Statistical Optimization Research Articles

Adoption of a novel medium for the industrial (3000L) production of Serendipita indica employing a nutrient limitation strategy using insoluble carbon and phosphate sources.

The use of the endophytic fungus Serendipita indica has rapidly increased due to its wide range of host species, ability to foster plant-growth, and ability to confer tolerance to a number of stresses. However, its industrial-scale production is still in its infancy due to its low-biomass yield and prolonged cultivation time. Thus far, Hill-Kafer medium has traditionally been used for S. indica cultivation, resulting in lower yields and excessively long incubation times. Here, we adopted a simple insoluble carbon and phosphate input medium for rapidly generating high biomass. We developed and optimized the SIF1 medium, achieving maximum biomass production (424.5±1.9g/L), significantly outperforming Hill-Kafer medium. Statistical optimization of SIF1 identified optimal levels (15g/L oats, 7.5g/L tricalcium phosphate, 95-hour incubation). Validated results in the laboratory (FUS-10L: 484.4±4.7), pilot (300L: 496.5±7g/L) and industrial (3000L: 492.4±7.1g/L) bioreactors proved the efficacy of SIF1. Compared to Hill-Kafer (54.8±3.7g/L), SIF1 showed nine-fold higher biomass productivity and reduced cultivation time by approximately 6 days. Based on our findings, it appears that SF1 will be a highly efficient medium for producing S. indica on an industrial scale and expanding its use.

Statistical optimisation of operational parameters using response surface methodology and phytoremediation of arsenic in constructed wetland

ABSTRACT Phytoremediation using the robust perennial grass Pennisetum purpureum has been researched as a substitute for traditional treatment approaches for arsenic (As) pollution remediation in the Constructed wetland system. In the current investigation, As absorption and removal through P. purpureum were measured and optimisation was done using Response surface methodology (RSM). To maximise the absorption and removal of As, the Box-Behnken design (BBD) was applied, with 3 key factors (As concentration in treatment sand: 5, 22, and 39 mg kg−1; exposure period: 14, 28, and 42 days; aeration rate: 0, 1, and 2 L min−1) in the optimisation. The estimated optimum conditions were 39 mg kg−1 As concentration, 42 days of retention time, and 0.18 L min−1 aeration rate, with an actual biological As accumulation and removal were 5,088.19 mg kg−1 dry weight (DW) and 91.45%, respectively. These amounts were comparable to the amount predicted through RSM 5,245.94 mg As kg−1 DW and 94.29%, respectively. The variance between the test and expected results was 3.10%, demonstrating that RSM could estimate the optimum biological accumulation of As correctly with relatively minimum error. Factors, like As concentration, retention time, and aeration rate, could influence the performance of arsenic phytoremediation through P. purpureum.

Enhancing lithographic accuracy by mitigating overlay errors via mask-induced thermal and mechanical optimization.

As technology nodes continue to shrink, the demand for higher lithographic accuracy in integrated circuit fabrication intensifies. To address the limitations of traditional compensation methods, this study proposes a mask-induced thermal and mechanical optimization approach to mitigate overlay errors, thereby enhancing lithographic precision in emerging techniques such as nanoimprint lithography (NIL) and surface plasmon lithography (SPL). This approach integrates stress application schemes with localized thermal effects, resulting in a range of compensation strategies based on mask-induced thermal-mechanical coupling. Through mathematical modeling and moment balance assumptions, the technique leverages the linear superposition property for overlay error compensation and identifies 20 key compensation parameters through statistical analysis and optimization algorithms. Experimental validation demonstrates that the compensation effectiveness for completely random, linear, quadratic, and higher-order overlay errors reaches 89.18%, 93.05%, 64.75%, and 53.89%, respectively. In 24 rounds of random testing, the average compensation in the X and Y directions was 91.98%, showing strong stability and consistency. Furthermore, finite element method (FEM) simulations validate the model, revealing a residual overlay error compensation of less than 0.2 nm, with a calculation-to-validation discrepancy under 0.9%, confirming the model's accuracy. This technology provides a reliable solution for overlay error compensation in emerging lithographic techniques like lensless SPL and NIL and offers valuable insights for future research in extreme ultraviolet lithography (EUVL) and deep ultraviolet lithography (DUVL), with potential applications in integrated circuit lithography and further validation across various mask types and complex exposure areas.&#xD.

Statistical modeling and optimization of ultrasonic vibration assisted end grinding of alumina ceramics

Statistical modeling and optimization of ultrasonic vibration assisted end grinding of alumina ceramics

Advanced statistical optimization and performance evaluation of self‐compacting geopolymer concrete utilizing industrial by‐products

AbstractThis study optimizes self‐compacting geopolymer concrete (SCGC) by incorporating industrial by‐products, such as fly ash, ground‐granulated blast furnace slag, and rice husk ash (RHA), as sustainable alternatives to conventional binders. The SCGC mixtures were designed with varying binder compositions and activator solutions, and their fresh and hardened properties were systematically evaluated. Workability tests, including slump flow, J‐ring, and V‐funnel tests, were conducted to assess the flowability and stability, while compressive, tensile, and flexural strength tests were performed at 3, 7, and 28 days to evaluate the mechanical performance. Advanced statistical tools, including response surface methodology and analysis of variance, were employed to identify key influencing factors and develop predictive models. The results indicate that an optimal RHA replacement of 5%–10% combined with a silica‐rich activator solution significantly enhances the mechanical properties of SCGC, achieving a 28‐day compressive strength of 55.6 MPa while maintaining excellent workability. The statistical models demonstrated high accuracy in predicting performance trends, validating the experimental findings. This study provides a robust framework for optimizing SCGC mix designs and for advancing sustainable and high‐performance construction materials.

Statistical Optimization and Evaluation of the Adsorptive Efficiency of Base Modified Saccharum munja Biomass for Safranine O and Crystal Violet Dyes in Single and Binary Systems

Statistical Optimization and Evaluation of the Adsorptive Efficiency of Base Modified Saccharum munja Biomass for Safranine O and Crystal Violet Dyes in Single and Binary Systems

Characterization and optimization of azo dyes degrading microbes isolated from textile effluent

Azo dyes are highly recalcitrant, persistent, and toxic compounds, extensively used in the textile industry. The untreated discharge of dye effluents from the textile industry poses severe environmental and health risks. This research aimed to isolate and identify bacterial strains from textile wastewater that can decolorize azo dyes. After the subsequent screening of 89 isolates, 4 novel strains were identified utilizing the 16S rRNA gene sequencing technique that could effectively decolorize and degrade azo dyes, methyl red, direct yellow 12, and acid black 210. A thorough assessment of physicochemical parameters was conducted to optimize for maximum decolorization for all four strains. At pH 7, 37° C, and 50 mg/L dye concentration, the maximum decolorization for methyl red, direct yellow 12, and acid black 210 was 79.09% > 72.20% > 64.76%; 84.45% > 62.59% > 54.29%; 83.12% > 70.22% > 61.42%; and 92.71% > 83.02% > 69.84%, for isolate 1, isolate 2, isolate 3, and isolate 4, respectively. The novel strains belonged to the Sphingomonas, Pseudomonas, Shewanella, and Priestia species. The unique sequences of these bacterial strains have been submitted to the GenBank database under the accession numbers “OQ202071”, “PP708911”, “PP708909”, and “PP086977,” respectively. Further, an enzyme study and statistical optimization of Priestia flexa species was performed. A Central Composite Design and Response Surface Methodology has been applied for synergistic effects of process parameters namely pH (5–9), initial dye concentration (100–250 mg/L), and temperature (25°–45° C) on the decolorization of the model dyes. The regression analysis indicated a strong correlation between the experimental data and the second-order polynomial supported by a high coefficient of determination (R²). For all three dyes analyzed, the difference between the experimental and predicted values was found to be less than 10%. Fourier Transform Infrared spectroscopy was further employed to analyze and confirm the degradation of the three dyes.

Coagulation/flocculation for effective removal of green bromocresol using NP/Fe₃O₄: a statistical optimization approach for sustainable wastewater treatment

Coagulation/flocculation for effective removal of green bromocresol using NP/Fe₃O₄: a statistical optimization approach for sustainable wastewater treatment

Terconazole loaded edge-activated hybrid elastosome for revamped corneal permeation in ocular mycosis: In-vitro characterization, statistical optimization, microbiological assessment, and in-vivo evaluation.

Terconazole loaded edge-activated hybrid elastosome for revamped corneal permeation in ocular mycosis: In-vitro characterization, statistical optimization, microbiological assessment, and in-vivo evaluation.

Thermomechanical Dynamics and Statistical Optimization in Bone Drilling: A Systematic Review on Mitigating Thermal Necrosis Through Multiscale Modeling and Clinical Validation

Thermomechanical Dynamics and Statistical Optimization in Bone Drilling: A Systematic Review on Mitigating Thermal Necrosis Through Multiscale Modeling and Clinical Validation

Feature Reconstruction-guided Transductive Few-Shot Learning with Distribution Statistics Optimization

Feature Reconstruction-guided Transductive Few-Shot Learning with Distribution Statistics Optimization

A Novel Chaotic Image Encryption Algorithm based on Coordinate Descent and SHA-256

Since each encryption necessitates the transmission of the key, chaotic image encryption methods with key and plaintext association have emerged in recent years. These algorithms are essentially one-time pad at a time. Nevertheless, some current systems are unable to map the seed key to the chaotic system's initial value in a unique way, which reduces the encryption system's key space. Furthermore, some techniques defy the one-time pad strategy by encrypting the same image with the same key. These issues are resolved in this paper in two ways. On the one hand, SHA-256 is used to calculate a hash value after randomly inserting pixels into a plain image. Even if the same image is encrypted, several seed keys can be obtained. However, to achieve the one-to-one connection between the seed key and the encrypted key stream, the Sequential Expansion Algorithm (SEA) and Feedback Iterative Piece-Wise Linear Chaotic Mapping (FI-PWLCM) are suggested. Random and seed key sensitive sequences can be produced rapidly via SEA. FI-PWLCM uses feedback iteration with additional control settings to achieve one-to-one correspondence with the seed key. The mapping can generate more intricate chaotic sequences in addition to having the speed of PWLCM. Additionally, in order to strengthen cryptosystems' resistance to statistical attacks, this study suggests the Segmented Coordinate Descent (SCD) technique for histogram statistical optimization of images. The algorithm can withstand brute force attacks, statistical attacks, chosen-plaintext (chosen-ciphertext) attacks, and more, according to experiments and security research. It performs best in the statistical qualities of entropy and histogram when compared to the majority of existing algorithms

Salmon futures prices as forecasts

Futures markets serve two main purposes, risk transfer and price forecasting. Both are relevant in the case of Norwegian farmed Atlantic salmon, as the spot price is highly volatile and hard to predict. However, the salmon futures market suffers from low liquidity, thus limiting the effectiveness of risk transfer. What about price forecasting? We consider futures prices as point forecasts of the future spot price. We evaluate them by statistical optimality criteria and find a downward bias that increases with the forecast horizon at a rate of over 10% a year. Our analysis reveals no additional evidence of forecast suboptimality. The results should be of interest to decision makers who rely on salmon futures prices as point forecasts of the future spot price.

Analysis and Optimization of Residual Stresses in Hard Turning of AISI M2 Tool Steel Using Taguchi Technique

Introduction: Residual stresses play a critical role in the performance and durability of machined components, particularly in the hard turning of tool steels. Objective: The main objective of this investigation to optimize the residual stress during hard turning of AISI M2 tool steel. Material and Method: This study investigates the optimization of residual stresses in the turning of AISI M2 tool steel using the Taguchi method. An L27 orthogonal array was employed to analyze the effects of cutting speed, feed rate, and depth of cut on residual stress formation. X-ray diffraction (XRD) was used for stress measurement. Result: Analysis of variance (ANOVA) identified cutting speed as the most significant parameter, followed by feed rate and depth of cut. The residual stress is minimum at level optimal cutting conditions: 100 m/min cutting speed, 0.2 mm/rev feed rate, and 0.4 mm depth of cut. Conclusion: The optimal cutting conditions: 100 m/min cutting speed, 0.2 mm/rev feed rate, and 0.4 mm depth of cut resulted in the lowest residual stress of 230 (compressive) MPa. The cutting speed as the most significant parameter, followed by feed rate and depth of cut. The findings demonstrate the effectiveness of statistical optimization techniques in enhancing machining quality and surface integrity in industrial applications. Application: The application of this project will be in cutting tool industries where AISI M2 tool steel is used as raw material.

Optimization of the manufacturing process of a pediatric omeprazole enteric pellets suspension: Full Factorial Design

Objective The purpose of the present study was to apply the design of experiments (DoE) to develop an omeprazole enteric pellets suspension for use in the pediatric population. Methodology This experimental study employed a Full Factorial Design for drug development, encompassing three factors (Aerosil® R972, cetostearyl alcohol, and Span 80) at two levels (2% and 6% for factor A (Aerosil® R972) and 2% and 4% for factors B and C (cetostearyl alcohol and Span 80, respectively)). Results Following the statistical optimization, the suspension F10 was formulated and subjected to a stability study for one month. The dissolution test results were suboptimal, achieving only an 22% release. Subsequently, eight additional suspensions were devised using hydrophilic oily vehicles (Labraphac Hydrophile WL 1219, Labrafil M2125 CS, and Labrafil M 1944 CS) and excipients (Gelucire 44/14 and Aerosil® 200) to enhance the dissolution profile. Suspension F17 showed over 75% within 30 min, displaying superior sedimentation time when compared to all other formulations, along with effortless resuspension. Conclusion The findings suggest that the optimal vehicle for the administration of omeprazole enteric pellets in suspension is the formulation comprising Labrafil M 1944 CS, Span 80, and Aerosil® 200. This study has paved the way for an oily suspension vehicle, opening new avenues of research for developing pediatric omeprazole formulations that fulfill gastro-resistance requirements.

Statistical Optimization of Exopolysaccharide and Biomass Production by Mangrove Fungi Fusarium equiseti ANP2 and its Potential Application as Bioemulsifier and Chelator.

The rationale of the study is to explore the bio functional industrial potential and optimized culture conditions of a Manno glucan heteropolysaccharide MF-1 (purified EPS fraction) produced by a newly discovered mangrove derived fungi Fusarium equiseti ANP2, isolated from the Krishna River delta mangrove sediments. Response surface methodology (RSM) was employed to optimize fungal EPS and Biomass production, achieving a significant 1.4-fold increase to 6.94g/L in EPS yield and a 2.1-fold increase in biomass production. RSM identified optimal levels of glucose, NH₄NO₃, NaCl, leucine, temperature, and pH, while minimizing the required glucose and nitrogen content compared to conventional methods. Notably, MF-1 exhibited promising emulsification potential (69.5% n-hexadecane emulsification), suggesting its prospective role as a novel emulsifier, particularly for n-hexadecane-based applications. Additionally, MF-1 also displayed a chelating activity for Fe2⁺ ions, suggesting its applicability as a natural chelating agent. The current study optimized the EPS production using RSM design and explored its potential for industrial applications as emulsification and chelating properties of the purified EPS fraction. Future research could explore the structural modifications of the fungal EPS to enhance its functionalities and delve deeper into the mechanisms governing EPS and biomass for large-scale, sustainable industrial production.

Enhanced Reepithelization and Dermal Regeneration of a Novel Pongamia Oil Combination Based Chloramphenicol-Coloaded Curcumin Nanoemulsion Fortified with a Chitosan Hydrogel: Statistical Optimization, ex vivo and in vivo Studies

Enhanced Reepithelization and Dermal Regeneration of a Novel Pongamia Oil Combination Based Chloramphenicol-Coloaded Curcumin Nanoemulsion Fortified with a Chitosan Hydrogel: Statistical Optimization, ex vivo and in vivo Studies

Statistical optimization characterizations and Eco- friendly synthesis of silica from sugarcane bagasse

This research explores the synthesis and optimization of Silica have been effectively produced from sugarcane bagasse (SB) using the sol-gel methods. Due to its rich silica content, sugarcane bagasse can be utilized as a viable alternative source for silica synthesis. Employing Central Composite Design, the study systematically varied combustion temperature (500–800 °C), combustion time (2–4 h), and digestion time (1–3 h) to enhance silica yield. The optimal conditions identified were a combustion temperature of 583.48 °C, a combustion time of 3.482 h, and a digestion time of 2.283 h, resulting in a silica yield of 69.6%. Comprehensive characterization of the synthesized silica was conducted through Fourier Transform Infrared Spectroscopy (FTIR), X-ray Diffraction (XRD), Scanning Electron Microscopy (SEM), Brunauer, Emmett, Teller model (BET) analysis and Thermo-gravimetric Analysis (TGA). XRD results indicated the amorphous nature of the silica, with a broad peak at 22.36°, akin to that of commercial silica. FTIR analysis revealed six characteristic peaks at wavenumbers corresponding to those found in commercial silica, confirming the presence of similar chemical groups. SEM imagery illustrated a disordered arrangement of silica with undefined morphology. The TGA analysis shows high thermal resistivity of silica with only 9% weigh loss at 800 °C. Overall, this study demonstrates that high-quality silica can be produced from sugarcane bagasse with minimal chemical input and energy consumption and highlighting its potential for diverse applications.

Enhancing Hierarchical Classification in Tree-Based Models Using Level-Wise Entropy Adjustment

Hierarchical classification, which organizes items into structured categories and subcategories, has emerged as a powerful solution for handling large and complex datasets. However, traditional flat classification approaches often overlook the hierarchical dependencies between classes, leading to suboptimal predictions and limited interpretability. This paper addresses these challenges by proposing a novel integration of tree-based models with hierarchical-aware split criteria through adjusted entropy calculations. The proposed method calculates entropy at multiple hierarchical levels, ensuring that the model respects the taxonomic structure during training. This approach aligns statistical optimization with class semantic relationships, enabling more accurate and coherent predictions. Experiments conducted on real-world datasets structured according to the GS1 Global Product Classification (GPC) system demonstrate the effectiveness of our method. The proposed model was applied using tree-based ensemble methods combined with the newly developed hierarchy-aware metric Penalized Information Gain (PIG). PIG was implemented with level-wise entropy adjustments, assigning greater weight to higher hierarchical levels to maintain the taxonomic structure. The model was trained and evaluated on two real-world datasets based on the GS1 Global Product Classification (GPC) system. The final dataset included approximately 30,000 product descriptions spanning four hierarchical levels. An 80-20 train–test split was used, with model hyperparameters optimized through 5-fold cross-validation and Bayesian search. The experimental results showed a 12.7% improvement in classification accuracy at the lowest hierarchy level compared to traditional flat classification methods, with significant gains in datasets featuring highly imbalanced class distributions and deep hierarchies. The proposed approach also increased the F1 score by 12.6%. Despite these promising results, challenges remain in scaling the model for very large datasets and handling classes with limited training samples. Future research will focus on integrating neural networks with hierarchy-aware metrics, enhancing data augmentation to address class imbalance, and developing real-time classification systems for practical use in industries such as retail, logistics, and healthcare.

FORMULATION AND OPTIMIZATION OF FLOATING SUSTAINED RELEASE TABLETS OF ATAZANAVIR SULFATE THROUGH BOX-BEHNKEN DESIGN

Objective: Atazanavir (ATZ) sulfate is widely prescribed as an antiretroviral drug belonging to BCS class II with low solubility. This research aims to design, formulate, and optimization of floating sustained-release tablets of ATZ through Box-Behnken design (BBD). Method: The formulation parameters were optimized using the BBD. Methocel K100M (A) was chosen as the primary release-retarding polymer, Sodium Bicarbonate (B) served as the gas-generating agent, Ethyl Cellulose (C) was utilized as an additional release-retarding polymer, and Cetyl Alcohol as a floating assistant. In this design, A, B, and C were designated as independent variables, while three response variables floating lag time (FLT) (Y1), swelling index (Y2), and percentage drug release (Y3) were selected as the dependent variables. The compatibility of the drug and excipients was evaluated through Fourier-transform infrared (FTIR) spectroscopy, differential scanning calorimetry (DSC), and morphology by scanning electron microscopy. Tablets were prepared through the direct compression method and subsequently evaluated for parameters including FLT, flotation time, swelling index, hardness, drug content, friability, in vitro drug release, and drug release kinetics. Results: FTIR and DSC investigations revealed no interaction between the drug and the excipients, physical mixture of the drug and the excipients indicated the amorphous state of ATZ. All the evaluated tablets showed satisfactory results. The drug release from the validated optimized tablets was gradual and sustained over 12 h (99.76±0.75) following zero-order kinetics. Conclusion: The optimized tablets with desirable formulation characters were determined through a statistical optimization model and the optimized formulation remarkably sustained the drug release for up to 12 h, indicating its improved therapeutic potential for the treatment of HIV.