's value for robust physiological sensing across emerging wearable form factors.

  PublisherDOI

• Incorporating Sustainability in Electronics Design: Obstacles and Opportunities

  ArXiv.org · 2025-03-19

  preprintOpen accessSenior author

  Life cycle assessment (LCA) is a methodology for holistically measuring the environmental impact of a product from initial manufacturing to end-of-life disposal. However, the extent to which LCA informs the design of computing devices remains unclear. To understand how this information is collected and applied, we interviewed 17 industry professionals with experience in LCA or electronics design, systematically coded the interviews, and investigated common themes. These themes highlight the challenge of LCA data collection and reveal distributed decision-making processes where responsibility for sustainable design choices, and their associated costs, is often ambiguous. Our analysis identifies opportunities for HCI technologies to support LCA computation and its integration into the design process to facilitate sustainability-oriented decision-making. While this work provides a nuanced discussion about sustainable design in the information and communication technologies (ICT) hardware industry, we hope our insights will also be valuable to other sectors.

  PublisherOA PDFDOI

• Flexible and Stretchable Vitrimers for Sustainable Electronics

  ACS Applied Materials & Interfaces · 2025-01-31 · 10 citations

  article

  The rapid increase in electronic waste (e-waste) necessitates sustainable materials that combine functionality with recyclability. Here, we introduce a novel approach for creating flexible vitrimers─reprocessable polymers with dynamic covalent bonds─for use in electronic applications, such as wiring and connectors. By extending polymer chains and employing transesterification reaction, we develop vitrimers that exhibit tunable viscoelastic properties, high stretchability (over 250% tensile strain), and enhanced toughness (up to 466 J/m3). Our vitrimers demonstrate a topological freezing temperature (Tv) of 185–248 °C, adjustable through catalyst concentration and chain length. The materials are synthesized by using a two-step process involving widely available industrial chemicals. Molecular dynamics simulations provide insight into how chain extension and network topology affect viscoelasticity, supporting the experimental findings. Using transesterification, covalent bonding between flexible and rigid vitrimers can be achieved. We prototype a functional USB cable that successfully transfers power and data, showcases repairability, and is recyclable through a solvent-based process. These results highlight the potential of flexible vitrimers in reducing e-waste and advancing sustainable electronic manufacturing.

  PublisherDOI

• Towards Autonomous Sustainability Assessment via Multimodal AI Agents

  ArXiv.org · 2025-07-22 · 1 citations

  preprintOpen accessSenior author

  Interest in sustainability information has surged in recent years. However, the data required for a life cycle assessment (LCA) that maps the materials and processes from product manufacturing to disposal into environmental impacts (EI) are often unavailable. Here we reimagine conventional LCA by introducing multimodal AI agents that emulate interactions between LCA experts and stakeholders like product managers and engineers to calculate the cradle-to-gate (production) carbon emissions of electronic devices. The AI agents iteratively generate a detailed life-cycle inventory leveraging a custom data abstraction and software tools that extract information from online text and images from repair communities and government certifications. This approach reduces weeks or months of expert time to under one minute and closes data availability gaps while yielding carbon footprint estimates within 19% of expert LCAs with zero proprietary data. Additionally, we develop a method to directly estimate EI by comparing an input to a cluster of products with similar descriptions and known carbon footprints. This runs in 3 ms on a laptop with a MAPE of 12.28% on electronic products. Further, we develop a data-driven method to generate emission factors. We use the properties of an unknown material to represent it as a weighted sum of emission factors for similar materials. Compared to human experts picking the closest LCA database entry, this improves MAPE by 120.26%. We analyze the data and compute scaling of this approach and discuss its implications for future LCA workflows.

  PublisherOA PDFDOI

• Flexible and Recyclable Vitrimers for Sustainable Electronic Composites

  Zenodo (CERN European Organization for Nuclear Research) · 2025-01-01

  articleOpen access

  Flexible electronic composites made from dynamic vitrimer networks offer tunable properties, recyclability, and repairability, enabling sustainable devices like USB cables to reduce e-waste

  PublisherDOI

• Tool or Toy? Student Views on ChatGPT in Culturally Responsive Computing Education: A Preliminary Study

  2025-09-21

  article

  Despite ongoing efforts to diversify engineering, underrepresented minority (URM) students face persistent systemic barriers to equitable participation. Beyond just access, culturally relevant pedagogy (CRP) and near-peer mentorship have shown to improve student engagement and retention. However, the currently sparse pool of URM STEM graduates limits students' access to formally educated mentors of similar cultural and ethnic backgrounds, challenging the scalability of representative CRP-based engineering programs. Free AI tools like large language models (LLMs) can offer novice programmers natural language support for debugging code and exploring new concepts, but it remains unclear whether they can provide enough technical support to help scale URM-led engineering education programs. We investigate the potential for LLMs, specifically ChatGPT 3.5, to meaningfully support CRP in an embedded systems summer course taught at a community center within the AVELA - A Vision for Engineering Literacy & Access framework. We ask how URM students will naturally adopt ChatGPT within the educational program when presented without scaffolding: as a learning tool to enhance their knowledge of class-related content, or as a toy that distracts from it? Analysis of classroom observations, student surveys, final presentations, and individual ChatGPT logs revealed a disconnect between students' personal interest and the course objectives. While students were able to use ChatGPT for course-related learning, they rarely did so. Instead, they primarily used it to enhance their knowledge of topics related to personal interest, suggesting a lack of motivation or perceived relevance of ChatGPT as a tool, rather than a lack of ability to use it. These preliminary findings suggest that without intentional integration and guidance, CRP frameworks cannot expect students to effectively leverage ChatGPT to enhance engineering related content.

  PublisherDOI

• TerraTrace - Spatio-Temporal Vegetation Signatures for Land Use Analytics

  2025-02-12

  preprintOpen access

  Every year, humanity clears 10 million hectares of forests, which releases more than 5.6 billion tonnes of greenhouse gases. This significant contribution to climate change has led to the passage of global regulations, such as the EUDR, which aims to ensure that products linked to deforestation are excluded from the European market. Satellite-based remote sensing tools are popularly used for global monitoring to enable such compliance. However, they struggle to differentiate vegetation types in farms and orchards from forests (Fig.1.A). To solve this, we develop TerraTrace, a temporal signature mapping tool that combines Spectral Vegetation Indices, Satellite Imagery, and open data like Cropland Data Layer (CDL) to estimate historical land use. The key insight is that satellite-based spectral index data shows temporal variables like agricultural practices and plant growth cycles. Specifically, we demonstrate that yearly patterns of the Normalized Difference Vegetation Index (NDVI), based on plant photosynthesis, have temporal signatures unique to different crops, can distinguish forests from crops, and follow consistent patterns across different locations. Leveraging this we make the following contributions (Fig.2):

  PublisherOA PDFDOI

• Living Sustainability: In-Context Interactive Environmental Impact Communication

  Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · 2025-09-03 · 1 citations

  articleOpen accessSenior author

  Climate change demands urgent action, yet understanding the environmental impact (EI) of everyday objects and activities remains challenging for the general public. While Life Cycle Assessment (LCA) offers a comprehensive framework for EI analysis, its traditional implementation requires extensive domain expertise, structured input data, and significant time investment, creating barriers for non-experts seeking real-time sustainability insights. Here we present the first autonomous sustainability assessment tool that bridges this gap by transforming unstructured natural language descriptions into in-context, interactive EI visualizations. Our approach combines language modeling and AI agents, and achieves >97% accuracy in transforming natural language into a data abstraction designed for simplified LCA modeling. The system employs a non-parametric datastore to integrate proprietary LCA databases while maintaining data source attribution and allowing personalized source management. We demonstrate through case studies that our system achieves results within 11% of traditional full LCA, while accelerating from hours of expert time to real-time. We conducted a formative elicitation study (N=6) to inform the design objectives of such EI communication augmentation tools. We implemented and deployed the tool as a Chromium browser extension and further evaluated it through a user study (N=12). This work represents a significant step toward democratizing access to environmental impact information for the general public with zero LCA expertise.

  PublisherOA PDFDOI

Frequent coauthors

• Shyamnath Gollakota

  University of Washington

  31 shared

• Shwetak Patel

  University of Washington

  20 shared

• Zachary Englhardt

  University of Washington

  15 shared

• Zhihan Zhang

  11 shared

• Vicente Arroyos

  10 shared

• Sawyer B. Fuller

  10 shared

• Kyle Johnson

  8 shared

• Anran Wang

  Zhejiang University

  8 shared

Labs

• Vikram Iyer LabPI

  Interdisciplinary approach to connect ideas between different engineering domains to build end-to-end systems that push the boundaries of technology, with a particular focus on environmental sustainability.

Education

• PhD, Electrical and Computer Engineering

  University of Washington

  2021

• BS, Electrical Engineering and Computer Science

  University of California Berkeley

  2015

Awards & honors

• NSF CAREER Award
• SIGMOBILE Dissertation Award
• Marconi Society Paul Baran Young Scholar award
• best paper awards