Summary of Heterogenous Multi-source Data Fusion Through Input Mapping and Latent Variable Gaussian Process, by Yigitcan Comlek et al.
Heterogenous Multi-Source Data Fusion Through Input Mapping and Latent Variable Gaussian Process
by Yigitcan Comlek, Sandipp Krishnan Ravi, Piyush Pandita, Sayan Ghosh, Liping Wang, Wei Chen
First submitted to arxiv on: 15 Jul 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a heterogeneous multi-source data fusion framework for combining different sources of data with varying input parameter spaces. The framework uses input mapping calibration (IMC) to transform the heterogeneous inputs into a unified reference space, followed by a latent variable Gaussian process (LVGP)-based multi-source data fusion model to build a single source-aware surrogate model. The proposed framework is demonstrated on three engineering case studies, showing improved predictive accuracy compared to traditional approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to combine different sources of data that have different input parameters. This can be useful in engineering when you need to use information from multiple sources to make predictions or design something. The authors suggest using a special kind of map called IMC to match the different inputs together, and then another type of model called LVGP to combine the data. They show how this works on some real-world problems, like designing a beam or modeling the properties of a material. |
