Search Results (223)

Change point detection in dynamic social graphs aims to identify significant transitions in evolving interaction patterns. The task is particularly challenging due to sparse and noisy interactions and frequent user turnover, while the existing methods largely overlook the semantic and emotional signals in user-generated content by focusing primarily on structural changes. To address these limitations, this paper proposes ECPD-SG, an emotion-aware contrastive prototype learning algorithm for unsupervised change point detection in dynamic social graphs. ECPD-SG constructs emotion-aware graph snapshots by integrating textual and affective features into node representations and recalibrating interaction weights through emotion-aware attention. It then summarizes temporal node representations into adaptive prototypes and models their evolution using optimal-transport-based alignment and contrastive learning. Change points are detected from prototype-level shift scores with an adaptive CUSUM decision rule. Experiments on real-world dynamic social graph datasets show that ECPD-SG achieves competitive or superior performance over representative baselines, while ablation and sensitivity analyses verify the effectiveness of its key components. Full article

Monitoring software architecture evolution is essential for maintaining system quality, but many practical change-detection pipelines still rely on syntactic differences. Such pipelines can produce large review streams in which minor edits, refactorings, and deeper implementation rewrites are mixed together. In this paper, we introduce ArchSense, a diagnostic framework for characterizing component-internal implementation-semantic evolution. ArchSense combines hierarchical structural alignment with method-level semantic displacement measurement. Instead of treating all code updates as equal, it uses vector representations from GraphCodeBERT to measure implementation-level semantic change intensity and then summarizes this signal within architectural components. We evaluate ArchSense on six large-scale open-source Java systems. The results show that semantic distance is positively associated with a three-annotator construct assessment of implementation change intensity. Additional disagreement analysis links high and low model decisions to concrete source code features, including control flow, call-set, return, exception, synchronization, and test-observable changes. A behavioral proxy check on 23,389 test method updates shows that the default threshold behaves as a conservative high-precision, low-recall review signal for implementation-semantic change. The validated scope of ArchSense is therefore component-internal diagnostic characterization for architecture-oriented review; connector topology, runtime communication, behavioral equivalence, and defect causality require complementary evidence. Full article

Career growth path planning is still dominated by statistical association models that summarize historical transitions but do not explicitly represent the causal mechanisms linking capability development, project exposure, policy support, performance improvement, and promotion outcomes. This study develops a reproducible simulation benchmark for evaluating whether prompt-structured priors, when coupled with dual validation, can help assemble intervention-ready career causal graphs. A structural causal model (SCM) first generated 20,000 synthetic career trajectories with known ground-truth dependencies among ten variables, including education, experience, training hours, certification, project exposure, performance, and promotion. Four prompt families-zero-shot, few-shot, Chain-of-Thought (CoT), and CoT plus schema constraints-were instantiated through a controlled prompt-response emulator so that prompt structure could be studied independently of vendor-specific model drift. The emulator gradients should therefore be read as literature-informed design assumptions about structured prompting rather than as empirical measurements from any named production LLM. Candidate edges were subsequently refined by data validation and expert-proxy domain rules. In the main 30-run benchmark, the best prompt-only setting (CoT plus schema) achieved an F1-score of 0.842, while the proposed hybrid method achieved an F1-score of 0.959 and an intervention-effect mean absolute error of 0.0046. Run-wise confidence intervals and approximate significance checks further indicated that the hybrid workflow materially outperformed the prompt-only variants under the benchmark protocol. A public employee-promotion dataset (N= 54,808) was further used as an external plausibility anchor, where KPI attainment, awards, previous ratings, training score, and length of service were all positively associated with promotion. The results indicate that prompt-structured priors can be useful as a transparent proposal-and-validation mechanism, but not as a substitute for direct validation on real LLMs, matched comparisons with standard causal-discovery baselines, or real HR deployment settings. Accordingly, the central aim is a domain-specific methodological benchmark for testing prompt-structured proposal mechanisms in career-growth causal modeling, rather than a claim of standalone LLM causal discovery or a universal benchmark for every causal-discovery setting. Full article

Human pose estimation (HPE) has advanced rapidly with deep learning, enabling a transition from specialized sensing and multi-view systems toward monocular RGB-based approaches. These developments have expanded applications in healthcare, robotics, sports analytics, and human–computer interaction. However, the growing diversity of deep learning paradigms, ranging from convolutional and recurrent models to graph-based and Transformer-based approaches, has resulted in a fragmented literature, making it difficult to systematically compare methods and guide system design. This paper addresses this challenge by providing a comprehensive survey of deep learning-based monocular HPE methods published over the past decade and introducing a unified modular framework. The proposed framework organizes HPE systems into six modular estimation paradigms, including single-image-based estimation, multi-frame-based estimation, Top-Down and Bottom-Up pose estimation strategies, 2D-to-3D pose reconstruction, and direct 3D estimation. Each module is analyzed in terms of representative approaches, design trade-offs, and practical considerations, supported by algorithmic formulations that outline the computational pipeline at each stage. Unlike prior surveys that primarily catalog methods or report benchmark results in isolation, this work emphasizes how component-level design choices relate to overall system performance. The paper summarizes performance trends on benchmarks including Human3.6M, COCO, and MPII, highlighting persistent challenges such as occlusion and viewpoint variation, and outlines future research directions including interaction-aware modeling, efficient deployment, and improved robustness under real-world conditions. Full article

Topological data analysis (TDA) has evolved into a flexible and robust paradigm for obtaining qualitative, geometry-inspired insights from high-dimensional, noisy, and complex data. Grounded in algebraic topology, geometry, statistics, and machine learning (ML), TDA provides multiscale descriptions through persistent homology, Mapper (a graph-based method that summarizes the shape of high-dimensional data), and related topological signatures that are often inaccessible to standard linear and metric methods. In recent years, and especially during 2024–2025, TDA has expanded rapidly across science, engineering, biomedical research, and socio-economic studies, while also being integrated with modern learning paradigms such as deep learning (DL) and graph learning. This survey summarizes recent developments in TDA using a carefully selected set of articles, with emphasis on 2024–2025. We first present the mathematical and computational foundations of TDA, covering simplicial complexes, filtrations, persistent homology, the Mapper algorithm, and computational advances such as data simplification, stability, and efficiency. We then review applications in time series and dynamical systems, biomedical imaging and precision medicine, engineering and physical sciences, finance and risk analysis, DL and interpretability, and security and critical infrastructure systems. Throughout, we highlight how TDA can extract informative features, function as a model component, and provide a conceptual lens for studying complex systems. However, the survey also emphasizes recurrent failure patterns: TDA performance is highly sensitive to filtration, embedding, and vectorization choices; aggressive simplification can dilute or remove informative topological signals; and integration into standard ML workflows still lacks uniform validation and reporting protocols. We conclude by outlining key challenges—including scalability, statistical foundations, interpretability, and compatibility with rapidly evolving artificial intelligence (AI) paradigms—and by identifying directions for future research. The survey also provides a unifying design perspective for TDA systems, highlighting methodological trade-offs and emerging research directions for integrating topology with modern ML. Full article

Introduction: Freshwater systems are increasingly being impacted by a plethora of pressures. Freshwater fish are thus periled, urging the need to investigate the drivers of population decrease to better counteract them, in order to provide some conservation relief to these pressured species. Methodology: To facilitate freshwater research, the Dammed Fish Project developed a series of free tools that simplify procedures and facilitate the access of correct data. Results: RivTool+ is a free software that evolved from RivTool (used in over 75 countries) and that integrates new functions and acts as a tool hub to host additional software apps. The computing engine of RivTool, that allows along the river network calculations and summarizations, is now able to be used by new tools. RivConnect—River network connectivity app that allows graph-based quantification of structural and functional connectivity, using several metrics and understanding network directionality. RivFish—App that contains the corrected, spatially and taxonomically, occurrence, at the basin and sub-basin level, of more than 600 native freshwater fish species of Europe. RivOpt—Optimization tool that allows for river network connectivity restoration optimization. RivOpt accounts for conflicting multiple objectives and is able to deal with different restoration actions for each barrier (removal, partial removal, fishway construction and retrofitting or no action). Conclusions: Dammed Fish tools facilitate research procedures and access to verified data, improving the information baseline, increasing the accuracy of results and accelerating research. Thus, it contributes to an improved understanding of the mechanisms controlling species vulnerability and contributes to their conservation. Full article

In the power industry, how to efficiently and reliably query relevant documents has always posed a challenge for electrical professionals. Unreliable or inefficient query results can lead to significant inefficiencies and introduce unpredictable errors. Hence, a reliable and efficient knowledge querying system is critical. In practice, the effectiveness of Graph-based Retrieval-Augmented Generation (RAG) systems lies in providing expressive representation of entities and graph structures and this makes it stand out as a widely-used approach for document retrieval. However, typical GraphRAG frameworks encounter challenges such as semantic dilution and topological drift caused by generic technical terminology and granular graph noise especially in professional documents like regulations, etc, which is one of the mostly used type of document in electric industry. Thus, we propose KG-Anchored RAG, a framework that shifts the retrieval paradigm from community-based summarization to precision-guided anchoring. During knowledge construction, our framework employs a topological skeleton refinement and constructs a Knowledge Attachment Matrix using latent topic modeling and one-hot feature injection. During inference, non-linear sharpening and PageRank-based structural resonance are utilized to locate high-density knowledge cells. Evaluation on professional documents in the power industry reveals that our method outperforms localized search baselines in terms of context precision, generative faithfulness, and ranking quality. The proposed framework demonstrates a superior ability to prioritize evidentiary clauses and reduce information redundancy without relying on computationally expensive external re-rankers. Experimental results indicate that KG-Anchored RAG effectively mitigates speculative hallucinations, establishes a reliable architectural paradigm for retrieval-augmented generation in high-stakes, safety-critical vertical industries. Full article

With the rapid development of intelligent shipping and the autonomy of marine engineering equipment, numerous studies have focused on the advancement of Autonomous Surface Vehicles (ASVs). As a fundamental component of ASV automation systems, path planning directly determines the safety and economy of ship navigation. This paper systematically reviews recent research progress in ASV path planning. First, five key issues are identified for ASV path planning: navigation environment, environment modeling, ship motion model, collision avoidance for safety, and optimization. Second, existing algorithms are classified into four categories: graph search-based, sampling-based, numerical optimization-based, and artificial intelligence-based. The improvement directions and application scenarios of each category are elaborated. Finally, the four types of algorithms are evaluated against three indicators: path quality, scalability and extensibility, and algorithm performance. Analysis of the reviewed literature shows that traditional graph search and sampling algorithms perform well in various aspects under static environments, but are insufficient in adapting to multiple constraints and generalizing to different environments. In contrast, artificial intelligence algorithms represented by deep reinforcement learning exhibit significant advantages in dynamic collision avoidance decision-making, multi-agent coordination, and environmental generalization, and have become the mainstream direction of current research. This paper summarizes the existing challenges in safety and optimization in current ASV path planning research and prospects future development directions. Full article

Agricultural AI agents play a crucial role in the evolution of smart agriculture, from single-point automated applications to intelligent systems driven by tasks, collaborative decision-making, and closed-loop execution. However, their practical implementation still faces key challenges, such as heterogeneous agricultural data processing, insufficient cross-scenario generalization ability, complexity of multi-agent collaboration, difficulties in integrating software and hardware, and insufficient security and trust guarantees in real agricultural environments. This paper presents a systematic review of the architecture design, business processes, key technologies, and future challenges of agricultural AI agents. Agricultural AI agents are classified into two types: virtual agricultural AI agents and embodied agricultural AI agents. The paper summarizes a four-layer system architecture consisting of the infrastructure layer, agent management layer, agent collaboration layer, and application layer. The paper also analyzes the model capabilities required by agricultural AI agents from four typical business dimensions: perception and state understanding, knowledge memory and experience management, reasoning decision-making and task planning, and collaborative execution and resource scheduling. This research shows that technologies such as multimodal perception, knowledge graphs, retrieval-enhanced generation, digital twins, reinforcement learning, and multi-agent collaboration can provide important support for agricultural AI agents to enhance their environmental understanding, knowledge reuse, autonomous decision-making, and physical execution capabilities. Future research should focus on robust perception in open environments, long-term memory and knowledge evolution, reliable multi-agent collaboration, edge-cloud collaborative deployment, and secure and trustworthy human–machine collaboration. Integrating agricultural domain knowledge with intelligent agent technology is an important direction for promoting the large-scale, adaptive, and sustainable application of agricultural AI agents. Full article

Pangenomics has become an important framework for representing genetic diversity beyond a single linear reference genome. In agricultural species, it improves access to structural variants (SVs), copy number variations (CNVs), presence/absence variations (PAVs), and non-reference regulatory or coding sequences that may contribute to domestication, adaptation, and breeding traits. This review summarizes recent progress in long-read sequencing, telomere-to-telomere (T2T) assembly, and graph-based genome analysis, with emphasis on both livestock and crop systems. We first define the conceptual boundary between pangenome representations and reference-based variant catalogs. We then compare three major technical routes: variant integration, reference-guided iterative graph construction, and reference-free graph construction. Their performance is evaluated in terms of accuracy, scalability, coordinate consistency, reference bias, computational demand, annotation transfer, and suitability for downstream breeding questions. We further discuss how pangenome resources support hidden variant discovery, QTL and GWAS interpretation, environmental adaptation analysis, and multi-omics-based candidate prioritization. Importantly, we highlight unresolved limitations, including graph complexity, pipeline-dependent SV calls, incomplete functional annotation, weak cross-study comparability, and the difficulty of distinguishing causal variants from linked or neutral variation. This review therefore treats pangenome studies as connected but non-equivalent evidence: resource-building studies establish representational breadth, method papers define technical feasibility, and trait-focused studies provide varying levels of biological support. Apparent inconsistencies among studies are interpreted as signals of differences in sampling, genome complexity, validation depth, and graph construction strategy rather than as simple disagreements. Full article

Hyperspectral image change detection (HSI-CD) is becoming increasingly important in understanding how the Earth’s surface evolves over time, from monitoring ecosystems to tracking urban expansion. Unlike traditional pixel-based or hand-crafted approaches, deep learning models can automatically learn powerful spectral–spatial features, making them especially effective for this task. In this review, we bring together recent advances in deep learning for HSI-CD, combining a meta-analysis of the literature with an overview of the main model families and training strategies. We cover supervised, semi-supervised, and unsupervised methods, as well as newer directions such as transfer learning, self-supervised frameworks, and hybrid designs that blend CNNs, transformers, and graph neural networks. We also discuss benchmark datasets, evaluation protocols, and case studies that show how these methods perform in practice. Beyond summarizing the current progress, the review highlights ongoing gaps, such as limited labeled data, generalization across sensors, computational efficiency, and the need for interpretability, and points to emerging opportunities for future work. Our goal is to provide both a snapshot of the current state of the field and a road map for advancing deep learning-based HSI-CD. Full article

The rapid evolution of next-generation electronics urgently demands high-performance functional materials. Two-dimensional (2D) semiconductors, characterized by tunable bandgaps, magnetic properties, and excellent optical and electronic properties, hold significant potential for applications in nanoelectronic devices, magnetic storage, and optoelectronics. However, the high computational cost of traditional Density Functional Theory (DFT) severely restricts large-scale high-throughput screening. Meanwhile, problems such as insufficient datasets and non-uniform data quality remain prevalent. Against this background, machine learning (ML), which captures intricate nonlinear correlations and accelerates the discovery of novel materials, has emerged as an efficient technical approach. This review systematically summarizes recent advances in ML-driven property prediction for 2D semiconductors. It first elaborates the fundamental properties and classifications of 2D semiconductors, and then compares traditional computational simulations with ML algorithms, clarifying the distinct advantages of data-driven approaches. Subsequently, this work focuses on the latest progress in predicting critical properties, including bandgap, magnetism, and other physical characteristics. For bandgap prediction, classical algorithms such as random forests are compared with deep learning models represented by graph neural networks. The results demonstrate that deep learning performs much better in low-data regimes and complex material systems. For magnetic property prediction, the impact of feature engineering strategies on model accuracy and efficiency is systematically analyzed. In addition, the research progress of other physical property prediction tasks is briefly summarized. Finally, future research directions for machine learning, including standardized materials databases, physics-informed machine learning, multimodal modeling, and the integration of machine learning with experimental and theoretical methods, are outlined to address challenges in data quality, model interpretability, and cross-system generalization ability. This work aims to provide a systematic theoretical foundation and methodological guidance for research on two-dimensional semiconductor materials assisted by machine learning. Full article

Large language models (LLMs) frequently produce text that is fluent yet factually inconsistent with source documents. Detecting such inconsistency remains challenging, particularly when errors involve subtle entity substitutions, temporal distortions, or relational misattributions embedded within lengthy outputs. We propose Atomic Contrastive Verification (ACV), a training-free, graph-grounded fact-checking framework that decomposes both generated claims and source documents into atomic claims—minimal, self-contained factual units—and performs structured contrastive reasoning over each unit independently. For each atomic claim, ACV extracts a knowledge graph triple and generates contrastive claim variants through a multi-type perturbation taxonomy covering entity, relation, temporal, and quantitative dimensions. A novel Knowledge-Weighted Contrastive MMR mechanism, integrating graph-structural centrality and NLI-based logical diversity, selects the most discriminative subset of variants. Each selected variant is then pairwise compared against the claim; the resulting comparison responses are summarized to produce a per-claim verdict, and per-claim verdicts are aggregated into a document-level judgment. Experiments on the LLM-AggreFact benchmark (eleven subsets) demonstrate that ACV achieves competitive or superior performance compared to both specialized fine-tuned fact-checkers and large-scale LLMs. Beyond accuracy, ACV provides interpretable, claim-level error localization that existing methods cannot offer. Full article

Proteomics has become central to pharmacological research by providing quantitative readouts of protein abundance, post-translational modifications, interactions, and spatial context. However, proteomic datasets are high-dimensional, heterogeneous, and frequently affected by missingness, batch effects, and limited cohort size. Artificial intelligence (AI) and machine learning (ML) can help convert these complex data into decision-relevant outputs for target identification, biomarker discovery, pharmacodynamic monitoring, and drug repurposing. This review critically compares supervised learning, ensemble methods, dimensionality reduction, clustering, deep learning, graph learning, survival modeling, causal inference, and calibration approaches in proteomics-driven drug discovery. We also summarize major software ecosystems for mass-spectrometry processing, targeted assays, spectrum prediction, phosphoproteomics, structure modeling, and reproducible workflows. Emphasis is placed on model selection, benchmarking, missing-data handling, batch correction, interpretability, uncertainty, experimental validation, and translational readiness. Finally, we highlight emerging directions, including contrastive learning, diffusion models, graph-based integration, and federated analytics. Full article

Social bots significantly threaten online public opinion through manipulation and misinformation, posing detection challenges due to high anthropomorphism and concealment. GNN methods show superior performance but face deployment hurdles on real-world platforms because of their reliance on multi-hop neighbor information during inference. Conversely, pure text-based methods lack collective behavior modeling and robustness against advanced bots. This paper proposes LKD, a social bot detection framework for graph-less deployment. The framework utilizes large language models to summarize historical tweets, compressing long-text information to construct multi-source inputs including metadata, profiles, and tweets. By employing a GNN as the teacher and a pre-trained LM as the student, LKD transfers structural knowledge to a text-based model via dual-objective knowledge distillation across prediction distributions and feature spaces. Experiments on Cresci-2015 and TwiBot-20 datasets show that the graph-less LKD-LM mode outperforms state-of-the-art methods in accuracy and F1-score. It maintains stable performance in label-scarce and sparse-graph scenarios, providing an efficient, robust solution for social media platforms with restricted interfaces or real-time requirements. Full article