Artificial Neural Network Model Research Articles

Convective drying of golden delicious apple enhancement: drying characteristics, artificial neural network modeling, chemical and ATR-FTIR analysis of quality parameters

AbstractIn recent years, many innovative methods have been investigated to provide alternative approaches to the food drying industry, but currently the most widely used method is convective drying. There are difficulties in integrating innovative methods into the food industry due to cost, inapplicability to every food material, or product quality, etc. In addition, it is possible to improve the convective drying method by pre-treating of foods. Thanks to the convective drying method with increased efficiency, shorter drying processes can be achieved. This study investigates the effects of ethanol and citric acid pretreatments on the convective drying process of apple slices and the drying rate, diameter and thickness shrinkage, color properties, total phenolic content (TPC), antioxidant activity (AA), ATR-FTIR spectra, and principal component analysis (PCA) of the dried samples. The results indicate that both ethanol and citric acid pretreatments significantly enhance the drying rate and decrease drying time, with the most favorable outcomes observed for apple slices immersed in an ethanol solution for 20 min. The study employs thin-layer and artificial neural network (ANN) modeling, revealing that ANN modeling outperforms thin-layer models in predicting moisture ratio. Shrinkage ratios in diameter and thickness were observed, but no significant statistical differences are found among the sample groups. The color properties of dried apple slices are influenced by pretreatments. L* values decreased in the ethanol-pretreated samples, whereas a* and b* values increased in all samples. On the other hand, drying process leads to a decrease in TPC and AA. Ethanol pretreatments caused higher losses; lower losses were observed in the citric acid–pretreated and untreated apples slices. ATR-FTIR analysis suggests distinct spectral changes in dried samples, particularly influenced by ethanol and citric acid pretreatments. The ATR-FTIR spectra highlighted shifts in water and carbohydrate levels, proteins, fibers, organic acids, and the occurrence of Maillard reactions throughout the drying process. PCA reveals that samples dried with ethanol and citric acid share a similar plane, while fresh samples and those dried at 60 °C exhibit different arrangements.

Laser processing characteristics of PCD tool and modeling analysis

Through in-depth analysis of the experimental details and forming patterns of the nanosecond laser ablation polycrystalline diamond (PCD) textured tool processing system, this study explores the microscopic morphology and dimensions of micro-pits texture on the surface of PCD tools influenced by defocus amount, laser power, and pulse frequency. Experimental results indicate that the micro-pit textures generated under different parameters exhibit diversity, including rounded structure, fragments, recast layers, and heat-affected zones. The diameter and depth of micro-pits are comprehensively affected by defocus amount, laser power, and pulse frequency, showing complex patterns. After a thorough analysis of the effects of each parameter on the texture morphology, an artificial neural network (ANN) model is introduced for the prediction of micro-pit dimensions. Through model training and optimization, accurate predictions of micro-pit diameter and depth are obtained. In comparison to traditional regression models, the ANN model demonstrates outstanding predictive performance, validating its applicability in complex machining processes. This study not only provides a profound understanding of the processing patterns of PCD textured tools but also offers an effective predictive model for the optimization and control of similar future machining processes.

Exploring the Influence of Dynamic Indicators in Urban Spaces on Residents’ Environmental Behavior: A Case Study in Shanghai Utilizing Mixed-Methods Approach and Artificial Neural Network (ANN) Modeling

The main aim of this article is to evaluate the impact of dynamic indicators associated with urban spaces on the environmental behavior of residents in Shanghai, China. With the city experiencing rapid urbanization and increasing environmental concerns, it is crucial to understand how the design and management of urban spaces can encourage pro-environmental attitudes and actions among the population. The study specifically focuses on dynamic indicators, namely vitality, accessibility, quality, and walkability, to develop a comprehensive understanding of the utilization and experience of urban spaces. The research outcomes will make valuable contributions towards Shanghai’s objectives of achieving environmental sustainability, while also providing insights that have broader relevance to sustainable urban development globally. As the built environment significantly influences energy consumption, resource utilization, pollution generation, and overall human wellbeing, attaining urban sustainability is of paramount importance. The findings of this study will aid in informing strategies and policies that promote sustainable practices, not only benefiting Shanghai but also serving as a valuable resource for urban development initiatives worldwide. Sustainable urban design principles, including compactness, density, mixed land use, greening, and walkability, have been associated with pro-environmental behaviors, including reduced reliance on automobiles, increased walking and cycling, and heightened environmental consciousness. Nevertheless, the relationship between the built environment and sustainability behaviors is intricate and is influenced by multiple factors. Consequently, further research is necessary to comprehend how specific spatial and temporal dynamics impact environmental behaviors within urban settings. In this study, an artificial neural network (ANN) was developed to estimate the quality and walkability of an area and environmental behaviors by considering the augmented vitality and accessibility factors. The ANN’s predictions demonstrate that higher levels of vitality and accessibility positively contribute to improved walkability and environmental behaviors. The accuracy of the ANN’s predictions was assessed using linear regression, which yielded acceptable error rates when compared with experimental results.

Application of artificial neural networks and Langmuir and Freundlich isotherm models to the removal of textile dye using biosorbents: A comparative study among methodologies

AbstractAdsorption isotherms are valuable tools for describing the interaction between adsorbate and adsorbent since they demonstrate the equilibrium relationship. The Langmuir and Freundlich models are the most commonly used isotherm models to describe these relationships; still, they cannot consistently deliver efficient results due to the assumptions of the model not predicting more complex situations as occurs in biosorption. Artificial neural networks (ANN) are a set of algorithms modelled loosely after the human brain and are designed to recognize patterns. The ANN tool can overcome problems isotherm models have in describing the interactions mentioned and help define the best conditions for a given adsorption process. This paper reports the application of ANNs for predicting the removal efficiency of textile dye Neolan Black WA (Acid Black 52) using orange peel and sugarcane bagasse as biosorbents. The Freundlich, Langmuir, pseudo‐first‐order, and pseudo‐second‐order models were applied and compared to the ANN model. The parameters evaluated were initial dye concentration (10–600 mg/L), final dye concentration (0–83.44 mg/L), biosorbent mass (1.5 g), pH (2), and contact time of dye (0.167–24 h). Two classes of ANNs, Elman and feed‐forward networks, were tested with a mean square error of 0.0212 and 0.7274 for the isotherm and kinetics, respectively. Compared to the conventional isotherm and kinetic models, the Elman network predicted the amount adsorbed by the biosorbents with higher precision, acquiring a determination coefficient of 0.9998 and a mean square error of 8.75 × 10−5.

A Final Cost Estimating Model for Building Renovation Projects

The construction sector in Greece has been developing radically in the field of building renovations. The foremost problem for projects in the building construction industry is producing an accurate and reliable cost estimate at the onset of construction. The artificial neural network (AΝΝ) approach, using data available at the early stages of the project, can help resolve or prevent any kind of difficulty that could make the successful completion of a building less likely. ANNs have been highly efficient in gaining results which could prevent the failure of building constructions projects. The ultimate goal is to highlight the usefulness of the adoption of ANNs models to predict the final cost of a building renovation project. Thus, construction companies could avoid financial failure, provided that the gap between cost prediction and final cost for renovation projects is minimized. This paper presents an artificial neural network (ANN) approach for predicting renovation costs in Greek construction projects. The study, based on a comprehensive literature review and real renovation data from construction companies, employs IBM SPSS Statistics software to build, train, and test the ANN model. The model, which uses initial cost, estimated time, and initial demolition cost as inputs, is based on the radial basis function procedure. The model presents high performance with up to 2% sum of squares error and near zero relative error, demonstrating the ANN’s effectiveness in estimating total renovation costs.

Application of Intercriteria and Regression Analyses and Artificial Neural Network to Investigate the Relation of Crude Oil Assay Data to Oil Compatibility

The compatibility of constituents making up a petroleum fluid has been recognized as an important factor for trouble-free operations in the petroleum industry. The fouling of equipment and desalting efficiency deteriorations are the results of dealing with incompatible oils. A great number of studies dedicated to oil compatibility have appeared over the years to address this important issue. The full analysis of examined petroleum fluids has not been juxtaposed yet with the compatibility characteristics in published research that could provide an insight into the reasons for the different values of colloidal stability indices. That was the reason for us investigating 48 crude oil samples pertaining to extra light, light, medium, heavy, and extra heavy petroleum crudes, which were examined for their colloidal stability by measuring solvent power and critical solvent power utilizing the n-heptane dilution test performed by using centrifuge. The solubility power of the investigated crude oils varied between 12.5 and 74.7, while the critical solubility power fluctuated between 3.3 and 37.3. True boiling point (TBP) analysis, high-temperature simulation distillation, SARA analysis, viscosity, density and sulfur distribution of narrow petroleum fractions, and vacuum residue characterization (SARA, density, Conradson carbon, asphaltene density) of the investigated oils were performed. All the experimentally determined data in this research were evaluated by intercriteria and regression analyses. Regression and artificial neural network models were developed predicting the critical solubility power with correlation coefficients R of 0.80 and 0.799, respectively.

Wearable Piezoelectric Sensors Based on BaTiO3 Films for Sarcopenia Recognition

AbstractSarcopenia recognition is very crucial in the early diagnosis of sarcopenia. However, the commonly used screening methods are limited by real‐time property, portability, and convenient usability at home. Herein, an electrospun BaTiO3 film is proposed and a piezoelectric sensor with silver electrodes and polyimide substrates is fabricated. The sensor exhibits high piezoelectricity (74.2 pC N−1), sensitivity, linearity, low detection limit (0.2 mN), and significant bending ability (bending angle can exceed 90°), maintaining stable output after more than 20 000 cycles during a week. Due to its excellent performance, the piezoelectric sensor to the recognition of sarcopenia is applied and a wearable system to collect piezoelectric signals from the lower limb movements of the elderly is developed. By selecting features from these signals, eight kinds of machine learning models are employed and their performances in recognizing sarcopenia are compared in both male and female groups. The results indicate that the artificial neural network (ANN) model has the highest performance, with accuracies of 92.9% in males and 98.1% in females. This piezoelectric sensor, combined with a wireless communication module, is expected to provide crucial evidence for sarcopenia detection, offering a new, convenient, and household screening solution for early diagnosis and prevention of sarcopenia.

A Comprehensive Flood Risk Inundation Mapping and Hybrid Model for Flood Forecasting in the Panam River Basin

The forecasting of flooding plays a pivotal role in the field of hydrology and serves as an essential measure for preventing any possible flood damage. This study presents an analysis of the utilization of an Adaptive Neuro-Fuzzy Inference System (ANFIS) to prevent floods in river basins. ANFIS represents a hybrid approach that combines elements of neural networks and fuzzy logic methodologies for the purpose of analyzing and comparing input and output data. Performance evaluation of ANFIS is based on the ratio of Discrepancy Ratio (D) along with the determination coefficient (R2), Coefficient of correlation (R), and Root Mean Square Error (RMSE). Results: The best ANFIS model was the one that gave the best results during training. The RMSE was 622.43, with a correlation coefficient of 0.93 and an R2 of 0.86. Nevertheless, its validation performance demonstrated slightly elevated RMSE figures and lower correlation and R2 values, with RMSE at 2847.99, R at 0.91, and R2 at 0.83. An Artificial Neural Network (ANN) model with three transfer functions (SIGMOID, HYPERBOLIC TANGENT, and LINEAR) is developed and evaluated based on R = correlation and MSE = mean squared error. Furthermore, the study also entails the development of a flood model for the research area, consisting of 38 cross profiles for a detailed analysis of the river’s profile and flood inundation. This analysis aims to provide precise recommendations for flood protection measures.

Investigation of maximum temperatures in lithium-ion batteries by CFD and machine learning

Alternative fuels are becoming more popular as awareness of fossil fuel depletion, pollution, and climate change grows. Numerous industrial companies are producing electric automobiles for use worldwide. Electric vehicles’ battery packs’ cooling causes firing due to high temperatures. In this study, the surface temperatures of a single electric battery with dimensions of 160 mm × 210 mm within a battery pack were investigated using computational fluid dynamics and, subsequently, Levenberg-Marquardt machine learning as a function of ambient temperature, convective heat transfer coefficient, nominal capacity of the electric battery, and discharge rate. The transport coefficient has been calculated for a rechargeable electric battery with a nominal capacity ranging from 14.6 to 20 Ah and a discharge rate varying between 1 and 15, taking into account conditions of stagnant air at temperatures ranging from 20°C to 35°C and values between 5 and 20 W/m2.K. Insufficient or absent cooling of battery temperatures can lead to them reaching combustion temperatures of electric vehicle batteries, typically from 50°C to 80°C, depending on the operational circumstances. An artificial neural network was utilized in machine learning to forecast maximum temperatures based on operating conditions without requiring simulation. The neural network achieved an estimated mean squared error of 0.00552 and a calculated coefficient of determination of 0.99. The neural network model can predict outputs with mean and standard deviation rates below 0.237. The anticipated artificial neural network model can accurately forecast the maximum surface temperature of an electric vehicle battery.

Emerging Vanadium-Doped Cobalt Chloride Carbonate Hydroxide for Flexible Electrochromic Micro-Supercapacitor: Charged-State Prediction from RGB Input by ANN Model.

Multifunctional devices integrated with electrochromic and supercapacitance properties are fascinating because of their extensive usage in modern electronic applications. In this work, vanadium-doped cobalt chloride carbonate hydroxide hydrate nanostructures (V-C3H NSs) are successfully synthesized and show unique electrochromic and supercapacitor properties. The V-C3H NSs material exhibits a high specific capacitance of 1219.9Fg-1 at 1mVs-1 with a capacitance retention of 100% over 30000 CV cycles. The electrochromic performance of the V-C3H NSs material is confirmed through in situ spectroelectrochemical measurements, where the switching time, coloration efficiency (CE), and optical modulation (∆T) are found to be 15.7 and 18.8s, 65.85cm2C-1 and 69%, respectively. A coupled multilayer artificial neural network (ANN) model is framed to predict potential and current from red (R), green (G), and blue (B) color values. The optimized V-C3H NSs are used as the active materials in the fabrication of flexible/wearable electrochromic micro-supercapacitor devices (FEMSDs) through a cost-effective mask-assisted vacuum filtration method. The fabricated FEMSD exhibits an areal capacitance of 47.15mFcm-2 at 1mVs-1 and offers a maximum areal energy and power density of 104.78Whcm-2 and 0.04mWcm-2, respectively. This material's interesting energy storage and electrochromic properties are promising in multifunctional electrochromic energy storage applications.

Prediction of HGI of South African coalfields: a comparative application of ANN, SVR and LSTM models

ABSTRACT Hardgrove grindability index (HGI) is a significant index used to determine a mill’s capability and overall efficiency in the grinding of coal. There are several factors that affect HGI due to the complex nature of coal. The influence of proximate analysis, calorific value, total sulfur, and pyrite content on the HGI values of 292 coal samples from South African coalfields were examined. Predictive models of HGI are developed by using soft computing techniques such as Long Short-Term Memory (LSTM), support vector regression (SVR), and Artificial Neural Network (ANN). This study shows that ANN is the most effective predictive model for all the three coalfields, with SVR models being second and LSTM models being the least effective. The correlation between the predicted value and the input data is established by using the cosine amplitude method (CAM). It was found that HGI is most influenced by the fixed carbon content, calorific value, ash content and volatile matter content while pyrite has the least influence.

Prediction and modeling of mechanical properties of concrete modified with ceramic waste using artificial neural network and regression model

Prediction and modeling of mechanical properties of concrete modified with ceramic waste using artificial neural network and regression model

Assessment of mechanical and physicochemical properties of palm fiber composites: Effect of alkaline treatment and volume alterations

This study assesses the impact of alkaline treatments and volume fractions on biocomposites composed of a high-density polyethylene (HDPE) matrix reinforced with date palm tree fibers (FPDS). Tensile tests were conducted on both untreated and NaOH-treated biocomposites. Additionally, fiber analysis was performed using scanning electron microscopy (SEM) and X-ray diffraction (XRD). The results reveal higher strength and stiffness compared to HDPE, albeit with limited plasticity making the material brittle. The NaOH treatment enhances certain mechanical properties. Further assessments encompassed hardness, density, melt index, and Izod impact tests. Two volume fractions, 20% and 25%, of FPDS were tested. The study establishes a correlation between empirical predictions and artificial neural network (ANN) models. Notably, an ANN architecture consisting of two input factors, 10 hidden nodes, and one output provides the analysis of mechanical properties. This investigation highlights the potential of FPDS-reinforced HDPE biocomposites, emphasizing their mechanical performance under various treatments and fiber levels.

A Hierarchy of Variables That Influence the Force–Velocity Profile of Acrobatic Gymnasts: A Tool Based on Artificial Intelligence

Jumping performance is considered an overall indicator of gymnastics ability. Acrobatic Gymnastics involves base and top gymnasts, considering the type of training that is performed and the distinct anthropometric traits of each gymnast. This work aims to investigate a hierarchy of variables that influence the force–velocity (F-V) profile of top and base acrobatic gymnasts through a deep artificial neural network model. Twenty-eight first division and elite acrobatic gymnasts (eleven tops and seventeen bases) performed two evaluations to assess the F-V profile during the Countermovement Jump and its mechanical variables, using My Jump 2 (a total of 56 evaluations). A training background survey and anthropometric assessments were conducted. The final model (R = 0.97) showed that the F-V imbalance (F-Vimb) increases with higher force and decreases with higher maximal power, fat percentage, velocity, and height. Coaches should prioritize the development of force, followed by maximal power, and velocity for the optimization of gymnasts’ F-Vimb. For training planning, the influences of body mass and push-off height are higher for the bases, and the influences of years of practice and competition level are higher for the tops.

Physics-informed loss functions for vertical total electron content forecast

AbstractWe design physics-informed loss functions for training Artificial Neural Network (ANN) models to forecast the ionospheric vertical Total Electron Content (vTEC) from 1 to 24 hours in advance. The ANN models exploit our physics-informed loss functions, data provided by the Global Navigation Satellite Systems (GNSS) receiver installed at Tsukuba (36.06$$^{o}$$ o N, 140.05$$^{o}$$ o E), Japan, and external drivers (solar and geomagnetic indices). The time series used span from January 1, 2006, to December 31, 2018, i.e., a full solar cycle. A proper set of external drivers for the ANN models training are selected by ranking their importance in relation to the vTEC dynamics at different forecasting horizons. They result to be the 10.7 cm Solar Flux (F10.7), the magnitude of the Interplanetary Magnetic Field (IMF) $$\boldsymbol{B}_{\boldsymbol{T}}$$ B T , and the Auroral Electrojet (AE) index. Moreover, a second set of indices among those available has been considered as constraints in the design of the physics-informed loss functions. They are the Disturbance Storm Time (Dst) index, the solar wind speed $$\boldsymbol{v}, \boldsymbol{B}_{\boldsymbol{T}}$$ v , B T , and the By and Bz components of the interplanetary magnetic field. To assess the performance of the resulting ANN models, we use the statistical parameter coefficient of determination ($$\boldsymbol{R}^{{\textbf {2}}}$$ R 2 ), the standard deviation (SD), and the Wilcoxon non-parametric signed ranked test. We show that, in the testing period analyzed (from 2017-09-13, at 04:40:00, to 2018-12-31, at 23:55:00), one of our physics-informed loss functions provides a better performance of the ANN with regard to the standard loss function commonly adopted. In particular, when the new loss function is used in the ANN model, the average SD is minimized across all forecasting horizons in the training, validation and test datasets. SD is 0.2560 TECU, 0.3183 TECU and 0.4240 TECU for the training, validation and test dataset respectively, where 1 TECU = $${\textbf {10}}^{{\textbf {16}}}$$ 10 16 electrons/$$\boldsymbol{m}^{{\textbf {2}}}$$ m 2 . The ANN model, incorporating the new loss function and applied to the test dataset, shows a significant improvement according to the Wilcoxon signed ranked test. In fact by selecting a significance level $$\boldsymbol{\alpha }~ \mathbf {= 0.05}$$ α = 0.05 , the probability to obtain results by chance with the new loss function as compared to the standard loss function is 0.01504 (i.e., $$<\alpha $$ < α ), which implies that the new loss function gives a statistical improvement to the forecasting capability of the ANN model. To the best of our knowledge, this is the first time a physics-informed loss function has been designed for the task of forecasting the ionospheric vTEC.

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models.

Landslide susceptibility mapping is essential for reducing the risk of landslides and ensuring the safety of people and infrastructure in landslide-prone areas. However, little research has been done on the development of well-optimized Elman neural networks (ENN), deep neural networks (DNN), and artificial neural networks (ANN) for robust landslide susceptibility mapping (LSM). Additionally, there is a research gap regarding the use of Bayesian optimization and the derivation of SHapley Additive exPlanations (SHAP) values from optimized models. Therefore, this study aims to optimize DNN, ENN, and ANN models using Bayesian optimization for landslide susceptibility mapping and derive SHAP values from these optimized models. The LSM models have been validated using the receiver operating characteristics curve, confusion matrix, and other twelve error matrices. The study used six machine learning-based feature selection techniques to identify the most important variables for predicting landslide susceptibility. The decision tree, random forest, and bagging feature selection models showed that slope, elevation, DFR, annual rainfall, LD, DD, RD, and LULC are influential variables, while geology and soil texture have less influence. The DNN model outperformed the other two models, covering 7839.54 km2 under the very low landslide susceptibility zone and 3613.44 km2 under the very high landslide susceptibility zone. The DNN model is better suited for generating landslide susceptibility maps, as it can classify areas with higher accuracy. The model identified several key factors that contribute to the initiation of landslides, including high elevation, built-up and agricultural land use, less vegetation, aspect (north and northwest), soil depth less than 140 cm, high rainfall, high lineament density, and a low distance from roads. The study's findings can help stakeholders make informed decisions to reduce the risk of landslides and ensure the safety of people and infrastructure in landslide-prone areas.

Predicting the complexity and mortality of polytrauma patients with machine learning models

We aim to develop machine learning (ML) models for predicting the complexity and mortality of polytrauma patients using clinical features, including physician diagnoses and physiological data. We conducted a retrospective analysis of a cohort comprising 756 polytrauma patients admitted to the intensive care unit (ICU) at Pizhou People’s Hospital Trauma Center, Jiangsu, China between 2020 and 2022. Clinical parameters encompassed demographics, vital signs, laboratory values, clinical scores and physician diagnoses. The two primary outcomes considered were mortality and complexity. We developed ML models to predict polytrauma mortality or complexity using four ML algorithms, including Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN) and eXtreme Gradient Boosting (XGBoost). We assessed the models’ performance and compared the optimal ML model against three existing trauma evaluation scores, including Injury Severity Score (ISS), Trauma Index (TI) and Glasgow Coma Scale (GCS). In addition, we identified several important clinical predictors that made contributions to the prognostic models. The XGBoost-based polytrauma mortality prediction model demonstrated a predictive ability with an accuracy of 90% and an F-score of 88%, outperforming SVM, RF and ANN models. In comparison to conventional scoring systems, the XGBoost model had substantial improvements in predicting the mortality of polytrauma patients. External validation yielded strong stability and generalization with an accuracy of up to 91% and an AUC of 82%. To predict polytrauma complexity, the XGBoost model maintained its performance over other models and scoring systems with good calibration and discrimination abilities. Feature importance analysis highlighted several clinical predictors of polytrauma complexity and mortality, such as Intracranial hematoma (ICH). Leveraging ML algorithms in polytrauma care can enhance the prognostic estimation of polytrauma patients. This approach may have potential value in the management of polytrauma patients.

Thermophysical dynamics of magnetohydrodynamic electroosmotic two phase mixed convective flow in vertical annulus: neuro computation

ABSTRACT The thermophysical dynamics of electro – magnetohydrodynamic mixed convective electrically conducting fluid flow in the vertical cylindrical annulus are explored with electric and magnetic fields. The flow and heat transfer properties are explicitly examined in viscous fluid and electroosmotic flow regions. The coupling between an external pressure gradient, electroosmosis, and an extended electromagnetic field can control fluid flow and heat transfer. The governing equations associated with the physical phenomenon are addressed with the Galerkin finite element method. Eloquently, the analysis revealed that, in the absence of a lateral electric field, the flow velocity decelerates as the Hartmann number increases, which in turn ultimately, causes the Nusselt number to rise. Since a lateral electric field is involved, the flow field, temperature field, and Nusselt number profiles are presented in two regions. The artificial neural network model discusses the thermal transport phenomenon in both regions. The artificial neural network models regression, performance plots, weights, and bias are presented. The research outcome can be utilized to design exquisite and efficacious electromagnetic devices, particularly within a particular range of thermal physical properties.

Machine learning predictions for carbon monoxide levels in urban environments

The increasing carbon emissions in Malaysia necessitate accurate methods to track and control pollution levels. This study focuses on predicting carbon monoxide (CO) concentrations in Petaling Jaya using various machine learning models, and two important parameters, CO concentration and time, were considered in the analysis. Six distinct machine learning models were assessed to gauge their predictive capabilities. These models encompassed a range of regression modeling techniques namely; Linear, Tree, Gaussian Process, Ensemble of Trees, Support Vector, and Artificial Neural Networks (ANN) modelling. The Matern 5/2 Gaussian Process Regression (GPR) model consistently outperformed other models across all scenarios, demonstrating high R2 values and low RMSE, MSE, and MAE values. Specifically, in scenarios 1, 2, 3, and 4, the Matern 5/2 model exhibited the lowest RMSE (0.084–0.088) and highest R2 (0.97), highlighting its reliability and robustness in predicting CO concentrations. Additionally, the Rational Quadratic model achieved an R2 of 0.97 with an RMSE of 0.088 in scenario 1, while the Quadratic SVM excelled in scenario 3 with an R2 of 0.965 and low RMSE, MSE, and MAE values (0.085, 0.007, and 0.066). These findings provide valuable insights for environmental protection, renewable energy transition, energy efficiency, sustainable land use planning, and public awareness. However, acknowledging the study's single-area focus and potential limitations in representing diverse regions, further research is warranted to explore carbon emissions across varied areas and enhance the generalizability of the findings.

MaMD Analytical 1.0

We outline the functionalities and application of MaMD Analytical—a new, freely available software package for the estimation of population affinity using human cranial macromorphoscopic (MMS) traits. MaMD Analytical captures MMS scores using line drawings following the procedures outlined by Hefner and Linde (2018). MaMD Analytical generates classifications (with estimated likelihoods) into forensically significant populations using an artificial neural network and reference samples drawn from the Macromorphoscopic Databank (MaMD). Summary data (sensitivity, specificity, x-validated classification accuracies) are provided. In this article, we apply MaMD Analytical to a large sample of identified individuals not used in the original model building to assess utility and demonstrate the typical outputs for MaMD Analytical. MaMD Analytical facilitates construction of the biological profile and provides a number of safeguards in summary statistics as a valuable addition to the forensic anthropological analysis toolkit. MaMD Analytical is written in the open-source R environment integrating a previously developed artificial neural network model to estimate population affinity using well-documented and validated approaches.