Exploring age-related changes in bone and muscle: Insights from radiomics and MRI.

A new distribution-free Phase II Shewhart max-type control chart is proposed for joint monitoring of process location and scale parameters. The method combines the Van der Waerden (VW) test for location and the Mood test for scale, ensuring robustness across diverse distributions. A regression-based approximation is developed to determine control limits without extensive simulations. Monte Carlo studies evaluate the average run length (ARL) performance and compare the proposed chart with existing Shewhart-type charts, including the Shewhart max-type chart based on the Wilcoxon rank-sum (WRS) and Ansari-Bradley (AB) tests, the Shewhart-Lepage chart, the Shewhart-Cucconi chart, and the Shewhart-Lepage-type chart based on VW and Mood tests. Results show superior or competitive detection of location, scale and joint shifts across normal, lognormal, Laplace and logistic distributions, with robustness under asymmetric and heavy-tailed settings. A real data application demonstrates its effectiveness.

ABSTRACT This paper proposes a novel statistical process control methodology by developing Combined Shewhart-EWMA (CSEWMA) control charts designed for high-dimensional two-sample data. These charts are highly proficient in identifying process variations, meeting the increasing demand for advanced SPC techniques in complex industrial contexts. The suggested methodology includes three unique control charts, DRCSEWMA, BSCSEWMA and SDCSEWMA, which are based on the Dempster (DR), Bai and Saranadasa (BS) and Srivastava–Du (SD) statistics, respectively. These charts are optimized to detect small to moderate process shifts and are evaluated using metrics such as the average and standard deviation of the run length and extra quadratic loss. The effectiveness of the proposed charts is benchmarked against each other and against conventional Shewhart and EWMA-based approaches in high-dimensional scenarios, including multivariate normal, t , and gamma data structures. Practical applicability is demonstrated using wind turbine bearing and daily stock price fluctuation datasets, where real-time responses from high-dimensional data are essential. The DRCSEWMA, BSCSEWMA and SDCSEWMA control charts exhibit exceptional sensitivity and efficient monitoring solutions. By enabling the early detection of process shifts, these charts enhance safety, operational efficiency and decision-making accuracy in environmental engineering processes, highlighting their potential for broader applications in high-dimensional environments.

Quality control is essential for ensuring manufacturing processes consistently meet predefined specifications and for minimizing the risks caused by process deviations. The MEWMA control chart is widely used for detecting small shifts in multivariate processes which does not require strict multivariate normality but the performance can be compromised when data contain outliers or high multicollinearity that commonly found in plastic waste processing. This study proposes a robust monitoring approach by integrating PCA to address multicollinearity, Bayesian estimation to improve parameter robustness. The four charts examined in this study are PCA-Bayesian MEWMA (SELF), PCA-Bayesian MEWMA (MSELF), PCA-Bayesian MEWMA (KLF), and PCA-MEWMA using Bootstrap control limit as comparison. These charts are evaluated across 324 simulated scenarios, varying in collinearity levels (0.2, 0.6, 0.95), sample sizes (10, 20, 30), outlier proportions (5%, 10%, 15%), and smoothing parameters (λ = 0.2, 0.5, 0.8). Performance is measured using Average Run Length (ARL), Standard Deviation of Run Length (SDRL), Median Run Length (MRL), and False Alarm Rate (FAR). Results indicate that the PCA-Bayesian MEWMA outperformed PCA-MEWMA using Bootstrap control limit. PCA-Bayesian MEWMA (SELF) excelled under clean data condition, whereas PCA-Bayesian (MSELF) provided stable detection under high correlation, moderate-to-high outlier contamination, and larger smoothing parameters, achieving an average ARL of 3.44, an SDRL of 0.58, an MRL of 3.46, and FAR of 0.03, making it well-suited for monitoring complex industrial plastic waste processes and demonstrating its effectiveness for robust quality monitoring in production.

ABSTRACT The Hotelling’s T 2 chart, which tracks the process mean vector, is a commonly used tool for tracking and managing multivariate processes. Nonetheless, the T 2 control chart is (i) ineffectual for monitoring processes with a restricted number of preliminary subgroups m relative to a greater number of variables p , and (ii) incalculable when p ≥ m due to the singularity of the sample covariance matrix. To address these computational challenges, this work proposes a modification of the classical Hotelling’s T 2 control statistic using a new Stein-type shrinkage estimator of the covariance matrix. The proposed approach shrinks the eigenvalues of the sample covariance matrix, producing a well-conditioned and invertible estimate suitable for high-dimensional settings. This enables effective monitoring of the mean vector in multivariate processes using individual observations for p ≥ m settings. The stability of the estimator is enhanced through an adjustment parameter based on perturbation theory. The methodology incorporates two different target structures and uses an iterative procedure to optimize shrinkage intensity. We evaluate the Phase II performance of the proposed control chart using out-of-control average run length measurements. Simulation results demonstrate that this modified T 2 control chart effectively detects process shifts in the p ≥ m paradigm.

Correlated data frequently result in misleading process control conclusions; thus, selecting effective control charts is crucial nowadays. The present work presents a mathematical approach to calculate the average run length (ARL) of an adaptive MEWMA (AMEWMA) control chart for the seasonal autoregressive model (SAR(P)L) aimed at identifying autocorrelated process variations in the zero state. The methodology for developing new one-sided and two-sided MEWMA control charts is delineated, and the ARL values derived from the explicit formulas are juxtaposed with the outcomes of four NIE approaches. Furthermore, the accuracy is analyzed by evaluating the standard deviation of run length (SDRL) and mean run length (MRL). At the same time, the control charts’ overall efficacy across all variation levels is assessed using EARL, ESDRL, and EMRL metrics. The findings demonstrated that the AMEWMA control charts surpass the MEWMA and EWMA control charts while c2 is decreasing. The ARL formula is also employed for seasonal statistics, namely the crude palm oil production index and refined palm oil shipment index.

Modern and evolving technologies have revolutionized the fields of inspection and quality control. In high-quality production processes where events occur infrequently, it is essential to effectively monitor the time between events (TBEs). This paper introduces a new cumulative sum (CUSUM) monitoring scheme designed for discrete TBE data modeled using the Poisson distribution. The study extends the Gumbel bivariate exponential (GBE) model to a Gumbel bivariate Poisson (GBPO) model. The run length characteristics of the proposed MCUSUM (GBPO) chart are evaluated through Monte Carlo simulations and compared with existing control charts. Results indicate that the proposed chart outperforms current alternatives. Both real and simulated datasets are used to demonstrate the implementation and performance of the proposed method. Additionally, a brief comparison is provided between the proposed chart and those based on other members of the Archimedean copula family.

PurposeThis study aimed to construct a risk prediction model based on radiomics, circulating tumor cells (CTCs), and dual-center clinical data to predict the invasiveness of lung adenocarcinoma, specifically for discriminating between minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC). The clinical value of this model in the precise diagnosis of early-stage lung adenocarcinoma was investigated to provide a reference for formulating reasonable treatment plans.Patients and MethodsClinical data, imaging data, CTCs, and pathological information from 202 patients with lung adenocarcinoma were retrospectively collected and analyzed from two medical centers between May 2022 and July 2023. The 146 cases from medical center 1 were randomly divided into a development set and an internal test set at a 3:2 ratio. The 56 cases from medical center 2 served as an external validation set. Machine learning was employed to analyze preoperative CTC counts and CT radiomic features. A feature selection method based on LASSO regression (with λ determined by the minimum criterion) was used to screen out 12 radiomic features. These features were subsequently incorporated into logistic regression to construct three prediction models: (1) a radiomics model based on radiomic features; (2) a CTCs-clinical data model based on the total development set; and (3) a composite clinical data-radiomics-CTCs model integrating the former two. The optimal model was selected to construct a nomogram. Its goodness-of-fit was assessed using a calibration curve (Hosmer-Lemeshow goodness-of-fit test), and its predictive performance was validated in the external validation set.ResultsA total of 107 radiomic features were extracted and categorized into 7 groups: 18 (16.8%) first-order features, 24 (22.4%) gray-level co-occurrence matrix (GLCM) features, 14 (13.1%) gray-level dependence matrix (GLDM) features, 16 (15.0%) each for gray-level run length matrix (GLRLM) and gray-level size zone matrix (GLSZM) features, 5 (4.7%) neighboring gray-tone difference matrix (NGTDM) features, and the remaining (13.1%) were shape-based features. In the total development set, significant differences were observed in clinical-imaging semantic features including CEA, CK19, CTC count, and lesion diameter, which were used to construct the clinical model. The area under the curve (AUC) for the radiomics model was 0.896 95% CI:0.832–0.960. The CTCs-clinical model demonstrated superior performance AUC:0.960, 95% CI:0.926–0.994. The composite clinical-radiomics-CTCs model showed the highest predictive accuracy AUC:0.980, 95% CI:0.960–1.000. According to decision curve analysis and the Akaike information criterion, the composite clinical-radiomics-CTCs model outperformed any single clinical or radiomic feature in terms of clinical predictive capability.ConclusionFor assessing the invasiveness of early-stage lung adenocarcinoma, the radiomics approach can effectively discriminate between MIA and IAC. However, compared to single-modality methods, the composite clinical-radiomics-CTCs model offers a novel auxiliary diagnostic method for evaluating the risk of invasiveness in early-stage lung cancer.

The zero-inflated Conway-Maxwell Poisson (ZICOMP) distribution models count data with many zero observations. This distribution assumes that zero observations occur with probability $$\:p$$, and the count of nonconformities in a product unit follows the Conway-Maxwell Poisson (COMP) distribution with parameters $$\:\mu\:$$ and $$\:\gamma\:$$. The ZICOMP distribution is flexible in accommodating various dispersion patterns in zero-inflated (ZI) datasets and effectively models over-dispersed, under-dispersed, or equi-dispersed data. This study provides an in-depth analysis of the ZICOMP-Shewhart control chart, as discussed by Alevizakos and Tasias1, to assess its effectiveness in detecting shifts in the rate parameter ($$\:\mu\:$$) while assuming constant dispersion and zero-inflation parameters. The key focus of this research is the selection of the limit coefficient to achieve the desired in-control (IC) average run length and assessing Type II error sensitivity for improved out-of-control (OOC) detection. Through extensive simulations, we examine the comparative efficiency of the ZICOMP-Shewhart chart against the traditional Shewhart chart under the COMP distribution. Additionally, the effectiveness of the ZICOMP-Shewhart control chart is demonstrated through a real-life example.

Abstract Joint optimization of production, quality control and maintenance offers substantial potential for cost savings and improvements in operational efficiency in manufacturing systems. However, existing integrated models are predominantly tailored to discrete piece-part manufacturing and suffer from three key limitations: they assume only a single assignable cause, rely on static quality control schemes that are insensitive to moderate-to-small process shifts, and employ design frameworks ill-suited for continuous flow manufacturing—where sampling is constrained by laboratory logistics rather than discrete production units. To address these gaps, this study develops an integrated model for continuous flow processes with multiple assignable causes, jointly optimizing production run length, a variable sampling interval X ̅ chart and condition-based maintenance. A developed genetic algorithm is utilized to minimize the expected total cost (including quality loss, inspection, maintenance, setup, and inventory holding costs) per production cycle while satisfying statistical quality constraints. Comparative analyses demonstrate that the proposed model achieves average cost savings of 6.08% compared to conventional static control charts and 10.82% compared to models assuming only a single assignable cause, under identical baseline parameter settings. Finally, Taguchi’s design of experiments is applied to explore parameter sensitivity, revealing that the in-control quality loss cost and variable inspection cost have significant effects on the total cost, while pairwise interactions between preventive maintenance cost, false alarm cost, and fixed inspection cost also exert non-negligible effects.

Effects of reaction temperature on fines deposition during hydrotreating of bitumen-derived light gas oil

This study introduces an enhanced Bayesian c-chart framework by incorporating two novel loss functions: the modified squared error loss function and the K loss function to improve the sensitivity and robustness of process monitoring for attribute data. Unlike traditional control charts that rely on fixed assumptions and static thresholds, the proposed Bayesian approaches dynamically update the control limits by integrating prior information with probabilistic loss structures. The study conducts a comprehensive simulation analysis under various process shift magnitudes and inspection unit sizes and evaluates performance using key indicators, including Average Run Length (ARL), Standard Deviation of Run Length (SDRL), Average Expected Quadratic Loss (AEQL), and the Performance Comparison Index (PCI). The results show that the proposed methods significantly outperform both classical and standard Bayesian c-charts, particularly in detecting small and moderate shifts. Furthermore, applying the proposed control charts to real-world industrial data—specifically defect monitoring in aircraft manufacturing—confirms their practical utility and adaptability. This work contributes a novel perspective to statistical process control (SPC) by integrating flexible Bayesian modeling with customized loss functions and offers a powerful alternative for quality assurance in high-stakes production environments.

This study proposes an explicit analytical formulation for calculating the Average Run Length (ARL) of a modified Exponentially Weighted Moving Average (MEWMA) control chart applied to an Autoregressive Integrated Moving Average of order (1,1,1) time series model with exponential white noise. The developed explicit formula provides a closed-form solution that enables efficient computation and theoretical insight into the control chart’s performance. The derived ARL values are validated against those obtained using the Numerical Integral Equation (NIE) method, ensuring accuracy and reliability. The comparative analysis shows that the explicit formula yields results that closely match those from the NIE method, with negligible absolute percentage differences while significantly reducing computational time. Simulation studies across various parameter settings and real-world applications, including climate and commodity price datasets, further confirm the consistency and practical utility of the proposed approach.

This study is intended to propose a formula for the Average Run Length (ARL) of the Exponentially Weighted Moving Average (EWMA) control chart when the observed data follow an autoregressive model of order p with quadratic trend. This research emphasizes the fundamental importance of developing precise ARL computation techniques with optimal processing efficiency, as ARL remains the predominant criterion for control chart performance evaluation. The derivation of the explicit ARL formula employs Fredholm’s integral equation methodology, with solution uniqueness assured through the application of Banach’s Fixed Point Theorem. Performance validation involves comparative analysis against approximate ARL values obtained via Numerical Integral Equation (NIE) approaches, specifically utilizing the Midpoint rule technique. The efficiency of the explicit formula of ARL is evaluated using two criteria: absolute percentage difference and CPU Time. The empirical results confirm that the ARL values derived from the explicit formula closely approximate those obtained via numerical integral equation methods, exhibiting an absolute percentage difference of less than 0.001%. Computationally, the proposed explicit formula achieves processing times of approximately 0.001 seconds, while the Midpoint rule method takes 2-3 seconds. In conclusion, the results demonstrate that the proposed explicit ARL formulas for EWMA charts provide accuracy comparable to the NIE method while significantly reducing computational time. This confirms the efficiency and practice applicability to the explicit formulas for monitoring real-world data, such as pneumonia cases at Siriraj Hospital.

This paper proposes three distribution-free homogeneously weighted moving average (HWMA) charts for joint monitoring of process location and scale parameters. The first chart is based on the Cucconi statistic, the second combines the van der Waerden (VW) and Ansari-Bradley (AB) tests, and the third combines the VW and Mood tests. Each chart can be implemented using either time-varying or steady-state control limits; however, they exhibit superior statistical performance with steady-state limits. Therefore, their statistical designs are developed with steady-state control limits. The out-of-control performances of the proposed charts as well as their competitor in the existing literature are compared numerically using average run length (ARL) metric across four process distributions: normal, lognormal, Laplace, and logistic (using both time-varying and steady-state control limits). The numerical results demonstrate that the overall performance of the chart based on the VW and Mood tests is significantly better than the other charts, across all considered distributions. Finally, the practical applicability of the proposed charts is illustrated using real-world data.

Electroencephalography (EEG) data comes with a large size due to the data's high sampling rate. Therefore, compressing EEG data is very important for storing the EEG files efficiently with less space and bandwidth capacity requirement. This research develops an efficient system for EEG data compression. The recorded EEG data are preprocessed and scaled using certain Resolution Factor and truncated to integer numbers, then the scaled EEG samples are classified into small and large vectors using a proposed adaptive thresholding which is based on using three computed factors: Standard deviation, Average of samples (Mean), and the multiplier factor (α). Then, each sample is passed through one of three procedures, then saved into the output file using multi-shift coding algorithm The best values are chosen as the tradeoff between the compression ratio and the processing time. The results indicated that the value of α parameter is significantly affects the threshold calculation, where the best-proven value for α is 1.30; the system achieves a compression gain of 65% while managing a reasonable processing time of 4.007 Second. The resolution factor affected the Mean Squared Error (MSE) and Mean Absolute Error (MEA) significantly, but it had a slight effect on the Compression Ratio (Cr). The α parameter has a great effect on Cr and a slight on MSE. The findings show a consistent trend whereby, as the resolution factor gradually decreases from 2 to 0.1, a concurrent decrease is observed in the MAE, MSE, Bitrate, Cr, and the overall processing time.

Effective process monitoring is essential in engineering and industrial systems to ensure product reliability and prevent costly failures of critical components. In such contexts, censoring techniques and control charts are indispensable tools for detecting deviations from desired operational standards. This study offers a new methodology to develop a novel Cumulative Sum (CUSUM) control chArt for monitoRing the Progressive Type-II (PT-II) CensOred data’s meaN from Burr-X dIstribution (MARCONI will be used hereafter for this monitoring frameworks). Named in honor of Guglielmo Marconi for his groundbreaking work in signal detection, the MARCONI control chart extends similar concepts to the domain of statistical process control. Unlike classical CUSUM or Shewhart charts, which assume simple distributional forms and cannot be directly applied under censoring without bias, MARCONI integrates three innovations: (i) censoring-adjusted mean statistics, (ii) distribution-specific formulations leveraging the Burr-X model, and (iii) adaptive, two-phase control limits that preserve nominal in-control performance under censoring. Through comprehensive simulation studies, we evaluate MARCONI’s performance in detecting small to moderate process shifts, achieving significantly lower average run lengths (ARLs) under varying censoring conditions. Performance metrics including ARL, standard deviation of run length (SDRL), and detection probability are analyzed across various shift magnitudes and censoring levels. The chart’s effectiveness is validated through application to stress-rupture life data of Kevlar 49/epoxy strands, demonstrating its superior performance, via lower out-of-control (OOC) ARLs compared to a Shewhart-type chart. To the best of our knowledge, this is the first SPC framework that unifies PT-II censoring, heavy-tailed Burr-X modeling, and CUSUM principles into a single tool, offering engineers a statistically rigorous and practically relevant solution for monitoring reliability in high-risk environments.

Monitoring systems are essential tools in various scientific fields for identifying changes in lifetime or survival-related phenomena. Statistical monitoring, especially control charts for censored data, is essential in oncology to track remission times and detect disease progression, particularly when patients are lost to follow-up. Therefore, this study presents a novel Adaptive Monitoring framework (control chart) for the Alpha Power Weibull distribution'z (APWD) quantile based on prOgressive type-II (PT-II) ceNsored data, (AMAZON will be used hereafter). AMAZON leverages the Quantile Function (QF) of APWD and an adaptive exponentially weighted moving average (AEWMA) chart, tailored for Bladder Cancer (BC) Care. Maximum likelihood estimators (MLE) for APWD under PT-II censoring form the backbone of AMAZON. A comprehensive simulation study assesses the performance using average run length. Besides an application to BC remission times confirms its ability to detect OOC signals. A rigorous comparative analysis with Weibull-based V-chart and EEP-based np-chart demonstrate that AMAZON significantly outperforms both benchmarks in sensitivity and stability. Application to real BC remission times confirms that AMAZON maintains perfect IC stability and triggers an immediate OOC signal at the first shifted sample, while V-chart suffers from false alarms and EEP based-chart fails to detect the shift entirely. Figure presents the graphical abstract of the proposed methodology. The AMAZON Framework: An Adaptive Quantile Monitoring Scheme for Alpha Power Weibull Data under Progressive Censoring. Highlights A novel AMAZON (Adaptive Monitoring) scheme is introduced for the Quantile Function of the Alpha Power Weibull Distribution. The scheme effectively monitors lifetime data subject to Progressive Type-II (PT-II) Censoring, crucial for clinical trials. Adaptive EWMA charting provides superior sensitivity to both small and large process shifts ( ϖ Q ). Application to Bladder Cancer remission times shows AMAZON significantly outperforms Weibull V-chart and EEP-based np-chart.

Background/Objectives: Acute heart failure (AHF) is a common critical condition in emergency departments, and traditional diagnostic methods have limitations, including high subjectivity and limited accuracy. This study aimed to develop an integrated machine learning model based on lung ultrasound (LUS) radiomics and clinical data for diagnosing AHF in patients presenting with acute dyspnea. Methods: A total of 301 patients were included and randomly split into training (n = 210) and testing (n = 91) sets. Using PyRadiomics 3.0, 107 radiomics features were extracted from standardized 6-zone LUS images, combined with 52 clinical features. Three random forest models were developed: clinical-only, radiomics-only, and integrated models. Results: The integrated model achieved optimal performance on the testing set with an AUC of 0.976 (95% CI: 0.950-0.994), accuracy of 90.1%, sensitivity of 91.1%, and specificity of 89.1%, significantly outperforming the radiomics model (AUC 0.940, p = 0.046) and clinical model (AUC 0.931, p = 0.111). Feature importance analysis revealed that radiomics features contributed 75.6% of the model's predictive power, with gray level run length matrix (GLRLM) features dominating the top-ranked features. Conclusions: As a proof-of-concept study, this research demonstrates the potential value of multimodal data fusion strategies for AHF diagnosis in the emergency department; however, external validation and prospective studies are required to further confirm its clinical applicability.

Hash tables are fundamental to computational genomics, where keys are often k -mers-fixed-length substrings that exhibit a "streaming" property: consecutive k -mers share k-1 nucleotides and are processed in order. Existing static data structures exploit this locality but cannot support dynamic updates, while state-of-the-art concurrent hash tables support dynamic operations but ignore k -mer locality. We introduce k ache-hash , the first dynamic, concurrent, and resizable hash table that exploits k -mer locality. k ache-hash builds on Iceberg hashing-a multi-level design achieving stability and low associativity-but replaces generic hashing with minimizer-based hashing, ensuring that consecutive k -mers map to the same buckets. This keeps frequently accessed buckets cache-resident during streaming operations. On the human genome, k ache-hash achieves 1.58-2.62× higher insertion throughput than IcebergHT and up to 6.1× higher query throughput, while incurring 7.39× fewer cache misses. k ache-hash scales near-linearly to 16 threads and supports dynamic resizing without sacrificing locality. Our theoretical analysis proves that streaming k -mer operations achieve 𝒪(1/r) amortized cache misses per operation, where r is the minimizer run length, explaining the substantial performance gains over general-purpose hash tables. k ache-hash is implemented in C++20 and is available at https://github.com/jamshed/kache-hash . p.pandey@northeastern.edu. Supplementary material are available for this manuscript.