Enhancing concrete strength for sustainability using a machine learning approach to improve mechanical performance by Amir Khan, Aneel Manan, Muhammad Umar, Mudassir Mehmood, Kennedy C. Onyelowe, Krishna Prakash Arunachalam

“…Three ML models Extreme Gradient Boosting (XGBoost), Decision Tree, and K-Nearest Neighbors (KNN) were developed and evaluated using metrics such as R2, RMSE, MAE, and MAPE. …”
Get full text

Response surface methodological approach for optimizing the enzyme activity and enzymatically mediated bioprecipitation of heavy metals by alkaline phosphatase by Virendra Vaishnav, Tanushree Chatterjee, Manisha Agrawal

“…Statistical analysis of variance (ANOVA) was performed to classify the competence of the developed model and revealed a good understanding between the experimental data and the proposed model. …”
Get full text

Moringa oleifera seed oils: Physico-chemical characterization and its authentication using FTIR spectroscopy and chemometrics by Irnawati, Abdul Rohman, Yamin, Nurrulhidayah Ahmad Fadzillah, Aida Azrina Azmi, Nurlatifah, Anjar Windarsih, Ratna Asmah Susidarti, Ruslin

“…The chemometrics of partial least square-discriminant analysis (PLS-DA) could classify of MOSO using fatty acid compositions as variable into two distinct groups using two discriminant components in which the first and second components could describe 62.5 % and 18.7 %, respectively. …”
Get full text

Community knowledge, perceptions and practices around COVID-19 in Sierra Leone: a nationwide, cross-sectional survey by Maike Winters, Helena Nordenstedt, Mohammad B Jalloh, Paul Sengeh, Nance Webber, Ibrahim Ngobeh, Thomas Samba, Harold Thomas

“…Objectives To assess the public’s knowledge, attitudes and practices about the novel coronavirus in Sierra Leone to inform an evidence-based communication strategy around COVID-19.Design Nationwide, cross-sectional Knowledge, Attitudes and Practices survey.Setting 56 randomly selected communities in all 14 districts in Sierra Leone.Participants 1253 adults aged 18 years and older of which 52% were men.Main outcome measures We calculated proportions of core indicators (awareness, knowledge, risk perception, practices). A composite variable for knowledge (based on seven variables) was created, and categorised into low (0–2 correct), medium (3–4) and high (5–7). …”
Get full text

Advancements in natural remediation management techniques for oil spills: Challenges, innovations, and future directions by Komal Sharma, Garishma Shah, Hanwant Singh, Upma Bhatt, Khushbu Singhal, Vineet Soni

“…These challenges include the variability in oil composition, environmental conditions, and the availability of suitable microorganisms or plants for degradation. …”
Get full text

Integrating human services and criminal justice data with claims data to predict risk of opioid overdose among Medicaid beneficiaries: A machine-learning approach. by Wei-Hsuan Lo-Ciganic, Julie M Donohue, Eric G Hulsey, Susan Barnes, Yuan Li, Courtney C Kuza, Qingnan Yang, Jeanine Buchanich, James L Huang, Christina Mair, Debbie L Wilson, Walid F Gellad

“…Nine of the top 30 most important predictors in the integrated model were human services and criminal justice variables. …”
Get full text

Isokinetic assessment of muscle function according to physical activity level and cardiovascular risk in asymptomatic adults aged 20 to 80 years by V.Z. Dourado, M.B. Nascimento, R.C. Navarro, R.P. da Silva, B.B. Gonze, K.M. Guedes, V.T. Lauria, W.O. Vieira, T.L.V.D.P. Ostolin

“…Percentiles of normality for muscle function were described by sex and age (20-39, 40-59, and >60 years). The models accounted for 49.6-70.9% of the total variability of muscle function, but MVPA and cardiovascular risk slightly influenced the coefficient of determination (additional ΔR2=0.003-0.006). …”
Get full text

Investigating the Lid Effect on the Generation of Ocean Island Basalts: 1. Geochemical Trends by Shihao Jiang, Rhys Hawkins, Mark J. Hoggard, D. Rhodri Davies, Ian H. Campbell

“…Here, we quantitatively investigate this relationship using a global data set of Neogene and younger OIB compositions. Local lithospheric thicknesses are estimated using theoretical plate‐cooling models and Bayes factors are applied to identify trends. …”
Get full text

Long-term evaluation of the impact of urbanization on native and non-native fish assemblages by Shubha N. Pandit, Mark S. Poesch, Jurek Kolasa, Laxmi Koirala Pandit, Jonathan L. W. Ruppert, Eva C. Enders

“…We used general linear models and the nestedness analysis to characterize matrices of species distributions of native and non-native fish assemblages among the catchments over time. …”
Get full text

Effectiveness of biofilm-targeted therapy in managing and preventing dental caries: protocol for a systematic review and meta-analysis by Venkata Suresh Venkataiah, Mohmed Isaqali Karobari

“…Discussion This review anticipates providing evidence on the efficacy of BTT in reducing bacterial load, altering biofilm composition, and preventing caries progression. Variability in study design and outcome measures is expected, underscoring the need for standardized methodologies and more robust clinical trials. …”
Get full text

Dietary Niche Variation in an Invasive Omnivore: The Effects of Habitat on Feral Pig Resource Use in Hawai‘i by Michael S. Peyton, Kealohanuiopuna M. Kinney, Sarah Knox, Grace Tredennick, Sara Hotchkiss

“…We investigated the feral pig trophic niche on Hawai‘i Island using stable isotopes (13C and 15N) and Bayesian mixing models to identify drivers of variation in resource use. …”
Get full text

Spatial and Temporal Pervasiveness of Indigenous Settlement in Oak Landscapes of Southern New England, US, During the Late Holocene by Stephen J. Tulowiecki, Brice B. Hanberry, Marc D. Abrams

“…Results suggested that fire-tolerant vegetation, mainly oak (<i>Quercus</i> spp.), was more abundant near Indigenous settlements from 4955 to 205 YBP (i.e., 86–91% fire-tolerant trees), and significantly (<i>p</i> < 0.05) higher from 3205 to 205 YBP; fire-tolerant vegetation was less abundant away from settlements, where it also experienced greater fluctuations. Correlative models showed that warmer temperatures and distance to Indigenous settlement, which are both indicators of fire, were important predictors in the 17th–18th centuries of fire-tolerant tree abundance; soil variables were less important and their relationships with vegetation were unclear. …”
Get full text

A novel data processing approach to detect fraudulent insurance claims for physical damage to cars by Ahmet Yücel

“…To this end, Singular Value Decomposition-based components and correlation-based composite variables were created. Machine learning models were then developed, with predictors and composite variables selected based on standard feature selection procedures. …”
Get full text

Investigating of the role of cybercrime and e-brand trust on purchase interest of e-commerce platforms by Mohammad Fadil Imran, Hendra Gunawa

“…In the study, the outer model which is called the measurement model has a meaning between indicators connected by other variables. …”
Get full text

Determinants of improvement trends in health workers' compliance with outpatient malaria case-management guidelines at health facilities with available "test and treat" commodities... by Beatrice Amboko, Kasia Stepniewska, Lucas Malla, Beatrice Machini, Philip Bejon, Robert W Snow, Dejan Zurovac

“…Association between 31 determinants and improvement trends in five outpatient compliance outcomes were examined using interactions between each determinant and time in multilevel logistic regression models and reported as an adjusted odds ratio of annual trends (T-aOR).…”
Get full text

Assessing the determinants associated with fidelity to the 2016 world health organization antenatal care policy across states in Nigeria by Christiana Ikemeh, Adedayo O. Adeyemi, Leah M. Frerichs, Christopher M. Shea, Justin G. Trogdon

“…Fidelity was measured as the proportion of women who cumulatively adhered to five selected ANC components—timing of first ANC visit, blood pressure measurement, tetanus vaccinations, urinalysis, and blood sample test. A binary outcome variable was generated as a fidelity index by creating a composite score from all the measures of the five components, which was categorized as ‘concordant’ and ‘partial/non-concordant’. …”
Get full text

Physical Classification of Soybean Grains Based on Physicochemical Characterization Using Near-Infrared Spectroscopy by Marisa Menezes Leal, Nairiane dos Santos Bilhalva, Rosana Santos de Moraes, Paulo Carteri Coradi

“…It is concluded that the NIR method combined with multivariate modeling allows for the rapid assessment of soybean grain quality in real time, optimizing, reducing waste in, and increasing the efficiency of post-harvest processes.…”
Get full text

Multi-criteria decision-based optimization and multivariable regression analysis of date palm fiber reinforced concrete modified with silica fume under normal and elevated temperat... by Musa Adamu, Ashwin Narendra Raut, Yasser E. Ibrahim, Hani Alanazi, Omar Shabbir Ahmed

“…Abstract Considering its affordability and accessibility, the deployment of date palm fiber (DPF) in cement composites is progressively escalating. However, the primary downside of DPF in cementitious composite is its deleterious effect on the properties of the composite. …”
Get full text

Production of Biodiesel from Mixed Castor Seed and Microalgae Oils: Optimization of the Production and Fuel Quality Assessment by Dejene Beyene, Mohammedsani Abdulkadir, Adisu Befekadu

“…Experimental results were analyzed by response surface regression to produce a model for predicting biodiesel yield. Model significance, fitness, the effect of significant variables, and interactions between the variables on the yield of biodiesel were studied through the analysis of variance (ANOVA). …”
Get full text

Using machine learning to unravel chemical and meteorological effects on ground-level ozone: Insights for ozone-climate control strategies by Zhiyuan Li, Yifan Wang, Junling Liu, Junrui Xian

“…In the present study, we evaluated the influence of key chemical-aerosol (e.g., volatile organic compounds, PM2.5, NOx) and meteorological drivers (e.g., air temperature, relative humidity) on ground-level O3 pollution at Tucheng site in New Taipei, Northern Taiwan, using fine-resolution atmospheric composition measurements and machine learning. The developed random forest machine learning models performed well, with 10-fold cross-validation R2 values above 0.867. …”
Get full text