Search Results (1,045)

Automatic speech recognition (ASR) has advanced rapidly, evolving from early template-matching systems to modern deep learning frameworks. This review systematically traces ASR’s technological evolution across four phases: the template-based era, statistical modeling approaches, the deep learning revolution, and the emergence of large-scale models under diverse learning paradigms. We analyze core technologies such as hidden Markov models (HMMs), Gaussian mixture models (GMMs), recurrent neural networks (RNNs), and recent architectures including Transformer-based models and Wav2Vec 2.0. Beyond algorithmic development, we examine how ASR integrates into intelligent information systems, analyzing real-world applications in healthcare, education, smart homes, enterprise systems, and automotive domains with attention to deployment considerations and system design. We also address persistent challenges—noise robustness, low-resource adaptation, and deployment efficiency—while exploring emerging solutions such as multimodal fusion, privacy-preserving modeling, and lightweight architectures. Finally, we outline future research directions to guide the development of robust, scalable, and intelligent ASR systems for complex, evolving environments. Full article

Background/Objectives: Laboratory tests are a cornerstone of modern medicine, and their interpretation depends on reference intervals (RIs) that define expected values in healthy populations. Standard RIs are obtained in cohort studies that are costly and time-consuming and typically do not account for demographic factors such as age, sex, and ethnicity that strongly influence biomarker distributions. This study establishes a data-driven approach for deriving RIs directly from routinely collected laboratory results. Methods: Multidimensional joint distributions of lipid biomarkers were estimated from large-scale real-world laboratory data from the Puerto Rican population using a Gaussian Mixture Model (GMM). GMM and additional statistical analyses were used to enable separation of healthy and pathological subpopulations and exclude the influence of comorbidities all without the use of diagnostic codes. Selective mortality patterns were examined to explain counterintuitive age trends in lipid values while comorbidity implication networks were constructed to characterize interdependencies between conditions. Results: The approach yielded sex- and age-stratified RIs for lipid panel biomarkers estimated from the inferred distributions (total cholesterol, LDL, HDL, triglycerides). Apparent improvements in biomarker profiles after midlife were explained by selective survival. Comorbidities exerted pronounced effects on the 95% ranges, with their broader influence captured through network analysis. Beyond fixed limits, the method yields full distributions, allowing each individual result to be mapped to a percentile and interpreted as a continuous measure of risk. Conclusions: Population-specific and sex- and age-segmented RIs can be derived from real-world laboratory data without recruiting healthy cohorts. Incorporating selective mortality effects and comorbidity networks provides additional insight into population health dynamics. Full article

This paper presents a real-time terrain mapping method for aircraft’s navigation, combining probabilistic terrain modeling with adaptive azimuth scan command adjustment. The method refines a preloaded DTED in real time using radar scan data, enabling aircraft to update and utilize terrain elevation information during flight. The terrain is represented using a Gaussian Mixture Model (GMM), where radar scan data are evaluated based on their posterior responsibilities. A conditional nested GMM refinement is selectively applied in structurally ambiguous regions to capture multi-modal elevation patterns. The azimuth scan command is adaptively adjusted based on posterior responsibilities by increasing the step size in well-mapped regions and decreasing it in areas with low responsibility. This lightweight and adaptive strategy supports real-time operation with low computational cost. Simulations across diverse terrain types demonstrate accurate grid updates and adaptive scan control, with the proposed method achieving max error 29 m compared to grid-based averaging of 43 m and K-means clustering of 81 m. As the total number of updates is comparable to the existing methods, the proposed approach offers an advantage for real-time applications with enhanced grid accuracy. Full article

The Gaussian Mixture Model (GMM) is commonly used to formulate the probabilistic model for quantifying uncertainties in renewable generation. However, traditional static probabilistic models may not efficiently adapt and learn from newly forecasted and measured data. In this paper, we propose a recursively updated probabilistic model that leverages a recursive estimation method to update the parameters of the GMM based on continuously arriving data of renewable generation. This recursive modeling approach effectively incorporates new observations while discarding outdated samples, enabling the tracking of time-varying uncertainties in renewable generation in an incremental manner. Furthermore, we introduce an extra calibration stage to enhance the long-term accuracy of the probabilistic model after a large number of incremental updates. The main contribution is to address the potential degradation of performance caused by suboptimal incremental updates accumulated over time. Numerical tests demonstrate that the proposed model achieves 5–10% higher log likelihood in characterizing renewable generation uncertainties compared to purely recursive models, while reducing computational time by three to four orders of magnitude (1000 to 10,000 times) relative to conventional EM. These results highlight the proposed model’s suitability for real-time probabilistic modeling of renewable generation, with potential applications in system operation. Full article

Skeleton is an extreme sliding sport in the Winter Olympics, where formulating targeted sliding strategies, based on training videos to navigate complex tracks, is particularly important. To make in-depth use of training video records, this study proposes an analytical method based on Mixture of Gaussians (MoG) and K-means clustering to extract and analyze trajectories from recorded videos for sliding performance evaluation and strategy development. A case study was conducted using data from the Chinese national skeleton team at the Yanqing Sliding Center, obtaining 741, 834, and 726 sliding trajectories from three representative curves. These trajectories were divided into groups based on sliding completion time (fast, medium, and slow groups). The consistency of trajectories within each group was calculated to evaluate sliding stability, while trajectory patterns in the fast group were clustered and described based on the average values of multiple features (starting position, ending position, and apex orthogonal offset). The results showed that more skilled athletes exhibited greater sliding stability (lower ${\rho }_C$-values), and on each curve, there were sliding patterns that performed significantly better than others. This research quantifies the characteristics of athletes’ sliding trajectories on curves, facilitating the visual tracking of training effects and the development of personalized strategies. It provides coaches and athletes with scientific decision-making support and clear directions for improvement, ultimately enabling precise enhancements in training efficiency and competitive performance, while also laying a technical foundation for the future development of intelligent training systems. Full article

The extraction of ocean wave wavelengths from optical imagery via Fast Fourier Transform (FFT) exhibits significant potential for Wave-Derived Bathymetry (WDB). However, in practical applications, this method frequently produces anomalously large wavelength estimates. To date, there has been insufficient exploration into the mechanisms underlying image spectral leakage to low wavenumbers and its suppression strategies. This study investigates three plausible mechanisms contributing to spectral leakage in optical images and proposes a subimage-based preprocessing framework: prior to executing two-dimensional FFT, the remote sensing subimages employed for wavelength inversion undergo three sequential steps: (1) truncation of distorted pixel values using a Gaussian mixture model; (2) application of a polynomial detrending surface; (3) incorporation of a two-dimensional Hann window. Subsequently, the dominant wavenumber peak is localized in the power spectrum and converted to wavelength values. Water depth is then inverted using the linear dispersion equation, combined with wave periods derived from ERA5. Taking 2 m-resolution WorldView-2 imagery of Sanya Bay, China as a case study, 1024 m subimages are utilized, with validation conducted against chart-sounding data. Results demonstrate that the proportion of subimages with anomalous wavelengths is reduced from 18.9% to 3.3% (in contrast to 14.0%, 7.8%, and 16.6% when the three preprocessing steps are applied individually). Within the 0–20 m depth range, the water depth retrieval accuracy achieves a Mean Absolute Error (MAE) of 1.79 m; for the 20–40 m range, the MAE is 6.38 m. A sensitivity analysis of subimage sizes (512/1024/2048 m) reveals that the 1024 m subimage offers an optimal balance between accuracy and coverage. However, residual anomalous wavelengths persist in near-shore subimages, and errors still increase with increasing water depth. This method is both concise and effective, rendering it suitable for application in shallow-water WDB scenarios. Full article

Unmanned aerial vehicle (UAV)-based light detection and ranging (LiDAR) technology enables the acquisition of high-precision three-dimensional point clouds of the Earth’s surface. These data serve as a fundamental input for applications such as digital terrain model (DTM) construction and terrain analysis. Nevertheless, accurately extracting ground points in densely vegetated areas remains challenging. This study proposes a point cloud filtering method for the separation of ground points by integrating elevation frequency histograms and a multi-feature Gaussian mixture model (GMM). Firstly, local elevation frequency histograms are employed to estimate the elevation range for the coarse identification of ground points. Then, GMM is applied to refine the ground segmentation by integrating geometric features, intensity, and spectral information represented by the green leaf index (GLI). Finally, Mahalanobis distance is introduced to optimize the segmentation result, thereby improving the overall stability and robustness of the method in complex terrain and vegetated environments. The proposed method was validated on three study areas with different vegetation cover and terrain conditions, achieving an average $OA$ of 94.14%, $IoUg$ of 88.45%, $IoUng$ of 88.35%, and F1-score of 93.85%. Compared to existing ground filtering algorithms (e.g., CSF, SBF, and PMF), the proposed method performs well in all study areas, highlighting its robustness and effectiveness in complex environments, especially in areas densely covered by low vegetation. Full article

With the rapid growth of global shipping, accurate vessel traffic prediction is essential for waterway management and navigation safety. This study proposes the Fusion Spatio-Temporal Transformer (FSTformer) to address non-Gaussianity, non-stationarity, and spatiotemporal heterogeneity in traffic flow prediction. FSTformer incorporates a Weibull–Gaussian Transformation for distribution normalization, a hybrid Transformer encoder with Heterogeneous Mixture-of-Experts (HMoE) to model complex dependencies, and a Kernel MSE loss function to enhance robustness. Experiments on AIS data from the Fujiangsha waters of the Yangtze River show that FSTformer consistently outperforms baseline models across multiple horizons. Compared with the best baseline (STEAformer), it reduces MAE, RMSE, and MAPE by 3.9%, 1.8%, and 6.3%, respectively. These results demonstrate that FSTformer significantly improves prediction accuracy and stability, offering reliable technical support for intelligent shipping and traffic scheduling in complex waterways. Full article

Fault identification in Printed Circuit Board Assembly (PCBA) testing is essential for assuring product quality; nevertheless, conventional methods still have difficulties due to the lack of labeled faulty data and the “black box” nature of advanced models. This study introduces a label-free, interpretable self-supervised framework that uses two pretext tasks: (i) an autoencoder (reconstruction error and two latent features) and (ii) isolation forest (faulty score) to form a four-dimensional representation of each test sequence. A two-component Gaussian Mixture Model is used, and the samples are clustered into normal and fault groups. The decision is explained with cluster mean differences, SHAP (LinearSHAP or LinearExplainer on a logistic-regression surrogate), and a shallow decision tree that generated if–then rules. On real PCBA data, internal indices showed compact and well-separated clusters (Silhouette 0.85, Calinski–Harabasz 50,344.19, Davies–Bouldin 0.39), external metrics were high (ARI 0.72; NMI 0.59; Fowlkes–Mallows 0.98), and the clustered result used as a fault predictor reached 0.98 accuracy, 0.98 precision, and 0.99 recall. Explanations show that the IForest score and reconstruction error drive most decisions, causing simple thresholds that can guide inspection. An ablation without the self-supervised tasks results in degraded clustering quality. The proposed approach offers accurate, label-free fault prediction with transparent reasoning and is suitable for deployment in industrial test lines. Full article

Mining-induced seismicity poses significant safety risks in deep coal mining operations, necessitating advanced monitoring and accurate hazard assessment. Based on 15,584 microseismic events from a coal mine in Gansu, China, in 2024, this study investigates the spatiotemporal characteristics of mining-induced seismicity and its quantitative relationship with excavation disturbances. The methodology integrates Gaussian Mixture Model (GMM) clustering analysis with maximum likelihood estimation of b-value. Key findings include: (1) GMM clustering effectively identifies distinct seismic zones under different stress states, with significant variations in b-values (0.64–0.70). Low b-value zones correspond to high stress concentration and potential for strong events, enabling refined hazard assessment; (2) The time-sliding window analysis reveals the dynamic evolution of the b-value, which exhibits a clear negative correlation with high-energy seismic activity. When the b-value drops sharply to 0.6 or below, the likelihood of high-energy events increases markedly. Notably, 7 out of 8 high-energy seismic events occurred below this threshold. (3) Seismicity migrates with working face advancement, with monthly excavation length positively correlating with seismic energy release, confirming excavation as the primary trigger. This b-value spatiotemporal analysis framework provides scientific basis for early warning and mining optimization in deep coal mines. Full article

The geometric Jensen–Shannon divergence (G-JSD) has gained popularity in machine learning and information sciences thanks to its closed-form expression between Gaussian distributions. In this work, we introduce an alternative definition of the geometric Jensen–Shannon divergence tailored to positive densities which does not normalize geometric mixtures. This novel divergence is termed the extended G-JSD, as it applies to the more general case of positive measures. We explicitly report the gap between the extended G-JSD and the G-JSD when considering probability densities, and show how to express the G-JSD and extended G-JSD using the Jeffreys divergence and the Bhattacharyya distance or Bhattacharyya coefficient. The extended G-JSD is proven to be an f-divergence, which is a separable divergence satisfying information monotonicity and invariance in information geometry. We derive a corresponding closed-form formula for the two types of G-JSDs when considering the case of multivariate Gaussian distributions that is often met in applications. We consider Monte Carlo stochastic estimations and approximations of the two types of G-JSD using the projective $\gamma$-divergences. Although the square root of the JSD yields a metric distance, we show that this is no longer the case for the two types of G-JSD. Finally, we explain how these two types of geometric JSDs can be interpreted as regularizations of the ordinary JSD. Full article

The characterization and mapping of urban landscape spatial form are critical for advancing sustainable planning and informed environmental management. From a morphometric perspective, this study introduces a novel, data-driven framework for typo-morphological analysis. First, morphological cells (MCs) are defined as objectively and universally applicable spatial units for morphometric investigation. Second, by integrating a multi-dimensional cognition of full-scale morphological and associated landscape elements, we construct a set of 48 spatial form indicators and attach them to morphological cells, enabling a precise description of each unit. Third, a Gaussian mixture model (GMM) is employed to cluster the metrical information within the spatially lagged context derived from the topological structure of the morphological cells, resulting in the delineation of distinct typo-morphological zones (TMZs). We then adopt Ward’s algorithm to establish a hierarchical relationship among identified urban landscape types. Using Wuxi City, China, as a case study, our results demonstrate the effectiveness of the proposed framework in capturing the heterogeneity and underlying connotation of urban landscape spatial characteristics. Building upon the unsupervised clustering results, we further apply the classification and regression tree (CART) to provide a supervised interpretation of the key spatial form conditions driving typological decisions. It facilitates the systematic identification of the components and formative mechanisms of spatial form. The findings contribute a scalable, reproducible, and interpretable typo-morphometric approach for analyzing urban landscape spatial characteristics, thereby providing a robust quantitative foundation for integrated decision-making in landscape planning, socio-ecological assessment, and urban design practices. More broadly, the study carries both applied and theoretical significance for advancing refined urban governance and fostering interdisciplinary research related to urban sustainable development. Full article

Monitoring multimode industrial processes presents significant challenges due to varying operating conditions, nonlinear dynamics, and mode-dependent feature distributions. This paper proposes a novel process monitoring framework that integrates an enhanced Gaussian Mixture Model (GMM) for mode identification with Label Consistent K-SVD (LC-KSVD) for sparse dictionary learning. The improved GMM employs a parallelized Expectation–Maximization algorithm to achieve accurate and scalable mode partitioning in high-dimensional environments. Subsequently, the LC-KSVD then learns label-consistent, discriminative sparse representations, enabling effective monitoring across modes. The proposed method is evaluated through a simulation study and the widely used Continuous Stirred Tank Heater (CSTH) benchmark. Comparative results with traditional techniques such as LNS-PCA and FGMM demonstrate that the proposed method achieves superior fault detection rates (FDRs) and significantly lower false alarm rates (FARs), even under complex mode transitions and mild fault scenarios. Furthermore, the method also provides interpretable fault isolation through reconstruction-error-guided variable contribution analysis. These findings confirm that the proposed LC-KSVD-based scheme offers a reliable solution for fault detection and isolation in multimode process systems. Full article

Slab–column structures are susceptible to sudden punching shear failure at connections due to the absence of traditional beam support, prompting the need for effective damage monitoring. This study employs an acoustic emission (AE) technique to investigate the failure process of reinforced concrete slab–column specimens, analyzing basic AE parameters (hits, amplitude, energy), improved b-value (Ib-value), and RA–AF correlation, while introducing a Gaussian Mixture Model (GMM) to establish a unified index integrating crack type identification and energy information. Experimental results show that AE parameters can effectively track different stages of crack development, with Ib-value reflecting the transition from micro-crack to macro-crack growth. The correlation between AE energy and structural strain energy enables quantitative damage assessment, while RA–AF analysis and GMM clustering reveal the shift from bending-dominated to shear-dominated failure modes. This study provides a comprehensive framework for real-time damage evaluation and failure mode prediction in slab–column structures, demonstrating that AE-based multi-parameter analysis and data-driven clustering methods can characterize damage evolution and improve the reliability of structural health monitoring. Full article

In this paper, a class of fully probabilistic time series models based on Gaussian Vector Mixtures (VMs), i.e., on linear combinations of multivariate Gaussian distributions, is proposed to model electricity Day Ahead Market (DAM) hourly prices and to generate consistent related DAM prices dynamic scenarios. These models, based on latent variables, intrinsically allow for organizing DAM data in hierarchically organized clusters, and for recreating the delicate balance of price spikes and baseline price dynamics present in the DAM data. The latent variables and the parameters of these models have a simple and clear interpretation in terms of market phenomenology, like market conditions, spikes and night/day seasonality. In the machine learning community, different to current deep learning models, VMs and the other members of the class discussed in the paper could be seen as just ‘oldish’ probabilistic models. In this paper it is shown, on the contrary, that they are still worthy models, excellent at extracting relevant features from data, and directly interpretable as a subset of the regime switching autoregressions still currently largely used in the econometric community. In addition, it is shown how they can include mixtures of mixtures, thus allowing for the unsupervised detection of hierarchical structures in the data. It is also pointed out that, as such, VMs cannot fully accommodate the autocorrelation information intrinsic to DAM data time series, hence extensions of VMs are needed. The paper is thus divided into two parts. In the first part, VMs are estimated and used to model daily vector sequences of 24 prices, thus assessing their scenario generation capability. In this part, it is shown that VMs can very well preserve and encode infra-day dynamic structure like autocorrelation up to 24 lags, but also that they cannot handle inter-day structure. In the second part, these mixtures are dynamically extended to incorporate dynamic features typical of hidden Markov models, thus becoming Vector Hidden Markov Mixtures (VHMMs) of Gaussian distributions, endowed with daily latent dynamics. VHMMs are thus shown to be very much able to model both infra-day and inter-day phenomenology, hence able to include autocorrelation beyond 24 lags. Building on the VM discussion on latent variables and mixtures of mixtures, these models are also shown to possess enough internal structure to exploit and carry forward hierarchical clustering also in their dynamics, their small number of parameters still preserving a simple and clear interpretation in terms of market phenomenology and in terms of standard econometrics. All these properties are thus also available to their regime switching counterparts from econometrics. In practice, these very simple models, bridging machine learning and econometrics, are able to learn latent price regimes from historical data in an unsupervised fashion, enabling the generation of realistic market scenarios while maintaining straightforward econometrics-like explainability. Full article