arXiv subjects

Jianqiu Xu

Publications and source records attributed to Jianqiu Xu.

9 recordsLinked to original sources

arXiv2026

NL4ST: A Natural Language Query Tool for Spatio-Temporal Databases

The advancement of mobile computing devices and positioning technologies has led to an explosive growth of spatio-temporal data managed in databases. Representative queries over such data include range queries, nearest neighbor queries, and join queries. However, formulating those queries usually requires domain-specific expertise and familiarity with executable query languages, which would be a challenging task for non-expert users. It leads to a great demand for well-supported natural language queries (NLQs) in spatio-temporal databases. To bridge the gap between non-experts and query plans in databases, we present NL4ST, an interactive tool that allows users to query spatio-temporal databases in natural language. NL4ST features a three-layer architecture: (i) knowledge base and corpus for knowledge preparation, (ii) natural language understanding for entity linking, and (iii) generating physical plans. Our demonstration will showcase how NL4ST provides effective spatio-temporal physical plans, verified by using four real and synthetic datasets. We make NL4ST online and provide the demo video at https://youtu.be/-J1R7R5WoqQ.

cs.DB↗

arXiv2026

A Tool for Semantic-Aware Spatial Corpus Construction

Spatial natural language interface to database systems provide non-expert users with convenient access to spatial data through natural language queries. However, the scarcity of high-quality spatial natural language query corpora limits the performance of such systems. Existing methods rely on manual knowledge base construction and template-based dynamic generation, which suffer from low construction efficiency and unstable corpus quality. This paper presents semantic-aware spatial corpus construction (SSCC), a tool designed for constructing high-quality spatial natural language query and executable language query pair corpora. SSCC consists of two core modules: (i) a knowledge base construction module based on spatial relations, which extracts and determines spatial relations from datasets, and (ii) a template-augmented query pair corpus generation module, which produces query pairs via template matching and parameter substitution. The tool ensures geometric consistency and adherence to spatial logic in the generated spatial relations. Experimental results demonstrate that SSCC achieves (i) a 53x efficiency improvement for knowledge base construction and (ii) a 2.5x effectiveness improvement for query pair corpus. SSCC provides high-quality corpus support for spatial natural language interface training, substantially reducing both time and labor costs in corpus construction.

cs.DB↗

arXiv2026

Multivariate Time-series Anomaly Detection via Dynamic Model Pool & Ensembling

Multivariate time-series (MTS) anomaly detection is critical in domains such as service monitor, IoT, and network security. While multi-model methods based on selection or ensembling outperform single-model ones, they still face limitations: (i) selection methods rely on a single chosen model and are sensitive to the strategy; (ii) ensembling methods often combine all models or are restricted to univariate data; and (iii) most methods depend on fixed data dimensionality, limiting scalability. To address these, we propose DMPEAD, a Dynamic Model Pool and Ensembling framework for MTS Anomaly Detection. The framework first (i) constructs a diverse model pool via parameter transfer and diversity metric, then (ii) updates it with a meta-model and similarity-based strategy for adaptive pool expansion, subset selection, and pool merging, finally (iii) ensembles top-ranked models through proxy metric ranking and top-k aggregation in the selected subset, outputting the final anomaly detection result. Extensive experiments on 8 real-world datasets show that our model outperforms all baselines, demonstrating superior adaptability and scalability.

cs.LG↗

arXiv2026

VARTS: A Tool for the Visualization and Analysis of Representative Time Series Data

Large-scale time series visualization often suffers from excessive visual clutter and redundant patterns, making it difficult for users to understand the main temporal trends. To address this challenge, we present VARTS, an interactive visual analytics tool for representative time series selection and visualization. Building upon our previous work M4-Greedy, VARTS integrates M4-based sampling, DTW-based similarity computation, and greedy selection into a unified workflow for the identification and visualization of representative series. The tool provides a responsive graphical interface that allows users to import time series datasets, perform representative selection, and visualize both raw and reduced data through multiple coordinated views. By reducing redundancy while preserving essential data patterns, VARTS effectively enhances visual clarity and interpretability for large-scale time series analysis. The demo video is available at https://youtu.be/mS9f12Rf0jo.

cs.GR↗

arXiv2026

A Graph-based Framework for Online Time Series Anomaly Detection Using Model Ensemble

With the increasing volume of streaming data in industrial systems, online anomaly detection has become a critical task. The diverse and rapidly evolving data patterns pose significant challenges for online anomaly detection. Many existing anomaly detection methods are designed for offline settings or have difficulty in handling heterogeneous streaming data effectively. This paper proposes GDME, an unsupervised graph-based framework for online time series anomaly detection using model ensemble. GDME maintains a dynamic model pool that is continuously updated by pruning underperforming models and introducing new ones. It utilizes a dynamic graph structure to represent relationships among models and employs community detection on the graph to select an appropriate subset for ensemble. The graph structure is also used to detect concept drift by monitoring structural changes, allowing the framework to adapt to evolving streaming data. Experiments on seven heterogeneous time series demonstrate that GDME outperforms existing online anomaly detection methods, achieving improvements of up to 24%. In addition, its ensemble strategy provides superior detection performance compared with both individual models and average ensembles, with competitive computational efficiency.

cs.LG↗

arXiv2025

NLI4DB: A Systematic Review of Natural Language Interfaces for Databases

As the demand for querying databases in all areas of life continues to grow, researchers have devoted significant attention to the natural language interface for databases (NLIDB). This paper presents a comprehensive survey of recently proposed NLIDBs. We begin with a brief introduction to natural language processing techniques, executable database languages and the intermediate representation between natural language and executable language, and then provide an overview of the translation process from natural language to executable database language. The translation process is divided into three stages: (i) natural language preprocessing, (ii) natural language understanding, and (iii) natural language translation. Traditional and data-driven methods are utilized in the preprocessing stage. Traditional approaches rely on predefined rules and grammars, and involve techniques such as regular expressions, dependency parsing and named entity recognition. Data-driven approaches depend on large-scale data and machine learning models, using techniques including word embedding and pattern linking. Natural language understanding methods are classified into three categories: (i) rule-based, (ii) machine learning-based, and (iii) hybrid. We then describe a general construction process for executable languages over relational and spatio-temporal databases. Subsequently, common benchmarks and evaluation metrics for transforming natural language into executable language are presented, and methods for generating new benchmarks are explored. Finally, we summarize the classification, development, and enhancement of NLIDB systems, and discuss deep language understanding and database interaction techniques related to NLIDB, including (i) using LLM for Text2SQL tasks, (ii) generating natural language interpretations from SQL, and (iii) transforming speech queries into SQL.

cs.DB↗

arXiv2024

Towards Mobility Data Science (Vision Paper)

Mobility data captures the locations of moving objects such as humans, animals, and cars. With the availability of GPS-equipped mobile devices and other inexpensive location-tracking technologies, mobility data is collected ubiquitously. In recent years, the use of mobility data has demonstrated significant impact in various domains including traffic management, urban planning, and health sciences. In this paper, we present the emerging domain of mobility data science. Towards a unified approach to mobility data science, we envision a pipeline having the following components: mobility data collection, cleaning, analysis, management, and privacy. For each of these components, we explain how mobility data science differs from general data science, we survey the current state of the art and describe open challenges for the research community in the coming years.

cs.OH↗

arXiv2016

Developing spatiotemporal solitons in step-index multimode fibers

Spatiotemporal solitons (STSs) are localized solitary waves in both space and time that involve complex linear and nonlinear processes. Optical STSs have been observed in various media, but they are difficult to be realized in multimode fibers due to their large modal dispersion. Here, we report STS mode-locking and spatiotemporal nonlinear dynamics in a step-index multimode fiber mediated by gain. Gain competition and energy redistribution among different spatial modes help nonlinearity effectively cancel both temporal splitting and spatial diffracting of the entire pulse (multicomponent soliton) and thereby maintain its shape during propagation. Optical STSs in multimode fibers therefore open a new way to clarify the fundamental science of spatiotemporal solitary waves and also imply important applications in multi-channel communications, optical switches and mode-area power scaling of fiber laser pulses.

nlin.PS↗

arXiv2015

Influences of pump transitions on thermal effects of multi-kilowatt thulium-doped fiber lasers

Thermal effects are critical constrains for developing high-power thulium-doped fiber lasers (TDFLs). In this paper, we numerically investigate the lasing and thermal characteristics of the TDFLs under different pump transitions. Our results show, the widely-used pump transition $^3H_6\rightarrow^3H_4$, taking advantages of high-power high-efficiency laser diodes at $\sim$0.8 $μ$m, may not be a superior choice for directly outputting multi-kilowatt at 2 $μ$m because of severe thermal problems. Meanwhile, using other pump transitions resulting 2-$μ$m emissions, especially the in-band pump transition $^3H_6\rightarrow^3F_4$, will decrease the generated heat to a large extent. By optimizing the power filling factor of the gain fiber, we find a 2-$μ$m TDFL cladding-pumped at 1.9 $μ$m will lead to the laser slope efficiency close to its quantum efficiency (95\%). The induced ultra-low quantum defect would be of great importance for power scaling. We thus propose tandem-pumped TDFLs for reducing the heat at high powers and discuss the related issues of design. Besides, we also explore the differences of the thermal characteristics between laser and superfluorescent operations, which will contribute to deepening the understanding of the thermal effects in high-power thulium-doped fiber amplifiers.

physics.optics↗