Search Results (197)

The rapid growth of the automobile industry has intensified the demand for accurate price prediction models in the used car market. Buyers often struggle to determine fair market value due to the complexity of factors such as mileage, brand, model, transmission type, accident history, and overall condition. This study presents a comparative analysis of machine learning models for used car price prediction, with a strong emphasis on the impact of feature engineering. We begin by evaluating multiple models, including Linear Regression, Decision Trees, Random Forest, Support Vector Regression (SVR), XGBoost, Stacking Regressor, and Keras-based neural networks, on raw, unprocessed data. We then apply a comprehensive feature engineering pipeline that includes categorical encoding, outlier removal, data standardization, and extraction of hidden features (e.g., vehicle age, horsepower). The results demonstrate that advanced preprocessing significantly improves predictive performance across all models. For instance, the Stacking Regressor’s R² score increased from 0.14 to 0.8899 after feature engineering. Ensemble methods, such as CatBoost and XGBoost, also showed strong gains. This research not only benchmarks models for this task but also serves as a practical tutorial illustrating how engineered features enhance performance in structured ML pipelines for the fellow researchers. The proposed workflow offers a reproducible template for building high-accuracy pricing tools in the automotive domain, fostering transparency and informed decision making. Full article

Synthetic data has become an increasingly important tool for semantic segmentation, where collecting large-scale annotated datasets is often costly and impractical. Prior work has leveraged computer graphics and game engines to generate training data, but many pipelines remain limited to single modalities and constrained environments or require substantial manual setup. To address these limitations, we present a fully automated pipeline built within Unreal Engine 5 (UE5) that procedurally generates diverse, labeled environments and collects multimodal visual data for semantic segmentation tasks. Our system integrates UE5’s biome-based procedural generation framework with a spline-following drone actor capable of capturing both RGB and depth imagery, alongside pixel-perfect semantic segmentation labels. As a proof of concept, we generated a dataset consisting of 1169 samples across two visual modalities and seven semantic classes. The pipeline supports scalable expansion and rapid environment variation, enabling high-throughput synthetic data generation with minimal human intervention. To validate our approach, we trained benchmark computer vision segmentation models on the synthetic dataset and demonstrated their ability to learn meaningful semantic representations. This work highlights the potential of game-engine-based data generation to accelerate research in multimodal perception and provide reproducible, scalable benchmarks for future segmentation models. Full article

This study develops an open, reproducible geospatial workflow to identify high-potential retail locations across Germany using a 1 km census grid and OpenStreetMap points of interest. It combines multi-criteria suitability modelling with spatial autocorrelation and Geographically Weighted Regression (GWR). Using fine-scale demographic and retail data, the results show clear regional differences in how drivers operate. Population density is most influential around large metropolitan areas, while the role of points of interest is stronger in smaller regional towns. A separate gap analysis identified forty grid cells with high suitability but no existing retail infrastructure. These locations are spread across both rural and urban contexts, from peri-urban districts in Baden-Württemberg to underserved municipalities in Brandenburg and Bavaria. The pattern is consistent under different model specifications and echoes earlier studies that reported supply deficits in comparable communities. The results are useful in two directions. Retailers can see places with demand that has gone unnoticed, while planners gain evidence that service shortages are not just an urban issue but often show up in smaller towns as well. Taken together, the maps and diagnostics give a grounded picture of where gaps remain, and suggest where investment could bring both commercial returns and community benefits. This study develops an open, reproducible geospatial workflow to identify high-potential retail locations across Germany using a 1 km census grid and OpenStreetMap points of interest. A multi-criteria suitability surface is constructed from demographic and retail indicators and then subjected to spatial diagnostics to separate visually high values from statistically coherent clusters. “White-spots” are defined as cells in the top decile of suitability with zero (strict) or ≤1 (relaxed) existing shops, yielding actionable opportunity candidates. Global autocorrelation confirms strong clustering of suitability, and Local Indicators of Spatial Association isolate hot- and cold-spots robust to neighbourhood size. To explain regional heterogeneity in drivers, Geographically Weighted Regression maps local coefficients for population, age structure, and shop density, revealing pronounced intra-urban contrasts around Hamburg and more muted variation in Berlin. Sensitivity analyses indicate that suitability patterns and priority cells stay consistent with reasonable reweighting of indicators. The comprehensive pipeline comprising suitability mapping, cluster diagnostics, spatially variable coefficients, and gap analysis provides clear, code-centric data for retailers and planners. The findings point to underserved areas in smaller towns and peri-urban districts where investment could both increase access and business feasibility. Full article

The Yangtze finless porpoise (Neophocaena asiaeorientalis asiaeorientalis, YFP) is the only freshwater cetacean species currently found in China’s Yangtze River. To accurately evaluate its genetic diversity and provide reliable molecular markers for population genetic studies, this study developed a highly efficient and reproducible method for identifying polymorphic microsatellite loci using whole-genome sequencing data. Using this method, we identified and validated a set of highly polymorphic microsatellite markers, which were then used to analyze the genetic diversity of the YFP populations in Poyang Lake to evaluate their effectiveness. Our results demonstrated that the screening pipeline successfully identified 220 tetranucleotide repeat microsatellite loci. Based on the principle of uniform chromosomal distribution, 190 loci were randomly selected for experimental validation, of which 19 exhibited stable amplification, high polymorphism, and a low genotyping error rate. Genetic diversity analysis based on these markers revealed significant genetic variation among YFP populations in Poyang Lake, confirming the effectiveness of the developed markers. The polymorphic microsatellite molecular marker system developed in this study demonstrates high reliability and applicability for assessing YFP genetic diversity. This system provides a critical technical foundation for future research in conservation genetics, genetic resource preservation, and the development of genetic management strategies for the species. Full article

The integration of large language models (LLMs) into structural engineering workflows presents both a transformative opportunity and a critical challenge. While LLMs enable intuitive, natural language interactions with complex data, their limited arithmetic reasoning, contextual fragility, and lack of verifiability constrain their application in safety-critical domains. This study introduces a novel automation pipeline that couples generative AI with finite element modelling through the Model Context Protocol (MCP)—a modular, context-aware architecture that complements language interpretation with structural computation. By interfacing GPT-4 with OpenSeesPy via MCP (JSON schemas, API interfaces, communication standards), the system allows engineers to specify and evaluate 3D frame structures using conversational prompts, while ensuring computational fidelity and code compliance. Across four case studies, the GPT+MCP framework demonstrated predictive accuracy for key structural parameters, with deviations under 1.5% compared to reference solutions produced using conventional finite element analysis workflows. In contrast, unconstrained LLM use produces deviations exceeding 400%. The architecture supports reproducibility, traceability, and rapid analysis cycles (6–12 s), enabling real-time feedback for both design and education. This work establishes a reproducible framework for trustworthy AI-assisted analysis in engineering, offering a scalable foundation for future developments in optimisation and regulatory automation. Full article

Data-driven forecasting is becoming increasingly central to modern energy management, yet nonspecialists without a background in artificial intelligence (AI) face significant barriers to entry. While Python is the dominant machine learning language, R remains a practical and accessible tool for users with expertise in statistics, engineering, or domain-specific analysis. To inform tool selection, we first provide an evidence-based comparison of R with major alternatives before reviewing 49 peer-reviewed articles published between 2020 and 2025 in Science Citation Index Expanded (SCIE)-level journals that utilized R for energy forecasting tasks, including electricity (regional and site-level), solar, wind, thermal energy, and natural gas. Despite such growth, the field still lacks a systematic, cross-domain synthesis that clarifies which R-based methods prevail, how accessible workflows are implemented, and where methodological gaps remain; this motivated our use of text mining. Text mining techniques were employed to categorize the literature according to forecasting objectives, modeling methods, application domains, and tool usage patterns. The results indicate that tree-based ensemble learning models—e.g., random forests, gradient boosting, and hybrid variants—are employed most frequently, particularly for solar and short-term load forecasting. Notably, few studies incorporated automated model selection or explainable AI; however, there is a growing shift toward interpretable and beginner-friendly workflows. This review offers a practical reference for nonexperts seeking to apply R in energy forecasting contexts, emphasizing accessible modeling strategies and reproducible practices. We also curate example R scripts, workflow templates, and a study-level link catalog to support replication. The findings of this review support the broader democratization of energy analytics by identifying trends and methodologies suitable for users without advanced AI training. Finally, we synthesize domain-specific evidence and outline the text-mining pipeline, present visual keyword profiles and comparative performance tables that surface prevailing strategies and unmet needs, and conclude with practical guidance and targeted directions for future research. Full article

Background: Dental caries arise from a multifactorial interplay between microbial dysbiosis, host immune responses, and enamel degradation visible on radiographs. Deep learning excels in image-based caries detection; however, integrative analyses that combine radiographic, microbiome, and transcriptomic data remain rare because public cohorts are seldom aligned. Objective: To determine whether three independent deep-learning pipelines—radiographic segmentation, microbiome regression, and transcriptome regression—can be reproducible implemented on non-aligned datasets, and to demonstrate the feasibility of estimating microbiome heritability in a matched twin cohort. Methods: (i) A U-Net with ResNet-18 encoder was trained on 100 annotated panoramic radiographs to generate a continuous caries-severity score from a predicted lesion area. (ii) Feed-forward neural networks (FNNs) were trained on supragingival 16S rRNA profiles (81 samples, 750 taxa) and gingival transcriptomes (247 samples, 54,675 probes) using randomly permuted severity scores as synthetic targets to stress-test preprocessing, training, and SHAP-based interpretability. (iii) In 49 monozygotic and 50 dizygotic twin pairs (n = 198), Bray–Curtis dissimilarity quantified microbial heritability, and an FNN was trained to predict recorded TotalCaries counts. Results: The U-Net achieved IoU = 0.564 (95% CI 0.535–0.594), precision = 0.624 (95% CI 0.583–0.667), recall = 0.877 (95% CI 0.827–0.918), and correlated with manual severity scores (r = 0.62, p < 0.01). The synthetic-target FNNs converged consistently but—as intended—showed no predictive power (R² ≈ −0.15 microbiome; −0.18 transcriptome). Twin analysis revealed greater microbiome similarity in monozygotic versus dizygotic pairs (0.475 ± 0.107 vs. 0.557 ± 0.117; p = 0.0005) and a modest correlation between salivary features and caries burden (r = 0.25). Conclusions: Modular deep-learning pipelines remain computationally robust and interpretable on non-aligned datasets; radiographic severity provides a transferable quantitative anchor. Twin-cohort findings confirm heritable patterns in the oral microbiome and outline a pathway toward future clinical translation once patient-matched multi-omics are available. This framework establishes a scalable, reproducible foundation for integrative caries research. Full article

We present new spectroscopic orbits for the bright binaries Mizar B, 3 Pup, $\nu$ Gem, 2 Lac, and $\varphi$ Aql. Our analysis is based on medium-resolution ($R\approx$ 12,000) échelle spectra obtained with the 0.81-m telescope and fiber-fed eShel spectrograph of the Three College Observatory (Greensboro, NC, USA) between 2015 and 2024. Orbital elements were inferred with an affine-invariant Markov-chain Monte-Carlo sampler; convergence was verified through the integrated autocorrelation time and the Gelman–Rubin statistic. Errors quote the 16th–84th-percentile credible intervals. Compared with previously published orbital solutions for the studied stars, our method improves the root-mean-square residuals by 25–50% and bring the 1$\sigma$ uncertainties on the radial velocity (RV) semi-amplitudes down to 0.02–0.15 km $s^{-1}$. These gains translate into markedly tighter mass functions and systemic RVs, providing a robust dynamical baseline for future interferometric and photometric studies. A complete Python analysis pipeline is openly available in a GitHub repository, ensuring full reproducibility. The results demonstrate that a Bayesian RV analysis with well-motivated priors and rigorous convergence checks yields orbital parameters that are both more precise and more reproducible than previous determinations, while offering fully transparent uncertainty budgets. Full article

The integrity of subsea oil and gas pipelines is essential for offshore safety and environmental protection. Conventional leak detection approaches, such as manual inspection and indirect sensing, are often costly, time-consuming, and prone to subjectivity, motivating the development of automated methods. In this study, we present a deep learning-based framework for detecting underwater leaks using images acquired in controlled experiments designed to reproduce representative conditions of subsea monitoring. The dataset was generated by simulating both gas and liquid leaks in a water tank environment, under scenarios that mimic challenges observed during Remotely Operated Vehicle (ROV) inspections along the Brazilian coast. It was further complemented with artificially generated synthetic images (Stable Diffusion) and publicly available subsea imagery. Multiple Convolutional Neural Network (CNN) architectures, including VGG16, ResNet50, InceptionV3, DenseNet121, InceptionResNetV2, EfficientNetB0, and a lightweight custom CNN, were trained with transfer learning and evaluated on validation and blind test sets. The best-performing models achieved stable performance during training and validation, with macro F1-scores above 0.80, and demonstrated improved generalization compared to traditional baselines such as VGG16. In blind testing, InceptionV3 achieved the most balanced performance across the three classes when trained with synthetic data and augmentation. The study demonstrates the feasibility of applying CNNs for vision-based leak detection in complex underwater environments. A key contribution is the release of a novel experimentally generated dataset, which supports reproducibility and establishes a benchmark for advancing automated subsea inspection methods. Full article

Microglia are central to neuroimmune responses and undergo dynamic structural and functional changes in models of stress and addiction, and in response to pharmacological treatments. While transcriptomic and proteomic assays provide insights into molecular profiles, morphological analysis remains a valuable proxy for assessing region-specific microglial response. However, morphological features alone often fail to capture the full complexity of microglial function, underscoring the need for standardized methods and complementary approaches. Here, we describe a standardized imaging pipeline for analyzing microglia in the nucleus accumbens core (NAcore), integrating unbiased confocal image acquisition with precise anatomical reference points. We compare two widely used image analysis platforms—IMARIS and CellSelect-3DMorph—highlighting their workflows, output metrics, and utility in quantifying microglial morphology following treatment with adenosine triphosphate (ATP). Both tools detect well described features of microglial dynamics, though they differ in automation level, analysis speed, and output types. Our findings demonstrate that both platforms provide reliable morphological data, with CellSelect-3DMorph offering a rapid, open-access alternative for high-throughput analysis. Additionally, using software-derived parameters in principal component analysis clustering has proven useful for identifying distinct subpopulations of microglia separated by their morphology. This work provides a practical framework for morphological analysis and promotes reproducibility in microglial studies under environmental and pharmacological interventions. Full article

In the manufacturing supply chain, management reports often begin with concise messages that summarize key inventory insights. Traditionally, human analysts manually crafted these summary messages by sifting through complex data—a process that is both time-consuming and prone to inconsistency. In this research study, we present an AI-based system that automatically generates high-quality inventory insight summaries, referred to as “headline messages,” using real-world inventory data. The proposed system leverages lightweight natural language processing (NLP) and machine learning models to achieve accurate and efficient performance. Historical messages are first clustered using a sentence-translation MiniLM model that provides fast semantic embedding. This is used to derive key message categories and define structured input features for this purpose. Then, an explainable and low-complexity classifier trained to predict appropriate headline messages based on current inventory metrics using minimal computational resources. Through empirical experiments with real enterprise data, we demonstrate that this approach can reproduce expert-written headline messages with high accuracy while reducing report generation time from hours to minutes. This study makes three contributions. First, it introduces a lightweight approach that transforms inventory data into concise messages. Second, the proposed approach mitigates confusion by maintaining interpretability and fact-based control, and aligns wording with domain-specific terminology. Furthermore, it reports an industrial validation and deployment case study, demonstrating that the system can be integrated with enterprise data pipelines to generate large-scale weekly reports. These results demonstrate the application and technological innovation of combining small-scale language models with interpretable machine learning to provide insights. Full article

Visual attractiveness perception—an individual’s capacity to recognise and evaluate the visual appeal of urban scene safety—has direct implications for well-being, economic vitality, and social cohesion. However, most empirical studies rely on single-source metrics or algorithm-centric pipelines that under-represent human perception. Addressing this gap, we introduce a fully reproducible, multimodal framework that measures and models this domain-specific facet of human intelligence by coupling Generative Pre-trained Transformer 4o (GPT-4o) with 1000 Street View images. The pipeline first elicits pairwise aesthetic judgements from GPT-4o, converts them into a latent attractiveness scale via Thurstone’s law of comparative judgement, and then validates the scale against 1.17 M crowdsourced ratings from MIT’s Place Pulse 2.0 benchmark (Spearman ρ = 0.76, p < 0.001). Compared with a Siamese CNN baseline (ρ = 0.60), GPT-4o yields both higher criterion validity and an 88% reduction in inference time, underscoring its superior capacity to approximate human evaluative reasoning. In this study, we introduce a standardised and reproducible streetscape evaluation pipeline using GPT-4o. We then combine the resulting attractiveness scores with network-based accessibility modelling to generate a “aesthetic–accessibility map” of urban central districts in Chongqing, China. Cluster analysis reveals four statistically distinct street types—Iconic Core, Liveable Rings, Transit-Rich but Bland, and Peripheral Low-Appeal—providing actionable insights for landscape design, urban governance, and tourism planning. Full article

Human Action Recognition has seen significant advances through transformer-based architectures, yet achieving a nuanced understanding often requires fusing multiple data modalities. Standard models relying solely on RGB video can struggle with actions defined by subtle motion cues rather than appearance. This paper introduces TransMODAL, a novel dual-stream transformer that synergistically fuses spatiotemporal appearance features from a pre-trained VideoMAE(Video Masked AutoEncoders) backbone with explicit skeletal kinematics from a state-of-the-art pose estimation pipeline (RT-DETR(Real-Time DEtection Transformer) + ViTPose++). We propose two key architectural innovations to enable effective and efficient fusion: a CoAttentionFusion module that facilitates deep, iterative cross-modal feature exchange between the RGB and pose streams, and an efficient AdaptiveSelector mechanism that dynamically prunes less informative spatiotemporal tokens to reduce computational overhead. Evaluated on three challenging benchmarks, TransMODAL demonstrates robust generalization, achieving accuracies of 98.5% on KTH, 96.9% on UCF101, and 84.2% on HMDB51. These results significantly outperform a strong VideoMAE-only baseline and are competitive with state-of-the-art methods, demonstrating the profound impact of explicit pose guidance. TransMODAL presents a powerful and efficient paradigm for composing pre-trained foundation models to tackle complex video understanding tasks by providing a fully reproducible implementation and strong benchmark results. Full article

Cultural heritage institutions, such as museums and galleries, today face the challenge of managing an increasing volume of unsolicited visitor feedback generated across online platforms. This study offers a practical and scalable methodology that transforms 5856 multilingual Google reviews from 59 globally ranked museums and galleries into actionable insights through sentiment analysis, correlation diagnostics, and guided Latent Dirichlet Allocation. By addressing the limitations of prior research, such as outdated datasets, monolingual bias, and narrow geographical focus, the authors analyze a current and diverse set of recent reviews to capture a timely and globally relevant perspective on visitor experiences. The adopted guided LDA model identifies 12 key topics, reflecting both operational issues and emotional responses. The results indicate that while visitors generally express overwhelmingly positive sentiments, dissatisfaction tends to be concentrated in specific service areas. Correlation analysis reveals that longer, emotionally rich reviews are more likely to convey stronger sentiment and receive peer endorsement, highlighting their diagnostic significance. From a practical perspective, the methodology empowers professionals to prioritize improvements based on data-driven insights. By integrating quantitative metrics with qualitative topics, this study supports operational decision-making and cultivates a more empathetic and responsive data management mindset for museums. The reproducible and adaptable nature of the pipeline makes it suitable for cultural institutions of various sizes and resources. Ultimately, this work contributes to the field of cultural informatics by bridging computational precision with humanistic inquiry. That is, it illustrates how intelligent analysis of visitor reviews can lead to a more personalized, inclusive, and strategic museum experience. Full article

This study presents a comparative evaluation of traditional machine-learning (ML) and deep-learning (DL) approaches for detecting and counting Varroa destructor mites in hyperspectral images. As Varroa infestations pose a serious threat to honeybee health, accurate and efficient detection methods are essential. The ML pipeline—based on Principal Component Analysis (PCA), k-Nearest Neighbors (kNN), and Support Vector Machine (SVM)—was previously published and achieved high performance (precision = 0.9983, recall = 0.9947), with training and inference completed in seconds on standard CPU hardware. In contrast, the DL approach, employing Faster R-CNN with ResNet-50 and ResNet-101 backbones, was fine-tuned on the same manually annotated images. Despite requiring GPU acceleration, longer training times, and presenting a reproducibility challenges, the deep-learning models achieved precision of 0.966 and 0.971, recall of 0.757 and 0.829, and F1-Score of 0.848 and 0.894 for ResNet-50 and ResNet-101, respectively. Qualitative results further demonstrate the robustness of the ML method under limited-data conditions. These findings highlight the differences between ML and DL approaches in resource-constrained scenarios and offer practical guidance for selecting suitable detection strategies. Full article