Author name cluster

Zeping Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2025 Journal Article

Intelligent fault diagnosis of nonlinear uncertain industrial processes based on kernel local–global interval embedding algorithm

Ning Li
Hua Ding
Xiaochun Sun
Zeping Liu

With the rapid development of a new generation of Big Data and artificial intelligence, intelligent fault diagnosis of industrial processes including chemical processes, coal mining equipment operations, etc. , has become increasingly important. The local–global interval embedding algorithm (LGIEA) has attracted significant attention for its capability to simultaneously extract local and global features from interval data. However, this method can only process linear interval data and performs poorly in terms of extracting strong nonlinear features. To solve the problem, this study proposes a new intelligent fault diagnosis method based on kernel LGIEA (KLGIEA), which extends the linear process monitoring model to nonlinearity. First, the interval inner product estimation (IIPE) is transformed into the kernel IIPE by introducing kernel function, which can not only inherit the advantage that LGIEA can extract both global and local features of data simultaneously, but also has stronger applicability to nonlinear data in industrial processes. Second, the four statistics defined can effectively monitor the fault of industrial equipment under strong interference environment such as noises, and the nonlinear reconstruction contribution (NRC) can effectively identify the fault variables, improve the fault diagnosis ability of KLGIEA. Finally, two cases of the Tennessee Eastman process (TEP) simulation data from Eastman Company and site shearer fault data obtained from Shaqu No. 2 coal mine show that KLGIEA is significantly superior to complete information principal component analysis (PCA), midpoint-radius kernel PCA, and LGIEA in processing nonlinear interval data, improving accuracy, applicability, and reliability of algorithm.

Details DOI

NeurIPS Conference 2025 Conference Paper

LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space

Zhangyu Wang
Zeping Liu
Jielu Zhang
Zhongliang Zhou
Qian Cao
Nemin Wu
Lan Mu
Yang Song

Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval, whose spatial generalizability significantly suffers if the spatial distribution of test images does not align with the choices of grids and galleries. Recently emerging generative approaches, while getting rid of grids and galleries, use raw geographical coordinates and suffer quality losses due to their lack of multi-scale information. To address these limitations, we propose a multi-scale latent diffusion model called LocDiff for image geolocalization. We developed a novel positional encoding-decoding framework called Spherical Harmonics Dirac Delta (SHDD) Representations, which encodes points on a spherical surface (e. g. , geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking on spherical probability distributions. We also propose a novel SirenNet-based architecture (CS-UNet) to learn an image-based conditional backward process in the latent SHDD space by minimizing a latent KL-divergence loss. To the best of our knowledge, LocDiff is the first image geolocalization model that performs latent diffusion in a multi-scale location encoding space and generates geolocations under the guidance of images. Experimental results show that LocDiff can outperform all state-of-the-art grid-based, retrieval-based, and diffusion-based baselines across 5 challenging global-scale image geolocalization datasets, and demonstrates significantly stronger generalizability to unseen geolocations.

PDF Details

NeurIPS Conference 2024 Conference Paper

TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning

Nemin Wu
Qian Cao
Zhangyu Wang
Zeping Liu
Yanlin Qi
Jielu Zhang
Joshua Ni
Xiaobai Yao

Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e. g. , points, polylines, polygons, networks, images, etc. ) in their native formats. Learning good spatial representations is a fundamental problem for various downstream applications such as species distribution modeling, weather forecasting, trajectory generation, geographic question answering, etc. Even though SRL has become the foundation of almost all geospatial artificial intelligence (GeoAI) research, we have not yet seen significant efforts to develop an extensive deep learning framework and benchmark to support SRL model development and evaluation. To fill this gap, we propose TorchSpatial, a learning framework and benchmark for location (point) encoding, which is one of the most fundamental data types of spatial representation learning. TorchSpatial contains three key components: 1) a unified location encoding framework that consolidates 15 commonly recognized location encoders, ensuring scalability and reproducibility of the implementations; 2) the LocBench benchmark tasks encompassing 7 geo-aware image classification and 10 geo-aware imageregression datasets; 3) a comprehensive suite of evaluation metrics to quantify geo-aware models’ overall performance as well as their geographic bias, with a novel Geo-Bias Score metric. Finally, we provide a detailed analysis and insights into the model performance and geographic bias of different location encoders. We believe TorchSpatial will foster future advancement of spatial representationlearning and spatial fairness in GeoAI research. The TorchSpatial model framework and LocBench benchmark are available at https: //github. com/seai-lab/TorchSpatial, and the Geo-Bias Score evaluation framework is available at https: //github. com/seai-lab/PyGBS.

PDF Details DOI