Search Results (720)

Bearing faults are the most common type of failure in induction motors, given their long operating times and mechanical loads. Because induction motors in industrial environments operate under various load conditions, effective methods for diagnosing bearing faults across these conditions have become increasingly important. Here, different load conditions were implemented with a powder clutch and a tension controller, and vibration data were acquired under both normal and faulty bearing conditions. To ensure diagnostic accuracy while improving time efficiency, a model bank-based fault diagnosis classifier is proposed, which utilizes independent classifiers trained for each load condition. For comparison, a single model-based classifier trained on all load conditions is also implemented. Both approaches are validated with three classifiers: support vector machine (SVM), multilayer neural network (MNN), and random forest (RF), with three input types: raw time-series signals, six statistical features, and three t-test–selected statistical features. Experimental results reveal that the model bank-based fault diagnosis classifier utilizing three statistical features selected by t-test maintained 98–100% accuracy while reducing operating time compared with Method 1 by 60.0, 71.2, and 60.0% for SVM, MNN, and RF, respectively. These results confirm that the proposed Method 2 utilizing time-domain analysis provides reliable and time-efficient performance for bearing fault diagnosis under variable load conditions. Full article

Landslide disasters pose severe threats to mountainous regions, where accurate monitoring and scientific prediction are crucial for early warning and risk mitigation. This study addresses this challenge by focusing on the Outang Landslide, a representative large-scale bank slope in the Three Gorges Reservoir area known for its significant deformation responses to rainfall and reservoir-level fluctuations. The landslide’s behavior, characterized by notable hysteresis and nonlinear trends, poses a significant challenge to accurate prediction. To address this, we derived high-precision time-series deformation data by applying atmosphere-corrected Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) to Sentinel-1A imagery, with validation from GNSS measurements. A systematic analysis was then conducted to uncover the correlation, hysteresis, and spatial heterogeneity between landslide deformation and key influencing variables (rainfall, water level, temperature). Furthermore, we proposed a Spatio-Temporal Enhanced Convolutional Neural Network (STE-CNN), which innovatively converts influencing variables into grayscale images to enhance spatial feature extraction, thereby improving prediction accuracy. The results indicate that: (1) From June 2022 to March 2024, the landslide showed an overall downward displacement trend, with maximum settlement and uplift rates of −49.34 mm/a and 21.77 mm/a, respectively; (2) Deformation exhibited significant correlation, hysteresis, and spatial variability with environmental factors, with dominant variables shifting across seasons—leading to intensified movement in flood seasons and relative stability in dry seasons; (3) The improved STE-CNN outperforms typical prediction models in forecasting landslide deformation.This study presents an integrated methodology that combines InSAR monitoring, multi-factor mechanistic analysis, and deep learning, offering a reliable solution for landslide early warning and risk management. Full article

Background: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder with unclear pathogenic mechanisms. Dysregulated zinc metabolism contributes to AD pathology. This study aimed to identify zinc metabolism-related hub genes to provide potential biomarkers and therapeutic targets for AD. Methods: We performed an integrative analysis of multiple transcriptomic datasets from AD patients and normal controls. Differentially expressed genes and weighted gene co-expression network analysis (WGCNA) were combined to identify hub genes. We then conducted Gene Set Enrichment Analysis (GSEA), immune cell infiltration analysis (CIBERSORT), and receiver operating characteristic (ROC) curve analysis to assess the hub gene’s biological function, immune context, and diagnostic performance. Drug-gene interactions were predicted using the DrugBank database. Results: We identified a single key zinc transporter–related hub gene, SLC30A3, which was significantly downregulated in AD and demonstrated potential diagnostic value (AUC 0.70–0.80). Lower SLC30A3 expression was strongly associated with impaired synaptic plasticity (long-term potentiation, long-term depression, calcium signaling pathway, and axon guidance), mitochondrial dysfunction (the citrate cycle and oxidative phosphorylation), and pathways common to major neurodegenerative diseases (Parkinson’s disease, AD, Huntington’s disease, and amyotrophic lateral sclerosis). Furthermore, SLC30A3 expression correlated with specific immune infiltrates, particularly the microglia-related chemokine CX3CL1. Zinc chloride and zinc sulfate were identified as potential pharmacological modulators. Conclusions: Our study systematically identifies SLC30A3 as a novel biomarker in AD, linking zinc dyshomeostasis to synaptic failure, metabolic impairment, and neuroimmune dysregulation. These findings offer a new basis for developing targeted diagnostic and therapeutic strategies for AD. Full article

This article presents the development and implementation of an IoT-enabled, off-grid solar power supply prototype designed to power a range of electrical devices. The developed system comprises a Photovoltaic panel, a Maximum Power Point Tracking (MPPT) charger, a 2.5 kWh/24 V high-performance LiFePO4 battery bank with a Battery Management System, an embedded controller with IoT connectivity, and DC/DC and DC/AC converters. The PV panel serves as the primary energy source, with the MPPT controller optimizing battery charging, while the DC/DC and DC/AC converters supply power to the connected electrical devices. The article includes a case study of a developed platform for powering an information and advertising system. The system features a predictive energy management algorithm, which optimizes the appliance operation based on daily solar irradiance forecasts and real-time battery State-of-Charge monitoring. The IoT-enabled controller obtains solar irradiance forecasts from an online meteorological service via API calls and uses these data to estimate energy availability for the next day. Using this prediction, the system schedules and prioritizes the operations of connected electrical devices dynamically to optimize the performance and prevent critical battery discharge. The IoT-based controller is equipped with both Wi-Fi and an LTE modem, enabling communication with online services via wireless or cellular networks. Full article

Within the innovation-driven development paradigm, transportation infrastructure is playing an increasingly prominent role in shaping innovative activity. This paper examines the impact of transportation infrastructure on firm innovation by exploiting the staggered expansion of China’s High-Speed Rail (HSR) network as a quasi-natural experiment. Using a difference-in-differences framework, we show that the introduction of HSR significantly increases firms’ patenting activity, and the effect remains robust across a battery of alternative specifications and checks. Mechanism analyses suggest that HSR alleviates financing constraints, facilitates the mobility of highly skilled workers, and enhances the efficiency of industry-level resource allocation, thereby fostering firm innovation. Heterogeneity analyses reveal that the effect is most pronounced among firms with stronger R&D capacity, located farther from banks, non-state-owned enterprises, and SMEs. Finally, we document that the innovation-enhancing effect of HSR translates into higher firm competitiveness and profitability, underscoring the broader economic implications of transportation infrastructure development. This study deepens understanding of the mechanisms through which transportation infrastructure shapes innovation and offers important implications for optimizing the HSR network and enhancing the efficiency of innovation resource allocation. These findings offer valuable insights into how enhancing transportation infrastructure can drive firm innovation, boost corporate competitiveness, and contribute to the coordinated and sustainable development of regional economies. Full article

Vegetation colonizing fluvial sandbars provides many noteworthy functions in river and floodplain systems, but it also influences hydrodynamic processes, mainly during flooding events. Numerical modelling is generally used to evaluate the impact of floods, but its reliability is very much connected with the accuracy of the bed and bank roughness, which is eventually altered by the presence of vegetation and its height. However, for the sake of simplicity, most models tend to ignore how the sandbar roughness varies over space and time, as a function of the local vegetation dynamics (spatial distribution and height). To determine the long-term dynamic vegetation condition using remote sensing multispectral indexes, this study leverages a deep-learning method to establish a relationship between vegetation height (h), a critical parameter for vegetation roughness estimation, and vegetation indexes (VIs) collected by an uncrewed aerial vehicle (UAV). A field campaign was performed in October 2024 covering the Baishazhou sandbar, located along a straight section of the Wuhan reach of the Changjiang River Basin, China. The results show that the R² and RMSE between the real and predicted vegetation height by the trained Fully Connected Neural Network (FCNN) are 0.85, 1.10 m, and the relative error reaches a maximum of 17.2%, meaning that the trained FCNN model performs rather well. Despite being tested on a single case study, the workflow presented here demonstrates the opportunity to use UAVs for depicting vegetation characteristics such as height over large areas, eventually using them to inform numerical models that consider sandbar roughness. Full article

Leptospirosis is a globally distributed zoonosis of major public health and veterinary relevance, caused by pathogenic species of the genus Leptospira. Brazil is a hotspot for transmission due to its ecological diversity and complex host–environment interfaces. This study explored the genetic diversity and structure of circulating pathogenic Leptospira spp. in Brazil through a single-locus sequence typing (SLST) analysis based on the secY gene. A total of 531 sequences were retrieved from GenBank and subjected to phylogenetic and haplotype diversity analyses. Maximum likelihood reconstruction revealed strongly supported clades for seven species, with L. interrogans being the most prevalent and broadly distributed across hosts and regions. This species showed evidence of clonal expansion, with a dominant haplotype (n = 242) shared by humans, domestic animals, and wildlife. In contrast, L. santarosai and L. noguchii exhibited high haplotypic diversity and reticulated network structures, reflecting greater evolutionary variability. The species L. kirschneri and L. borgpetersenii displayed reduced haplotypic variation, the latter mainly associated with cattle, consistent with its host-adapted profile. Host- and biome-based haplotype networks revealed both the broad ecological adaptability of certain lineages and the exclusive presence of haplotypes restricted to specific environments, such as those found in marine mammals from the Atlantic Ocean. Genetic distance analyses confirmed the strong taxonomic resolution of the gene secY, which effectively distinguished closely related species while capturing intraspecific diversity. These findings provide a comprehensive molecular overview of pathogenic Leptospira in Brazil, highlighting ecological connectivity across hosts and biomes, as well as the contrasting evolutionary dynamics among species. Beyond describing genetic patterns, our analyses emphasize evolutionary processes, host–environment connectivity, and the implications for One Health. This integrative framework strengthens the basis for surveillance and control strategies in other endemic regions in the world. Full article

In pursuit of sustainable development goal 5 (SDG5), this study underscores gender equity and women’s empowerment as pivotal themes in sustainable development. It examines the drivers of women’s empowerment, including education, economics, finance, and legal rights, using data from $n=223$ individuals, primarily women (68.4%) aged 20–30 (69.6%). The research methodology integrates descriptive statistical measures, machine learning (ML) algorithms, and graphical representations to systematically explore the fundamental research inquiries that align with SDG5, which focuses on achieving gender equity. The results indicate that higher educational levels, captured through ordinal encoding and correlation analyzes, are strongly linked to increased labor market participation and entrepreneurial activity. The random forest (RF) and support vector machine (SVM) classifiers achieved overall accuracies of 89% and 93% for the categorization of experience, respectively. Although 91% of women have bank accounts, only 47% reported financial independence due to gendered barriers. Logistic regression correctly identified financially independent women with a 93% recall, but the classification of non-independent participants was less robust, with a 44% recall. Access to legal services, modeled using a neural network, was a potent predictor of empowerment (F1-score 0.83 for full access cases), yet significant obstacles persist for those uncertain about or lacking legal access. These findings underscore that, while formal institutional access is relatively widespread among educated women literate in the digital world, perceived and practical barriers in the financial and legal realms continue to hinder empowerment. The results quantify these effects and highlight opportunities for tailored, data-driven policy interventions targeting persistent gaps. Full article

Distant hybridization is key to trait innovation and speciation, with Cyprinidae hybrid phylogeny helping to clarify diversification mechanisms. Yet, a major gap persists in Cyprinidae studies: the stabilization mechanisms of interspecific distant hybrid lineages. To address this, we systematically analyzed the molecular phylogeny of seven Cyprinidae distant hybrid lineages and their parental species, using an integrative genetic framework encompassing four mitochondrial genes (Cytb, COI, 16S rRNA, D-loop) and five nuclear genes (EGR2b, IRBP2, RAG1, RAG2, RH2). Homologous sequences of 41 representative Cyprinidae species (85 samples) were retrieved from GenBank to supplement the dataset. Phylogenies were reconstructed from concatenated sequences, complemented by haplotype networks. Intra-/interspecific divergence was quantified using two mitochondrial genes (COI, Cytb) and two nuclear (RAG1, RH2). The results showed that these hybrid lineages exhibited variation patterns analogous to other Cyprinidae species. Both ML and BI trees reconstructed exhibited congruent topologies with high support (bootstrap/BPP > 80%), resolving genus/species-level relationships. While most hybrids clustered intermediately between their parental species, they typically displayed maternal affinity. A notable exception was the 2nNCRC (a homodiploid hybrid from Cyprinus carpio ♀ × Megalobrama amblycephala ♂), which displayed convergent evolution toward Carassius auratus. COI-based K2P genetic distance analysis revealed 2nNCRC had a much closer relationship with C. auratus (0.0119) than with its parents (0.1249 to C. carpio, 0.1552 to M. amblycephala). These nine genes elucidate the genetic relationships between Cyprinid hybrid lineages and progenitors, serving as pivotal molecular markers for parentage tracing and genetic dissection of distant hybridization mechanisms. The integrated mitochondrial–nuclear marker system in this study advances understanding of cytonuclear coadaptation and the stabilization of interspecific distant hybrid lineages in Cyprinidae. Specifically, it provides a precise tool for parentage tracing, Cyprinid germplasm conservation, and targeted regulation of hybrid breeding—laying a foundation for exploring hybrid speciation and developing elite aquaculture germplasms. Full article

Urban mobility in Bangkok is constrained by congestion, modal fragmentation, and gaps in First and Last Mile (FLM) access. This study develops a GIS-based framework that combines maximal-coverage location allocation with post-optimization accessibility diagnostics to inform intermodal hub siting. The network model compares one-, three-, and five-hub configurations using a 20 min coverage standard, and we conduct sensitivity tests at 15 and 25 min to assess robustness. Cumulative isochrones and qualitative overlays on BTS, MRT, SRT, Airport Rail Link, and principal water routes are used to interpret spatial balance, peripheral reach, and multimodal alignment. In the one-hub scenario, the model selects Pathum Wan as the optimal central node. Transitioning to a small multi-hub network improves geographic balance and reduces reliance on the urban core. The three-hub arrangement strengthens north–south accessibility but leaves the west bank comparatively underserved. The five-hub configuration is the most spatially balanced and network-consistent option, bridging the west bank and reinforcing rail interchange corridors while aligning proposed hubs with existing high-capacity lines and waterway anchors. Methodologically, the contribution is a transparent workflow that pairs coverage-based optimization with isochrone interpretation; substantively, the findings support decentralized, polycentric hub development as a practical pathway to enhance FLM connectivity within Bangkok’s current network structure. Key limitations include reliance on resident population weights that exclude floating or temporary populations, use of typical network conditions for travel times, a finite pre-screened candidate set, and the absence of explicit route choice and land-use intensity in the present phase. Full article

Against the backdrop of safety becoming a key objective in the restructuring of industrial chains, the impact of China’s outbound foreign direct investment (OFDI) on industrial chain risks warrants further exploration. Based on the Asian Development Bank’s Multi-Regional Input-Output Data (ADB-MRIOD) from 2007 to 2023, this study measures the external risk exposure of industrial chains from both supply-side and demand-side perspectives across 41 Belt and Road Initiative (BRI) economies. Utilizing a two-way fixed effects panel model with lagged variables and instrumental techniques to mitigate endogeneity, we empirically investigate the mechanisms through which China’s OFDI influences the external risk exposure of industrial chains. The findings reveal that (1) China’s OFDI significantly reduces such risk exposure, and (2) effect heterogeneity observed across country groups and sectors—showing stronger mitigation in high-innovation and developing countries, as well as in capital-intensive industries. (3) Mechanism analysis identifies three transmission channels: enhancing the host country’s trade network status, rationalizing its industrial structure, and strengthening Sino-host country industrial linkages. The study provides empirical support for formulating targeted investment policies to enhance supply chain resilience under the BRI framework. Full article

This study examines the peer effects of bank digital transformation facilitated by shareholder networks and explores the underlying mechanisms. A time-varying network is constructed based on common shareholder connections among banks, and a corresponding measure is developed to quantify peer effects in digital transformation. Using the Peking University digital transformation index together with ownership and financial data from CSMAR, an empirical analysis is performed on a panel of 114 Chinese commercial banks from 2010 to 2021 to evaluate these effects. Fixed-effects estimations indicate that bank digital transformation is significantly affected by peer effects transmitted through common shareholder connections, with a one-unit increase in peers’ digitalization index associated with a 0.151-unit rise in the focal bank’s index. These findings remain robust and economically meaningful across alternative specifications, including system GMM, IV/2SLS designs, and different ownership thresholds. Further analyses indicate that the peer effects operate through mechanisms such as intensified competition, enhanced information sharing, and pooled resources. However, such peer influence also exacerbates disparities in digital progress across the industry, reflecting a Matthew Effect in which leading banks consolidate their advantages. Heterogeneity analysis reveals that the peer effects are more pronounced among banks with larger workforces, more diversified operations, and higher ownership concentration. The findings of this study provide insights into how financial institutions can leverage technological innovations through network-based channels, offering practical implications for promoting industry-wide transformation in the digital economy era. Full article

The tokay gecko (Gekko gecko) is a widely distributed lizard species in Southeast Asia, with significant importance in traditional medicine and the pet trade. Previous studies using mitochondrial DNA sequences revealed extensive genetic variation across its range, indicating the presence of distinct evolutionary lineages. In this study, we assessed the nuclear genetic variation and phylogenetic pattern of G. gecko using the recombination activating gene 1 (RAG1). We analyzed 105 RAG1 sequences from 16 localities across Thailand, Laos, and Cambodia, along with additional sequences from GenBank. Sequence analysis revealed 20 variable sites and 20 haplotypes (TgR1–TgR20). Haplotype network and phylogenetic analyses revealed strong regional structuring and at least three distinct evolutionary lineages (A–C), supported by the species delimitation test (PTP). Both red- and black-spotted morphs were present in different clades, indicating that external coloration does not correspond to genetic differentiation at this locus. Our results support the presence of distinct evolutionary lineages in G. gecko and emphasize the importance of integrative taxonomy for accurate species delimitation. These findings have implications for conservation, sustainable management, and regulation of international trade in this commercially exploited species. Full article

We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as a time series classification task. As financial transaction data streams grow in scale and complexity, traditional methods often require large labeled datasets and struggle with time series of irregular sampling frequencies and varying sequence lengths. To address these challenges, we extend conditional Generative Adversarial Networks (GANs) for targeted data augmentation, integrate Bayesian inference to obtain predictive distributions and quantify uncertainty, and leverage log-signatures for robust feature encoding of transaction histories. We propose a composite Wasserstein distance-based loss to align generated and real unlabeled samples while simultaneously maximizing classification accuracy on labeled data. Our approach is evaluated on the BankSim dataset, a widely used simulator for credit card transaction data, under varying proportions of labeled samples, demonstrating consistent improvements over benchmarks in both global statistical and domain-specific metrics. These findings highlight the effectiveness of GAN-driven semi-supervised learning with log-signatures for irregularly sampled time series and emphasize the importance of uncertainty-aware predictions. Full article

The prediction of stock prices is challenging due to their volatility, irregular patterns, and complex time-series structure. Reliably forecasting stock market data plays a crucial role in minimizing financial risk and optimizing investment strategies. However, traditional models often struggle to capture temporal dependencies and extract relevant features from noisy inputs, which limits their predictive performance. To improve this, we developed an enhanced recursive feature elimination (RFE) method that blends the importance of impurity-based features from random forest and gradient boosting models with Kendall tau correlation analysis, and we applied SHapley Additive exPlanations (SHAP) analysis to externally validate the reliability of the selected features. This approach leads to more consistent and reliable feature selection for short-term stock prediction over 1-, 3-, and 7-day intervals. The proposed deep learning (DL) architecture integrates a temporal convolutional network (TCN) for long-term pattern recognition, a gated recurrent unit (GRU) for sequence capture, and multi-head attention (MHA) for focusing on critical information, thereby achieving superior predictive performance. We evaluate the proposed approach using daily stock price data from three leading companies—HDFC Bank, Tata Consultancy Services (TCS), and Tesla—and two major stock indices: Nifty 50 and S&P 500. The performance of our model is compared against five benchmark models: temporal convolutional network (TCN), long short-term memory (LSTM), GRU, Bidirectional GRU, and a hybrid TCN–GRU model. Our method consistently shows lower error rates and higher predictive accuracy across all datasets, as measured by four commonly used performance metrics. Full article