arXiv subjects

Shuliang Wang

Publications and source records attributed to Shuliang Wang.

17 recordsLinked to original sources

arXiv2026

Prior Knowledge-enhanced Spatio-temporal Epidemic Forecasting

Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidemic signals, over-simplified spatial relations, and unstable parameter estimation. To address these challenges, we propose the Spatio-Temporal priOr-aware Epidemic Predictor (STOEP), a novel hybrid framework that integrates implicit spatio-temporal priors and explicit expert priors. STOEP consists of three key components: (1) Case-aware Adjacency Learning (CAL), which dynamically adjusts mobility-based regional dependencies using historical infection patterns; (2) Space-informed Parameter Estimating (SPE), which employs learnable spatial priors to amplify weak epidemic signals; and (3) Filter-based Mechanistic Forecasting (FMF), which uses an expert-guided adaptive thresholding strategy to regularize epidemic parameters. Extensive experiments on real-world COVID-19 and influenza datasets demonstrate that STOEP outperforms the best baseline by 11.1% in RMSE. The system has been deployed at a provincial CDC in China to facilitate downstream applications.

cs.LG↗

arXiv2026

Meta Dynamic Graph for Traffic Flow Prediction

Traffic flow prediction is a typical spatio-temporal prediction problem and has a wide range of applications. The core challenge lies in modeling the underlying complex spatio-temporal dependencies. Various methods have been proposed, and recent studies show that the modeling of dynamics is useful to meet the core challenge. While handling spatial dependencies and temporal dependencies using separate base model structures may hinder the modeling of spatio-temporal correlations, the modeling of dynamics can bridge this gap. Incorporating spatio-temporal heterogeneity also advances the main goal, since it can extend the parameter space and allow more flexibility. Despite these advances, two limitations persist: 1) the modeling of dynamics is often limited to the dynamics of spatial topology (e.g., adjacency matrix changes), which, however, can be extended to a broader scope; 2) the modeling of heterogeneity is often separated for spatial and temporal dimensions, but this gap can also be bridged by the modeling of dynamics. To address the above limitations, we propose a novel framework for traffic prediction, called Meta Dynamic Graph (MetaDG). MetaDG leverages dynamic graph structures of node representations to explicitly model spatio-temporal dynamics. This generates both dynamic adjacency matrices and meta-parameters, extending dynamic modeling beyond topology while unifying the capture of spatio-temporal heterogeneity into a single dimension. Extensive experiments on four real-world datasets validate the effectiveness of MetaDG.

cs.LG↗

arXiv2025

UREM: A High-performance Unified and Resilient Enhancement Method for Multi- and High-Dimensional Indexes

Numerous multi- or high-dimensional indexes with distinct advantages have been proposed on various platforms to meet application requirements. To achieve higher-performance queries, most indexes employ enhancement methods, including structure-oriented and layout-oriented enhancement methods. Existing structure-oriented methods tailored to specific indexes work well under static workloads but lack generality and degrade under dynamic workloads. The layout-oriented methods exhibit good generality and perform well under dynamic workloads, but exhibit suboptimal performance under static workloads. Therefore, it is an open challenge to develop a unified and resilient enhancement method that can improve query performance for different indexes adaptively under different scenarios. In this paper, we propose UREM, which is the first high-performance Unified and Resilient Enhancement Method designed for both multi- and high-dimensional indexes, capable of adapting to different scenarios. Specifically, UREM (1) can be uniformly applied with different indexes on various platforms; (2) enhances the query performance of indexes by layout optimization under static workloads; (3) enables indexes to stabilize performance when queries shift through partial layout reorganization. We evaluate UREM on 20 widely used indexes. Experimental results demonstrate that UREM improves the query performance of multi- and high-dimensional indexes by up to 5.73x and 9.18x under static workloads, and by an average of 5.72x and 9.47x under dynamic workloads. Moreover, some traditional indexes enhanced by UREM even achieve performance comparable to or even surpassing that of recent advanced indexes.

cs.DB↗

arXiv2024

Detecting outliers by clustering algorithms

Clustering and outlier detection are two important tasks in data mining. Outliers frequently interfere with clustering algorithms to determine the similarity between objects, resulting in unreliable clustering results. Currently, only a few clustering algorithms (e.g., DBSCAN) have the ability to detect outliers to eliminate interference. For other clustering algorithms, it is tedious to introduce another outlier detection task to eliminate outliers before each clustering process. Obviously, how to equip more clustering algorithms with outlier detection ability is very meaningful. Although a common strategy allows clustering algorithms to detect outliers based on the distance between objects and clusters, it is contradictory to improving the performance of clustering algorithms on the datasets with outliers. In this paper, we propose a novel outlier detection approach, called ODAR, for clustering. ODAR maps outliers and normal objects into two separated clusters by feature transformation. As a result, any clustering algorithm can detect outliers by identifying clusters. Experiments show that ODAR is robust to diverse datasets. Compared with baseline methods, the clustering algorithms achieve the best on 7 out of 10 datasets with the help of ODAR, with at least 5% improvement in accuracy.

cs.LG↗

arXiv2024

MQRLD: A Multimodal Data Retrieval Platform with Query-aware Feature Representation and Learned Index Based on Data Lake

Multimodal data has become a crucial element in the realm of big data analytics, driving advancements in data exploration, data mining, and empowering artificial intelligence applications. To support high-quality retrieval for these cutting-edge applications, a robust multimodal data retrieval platform should meet the challenges of transparent data storage, rich hybrid queries, effective feature representation, and high query efficiency. However, among the existing platforms, traditional schema-on-write systems, multi-model databases, vector databases, and data lakes, which are the primary options for multimodal data retrieval, make it difficult to fulfill these challenges simultaneously. Therefore, there is an urgent need to develop a more versatile multimodal data retrieval platform to address these issues. In this paper, we introduce a Multimodal Data Retrieval Platform with Query-aware Feature Representation and Learned Index based on Data Lake (MQRLD). It leverages the transparent storage capabilities of data lakes, integrates the multimodal open API to provide a unified interface that supports rich hybrid queries, introduces a query-aware multimodal data feature representation strategy to obtain effective features, and offers high-dimensional learned indexes to optimize data query. We conduct a comparative analysis of the query performance of MQRLD against other methods for rich hybrid queries. Our results underscore the superior efficiency of MQRLD in handling multimodal data retrieval tasks, demonstrating its potential to significantly improve retrieval performance in complex environments. We also clarify some potential concerns in the discussion.

cs.DB↗

arXiv2024

A parameter-free clustering algorithm for missing datasets

Missing datasets, in which some objects have missing values in certain dimensions, are prevalent in the Real-world. Existing clustering algorithms for missing datasets first impute the missing values and then perform clustering. However, both the imputation and clustering processes require input parameters. Too many input parameters inevitably increase the difficulty of obtaining accurate clustering results. Although some studies have shown that decision graphs can replace the input parameters of clustering algorithms, current decision graphs require equivalent dimensions among objects and are therefore not suitable for missing datasets. To this end, we propose a Single-Dimensional Clustering algorithm, i.e., SDC. SDC, which removes the imputation process and adapts the decision graph to the missing datasets by splitting dimension and partition intersection fusion, can obtain valid clustering results on the missing datasets without input parameters. Experiments demonstrate that, across three evaluation metrics, SDC outperforms baseline algorithms by at least 13.7%(NMI), 23.8%(ARI), and 8.1%(Purity).

cs.LG↗

arXiv2023

A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning

Construction of dictionaries using nonnegative matrix factorisation (NMF) has extensive applications in signal processing and machine learning. With the advances in deep learning, training compact and robust dictionaries using deep neural networks, i.e., dictionaries of deep features, has been proposed. In this study, we propose a probabilistic generative model which employs a variational autoencoder (VAE) to perform nonnegative dictionary learning. In contrast to the existing VAE models, we cast the model under a statistical framework with latent variables obeying a Gamma distribution and design a new loss function to guarantee the nonnegative dictionaries. We adopt an acceptance-rejection sampling reparameterization trick to update the latent variables iteratively. We apply the dictionaries learned from VAE-NMF to two signal processing tasks, i.e., enhancement of speech and extraction of muscle synergies. Experimental results demonstrate that VAE-NMF performs better in learning the latent nonnegative dictionaries in comparison with state-of-the-art methods.

cs.LG↗

arXiv2022

Information Systems Dynamics: Foundations and Applications

This article firstly reviews and summarizes the rapid development of information technology, characterized by the close combination of computer and network communication, which leads to a series of investigations, including the analyses of the important role of a series of technological achievements in the context of information movement and application, the interrelationship between the real-world, information space and information system, and the integrated framework of the real-world and information system, and the modifications and improvements of the Xu's previous mathematical theory on information models, properties and metrics. Based on the mathematical foundations, eleven types of information measure efficacies and their distribution across information systems are put forward, and then the dynamics configurations of information systems are comprehensively analyzed, which constitutes the basic theoretical framework of information systems dynamics with general significance. Finally, Smart Court SoSs (System of Systems) Engineering Project of China are introduced as the exemplified application of the theoretical work, which aims at providing a reference for the analysis, design, development and evaluation of large-scale complex information systems.

cs.IT↗

arXiv2022

Cost-effective Land Cover Classification for Remote Sensing Images

Land cover maps are of vital importance to various fields such as land use policy development, ecosystem services, urban planning and agriculture monitoring, which are mainly generated from remote sensing image classification techniques. Traditional land cover classification usually needs tremendous computational resources, which often becomes a huge burden to the remote sensing community. Undoubtedly cloud computing is one of the best choices for land cover classification, however, if not managed properly, the computation cost on the cloud could be surprisingly high. Recently, cutting the unnecessary computation long tail has become a promising solution for saving the cost in the cloud. For land cover classification, it is generally not necessary to achieve the best accuracy and 85% can be regarded as a reliable land cover classification. Therefore, in this paper, we propose a framework for cost-effective remote sensing classification. Given the desired accuracy, the clustering algorithm can stop early for cost-saving whilst achieving sufficient accuracy for land cover image classification. Experimental results show that achieving 85%-99.9% accuracy needs only 27.34%-60.83% of the total cloud computation cost for achieving a 100% accuracy. To put it into perspective, for the US land cover classification example, the proposed approach can save over $1,593,490.18 for the government in each single-use when the desired accuracy is 90%.

cs.DC↗

arXiv2022

Position-enhanced and Time-aware Graph Convolutional Network for Sequential Recommendations

Most of the existing deep learning-based sequential recommendation approaches utilize the recurrent neural network architecture or self-attention to model the sequential patterns and temporal influence among a user's historical behavior and learn the user's preference at a specific time. However, these methods have two main drawbacks. First, they focus on modeling users' dynamic states from a user-centric perspective and always neglect the dynamics of items over time. Second, most of them deal with only the first-order user-item interactions and do not consider the high-order connectivity between users and items, which has recently been proved helpful for the sequential recommendation. To address the above problems, in this article, we attempt to model user-item interactions by a bipartite graph structure and propose a new recommendation approach based on a Position-enhanced and Time-aware Graph Convolutional Network (PTGCN) for the sequential recommendation. PTGCN models the sequential patterns and temporal dynamics between user-item interactions by defining a position-enhanced and time-aware graph convolution operation and learning the dynamic representations of users and items simultaneously on the bipartite graph with a self-attention aggregator. Also, it realizes the high-order connectivity between users and items by stacking multi-layer graph convolutions. To demonstrate the effectiveness of PTGCN, we carried out a comprehensive evaluation of PTGCN on three real-world datasets of different sizes compared with a few competitive baselines. Experimental results indicate that PTGCN outperforms several state-of-the-art models in terms of two commonly-used evaluation metrics for ranking.

cs.IR↗

arXiv2020

High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone and a key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC)layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message-passing of meaningless features by dynamically learning di-rection and degree of linkage. When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer not only take full use of alignment learned by graph matching but also re-place sensitive one-to-one matching with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.

cs.CV↗

arXiv2019

Cutting the Unnecessary Long Tail: Cost-Effective Big Data Clustering in the Cloud

Clustering big data often requires tremendous computational resources where cloud computing is undoubtedly one of the promising solutions. However, the computation cost in the cloud can be unexpectedly high if it cannot be managed properly. The long tail phenomenon has been observed widely in the big data clustering area, which indicates that the majority of time is often consumed in the middle to late stages in the clustering process. In this research, we try to cut the unnecessary long tail in the clustering process to achieve a sufficiently satisfactory accuracy at the lowest possible computation cost. A novel approach is proposed to achieve cost-effective big data clustering in the cloud. By training the regression model with the sampling data, we can make widely used k-means and EM (Expectation-Maximization) algorithms stop automatically at an early point when the desired accuracy is obtained. Experiments are conducted on four popular data sets and the results demonstrate that both k-means and EM algorithms can achieve high cost-effectiveness in the cloud with our proposed approach. For example, in the case studies with the much more efficient k-means algorithm, we find that achieving a 99% accuracy needs only 47.71%-71.14% of the computation cost required for achieving a 100% accuracy while the less efficient EM algorithm needs 16.69%-32.04% of the computation cost. To put that into perspective, in the United States land use classification example, our approach can save up to $94,687.49 for the government in each use.

cs.DC↗

arXiv2015

Comment on "Clustering by fast search and find of density peaks"

In [1], a clustering algorithm was given to find the centers of clusters quickly. However, the accuracy of this algorithm heavily depend on the threshold value of d-c. Furthermore, [1] has not provided any efficient way to select the threshold value of d-c, that is, one can have to estimate the value of d_c depend on one's subjective experience. In this paper, based on the data field [2], we propose a new way to automatically extract the threshold value of d_c from the original data set by using the potential entropy of data field. For any data set to be clustered, the most reasonable value of d_c can be objectively calculated from the data set by using our proposed method. The same experiments in [1] are redone with our proposed method on the same experimental data set used in [1], the results of which shows that the problem to calculate the threshold value of d_c in [1] has been solved by using our method.

cs.LG↗

arXiv2014

Adaptive Minimum-Maximum Exclusive Mean Filter for Impulse Noise Removal

Many filters are proposed for impulse noise removal. However, they are hard to keep excellent denoising performance with high computational efficiency. In response to this difficulty, this paper presents a novel fast filter, adaptive minimum-maximum exclusive mean (AMMEM) filter to remove impulse noise. Although the AMMEM filter is a variety of the maximum-minimum exclusive mean (MMEM) filter, however, the AMMEM filter inherits the advantages, and overcomes the drawbacks, compared with the MMEM filter. To increase the various performances of noise removal, the AMMEM filter uses an adaptive size window, introduces two flexible factors, projection factor P and detection factor T, and limits the calculation scope of the AVG. The experimental results show the AMMEM filter makes a significant improvement in terms of noise detection, image restoration, and computational efficiency. Even at noise level as high as 95%, the AMMEM filter still can restore the images with good visual effect.

cs.OH↗

arXiv2014

A Novel Method to Extract Rocks from Mars Images

In this paper, a novel method is proposed to extract rocks from Martian surface images by using 8 data field. It models the interaction between two pixels of an image in the context of imagery 9 characteristics. First, foreground rocks are differed from background information by binarizing 10 image on roughly partitioned images. Second, foreground rocks are grouped into clusters by 11 locating the centers and edges of clusters in data field via hierarchical grids. Third, the target 12 rocks are discovered for the Mars Exploration Rover (MER) to keep healthy paths. The 13 experiment with images taken by MER shows the proposed method is practical and potential.

cs.CV↗

arXiv2014

Analyzing Large Biological Datasets with an Improved Algorithm for MIC

A computational framework utilizes the traditional similarity measures for mining the significant relationships in biological annotations is recently proposed by Tatiana V. Karpinets et al. [2]. In this paper, an improved approximation algorithm for MIC (maximal information coefficient) named IAMIC is suggested to perfect this framework for discovering the hidden regularities between biological annotations. Further, IAMIC is the enhanced algorithm for approximating a novel similarity coefficient MIC with generality and equitability, which makes it more appropriate for data exploration. Here it is shown that IAMIC is also applicable for identify the associations between biological annotations.

cs.DB↗

arXiv2013

Algorithm and approaches to handle large Data- A Survey

Data mining environment produces a large amount of data, that need to be analyzed, patterns have to be extracted from that to gain knowledge. In this new era with boom of data both structured and unstructured, in the field of genomics, meteorology, biology, environmental research and many others, it has become difficult to process, manage and analyze patterns using traditional databases and architectures. So, a proper architecture should be understood to gain knowledge about the Big Data. This paper presents a review of various algorithms from 1994-2013 necessary for handling such large data set. These algorithms define various structures and methods implemented to handle Big Data, also in the paper are listed various tool that were developed for analyzing them.

cs.DB↗