Jiancong Li | Neutron Imaging ,Image Segmentation ,Deep learning | Research Excellence Award

PublishedΒ on by Physicist Particle

Research Excellence Award

Jiancong Li
Researcher Jiancong Li
Affiliation China Spallation Neutron Source
Country China
Scopus ID 59758322200
Documents 4
Citations 3
h-index 1
Subject Area Neutron Imaging, Image Segmentation, Deep Learning
Event Global Particle Physics Excellence Awards

Jiancong Li is a researcher affiliated with the China Spallation Neutron Source, China, whose scholarly activities are associated with neutron imaging, image segmentation methodologies, and deep learning applications. His research profile reflects interdisciplinary work at the intersection of particle science instrumentation, imaging technologies, and computational analysis. These areas contribute to the advancement of data interpretation and visualization techniques relevant to modern neutron-based experimental facilities.[1]

Abstract

This article presents an overview of the academic profile and research activities of Jiancong Li. The research themes associated with his scholarly work include neutron imaging, image segmentation, and deep learning-driven analytical techniques. These fields are increasingly important for the processing, visualization, and interpretation of scientific imaging data generated in advanced research infrastructures such as neutron scattering and spallation facilities.[1][2]

Keywords

  • Neutron Imaging
  • Image Segmentation
  • Deep Learning
  • Scientific Computing
  • Data Analysis
  • Particle Physics Instrumentation

Introduction

Neutron imaging has emerged as a valuable non-destructive investigation technique used in materials science, engineering, energy research, and particle science infrastructure. The integration of artificial intelligence and deep learning algorithms has expanded the capabilities of image processing systems by improving segmentation accuracy, feature recognition, and automated analysis.[2][3]

Research Profile

According to publicly available author-indexed records, Jiancong Li is associated with the China Spallation Neutron Source and has a documented publication profile indexed through Scopus. His recorded scholarly metrics include publications, citations, and an h-index that collectively reflect ongoing participation in scientific research and dissemination activities.[1]

  • Affiliation with a major neutron science research facility.
  • Research involvement in imaging technologies.

Research Contributions

The primary areas associated with Jiancong Li’s research include neutron imaging and machine-learning-assisted image analysis. These disciplines are increasingly important in scientific facilities where large imaging datasets require automated interpretation and reliable feature extraction. Deep learning models have demonstrated effectiveness in segmentation and classification tasks, supporting improved experimental efficiency and reproducibility.[2][3]

Publications

Publicly indexed records indicate that Jiancong Li has authored and co-authored scholarly works within his research specialties. These publications contribute to ongoing scientific discussions related to imaging technologies, computational methods, and analytical innovation.[1]

  • Neutron imaging applications and methodologies.
  • Image segmentation techniques using machine learning.

Research Impact

Through participation in these research areas, Jiancong Li contributes to the broader scientific effort aimed at improving analytical precision and computational efficiency in advanced research environments.[1]

Award Suitability

The Research Excellence Award category recognizes researchers who demonstrate scholarly engagement, publication activity, and contributions to advancing scientific knowledge.His profile reflects participation in research areas relevant to modern particle science infrastructure and data-intensive scientific investigations.[1][3]

Conclusion

Jiancong Li’s academic profile highlights research interests focused on neutron imaging, image segmentation, and deep learning. These areas contribute to the ongoing evolution of scientific imaging and computational analysis. Through association with the China Spallation Neutron Source and participation in interdisciplinary research, his work represents an example of contemporary scientific engagement within advanced research infrastructures.[1]

References

  1. Elsevier. (n.d.). Scopus author details: Jiancong Li, Author ID 59758322200. Scopus.
    https://www.scopus.com/authid/detail.uri?authorId=59758322200
  2. Li, J., Wang, S., Shu, X., Dong, L., Wang, Z., Lei, Y., & Chen, J. (2026). Application of deep learning to crack segmentation in neutron CT images of ancient shu dao (δΉ¦εˆ€). Digital Applications in Archaeology and Cultural Heritage, 41, e00532.
    https://doi.org/10.1016/j.daach.2026.e00532
  3. Global Particle Physics Excellence Awards. (n.d.). Physicist Particle.
    https://physicistparticle.com/

“`

Vaneet | Machine Learning | Best Researcher Award

PublishedΒ on by Physicist Particle

Prof. Dr. Vaneet | Machine Learning | Best Researcher Award

Professor at PURDUE UNIVERSITY, United States

vaneet aggarwal is a distinguished professor and university faculty scholar at purdue university, specializing in reinforcement learning, generative AI, quantum machine learning, and LLM alignment πŸ€–βš›οΈ. With a Ph.D. from Princeton University πŸŽ“ and extensive experience in industry and academia, he has made groundbreaking contributions to networking, robotics, healthcare, and computational biology 🌍🩺. He has served as a visiting professor at KAUST, IIIT Delhi, and IISc Bangalore πŸ“š and has led major research initiatives at AT&T Labs and Purdue CLAN Labs. His work has been recognized globally through high-impact publications and awards πŸ….

Professional ProfileΒ 

Education & Experience πŸŽ“πŸ’Ό

πŸ“Œ Education:

  • Ph.D. in Electrical Engineering – Princeton University, 2010 πŸŽ“ (GPA 4.0/4.0)
  • M.A. in Electrical Engineering – Princeton University, 2007 πŸ… (GPA 4.0/4.0)
  • B.Tech in Electrical Engineering – IIT Kanpur, 2005 πŸŽ“ (GPA 9.6/10)

πŸ“Œ Experience:

  • Purdue University (2015–Present) 🏫 – Professor & University Faculty Scholar
  • KAUST, Saudi Arabia (2022–2023) 🏝️ – Visiting Professor
  • IIIT Delhi (2022–2023) 🌏 – Adjunct Professor
  • Plaksha University (2022–2023) πŸ“‘ – Adjunct Professor
  • IISc Bangalore (2018–2019) πŸ† – VAJRA Adjunct Faculty
  • AT&T Labs Research, NJ (2010–2014) πŸ“‘ – Senior Member, Technical Staff
  • Columbia University, NY (2013–2014) πŸ“š – Adjunct Assistant Professor

Professional Development πŸš€πŸ“š

vaneet aggarwal has consistently contributed to cutting-edge advancements in AI, machine learning, and quantum computing 🧠⚑. As Editor-in-Chief of the ACM Journal of Transportation Systems πŸš—πŸ“–, he shapes global research trends. He has been a technical lead in Purdue’s AI and security programs, fostering industry collaborations πŸ€πŸ’‘. His leadership in AI decision-making, intelligent infrastructures, and computational biology has driven groundbreaking innovations πŸ—οΈπŸ”¬. He frequently mentors Ph.D. students and collaborates with top institutions worldwide, ensuring continuous academic excellence and technological impact 🌍🎯. His work bridges fundamental research with real-world applications, influencing multiple industries πŸš€.

Research Focus Areas πŸ”πŸ’‘

πŸ”¬ Artificial Intelligence & Machine Learning: Reinforcement learning, generative AI, LLM alignment πŸ€–
βš›οΈ Quantum Computing: Quantum machine learning, hidden Markov models 🧠
πŸ“‘ Networking & Systems: Cloud computing, 5G/6G networks, network virtualization 🌐
πŸ› οΈ Optimization & Control: Combinatorial bandits, linear optimization βš™οΈ
πŸš— Transportation & Robotics: AI for intelligent infrastructure and automation 🏎️
🩺 Healthcare & Biomedical AI: Drug discovery, computational biology, medical AI πŸ§¬πŸ’Š

His research transforms fundamental theories into real-world applications, influencing technology, healthcare, and sustainable infrastructure 🌍.

Awards & Honors πŸ…πŸŽ–οΈ

πŸ† University Faculty Scholar, Purdue University (2024) 🏫
πŸŽ–οΈ Best Paper Award – NeurIPS Workshop on Cooperative AI (2021) πŸ“
πŸ“š VAJRA Adjunct Faculty, IISc Bangalore (2018–2019) πŸ”¬
πŸ₯‡ Editor-in-Chief, ACM Journal of Transportation Systems (2022–Present) πŸš—πŸ“–
🌍 Senior Member, IEEE & ACM ⚑
πŸ… Best Research Contributions in AI & Quantum Computing πŸ€–βš›οΈ

Publication Top Notes

1. Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback

  • Authors: Mohammad Pedramfar, Vaneet Aggarwal
  • Published in: IEEE Transactions on Artificial Intelligence, 2025
  • Summary: This paper addresses the combinatorial multi-armed bandit problem with stochastic submodular rewards and delayed, composite anonymous feedback. The authors analyze three delay modelsβ€”bounded adversarial, stochastic independent, and stochastic conditionally independentβ€”and derive regret bounds for each. Their findings indicate that delays introduce an additive term in the regret, affecting overall performance.
  • Access: The paper is available as open access.

2. FilFL: Client Filtering for Optimized Client Participation in Federated Learning

  • Authors: Fares Fourati, Salma Kharrat, Vaneet Aggarwal, Mohamed-Slim Alouini, Marco Canini
  • Published in: [No source information available]
  • Summary: This conference paper introduces FilFL, a method to enhance federated learning by optimizing client participation through a filtering mechanism. By selecting a subset of clients that maximizes a combinatorial objective function, FilFL aims to improve learning efficiency, accelerate convergence, and boost model accuracy. Empirical evaluations demonstrate benefits such as faster convergence and up to a 10% increase in test accuracy compared to scenarios without client filtering.
  • Access: The paper is available as open access.

3. Prism Blockchain Enabled Internet of Things with Deep Reinforcement Learning

  • Authors: Divija Swetha Gadiraju, Vaneet Aggarwal
  • Published in: Blockchain: Research and Applications, 2024
  • Summary: This article explores the integration of Prism blockchain technology with the Internet of Things (IoT) using deep reinforcement learning techniques. The approach aims to enhance security, scalability, and efficiency in IoT networks by leveraging the unique features of Prism blockchain and the adaptive capabilities of deep reinforcement learning.
  • Access: The paper is available as open access.

4. GLIDE: Multi-Agent Deep Reinforcement Learning for Coordinated UAV Control in Dynamic Military Environments

  • Authors: Divija Swetha Gadiraju, Prasenjit Karmakar, Vijay K. Shah, Vaneet Aggarwal
  • Published in: Information (Switzerland), 2024
  • Summary: GLIDE presents a multi-agent deep reinforcement learning framework designed for the coordinated control of unmanned aerial vehicles (UAVs) in dynamic military settings. The framework focuses on enhancing mission success rates and operational efficiency by enabling UAVs to adapt to changing environments and collaborate effectively.
  • Access: The paper is available as open access.

5. Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

  • Authors: Washim Uddin Mondal, Veni Goyal, Satish V. Ukkusuri, Mohamed-Slim Alouini, Vaneet Aggarwal
  • Published in: IEEE Networking Letters, 2024
  • Summary: This article proposes a method for estimating coverage manifolds in cellular networks using conditional Generative Adversarial Networks (GANs). The approach aims to achieve near-perfect coverage predictions, which are crucial for optimizing network performance and ensuring reliable communication services.
  • Access: The paper is available as open access.

Conclusion

vaneet aggarwal is a highly suitable candidate for the Best Researcher Award, given his strong publication record, leadership, and multidisciplinary impact. If he strengthens his global recognition, large-scale funding acquisition, and public engagement, he could be an even stronger contender for such an award.