Search

Defect detection is crucial in ensuring the quality of steel products. This paper proposes a novel deep neural network, cascaded adaptive global location network (CAGLNet), for detecting steel surface defects. The main objective of this study is to address the challenges associated with the irregular shape and dense spatial distribution of defects on steel. To achieve this goal, CAGLNet integrates a feature extraction network that combines residual and feature pyramid networks, a cascade adaptive tree-structure region proposal network (CAT-RPN) that eliminates the need for prior knowledge, and a global localisation regression for steel defect detection. This paper evaluates the effectiveness of CAGLNet on the NEU-DET dataset and demonstrates that the proposed model achieves an average accuracy of 85.40% with a fast frames per second of 10.06, outperforming those state-of-the-art methods. These results suggest that CAGLNet has the potential to significantly improve the effectiveness of defect detection in industrial production processes, leading to increased production yield and cost savings. Abbreviations: AT-RPN, adaptive tree-structure region proposal network; CAGLNet, cascaded adaptive global location network; CAT-RPN, cascade adaptive tree-structure region proposal network; CNN, convolutional neural network; DNN, deep neural network; EPNet, edge proposal network; FPN, feature pyramid network; FCOS, fully convolutional one-stage detector; FPS, frames per second; GMM, Gaussian mixture model; IoU, intersection-over-union; ROIAlign, region of interest align; RPN, region proposal network; ResNet, residual network; ResNet50_FPN, residual network and feature pyramid network; SABL, side aware boundary localisation; SSD, single-shot multiBox detector; TPE, Tree-structured Parzen estimator [ABSTRACT FROM AUTHOR]

The competition among Food & Beverage companies has substantially increased in today's age of digitization. Sales forecasting is one of their main challenges. Due to space limitations, employee shortages, and rising online demand, retail sales forecasting became extremely important for Food and Beverage companies. This research analyzed the sales data of a multinational Food & Beverage Company. It proposed a framework using Gaussian Mixture Model (GMM) clustering, Hierarchical Agglomerative Clustering (HAC), and Random Forest algorithm for forecasting sales. This model analyzes the impact of the weekends, holidays, promotional activities, customer sentiments, festivals, and socio-economic situations in sales data and is able to forecast sales ranging from one to 15 months. An investigation of the suggested model's performance compared to numerous cutting-edge sales forecasting techniques is carried out to show its efficacy. Here, we demonstrate that the proposed hybrid model surpasses current predicting and computing efficiency methods. The results of this study can help retail managers to allocate resources and manage inventories in well-informed ways. The findings suggest that combining many strategies may produce the most precise forecasts. [ABSTRACT FROM AUTHOR]

Semi-supervised object detection aims to enhance object detectors by utilizing a large number of unlabeled images, which has gained increasing attention in natural scenes. However, when these methods are directly applied to scenes with tiny objects, they face the challenge of selecting pseudo-labels with high localization quality due to the minuscule and blurred characteristics of these objects. To address this issue, we propose a novel method called semi-supervised tiny object detection (STOD). Firstly, to enhance the localization accuracy of pseudo-labels, we design a dense IoU-aware head that evaluates the quality of bounding box localization by incorporating additional predicted overlap values. Secondly, to mine more potential pseudo-labels, we propose a GMM-based multi-threshold pseudo-labels mining module that dynamically generates multiple thresholds using classification scores and overlap values to classify bounding boxes into strong positive and weak positive pseudo-labels. Lastly, we design the localization-aware weighting loss to incorporate the localization quality of both positive and negative samples in order to enhance the accuracy of pseudo-label localization. The experimental results show that STOD achieves comparable performance when compared to both fully and semi-supervised methods. Notably, on the VisDrone-Partial benchmark, STOD achieves outstanding results by outperforming our baseline model with improvements of 3.1 mAP, 5.7 A P 50 , and 3.0 A P 75 . [ABSTRACT FROM AUTHOR]

Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks. However, the current learning based image compression methods suffer from the huge computational cost, which limits their capacity for practical applications. In this paper, we propose a unified framework called Efficient Deep Image Compression (EDIC) based on three new technologies, including a channel attention module, a Gaussian mixture model and a decoder-side enhancement module. Specifically, we design an auto-encoder style network for learning based image compression. To improve the coding efficiency, we exploit the channel relationship between latent representations by using the channel attention module. Besides, the Gaussian mixture model is introduced for the entropy model and improves the accuracy for bitrate estimation. Furthermore, we introduce the decoder-side enhancement module to further improve image compression performance. Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework (Lu et al. 2019) to further improve the video compression performance. Simultaneously, our EDIC method boosts the coding performance significantly while bringing slightly increased computational cost. More importantly, experimental results demonstrate that the proposed approach outperforms the current image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method (Minnen et al. 2018). Moreover, we also evaluate the performance of the human-centric task (i.e., face recognition) by using different coding strategies. [ABSTRACT FROM AUTHOR]

AbstractUnderstanding the various roles and their corresponding evolving patterns is essential for evaluating the health of learning communities, such as in Asynchronous Online Discussion (AOD) forums. Existing research primarily focuses on identifying specific roles without considering the dynamics of role evolution, which are significant to ongoing community development. Guided by the Reader-to-Leader Framework (RtLF), this study employs multiple machine learning approaches to identify and predict the evolution of roles over time in a learning community. Our approach was applied to a K-12 Math online learning community, using data from 51,821 students to evaluate the community’s health over two years. First, a Gaussian Mixture Model was used to cluster students into five groups that represent their roles roughly in RtLF using the first nine months of learning activities. We then trained an XGBoost model to classify learner roles for subsequent periods based on meta-data. Third, we evaluate the health of the community by comparing the distribution of different roles over time and argue it is a healthy community. This study demonstrates how machine learning approaches can identify learner roles and support the health and development of learning communities. [ABSTRACT FROM AUTHOR]

A vast number of mass flow controllers (MFCs) are used in semiconductor industry. For the stable supply, an efficient production method of MFC is required. The gain tuning of the proportional-integral (PI) control to realize a setting flow rate is essential for efficient mass production. The gains are tuned to meet the specifications required for evaluation indices of response time and overshoot amount in a step response waveform. The tuning is complicated especially for the case of pressure-based MFCs. In this paper, we propose a simple method for the PI gain tuning using the Gaussian mixture model (GMM) and the direct inverse analysis applicable to the pressure-based MFCs' production. The relationship between the gains and evaluation indices for a standard unit of the MFC is modeled as the GMM. The direct inverse analysis calculates the difference between the standard and a test unit. Under the assumption that the difference can be compensated by a simple shift, gains likely to meet the specifications for the test unit are searched. We applied the method to seven test units. The result showed that the gains of all the test units were tuned within only a few iterations whose numbers were much less than the conventional manual tuning method, and there was no untunable unit. [ABSTRACT FROM AUTHOR]

Due to intermittent renewable energy and fluctuating load demand, distribution networks with renewable distributed generation (DG) installations are more likely to suffer voltage issues and significant power losses. The performance of conservation voltage regulation (CVR) schemes may be adversely affected by the undesirable voltage profile at specific nodes. This paper aims to reduce power losses in CVR‐implemented networks by optimally planning new renewable DGs without changing the existing ones. A scenario‐based optimal renewable DG planning model is proposed with a novel scenario formation method. The uncertainties of load demand and renewables are captured jointly and formed into a finite number of scenarios based on a multivariate Gaussian mixture model (MultiGMM). The locations and capacities of different types of new renewable DGs are optimally planned for CVR performance improvements on power loss saving by aggregating the operation status and probabilities of the scenarios using mixed‐integer non‐linear programming (MINLP). A time‐series simulation is formulated for accuracy verification. The results of case studies show that the proposed model can significantly reduce power losses, active load demand, and reactive load demand. The accuracy of the planning results can be guaranteed with fewer scenarios compared to a widely used classical scenario‐based planning method. [ABSTRACT FROM AUTHOR]

The Gaussian mixture model (GMM) is a probabilistic model that represents the behavior of a data set as a linear combination of K Gaussian densities. The most used method to estimate the parameters of a GMM is the maximum likelihood, giving rise to the EM-algorithm. Another alternative is minimizing the Gini index of dissimilarity between the empirical distribution of the observed data and the parametric distribution GMM, deriving in an iterative algorithm called GID-algorithm. In this work, we prove its convergence with the help of the χ 2 divergence. [ABSTRACT FROM AUTHOR]

The question of whether the Milky Way's disc extends to low metallicity has been the subject of debate for many years. We aim to address the question by employing a large sample of giant stars with radial velocities and homogeneous metallicities based on the Gaia Data Release 3 BP/RP(XP) spectra. We study the 3D velocity distribution of stars in various metallicity ranges, including the very metal-poor (VMP) regime (⁠|$\mathrm{[M/H]} < -2.0$|⁠). We find that a clear, stand-alone disc population, i.e. that with a ratio of rotational velocity to velocity dispersion |$v/\sigma > 1$|⁠ , starts to emerge only around |$\mathrm{[M/H]} \sim -1.3$|⁠ , and is not visible for |$\mathrm{[M/H]} < -1.6$|⁠. Using Gaussian mixture modelling, we show that there are two halo populations in the VMP regime: one stationary and one with a net prograde rotation of |$\sim\!\! 80\ \mathrm{km\, s}^{-1}$|⁠. In this low-metallicity range, we are able to place constraints on the contribution of a rotation-supported thick disc sub-population to a maximum of |$\sim\!\! 3$| per cent in our sample. We compare our results to previous claims of discy VMP stars in both observations and simulations and find that having a prograde halo component could explain most of these. [ABSTRACT FROM AUTHOR]

Objective: Alzheimer's disease (AD) is believed to be more common in African Americans (AA), but biomarker studies in AA populations are limited. This report represents the largest study to date examining cerebrospinal fluid AD biomarkers in AA individuals. Methods: We analyzed 3,006 cerebrospinal fluid samples from controls, AD cases, and non‐AD cases, including 495 (16.5%) self‐identified black/AA and 2,456 (81.7%) white/European individuals using cutoffs derived from the Alzheimer's Disease Neuroimaging Initiative, and using a data‐driven multivariate Gaussian mixture of regressions. Results: Distinct effects of race were found in different groups. Total Tauand phospho181‐Tau were lower among AA individuals in all groups (p < 0.0001), and Aβ42 was markedly lower in AA controls compared with white controls (p < 0.0001). Gaussian mixture of regressions modeling of cerebrospinal fluid distributions incorporating adjustments for covariates revealed coefficient estimates for AA race comparable with 2‐decade change in age. Using Alzheimer's Disease Neuroimaging Initiative cutoffs, fewer AA controls were classified as biomarker‐positive asymptomatic AD (8.0% vs 13.4%). After adjusting for covariates, our Gaussian mixture of regressions model reduced this difference, but continued to predict lower prevalence of asymptomatic AD among AA controls (9.3% vs 13.5%). Interpretation: Although the risk of dementia is higher, data‐driven modeling indicates lower frequency of asymptomatic AD in AA controls, suggesting that dementia among AA populations may not be driven by higher rates of AD. ANN NEUROL 2024;96:463–475 [ABSTRACT FROM AUTHOR]

Chub mackerel (Scomber japonicus, Scombridae) and blue mackerel (Scomber australasicus) are two important fishery resources in the western North Pacific that spawn eggs during the same season. Although estimating the total egg production (TEP) is important for evaluating the spawning stock biomass of mackerel species, it is difficult to accurately identify formalin‐preserved eggs collected during ichthyoplankton surveys. Hence, a new identification criterion that incorporates the effects of water temperature on egg size was developed in this study. The diameter of 37,304 mackerel eggs collected over 16 years (2006–2021) was measured, and frequency distributions of egg size across sea surface temperature (SST) ranges at 1°C interval were constructed. The frequency distributions were classified into two groups using a Gaussian mixture model; based on the results of DNA analysis, the small group was chub mackerel, while the large group was blue mackerel. The SST at the sampling stations and the mean egg size of both groups were negatively correlated. The new identification criterion, incorporating the relationship between SST and egg size, provided reasonable estimates of the TEP of the two mackerel species compared with the conventional criterion. The new species identification approach is applicable to other fish taxa in the western North Pacific. [ABSTRACT FROM AUTHOR]

Understanding spatial ecology and predicting animal movements in response to environmental changes, such as anthropogenic climate change and multidecadal variability, is critical for effective conservation strategies. Niche structuring is key to some coastal shark species and size classes coexisting in the US Atlantic and Gulf of Mexico to limit interspecific and intraspecific interaction. Data from four fishery‐independent bottom longline surveys were used to evaluate the abiotic ecological niches of eight species of small and large coastal sharks. Gaussian mixture models separated length composition data into 14 size categories for ecological niche analysis. Generalized additive mixed effect models were fit and coupled with output from dynamic high‐resolution ocean models to predict suitable abiotic habitats, evaluate potential shifts in distribution, and explore the impacts of large‐scale climatological trends on abiotic habitats from 1994 to 2019. The abiotic niche for small coastal sharks generally tended toward warmer, high salinity, shallow bottom waters close to shore. No overarching niche was found for large coastal sharks, but appreciable ontogenetic differences were seen. Most taxa analyzed exhibited declining annual trends in higher quality habitats, particularly during fall months. The analysis provided evidence of shifts north along the Atlantic, to deeper offshore waters in the Atlantic and Gulf of Mexico, and the potential to redistribute in response to multidecadal climate variability for multiple species. The analytical framework described could aid in developing various spatiotemporal management measures, and results provide insight into the habitat characteristics of several species over broad spatiotemporal ranges and through ontogeny. [ABSTRACT FROM AUTHOR]

A major technique for tackling unsupervised domain adaptation involves mapping data points from both the source and target domains into a shared embedding space. The mapping encoder to the embedding space is trained such that the embedding space becomes domain agnostic, allowing a classifier trained on the source domain to generalize well on the target domain. To further enhance the performance of unsupervised domain adaptation (UDA), we developed an additional technique which makes the internal distribution of the source domain more compact, thereby improving the model's ability to generalize in the target domain. We demonstrate that by increasing the margins between data representations for different classes in the embedding space, we can improve the model performance for UDA. To make the internal representation more compact, we estimate the internally learned multimodal distribution of the source domain as Gaussian mixture model (GMM). Utilizing the estimated GMM, we enhance the separation between different classes in the source domain, thereby mitigating the effects of domain shift. We offer theoretical analysis to support outperformance of our method. To evaluate the effectiveness of our approach, we conduct experiments on widely used UDA benchmark UDA datasets. The results indicate that our method enhances model generalizability and outperforms existing techniques. [ABSTRACT FROM AUTHOR]

Lineaments play a critical role in the study of lunar geological evolution. However, lineaments still need to be extracted manually which constrains lunar research. To fill this gap, a Markov chain-based methodology is introduced for automatically extracting vector-based non-bifurcated lineaments from images. The extracted lineaments are formed by successive nodes and line segments, where nodes denote pixel positions and line segments represented connecting lines between nodes. A modified U-net with residual shortcut connections and dilated convolutions is proposed based on the elongated shapes of lineaments to evaluate the probability of nodes belonging to lineaments. Four connection shape features are proposed to describe the connection shapes of nodes and a Gaussian Mixture Model is used to evaluate the probability of line segments belonging to the lineaments based on the proposed features. In the final stage, the lineament probabilities of both nodes and line segments to extract lineaments are considered in the Markov chain. Our method has experimented on a dataset containing 220 samples and 10-fold cross-validation was used to evaluate the performance. Both qualitative and quantitative results indicated that our method can effectively extract non-bifurcated lunar lineaments with arbitrary bending. The method sheds useful light on automatic lineament extraction. [ABSTRACT FROM AUTHOR]

Global shipment volumes have been increasing due to changes in the business environment of e‐commerce and manufacturing. Consequently, container vessels carry more cargo for international trade, increasing uncertainties in terminal management. Terminal operators manage terminals by establishing a proactive schedule that responds to disruptions such as vessel delays, and the introduction of buffer time is a representative proactive strategy. In this study, by analyzing historical delay data with machine learning, we propose data‐driven buffer times to consider the heterogeneous arrival uncertainty of vessels. Thus, we proactive scheduling with data‐driven buffer times according to the desired robustness levels. This is a novel study on berth scheduling that applies data mining approaches to improve operations research techniques. Numerical experiments were conducted on the berth scheduling with time‐invariant quay crane assignment using real‐life data to validate the effectiveness of the proposed method. These experimental results revealed that applying the data‐driven buffer time could effectively reduce the cost incurred at the terminal by balancing baseline and recovery costs. In addition, our proposed methodology ensured the quality of the solution compared with a stochastic method and reduced the computational burden of a stochastic problem by using the data‐driven buffer times obtained prior to the solution construction. Therefore, the proposed method can be introduced into terminal operations to overcome the deficiencies of traditional approaches in terms of academic perspective. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have revolutionized various fields through their ability to model complex patterns, yet their performance critically hinges on the availability of large-scale, accurately labeled datasets. The costly and time-consuming process of creating such datasets has motivated research into Learning with Noisy Labels (LNL), which aims to reduce reliance on perfect labels. This paper introduces CoFix, an innovative LNL framework that integrates sample selection with semi-supervised learning techniques to address the challenge of noisy labels in training. CoFix employs a Gaussian Mixture Model (GMM) to dynamically segment the training data into clean and noisy subsets, leveraging semi-supervised learning approaches on both. Inspired by the FixMatch algorithm, CoFix refines consistent regularization and pseudo-labeling strategies, enhancing augmentation strategies and temperature sharpening techniques. Additionally, CoFix explores label smoothing to augment the loss function, further refining model performance. Our experiments demonstrate CoFix’s superiority over state-of-the-art methods, achieving significant improvements in fewer training epochs, particularly in lower noise scenarios. The robustness and versatility of CoFix are evident through its consistent performance across various benchmark datasets and noise levels. The contributions of this paper include a novel LNL method with enhanced generalization capability, an investigation into the impact of label smoothing on the loss function, and extensive testing that confirms CoFix’s efficiency and adaptability to different noise levels. [ABSTRACT FROM AUTHOR]

Summary Background Objective Methods Results Conclusions Calcium intake has been associated with lower adiposity, but few studies explored the longitudinal relation of calcium from different sources and cardiometabolic markers in young population.Prospectively estimate the association between dairy and non‐dairy calcium intake at 4, 7, and 10 years (y) of age and cardiometabolic risk at 13 y.The sample included 4017 participants from the Generation XXI birth cohort. Dietary data were collected from a 3‐day food diary. Cardiometabolic clusters at 13 y were estimated by a probabilistic Gaussian mixture model (z‐score of waist circumference [WC], HOMA‐IR; HDL cholesterol, triglycerides, and systolic blood pressure [BP]). Multivariable linear and logistic regression models were used to estimate associations.Calcium intake (/100 mg), after adjustment for confounders, was negatively and significantly associated with body mass index (BMI) (β = −0.02, 95% CI: −0.04; −0.01), WC (cm) (β = −0.23, 95% CI: −0.36; −0.11), and diastolic BP (mmHg) (β = −0.14, 95% CI: −0.26; −0.03). After additional adjustment for total energy intake, associations lose statistical significance. Calcium intake from milk at 7 y was inversely associated with WC (β = −0.25, 95% CI: −0.48; −0.03) and from yogurt at 10 y was associated with higher BMI (β = 0.08, 95% CI: 0.03; 0.13) and WC (β = 0.54, 95% CI: 0.12; 0.96). Calcium from vegetables at 4, 7, 10 y reduces later cardiometabolic risk (OR = 0.71; OR = 0.84; OR = 0.98, respectively).This study supports a protective effect of calcium on adolescents' cardiometabolic health, especially from vegetables. [ABSTRACT FROM AUTHOR]

Nowadays, intermittent energy resources, such as wind turbines, and direct current (DC) transmission have been extensively integrated into power systems. This paper proposes an identifying method for weak lines of novel power systems with intermittent energy resources and DC lines integration, which aims to provide decision making for control strategies of novel power systems and prevent system blackouts. First, from the perspective of power system safety and stability, a series of risk indicators for the risk assessment of vulnerable lines is proposed. Then, lines in the system are tripped one by one. The calculation method for the proposed risk indicators is introduced. The impact of each line outage on system safety and stability can be fairly evaluated by these proposed risk indicators. On this basis, each risk assessment indicator is weighted to obtain a comprehensive risk assessment indicator, and then the risk caused by each line outage on the system can be quantified efficiently. Finally, the test system of a modified IEEE-39 bus system with wind farms and DC lines integration is used to verify the applicability of the proposed method, and the effectiveness of the proposed method is also demonstrated by comparing with existing methods. [ABSTRACT FROM AUTHOR]

Sea surface salinity (SSS) observed by satellite has been widely used since the successful launch of the first salinity satellite in 2009. However, compared with other oceanographic satellite products (e.g., sea surface temperature, SST) that became operational in the 1980s, the SSS product is less mature and lacks effective validation from the user end. We employed an unsupervised machine learning approach to classify the Level 3 SSS bias from the Soil Moisture Active Passive (SMAP) satellite and its observing environment. The classification model divides the samples into fifteen classes based on four variables: satellite SSS bias, SST, rain rate, and wind speed. SST is one of the most significant factors influencing the classification. In regions with cold SST, satellite SSS has an accuracy of less than 0.2 PSU (Practical Salinity Unit), mainly due to the higher uncertainty in the cold environment. A small number of observations near the seawater freezing point show a significant fresh bias caused by sea ice. A systematic bias of the SMAP SSS product is found in the mid-latitudes: positive bias tends to occur north (south) of 45°N(S) and negative bias is more common in 25°N(S)–45°N(S) bands, likely associated with the SMAP calibration scheme. A significant bias also occurs in regions with strong ocean currents and eddy activities, likely due to spatial mismatch in the highly dynamic background. Notably, satellite SSS and in situ data correlations remain good in similar environments with weaker ocean dynamic activities, implying that satellite salinity data are reliable in dynamically active regions for capturing high-resolution details. The features of the SMAP SSS shown in this work call for careful consideration by the data user community when interpreting biased values. [ABSTRACT FROM AUTHOR]

Distributed machine learning has received much attention for more than two decades. Yet, it is still a challenge to achieve acceptable performance in practical scenarios when some features of data samples are missing. Although some imputation methods have been proposed for handling missing data, their performance deteriorates significantly when data are heterogeneously distributed over different nodes in the network. Considering this, in this article, we first propose a general Gaussian mixture model (GMM) consisting of both public and personalized components for modeling the homogeneous and the heterogeneous parts of data distribution, respectively. Then, we develop a distributed personalized expectation–maximization method based on knowledge transfer (KT-dpEM) to estimate the parameters of the proposed general GMM. After that, based on the estimated general GMM, missing data are imputed using the posterior conditional mean. Experimental results show that the proposed KT-dpEM algorithm has better imputation accuracy, higher robustness against different missing probabilities and better classification performance in the downstream classification tasks, compared with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Wind turbine components' failure prognosis allows wind farm owners to apply predictive maintenance techniques to their fleets. Determining the health status of a turbine's component typically requires verifying many variables that should be monitored simultaneously. The scope of this study is the selection of the more relevant variables and the generation of a health status indicator (Failure Index) to be considered as a decision criterion in Operation and Maintenance activities. The proposed methodology is based on Gaussian Mixture Copula Models (GMCMs) combined with a smoothing method (Cubic spline smoothing) to define a component's health index based on the previous behavior and relationships between the considered variables. The GMCM allows for determining the component's status in a multivariate environment, providing the selected variables' joint probability and obtaining an easy-to-track univariate health status indicator. When the health of a component is degrading, anomalous behavior becomes apparent in certain Supervisory Control and Data Acquisition (SCADA) signals. By monitoring these SCADA signals using this indicator, the proposed anomaly detection method could capture the deviations from the healthy working state. The resulting indicator shows whether any failure is likely to occur in a wind turbine component and would aid in a preventive intervention scheduling. [ABSTRACT FROM AUTHOR]

Proteins play a key role in biological electron transport, but the structure-function relationships governing the electronic properties of peptides are not fully understood. Despite recent progress, understanding the link between peptide conformational flexibility, hierarchical structures, and electron transport pathways has been challenging. Here, we use single-molecule experiments, molecular dynamics (MD) simulations, nonequilibrium Green's function-density functional theory (NEGF-DFT), and unsupervised machine learning to understand the role of secondary structure on electron transport in peptides. Our results reveal a two-state molecular conductance behavior for peptides across several different amino acid sequences. MD simulations and Gaussian mixture modeling are used to show that this two-state molecular conductance behavior arises due to the conformational flexibility of peptide backbones, with a high-conductance state arising due to a more defined secondary structure (beta turn or 310 helices) and a low-conductance state occurring for extended peptide structures. These results highlight the importance of helical conformations on electron transport in peptides. Conformer selection for the peptide structures is rationalized using principal component analysis of intramolecular hydrogen bonding distances along peptide backbones. Molecular conformations from MD simulations are used to model charge transport in NEGF-DFT calculations, and the results are in reasonable qualitative agreement with experiments. Projected density of states calculations and molecular orbital visualizations are further used to understand the role of amino acid side chains on transport. Overall, our results show that secondary structure plays a key role in electron transport in peptides, which provides broad avenues for understanding the electronic properties of proteins. [ABSTRACT FROM AUTHOR]

Due to the fluctuating and intermittent nature of wind energy, its prediction is uncertain. Hence, this paper suggests a method for predicting wind power in the short term and analyzing uncertainty using the VDM-TCN approach. This method first uses Variational Mode Decomposition (VDM) to process the data, and then utilizes the temporal characteristics of Temporal Convolutional Neural Network (TCN) to learn and predict the dataset after VDM processing. Through comparative experiments, we found that VDM-TCN performs the best in short-term wind power prediction. In wind power prediction for 4-h and 24-h horizons, the RMSE errors were 1.499% and 4.4518% respectively, demonstrating the superiority of VDM-TCN. Meanwhile, the Gaussian Mixture Model (GMM) can effectively quantify the uncertainty of wind power generation at different time scales. [ABSTRACT FROM AUTHOR]

Motivation Advances in whole-genome single-cell DNA sequencing (scDNA-seq) have led to the development of numerous methods for detecting copy number aberrations (CNAs), a key driver of genetic heterogeneity in cancer. While most of these methods are limited to the inference of total copy number, some recent approaches now infer allele-specific CNAs using innovative techniques for estimating allele-frequencies in low coverage scDNA-seq data. However, these existing allele-specific methods are limited in their segmentation strategies, a crucial step in the CNA detection pipeline. Results We present SEACON (Single-cell Estimation of Allele-specific COpy Numbers), an allele-specific copy number profiler for scDNA-seq data. SEACON uses a Gaussian Mixture Model to identify latent copy number states and breakpoints between contiguous segments across cells, filters the segments for high-quality breakpoints using an ensemble technique, and adopts several strategies for tolerating noisy read-depth and allele frequency measurements. Using a wide array of both real and simulated datasets, we show that SEACON derives accurate copy numbers and surpasses existing approaches under numerous experimental conditions, and identify its strengths and weaknesses. Availability and implementation SEACON is implemented in Python and is freely available open-source from https://github.com/NabaviLab/SEACON and https://doi.org/10.5281/zenodo.12727008. [ABSTRACT FROM AUTHOR]

In the realm of bioinformatics, we frequently encounter discrete data, particularly microbiome taxa count data obtained through 16S rRNA sequencing. These microbiome datasets are commonly characterized by their high dimensionality and the ability to provide insights solely into relative abundance, necessitating their classification as compositional data. Analyzing such data presents challenges due to their confinement within a simplex. Additionally, microbiome taxa counts are subject to influence by various biological and environmental factors like age, gender, and diet. Thus, we have developed a novel approach involving regression-based mixtures of logistic normal multinomial models for clustering microbiome data. These models effectively categorize samples into more homogeneous subpopulations, enabling the exploration of relationships between bacterial abundance and biological or environmental covariates within each identified group. To enhance the accuracy and efficiency of parameter estimation, we employ a robust framework based on variational Gaussian approximations (VGA). Our proposed method's effectiveness is demonstrated through its application to simulated and real datasets. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG)-based applications in brain–computer interfaces (BCIs), neurological disease diagnosis, rehabilitation, etc., rely on supervised approaches such as classification that requires given labels. However, with the ever-increasing amount of EEG data, incomplete or incorrectly labeled or unlabeled EEG data are increasing. It likely degrades the performance of supervised approaches. In this work, we put forward a novel unsupervised exploratory EEG analysis solution by clustering based on low-dimensional prototypes in latent space that are associated with the respective clusters. Having the prototype as a baseline of each cluster, a compositive similarity is defined to act as the critic function in clustering, which incorporates similarities on three levels. The approach is implemented with a Generative Adversarial Network (GAN), termed W-SLOGAN, by extending the Stein Latent Optimization for GANs (SLOGAN). The Gaussian Mixture Model (GMM) is utilized as the latent distribution to adapt to the diversity of EEG signal patterns. The W-SLOGAN ensures that images generated from each Gaussian component belong to the associated cluster. The adaptively learned Gaussian mixing coefficients make the model remain effective in dealing with an imbalanced dataset. By applying the proposed approach to two public EEG or intracranial EEG (iEEG) epilepsy datasets, our experiments demonstrate that the clustering results are close to the classification of the data. Moreover, we present several findings that were discovered by intra-class clustering and cross-analysis of clustering and classification. They show that the approach is attractive in practice in the diagnosis of the epileptic subtype, multiple labelling of EEG data, etc. [ABSTRACT FROM AUTHOR]

The primary focus of this research is the proposition of a methodological framework for the clinical application of the long COVID symptoms and severity score (LC-SSS). This tool is not just a self-reported assessment instrument developed and validated but serves as a standardized, quantifiable means to monitor the diverse and persistent symptoms frequently observed in individuals with long COVID. A 3-stage process was used to develop, validate, and establish scoring standards for the LC-SSS. Validation measures included correlations with other patient-reported measures, confirmatory factor analysis, Cronbach's α for internal consistency, and test-retest reliability. Scoring standards were determined using K-means clustering, with comparative assessments made against hierarchical clustering and the Gaussian Mixture Model. The LC-SSS showed correlations with EuroQol 5-Dimension 5-Level (r s = −0.55), EuroQol visual analog scale (r s = −0.368), Patient Health Questionnaire-9 (r s = 0.538), Beck Anxiety Inventory (r s = 0.689), and Insomnia Severity Index (r s = 0.516), confirming its construct validity. Structural validity was good with a comparative fit index of 0.969, with Cronbach's α of 0.93 indicating excellent internal consistency. Test-retest reliability was also satisfactory (intraclass correlation coefficient 0.732). K-means clustering identified 3 distinct severity categories in individuals living with long COVID, providing a basis for personalized treatment strategies. The LC-SSS provides a robust and valid tool for assessing long COVID. The severity categories established via K-means clustering demonstrate significant variation in symptom severity, informing personalized treatment and improving care quality for patients with long COVID. • This study introduces the long COVID symptoms and severity score (LC-SSS), a novel, validated tool incorporating unsupervised machine learning to categorize symptom severity. This addresses a critical gap in standardized and quantifiable monitoring of long COVID, going beyond the limitations of traditional patient-reported outcome measures and offering a refined, personalized assessment framework. • The research demonstrates that the LC-SSS is strongly correlated with existing health quality measures, showing high construct and structural validity, excellent internal consistency, and satisfactory test-retest reliability. K-means clustering further identified 3 distinct severity categories among patients with long COVID, which can guide personalized treatment strategies, highlighting the tool's efficacy in capturing the complexity of long COVID symptoms. • By enabling precise classification of symptom severity, the LC-SSS facilitates tailored treatment plans and informs healthcare resource allocation and policy formulation for long COVID management. Its integration into clinical practice promises to improve diagnostic accuracy, enhance care quality, and potentially uplift patient outcomes in the context of health economics and outcomes research, making a significant contribution to the field. [ABSTRACT FROM AUTHOR]

The precise segmentation of white blood cells (WBCs) within blood smear images is a significant challenge with implications for both medical research and image processing. Of particular importance is the often neglected task of accurately segmenting WBC nuclei, an aspect that currently lacks dedicated methodologies. This paper introduces a straightforward and efficient method designed to fill this critical gap, providing an effective solution for the efficient segmentation of WBC nuclei. In blood smear imagery, the distinctive coloration of WBCs contrasts with the hues of other blood components. The inherent obscurity of WBCs prompts their segmentation by isolating pixels with minimal intensities. To streamline this process, our proposed method employs the Laplacian pyramid technique to decorrelate pixels in blood smear images, thereby amplifying the contrast. Subsequently, the intensities of pixels constituting blood cells, encompassing WBCs and the background, are modeled using three Gaussian random variables. Capitalizing on this feature, we implement the Gaussian mixture model (GMM) clustering method to determine the optimal threshold value, facilitating a highly precise segmentation of WBC nuclei. The proposed method demonstrates the capability to process images containing a single WBC as well as effectively functioning with images containing multiple cells of this type. Evaluation of the method on the ALL-IDB, ALL-IDB2, CellaVision, and JTSC datasets yielded accuracy values of 0.9802, 0.9725, 0.9772, and 0.9730, respectively. Comparative analysis with state-of-the-art methods revealed a notably comparable performance, underscoring the effectiveness of the proposed approach. The method presented in this article is highly competitive for segmenting the nuclei of WBCs compared to state-of-the-art methods. The three main advantages of our method are its ability to process images containing one or more WBCs, the automatic calculation of threshold values for each processed image, eliminating the need for manual parameter adjustments. Lastly, the method is efficient, as its algorithmic complexity is approximately O (n m) . [ABSTRACT FROM AUTHOR]

For the accurate estimation of neutron cross-section data, evaluation of nuclear data is mandatory to fulfill the need of nuclear science and technology. In this work, the evaluation of 232Th(n,2n)231Th, 241Am(n,2n)240Am, 100Mo(n,2n)99Mo, and 96Mo(n,p)96Nb reaction cross-section data is carried out using a novel method. This novel method of evaluation employs a cluster-based piecewise evaluation followed by a digital filter for merging the evaluated curves. The clusters in the experimental data and model data are identified using the probabilistic method of the Gaussian Mixture Model. The clustered experimental data are then regressed using the polynomial regression technique. The model data are generated using the Talys 1.9 code, and the model deficiency due to the complex random nature of nuclear reactions is also accounted here using chi-squared analysis. Evaluation in each cluster is then carried out independently using the popular Kalman filter technique. For obtaining a single smooth evaluated curve for the whole energy range, the popular smoothing digital filter, the Savitzky-Golay Filter, is employed for the first time in nuclear data evaluation. The proposed evaluated curves and existing evaluated curves of 232Th(n,2n)231Th, 241Am(n,2n)240Am, 100Mo(n,2n)99Mo, and 96Mo(n,p)96Nb reactions from nuclear data libraries such as ENDF/BVIII.0, JEFF-3.3, JENDL-4.0, CENDL-3.1, and TENDL 2021 are compared and found to be in good agreement. It is also found that generally, evaluation methods are data dependent, and so, a single evaluation method may not be applicable for all reactions of all nuclides. Since piecewise evaluation is cluster dependent, selecting the appropriate cluster makes this method robust for almost all reactions of all nuclides. Also, it is proven that this novel method of evaluation is a promising method demonstrating the potential of this approach for evaluation based on the chi-squared goodness-of-fit test with respect to standard evaluated library ENDF/BVIII.0 and experimental data. [ABSTRACT FROM AUTHOR]

Based on a sample of K giant from Large sky Area Multi-Object fibre Spectroscopic Telescope Data Release 8 and a sample of RR Lyrae (RRL) from Gaia Data Release 3, we investigate the compositions of the Hercules–Aquila Cloud (HAC) and Virgo Overdensity (VOD) and their collective contribution to the tilt and triaxiality of the stellar halo (⁠|$r\, \lt \, 40\, {\rm kpc}$|⁠) as well as two breaks at |$\approx 15\, {\rm kpc}$| and 30 kpc. We apply the Gaussian mixture model to divide the stellar halo into the isotropic component and the radially biased anisotropic component, namely Gaia–Sausage–Enceladus (GSE), and find that both HAC and VOD are dominated by the GSE debris stars with weights of |$0.67^{+0.09}_{-0.07}$| and |$0.57^{+0.07}_{-0.06}$|⁠ , respectively. In addition, using the K giants with orbital parameters, we identify the member stars of known substructures, including GSE, Sagittarius (Sgr), Helmi Streams, Sequoia, Thamnos, Pontus, Wukong, and Metal-weak Thick Disc, to probe the compositions of low-eccentricity stars in the HAC and VOD regions. In density fittings of the RRL sample, we note that the absence of HAC and VOD has a weak effect on the shape of halo. Finally, we find that the radially biased anisotropic halo contributes majorly to the stellar halo that can be modelled with a tilted triaxial ellipsoid and a doubly broken power law with breaking radii at |$18.08^{+2.04}_{-3.22}\, {\rm kpc}$| and |$33.03^{+1.30}_{-1.21}\, {\rm kpc}$|⁠. This has important significance for understanding the status of large diffuse overdensities in the Milky Way. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive multiwavelength investigation of the intermediate-age open cluster NGC 1912. We identified 401 member stars for NGC 1912 using K-nearest neighbour and Gaussian Mixture Model machine learning techniques. The fundamental parameters determined for the cluster are metallicity (z) = 0.0141 |$\pm$| 0.0006, log(age) = 8.519 |$\pm$| 0.040, binary fraction (⁠|$b_{\text{frac}}$|⁠) = 0.445 |$\pm$| 0.035, visual extinction (⁠|$A_V$|⁠) = 0.864 |$\pm$| 0.033 mag, total-to-selective extinction ratio (⁠|$R_V$|⁠) = 3.007 |$\pm$| 0.096, distance = 1096 |$\pm$| 15 pc. The central density (⁠|$\rho _o$|⁠), core radius (⁠|$r_c$|⁠), tidal radius (⁠|$r_t$|⁠), and background density (⁠|$\rho _{\mathrm{bg}}$|⁠) for the cluster are obtained as 0.643 |$\pm$| 0.067 stars arcmin |$^{-2}$| , 7.743 |$\pm$| 0.784 arcmin, 84.633 |$\pm$| 7.188 arcmin, and 0.001 |$\pm$| 0.000 stars arcmin |$^{-2}$| , respectively. Dynamical mass segregation study revealed a concentration of some apparently massive stars towards the cluster centre. Polarimetric analysis of 90 stars in |$BVR_cI_c$| wavelength bands revealed that the observed polarization in NGC 1912 is not solely attributed to interstellar dust. The Galactic magnetic field is dominant in this region. Dust grain sizes within the intracluster region are found to be relatively smaller than that of the general ISM. The extinction map revealed the existence of a potential 'interstellar bubble' located close to the cluster region. Towards the periphery of the probable bubble region, which displays an ovoid-like geometry, 16 probable young stellar objects have been detected, suggesting the ongoing triggering of secondary star formation events in this region. [ABSTRACT FROM AUTHOR]

This article investigates the effectiveness of feature extraction and selection techniques in enhancing the performance of classifier accuracy in Type II Diabetes Mellitus (DM) detection using microarray gene data. To address the inherent high dimensionality of the data, three feature extraction (FE) methods are used, namely Short-Time Fourier Transform (STFT), Ridge Regression (RR), and Pearson's Correlation Coefficient (PCC). To further refine the data, meta-heuristic algorithms like Bald Eagle Search Optimization (BESO) and Red Deer Optimization (RDO) are utilized for feature selection. The performance of seven classification techniques, Non-Linear Regression—NLR, Linear Regression—LR, Gaussian Mixture Models—GMMs, Expectation Maximization—EM, Logistic Regression—LoR, Softmax Discriminant Classifier—SDC, and Support Vector Machine with Radial Basis Function kernel—SVM-RBF, are evaluated with and without feature selection. The analysis reveals that the combination of PCC with SVM-RBF achieved a promising accuracy of 92.85% even without feature selection. Notably, employing BESO with PCC and SVM-RBF maintained this high accuracy. However, the highest overall accuracy of 97.14% was achieved when RDO was used for feature selection alongside PCC and SVM-RBF. These findings highlight the potential of feature extraction and selection techniques, particularly RDO with PCC, in improving the accuracy of DM detection using microarray gene data. [ABSTRACT FROM AUTHOR]

SUMMARY: Applications of machine learning in seismology have greatly improved our capability of detecting earthquakes in large seismic data archives. Most of these efforts have been focused on continental shallow earthquakes, but here we introduce an integrated deep-learning-based workflow to detect deep earthquakes recorded by a temporary array of ocean-bottom seismographs (OBSs) and land-based stations in the Tonga subduction zone. We develop a new phase picker, PhaseNet-TF, to detect and pick P- and S-wave arrivals in the time–frequency domain. The frequency-domain information is critical for analysing OBS data, particularly the horizontal components, because they are contaminated by signals of ocean-bottom currents and other noise sources in certain frequency bands. PhaseNet-TF shows a much better performance in picking S waves at OBSs and land stations compared to its predecessor PhaseNet. The predicted phases are associated using an improved Gaussian Mixture Model Associator GaMMA-1D and then relocated with a double-difference package teletomoDD. We further enhance the model performance with a semi-supervised learning approach by iteratively refining labelled data and retraining PhaseNet-TF. This approach effectively suppresses false picks and significantly improves the detection of small earthquakes. The new catalogue of Tonga deep earthquakes contains more than 10 times more events compared to the reference catalogue that was analysed manually. This deep-learning-enhanced catalogue reveals Tonga seismicity in unprecedented detail, and better defines the lateral extent of the double-seismic zone at intermediate depths and the location of four large deep-focus earthquakes relative to background seismicity. It also offers new potential for deciphering deep earthquake mechanisms, refining tomographic models, and understanding of subduction processes. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have achieved breakthrough progress in various fields, largely owing to the support of large-scale datasets with manually annotated labels. However, obtaining such datasets is costly and time-consuming, making high-quality annotation a challenging task. In this work, we propose an improved noisy sample selection method, termed "sample selection framework", based on a mixup loss and recalibration strategy (SMR). This framework enhances the robustness and generalization abilities of models. First, we introduce a robust mixup loss function to pre-train two models with identical structures separately. This approach avoids additional hyperparameter adjustments and reduces the need for prior knowledge of noise types. Additionally, we use a Gaussian Mixture Model (GMM) to divide the entire training set into labeled and unlabeled subsets, followed by robust training using semi-supervised learning (SSL) techniques. Furthermore, we propose a recalibration strategy based on cross-entropy (CE) loss to prevent the models from converging to local optima during the SSL process, thus further improving performance. Ablation experiments on CIFAR-10 with 50% symmetric noise and 40% asymmetric noise demonstrate that the two modules introduced in this paper improve the accuracy of the baseline (i.e., DivideMix) by 1.5% and 0.5%, respectively. Moreover, the experimental results on multiple benchmark datasets demonstrate that our proposed method effectively mitigates the impact of noisy labels and significantly enhances the performance of DNNs on noisy datasets. For instance, on the WebVision dataset, our method improves the top-1 accuracy by 0.7% and 2.4% compared to the baseline method. [ABSTRACT FROM AUTHOR]

In recent years, the Internet of Things (IoT) has grown rapidly, as has the number of attacks against it. Certain limitations of the paradigm, such as reduced processing capacity and limited main and secondary memory, make it necessary to develop new methods for detecting attacks in real time as it is difficulty to adapt as has the techniques used in other paradigms. In this paper, we propose an architecture capable of generating complex event processing (CEP) rules for real-time attack detection in an automatic and completely unsupervised manner. To this end, CEP technology, which makes it possible to analyze and correlate a large amount of data in real time and can be deployed in IoT environments, is integrated with principal component analysis (PCA), Gaussian mixture models (GMM) and the Mahalanobis distance. This architecture has been tested in two different experiments that simulate real attack scenarios in an IoT network. The results show that the rules generated achieved an F1 score of.9890 in detecting six different IoT attacks in real time. [ABSTRACT FROM AUTHOR]

As an essential aspect of semantic segmentation, real-time semantic segmentation poses significant challenge in achieving trade-off between segmentation accuracy and inference speed. Standard non-local block can effectively capture the long-range dependencies that are critical to semantic segmentation, while its huge computational cost is unacceptable for real-time semantic segmentation. To confront this issue, we propose fast non-local attention network (FNANet) with encoder–decoder structure for real-time semantic segmentation. FNANet relies on the utilization of fast non-local attention module and fast non-local attention fusion module. These modules serve the dual purpose of reducing computational demands and capturing essential contextual information, thereby achieving an equilibrium between enhanced segmentation accuracy and minimized computational overhead. Furthermore, improved non-local attention is incorporated to augment feature representation, consequently facilitating precise class label prediction. Experimental results demonstrate that FNANet outperforms state-of-the-art methods in terms of segmentation accuracy and speed on Cityscapes and CamVid. [ABSTRACT FROM AUTHOR]

Virtual metrology (VM) is crucial for improving process capability and production yield during semiconductor manufacturing processes. However, the performance of VM deteriorates owing to the variable operating regime and the nonlinear characteristics of the process. Herein, Variational inference Gaussian mixture model (VIGMM) and extreme learning machine (ELM) are combined to solve these issues. First, variational inference is conducted on a Gaussian mixture model to determine the number of Gaussian components automatically and the corresponding operating regimes are identified. Subsequently, an extreme learning machine is developed for each operating regime to investigate the nonlinear relationship between process inputs and outputs. Finally, VM is implemented using the corresponding local ELM, which is determined based on the responsibility of the Gaussian components. The feasibility and effectiveness of the proposed methods are validated based on a numerical case and the plasma sputtering process for fabricating thin-film transistor liquid-crystal displays. The proposed VIGMM-ELM can serve as a VM algorithm for manufacturing processes with multiple stages. [ABSTRACT FROM AUTHOR]

As video lectures are gaining more popularity, determining their effectiveness and obtaining valuable feedback have become necessary. To measure the learners' attention state during video lectures, we specified the conceptual "with-me-ness" (WMN) as slide-level WMN (SL-WMN). The content domain on each slide was automatically extracted via an optical character recognition (OCR)-based method, while the eye gazing behaviors were analyzed through a Gaussian mixture modeling (GMM) fixation clustering method. Both domain-specific WMN and behavior-enriched WMN were then computed via OCR- and GMM-OCR-based methods to measure the learners' attention levels. We conducted an experiment to collect in-lecture eye-tracking data, video recordings, and post-lecture test scores from 50 Grade 8 students. The results demonstrated that both OCR- and GMM-OCR-based SL-WMNs are reliable and compatible automatic measurements of learners' attention states during video lectures. A survey from participating learners and lecturers also revealed highly favorable feedback for the developed SL-WMNs. [ABSTRACT FROM AUTHOR]

Modeling spatial search processes such as residential location search are challenging, particularly, due to the need to deal with a large dataset and wide array of factors. This introduces a multi-dimensionality challenge to location search modeling. With the motivation to accommodate multi-dimensionality, this paper develops a machine learning–based Gaussian mixture model (GMM) for location search. This study accommodates the effects of several factors including accessibility, land use, dwelling, transportation infrastructure, and neighborhood attributes on location search decisions. The spatial unit of analysis is dwelling-level. This study conceptualizes that households' search for location based on their reason to move. The pool of alternatives for each household is generated based on probability estimates of GMM. The location choice model considering the reason-based GMM outperforms the model without considering relocation reasons in GMM and random sampling-based model in-terms of predictive performance. The search model has been implemented in an integrated urban model. [ABSTRACT FROM AUTHOR]

Fall prediction using machine learning has become one of the most fruitful and socially relevant applications of computer vision in gerontological research. Since its inception in the early 2000s, this subfield has proliferated into a robust body of research underpinned by various machine learning algorithms (including neural networks, support vector machines, and decision trees) as well as statistical modeling approaches (Markov chains, Gaussian mixture models, and hidden Markov models). Furthermore, some advancements have been translated into commercial and clinical practice, with companies in various stages of development capitalizing on the aging population to develop new commercially available products. Yet despite the marvel of modern machine learning-enabled fall prediction, little research has been conducted to shed light on the security and privacy concerns that such systems pose for older adults. The present study employs an interdisciplinary lens in examining privacy issues associated with machine learning fall prediction and exploring the implications of these models in elderly care and the Internet of Medical Things (IoMT). Ultimately, a justice-informed set of best practices rooted in social geroscience is suggested to help fall prediction researchers and companies continue to advance the field while preserving elderly privacy and autonomy. [ABSTRACT FROM AUTHOR]

Our study uses data from Holocene core samples and modern death assemblages to understand how human-induced environmental change in the northern Adriatic Sea (Italy) may have affected parasite-host dynamics in the economically important bivalve Chamelea gallina. Thirty-one radiocarbon dates confirm temporal distinctness between the periods before and after the onset of significant human influence and confirm that trematode prevalence has decreased by an order of magnitude over the past ∼2 k.y. The median number of parasite-induced pits per bivalve host and parasite aggregation has also decreased significantly, signaling a substantial decrease in the effective population size of digenean trematodes. Gaussian finite mixture modeling of pit size does not support the hypothesis of parasite extinction. Combined, these results indicate the (potentially ongoing) collapse of parasite-host interactions in C. gallina in concert with human influence on the Adriatic and its transition to an “urban sea.” [ABSTRACT FROM AUTHOR]

Traffic congestion has caused great concern among policymakers in large cities around the world. In contrast with constantly increasing transport supply, individual-based active travel demand management (ATDM) has been proposed as a more efficient policy alternative for combating congestion. However, how individuals make routing choices during commuting in response to ATDM incentives is still largely unknown, given the lack of individual travel data. Using a desensitized one-week travel trajectory data set involving 5641 personal electric vehicles, we examine the major influencing factors of commuting route stability during working days and make suggestions on targeting the most responsive commuters. We first filter family-used vehicles by clustering vehicle usage patterns through employing the Gaussian mixture model and interpret drivers' route choice behaviors during morning peak hours. To look for factors affecting route stability, we develop a generalized additive model and find that route stability is significantly associated with road network density of origins and destinations, departure time, travel duration, commuting distance, reliability of the expressway, and volatility of the congested sections by which the routes passed. The empirical results may contribute to the understanding of individual route choices, and help urban managers develop more refined ATDM policies to alleviate traffic congestion in the future. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a novel deep image coding and decoding model for GMMQI (Gaussian mixture model quartile intervals, GMMQI) and a variable rate bit allocation method to optimize the rate distortion performance and prioritize the transmissions of more significant information. First, to address the problem of bit streams leading to ambiguity during encoding and decoding, we convert the image into a potential tensor, each element of which uses a four-bit parameter dictionary to preserve the parameter bits. Then, the variable rate is calculated using quaternions based on the parameter dictionary, and a hybrid CLM &BAM (Channel latent map & Bit allocation map) approach is designed to assign bits to the potential tensor and encode it, which transforms the problem of finding the optimal encoder-decoder into finding the optimal hyper-parameters in the model and reduces the complexity of the GMMQI model. Finally, a GMMQI approach with variable rate bit allocation is developed in combination with CLM &BAM, to be able to prioritize the transmission of more significant information. The experimental results show that the GMMQI method reaches an advanced level compared to the traditional image compression standards BPG, JPEG2000, and JPEG, and is comparable to the most advanced level compared to the existing deep learning based compression methods. [ABSTRACT FROM AUTHOR]

Learning from multi-class imbalanced data has still received limited research attention. Most of the proposed methods focus on the global class imbalance ratio only. In contrast, experimental studies demonstrated that the imbalance ratio itself is not the main difficulty in the imbalanced learning. It is the combination of the imbalance ratio with other data difficulty factors, such as class overlapping or minority class decomposition into various subconcepts, that significantly affects the classification performance. This paper presents GMMSampling—a new resampling method that exploits information about data difficulty factors to clear class overlapping regions from majority class instances and to simultaneously oversample each subconcept of the minority class. The experimental evaluation demonstrated that the proposed method achieves better results in terms of G-mean, balanced accuracy, macro-AP, MCC and F-score than other related methods. [ABSTRACT FROM AUTHOR]

Non-destructive testing (NDT) techniques are crucial in making informed decisions about reconstructing or repairing building structures. The SonReb method, a combination of the rebound hammer (RH) and the ultrasonic pulse velocity (UPV) tests, is widely used for this purpose. To evaluate the compressive strength, C S , of the concrete under investigation, the ultrasonic pulse velocity V p and the rebound index R must be mapped to the compressive strength C S using a suitable conversion model, the identification of which requires supplementing the NDT measurements with destructive-type measurements (DT) on a relatively large number of concrete cores. An approach notably indicated in all cases where the minimization of the number of cores is essential is to employ a pre-existing conversion model, i.e., a model derived from previous studies conducted in the literature, which must be appropriately calibrated. In this paper, we investigate the performance of Gaussian process regression (GPR) in calibrating the pre-existing SonReb conversion models, exploiting their ability to handle nonlinearity and uncertainties. The numerical results obtained using experimental data collected from the literature show that GPR calibration is very effective, outperforming, in most cases, the standard multiplicative and additive techniques used to calibrate the SonReb models. [ABSTRACT FROM AUTHOR]

In hazard-sensitive processes, the monitoring upsets and malfunctions correctly is an important challenge to operation safely and enhance the performance. Conventional process monitoring frequently assumes that process data follow only one Gaussian distribution, which generates a constant confidence limit and hence produces a high number of false alarms. However, in fact, industrial processes usually include various operating modes. To ovoid this drawback, the suggested approach employs an adaptive confidence limit (ACL) when a substantial number of false alarms are created. The fundamental concept underlying this study is to extract internally several local linear sub-modes of the monitored variables. In typical operating circumstances, the Gaussian mixture model (GMM) is utilized to extract several local linear sub-modes, followed by fuzzy linearization using the Takagi-Sugeno model, thereafter a bank of Luenberger observers to construct the residual spaces. An abnormal event is detected when the squared prediction error (SPE) is too great or exceeds the adaptive threshold designed to prevent the false alarms. Furthermore, an enhanced contribution plots is effectively used to identify the defective variable. [ABSTRACT FROM AUTHOR]

The paper proposes a robust and efficient model designed for multi-label abdominal organ segmentation, featuring a substantially reduced number of parameters. The model focuses on the effectiveness of edge guidance in segmentation and leverages a 3D-Unet architecture with deep supervision, incorporating the robust deep thinking gate (DTG) architecture. Our DTG-incorporated model architecture excels in both efficiency and effectiveness, demonstrating notable enhancements in multi-label abdominal organ segmentation performance. A comprehensive evaluation of the model employed on two datasets of MRI scan of BTCV and FLARE 2022, comparing its performance against state-of-the-art counterparts. The outcomes revealed that the proposed model achieved the highest dice score in the esophagus (0.795), gallbladder (0.945), and pancreas (0.87) while maintaining a most significantly reduced parameter count (13.3 million parameters count). This achievement underscores the model's efficiency and its suitability for seamless integration into real-world applications, offering promising prospects for enhanced medical image analysis. [ABSTRACT FROM AUTHOR]

Background Subtraction (BgS) is a widely researched technique to develop online Change Detection algorithms for static video cameras. Many BgS methods have employed the unsupervised, adaptive approach of Gaussian Mixture Model (GMM) to produce decent backgrounds, but they lack proper consideration of scene semantics to produce better foregrounds. On the other hand, with considerable computational expenses, BgS with Deep Neural Networks (DNN) is able to produce accurate background and foreground segments. In our research, we blend both approaches for the best. First, we formulated a network called Convolutional Density Approximation (CDA) for direct density estimation of background models. Then, we propose a self-supervised training strategy for CDA to adaptively capture high-frequency color distributions for the corresponding backgrounds. Finally, we show that background models can indeed assist foreground extraction by an efficient Neural Motion Subtraction (NeMos) network. Our experiments verify competitive results in the balance between effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

AbstractAdvanced production systems, such as multi-step assembly processes, predominantly comprise repetitive operations. The repetitive manual or human-robot integrated production operations call for new real-time process management technologies as the increasing use of sensors and the development of system intelligence. Conventional process monitoring and management methods, which are often labor-intensive, fall short in providing immediate and actionable insights. To tackle this limitation, we develop an unsupervised embedding method to automatically delineate the process into different stages and predict real-time progress information. We propose a Contrastive Variational Autoencoder (CVAE) as a feature extractor to adeptly embed repetitive processes into a Gaussian Mixture Model (GMM). Based on the extracted features, we propose an adaptive change-point detection and an Iterative Dynamic Time Wrapping (IDTW) algorithm to identify and segment multiple standardized process stages automatically. Theoretically, we establish the asymptotic optimality of the detected change-points associated with the given precision of image and feature extractors, ensuring the high-quality process stage separation and labeling. The proposed method autonomously extracts essential features encapsulating progress information from a limited set of unlabelled process videos. Through four diverse case studies including an actual aircraft spoiler production, our method exhibits very promising performance. Specifically, it achieves an average of 98.14% accuracy in predicting production progress and 0.9202 area under the curve (AUC) in predicting progress deviation across three distinct production environments. The proposed process monitoring method in repetitive production systems has the potential to significantly improve productivity, promote standardization of repetitive operations, and predict production deviations. [ABSTRACT FROM AUTHOR]

Data scarcity in paleographic image datasets poses a significant challenge to researchers and scholars in the field. Unlike modern printed texts, historical manuscripts and documents are often scarce and fragile, making them difficult to digitize and create comprehensive datasets. Recently many innovations have been arrived on single image generative models for natural images but none of them are focused on paleographic character images and other handwritten datasets. In paleographic images like stone inscription characters, maintaining exact shape and structure of character is important unlike natural images. In this paper we propose an unconditional single image generative model, CharGAN for isolated paleographic character images. In the proposed system, augmented images are generated from a single image using generative adversarial networks, while maintaining their structure. Specifically, an external augmentation inducer is used to create higher-level augmentations in the generated images. In addition, the input to the generator is replaced with dynamic sampling from a Gaussian mixture model to make changes to the low-level features. From our experimental results, we infer that these two enhancements make single-image generative models suitable not only for natural images, but also for paleographic character images and other handwritten character datasets, the AHCD dataset, and EMNIST, where the global structure is important. Both the qualitative and quantitative results show that our approach is effective and superior in single-image generative tasks, particularly in isolated character image generation. [ABSTRACT FROM AUTHOR]