Journals
2025 EN
Elbatal Ibrahim · Araibi Mustafa Ibrahim Ahmed · Ocloo Selasi Kwaku
+3 more
ABSTRACT This article introduces a two‐parameter statistical model derived by applying an inverse transformation to the cumulative distribution function of the Pham distribution. The proposed model offers a flexible and tractable framework for modeling skewed and heavy‐tailed data, making it well‐suited for applications in reliability engineering, survival analysis, and related fields. We derive key statistical properties of the model, including the quantile function, moments, and the moment‐generating function. Furthermore, we assess the performance of fifteen different estimation methods through extensive simulations to identify the most efficient techniques for parameter estimation. The practical utility of the proposed model is demonstrated using real‐life datasets, where it outperforms several existing competing models. Also, Bayesian inference is implemented in the application section to provide a more comprehensive analysis. The results underscore the model's flexibility, robustness, and computational efficiency in real‐world settings.
Journals
2025 EN
Ibrahim Tamer K. · Ragab Ibrahim E. · Kwaku Ocloo Selasi
+1 more
ABSTRACT This paper introduces the Inverse Mustapha Type‐II Distribution ( IMU I I D }_{II}, a novel lifetime model derived through the inverse transformation of the Mustapha Type‐II distribution. Designed for modeling data on the positive real line, theIMU I I D }_{II} $$ offers enhanced flexibility in reliability and survival analysis, particularly where traditional models fall short. We derive key statistical properties of the distribution, including moments, mean residual life, mean inactivity time, and entropy measures. Parameter estimation is explored using multiple methods, with simulation studies demonstrating the robustness of the estimators. The practical applications of theIMU I I D }_{II} $$ are validated through applications to real‐world datasets, where it outperforms competing lifetime models in goodness‐of‐fit tests. Our results highlight theIMU I I D }_{II} $$ as a valuable tool for reliability analysis, survival studies, and related fields, providing a versatile alternative for practitioners.
Journals
2025 EN
Gemeay Ahmed M. · Araibi Mustafa Ibrahim Ahmed · Almetwally Ehab M.
+4 more
ABSTRACT This paper proposes a novel form of the unit new XLindley distribution, which is derived by incorporating the idea of inverse transformation of the cumulative distribution function. The derived distribution is defined on the positive real line( 0 , ∞ left(0, $$ and it exhibits a different range of shapes. We also discuss some important statistical properties of the proposed model, including moments, moment‐generating function, survival and hazard rate functions, quantiles, order statistics, etc., to present a comprehensive theoretical framework. In addition to these, fifteen different estimation methods are employed for conducting the parameter estimation for the new distribution. Besides, a simulation study is performed to evaluate their behaviors using some measures like bias, mean squared error, relative error, and absolute differences. Besides, the usefulness and utility of the newly proposed distribution are checked through real‐life applications via some practical datasets. This practical application is conducted by comparing the new distribution with some other existing counterparts in terms of the value of some model selection criterion.
Journals
2025 EN
AlDouri Asaad T. · Salman Safa salah · AlDoori Maksood Adil Mahmoud
+8 more
ABSTRACT Rosemary extract produced nanoscale magnesium oxide (MgO) using a green synthesis methodology, specifically a chemical co‐precipitation process. This work investigates the effects of nanoscale MgO on Swiss mice. Fourier transform infrared (FTIR) and scanning electron microscopy (SEM) are used to characterize the synthesized material. Nano‐MgO is administered orally to mice, and then the liver and kidney tissues are examined histologically to evaluate its biological effects. The results demonstrated the remarkable biological activity of nanoscale MgO, revealing a clear inhibitory effect on these organs. According to the findings, nanoscale MgO may be useful and suitable for biomedical applications, especially for targeted inhibition in kidney and liver tissues without causing serious toxicity risks.
Journals
2025 EN
Pourgholi Mehran · Gilarlue Mohsen Mohammadzadeh · Gannadi Mahin
ABSTRACT Operational Modal Analysis (OMA) has become a fundamental tool for identifying structural systems, particularly in scenarios where structures are excited solely by ambient vibrations. However, conventional OMA techniques are often sensitive to noise and require considerable expert intervention for mode selection and clustering. This study presents a semi‐automated OMA framework that integrates Stochastic Subspace Identification with Canonical Correlation Analysis (SSI‐CCA), a novel similarity filtering process, and Fuzzy C‐Means (FCM) clustering. The objective is to enhance robustness in noisy environments and significantly reduce manual intervention. The proposed framework introduces three key innovations: (i) Data‐space optimization through canonical correlation analysis of the Hankel matrix, followed by an energy‐and‐error analysis using the Energy Index (EI) and Figure of Merit (FOM) to determine its optimal size; (ii) Stable system extraction using a new similarity filtering approach that isolates physical modes by evaluating their consistency across increasing model orders, thereby replacing traditional hard/soft stabilization criteria; and (iii) Automated validation and modeling through complexity analysis of the mode shapes associated with stable poles, employing the Modal Complexity Factor (MCF) for physical plausibility, and structurally representative modeling via optimized fuzzy clustering of stable modal parameters. The method was validated on a six‐story reinforced concrete building. It successfully identified structural modes with frequency errors below 5% compared to a finite element model. Furthermore, it effectively filtered out non‐structural spurious modes, which were characterized by anomalous damping ratios (< 1%) and high modal complexity (> 30%). The results demonstrate that the proposed framework offers significant improvements in automation and reliability for structural system identification under operational conditions.
Journals
2025 EN
Mohammed Abdullahi Abula · Hamdani Hanene · Zakari Yahaya
+5 more
ABSTRACT This research centers on the creation of an innovative statistical model that extends the inverse exponential (IE) distribution by employing the Rayleigh‐exponentiated odd generalized (REOG) family of distributions, which is designated as the REOG‐IE distribution. Various structural characteristics of the REOG‐IE distribution have been derived, encompassing moments, skewness, kurtosis, and the behavior of the hazard function. The parameters of the proposed distribution were estimated through the maximum likelihood estimation (MLE) technique, and a simulation study was performed to assess the performance and consistency of the parameter estimates. The REOG‐IE distribution was utilized on several real‐world datasets, including the fatigue life of 6061‐T6 aluminium coupons, the remission time of bladder cancer patients, and the radiation susceptibility data of peppermint exposed to gamma and microwave radiation. These applications illustrate the model's versatility and robustness in managing various types of survival and reliability data. The performance of the REOG‐IE distribution was compared against several competing models. The findings indicate that the REOG‐IE distribution consistently surpassed all rival models, achieving the lowest values for AIC, BIC, HQIC, and CAIC across all datasets. Notably, its application to radiation exposure data demonstrated exceptional adaptability in modeling the impacts of gamma and microwave radiation on the susceptibility of peppermint to pest infestation, further underscoring its practical significance. These results validate the REOG‐IE distribution as a more flexible and dependable model for analyzing intricate data patterns in survival analysis, engineering, and biomedical research.
Journals
2025 EN
Ado Osi Abdulhameed · Metwally Diaa S. · Semary Hatem E.
+4 more
ABSTRACT The development of flexible probability distributions has become essential for accurately modelling real‐world data. In this study, we introduce a new three‐parameter lifetime model, the New Heavy‐Tailed Cosine‐Weibull (NHTCW) distribution, which extends the Cosine‐Weibull distribution using a heavy‐tailed framework. This extension enhances the model's capacity to capture skewness and tail behavior commonly observed in lifetime and survival data. We derive several statistical properties of the NHTCW distribution, including its ordinary and incomplete moments, quantile and generating functions, and order statistics. Maximum likelihood estimation (MLE) is used to estimate the model parameters, and a simulation study is conducted to evaluate the performance of the estimators in terms of accuracy and consistency. We propose a regression model based on the NHTCW distribution, making its first introduction in this context. The practical usefulness of the proposed distribution is demonstrated through three real‐data applications. Two data sets are related to COVID‐19 mortality rates in Italy and Canada, while the third is related to injury rate data. In all cases, the NHTCW model outperforms several existing distributions in terms of goodness‐of‐fit criteria, underscoring its flexibility and practical relevance.
Journals
2025 EN
Mamun Mohammad · Chowdhury Safiul Haque · Faruq Md. Omar
+4 more
ABSTRACT Maternal health is a significant global crisis that affects women every day, resulting in severe complications related to pregnancy or childbirth. As a response to this urgent need for effective risk management, we have developed an automated system for maternal health risk (MHR) prediction that utilizes machine learning (ML) and explainable artificial intelligence (XAI). Our research aims to enhance the accuracy and efficiency of risk assessment by employing rigorous preprocessing techniques on a dataset of 1014 samples. To achieve this goal, we employ 10 ensemble ML models and use diverse feature optimization methods such as principal component analysis (PCA), linear discriminant analysis (LDA), and recursive feature elimination (RFE). To clearly understand the decision‐making processes of the selected ensemble model, we employ XAI as Shapley additive explanations (SHAP) plots, local interpretable model‐agnostic explanation (LIME) plots, and individual conditional expectation (ICE) plots. Our evaluation includes various ML performance metrics and a variety of statistical measures, which demonstrate that the Bagging, in conjunction with PCA, emerges as the optimal model, achieving an impressive accuracy of 99.51%. This research uses 10‐fold cross‐validation throughout the whole analysis. By emphasizing proactive risk detection and personalized interventions, we aim to improve understanding of MHR and help women worldwide make informed decisions.
Journals
2025 EN
Gümrükçü Selin · Kaplan Ekrem · Arvas Melih Beşir
+4 more
Pincer‐type ligands are coated on the carbon felt (CF) surface in one step via the electrodeposition method, and their use as supercapacitor electrode materials is reported for the first time in this research study. Raman spectroscopy, X‐ray diffraction, scanning electron microscopy‐energy dispersive X‐ray analysis and mapping, and X‐ray photoelectron spectroscopy are used to characterize the bis(pyridyl) iminoisoindoline (BPI) derivates/CF electrodes. The galvanostatic charge–discharge study indicates that the calculated specific capacitance ( C s ) of the PdBPI/CF electrode is 271.2 F g −1 at 1.0 mA current. The symmetrical supercapacitor has a high capacitance retention of up to 80.6% after 10 000 cycles, showing extended cycle life and strong electrochemical stability. The highest energy and power density values obtained for the PdBPI/CF symmetric supercapacitor are calculated to be 25.9 Wh kg −1 and 981.8 W kg −1 , respectively.
Journals
2025 EN
Akter Mahmuda · Hossain Ibrahim · Howlader Maitree
+2 more
Energy consumption is a critical element in human evolution, and rapid advances in science and technology necessitate adequate energy. As human society evades, the advancement of energy storage components has become critical in addressing societal challenges. Lithium‐ion batteries (LIBs) are promising candidates for future extensive use as optimal energy storage devices. However, the current limitations of LIBs pose a challenge to their continued dominance. Researchers are constantly exploring new materials to enhance the performance of LIBs, and carbon fiber (CF) is a dominant contender in this pursuit. The high electrical conductivity of carbon‐based materials benefits the battery system by facilitating efficient electron transfer and improving overall performance. CF‐based materials provide enhanced energy storage capacity and cycling stability in LIBs. Progress in carbon‐based materials has resulted in electrodes with increased surface areas, enabling greater rates of charging and discharging. In addition, the exceptional corrosion resistance of CF ensures the durability and robustness of LIBs. A comprehensive review is carried out on the correlation between the material's structure and its electrochemical performance, with a special emphasis on the uses of pure carbon fibers, transition metal oxides, sulfides, and MXene carbon‐based transition metal compounds in LIBs.