Inference System Model Research Articles

Heat transfer and erosion control of nanofluid flow with tube inserts: Discrete phase model and adaptive neuro-fuzzy inference system approach

The current research explores the heat transfer and erosion phenomena in a tube employing newly designed inserts. Seven different geometries for the inserts have been developed into three dimensions. The fluid used is water with iron oxide nanoparticles and the flow regime is turbulent. The modeling technique involves a finite volume method with the Eulerian-Lagrangian framework incorporating a particle-scale erosion model. The outcomes indicate that raising the velocity and volume fraction of nanoadditives enhance both the heat transfer and erosion. In comparison to the scenario without fins, the heat transfer can be increased by approximately 8.07, 6.22, 18.03, 53.72, 45.21, 14.74 and 13.08 for the considered cases G1, G2, G3, G4, G5, G6 and G7, respectively. The specific geometric design of the inserts significantly influences the heat transfer and erosion in the tube, with geometry G4 showing the most substantial improvements in the heat transfer (approximately 53 %) and erosion (around 100 %) compared to a smooth tube. Factors such as velocity, particle size, fluid viscosity and insert shape affect the erosion in the tube with water demonstrating higher erosion rates than oil. The introduction of iron oxide nanoparticles leads to 2–3 times increment in the tube wall erosion. The erosion estimation on the tube wall has been performed using an adaptive neuro-fuzzy inference system artificial intelligence model with R2 = 0.981.

Quantifying suicide contagion at population scale.

The spread of suicidal behavior among individuals is often described as a contagion; however, rigorous modeling of suicide as a dynamic, contagious process is minimal. Here, we develop and validate a model-inference system depicting suicide ideation and death and use it to quantify the contagion processes in the US associated with two prominent celebrity suicide events: Robin Williams during 2014 and Kate Spade and Anthony Bourdain, which occurred 3 days apart during 2018. We show that both events produced large transient increases of suicide contagion contact rates, i.e., the spread of suicidal thought and behavior, and a period of elevated suicidal ideation in the general population. Our modeling approach provides a framework for quantifying suicidal contagion and better understanding, preventing, and containing its spread.

SARS-CoV-2 dynamics in New York City during March 2020-August 2023.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been widespread since 2020 and will likely continue to cause substantial recurring epidemics. However, understanding the underlying infection burden (i.e., including undetected asymptomatic/mild infections) and dynamics, particularly since late 2021 when the Omicron variant emerged, is challenging due to the potential for asymptomatic and repeat SARS-CoV-2 infection, changes in testing practices, and changes in disease reporting. Here, we leverage extensive surveillance data available in New York City (NYC) and a comprehensive model-inference system to reconstruct SARS-CoV-2 dynamics therein from the pandemic onset in March 2020 to August 2023, and further validate the estimates using independent wastewater surveillance data. The validated model-inference estimates indicate a very high infection burden totaling twice the population size (>5 times documented case count) but decreasing infection-fatality risk (a >10-fold reduction) during the first 3.5 years. The detailed estimates also reveal highly complex variant dynamics and immune landscape, changing virus transmissibility, and higher infection risk during winter in NYC over this time period. These transmission dynamics and drivers, albeit based on data in NYC, may be relevant to other populations and inform future planning to help mitigate the public health burden of SARS-CoV-2.

Penetralium: Privacy-preserving and memory-efficient neural network inference at the edge

The proliferation of artificial intelligence and edge computing has led to an increase in the deployment of proprietary deep learning models on third-party edge servers or devices to power mission-critical applications. However, this trend raises concerns about model privacy, particularly on untrusted edge platforms. Protecting model privacy in such scenarios requires addressing challenges such as untrustworthy model deployment environments, resource-constrained Trusted Execution Environments (TEE), and vulnerability to privacy inference attacks. To address these challenges, this paper proposes Penetralium, a system-algorithm jointly optimized model inference system on edge computing platforms. Penetralium runs models in the TEE by building an underlying computational engine. We propose an adaptive decomposition algorithm that builds a computing pipeline for models, which adapts to the underlying trusted components. Additionally, Penetralium uses a lightweight confidence score perturbation policy to protect against advanced privacy inference attacks on deep learning models. Experimental results demonstrate that Penetralium provides strong security guarantees with reasonable performance. The system not only reduces inference latency and memory consumption overhead but also improves the overall robustness of the system against advanced attacks.

System identifiability in a time-evolving agent-based model.

Mathematical models are a valuable tool for studying and predicting the spread of infectious agents. The accuracy of model simulations and predictions invariably depends on the specification of model parameters. Estimation of these parameters is therefore extremely important; however, while some parameters can be derived from observational studies, the values of others are difficult to measure. Instead, models can be coupled with inference algorithms (i.e., data assimilation methods, or statistical filters), which fit model simulations to existing observations and estimate unobserved model state variables and parameters. Ideally, these inference algorithms should find the best fitting solution for a given model and set of observations; however, as those estimated quantities are unobserved, it is typically uncertain whether the correct parameters have been identified. Further, it is unclear what 'correct' really means for abstract parameters defined based on specific model forms. In this work, we explored the problem of non-identifiability in a stochastic system which, when overlooked, can significantly impede model prediction. We used a network, agent-based model to simulate the transmission of Methicillin-resistant staphylococcus aureus (MRSA) within hospital settings and attempted to infer key model parameters using the Ensemble Adjustment Kalman Filter, an efficient Bayesian inference algorithm. We show that even though the inference method converged and that simulations using the estimated parameters produced an agreement with observations, the true parameters are not fully identifiable. While the model-inference system can exclude a substantial area of parameter space that is unlikely to contain the true parameters, the estimated parameter range still included multiple parameter combinations that can fit observations equally well. We show that analyzing synthetic trajectories can support or contradict claims of identifiability. While we perform this on a specific model system, this approach can be generalized for a variety of stochastic representations of partially observable systems. We also suggest data manipulations intended to improve identifiability that might be applicable in many systems of interest.

Comparison of Artificial Neural Fuzzy Inference System (ANFIS) and Response Surface Methodology (RSM) Model in Predicting the Outlet Flow Rate of Passive Treatment System Column

Acid mine drainage (AMD) is one of the major environmental problems the mining and mineral processing industries face. Treatment of AMD involves active and passive treatment. In the long term, passive treatment is the most effective way to treat acid mine drainage, but it can be expensive. if handled properly. Therefore, the study of flow rate in a passive treatment system is one of the important ways to identify optimum hydraulic retention time to ensure the maximum percentage of heavy metal removal can be achieved while keeping the cost to a minimum level. This study focused on developing and comparing the Response Surface Methodology (RSM) model and Artificial Neural Fuzzy Inference System (ANFIS) model to predict the outlet flow rate of the passive treatment system column based on three parameters inlet flow time, thickness of peat soil bed, and inlet flow rate. The RSM model was created by Design-Expert software whereas MATLAB created the ANFIS model with 80% of data used for the model training and 20% of the data for model testing. The models' performances were compared in terms of statistical errors (AAPE, RMSE, R2, STD, minimum error, and maximum error). It was found the ANFIS model has performed better in predicting the outlet flowrate with R2 value of 0.99 RSM model with the value of 0.97. The inlet flow rate was an insignificant parameter affecting the outlet flow rate of the passive treatment column. From the 3-D surface response plot, the highest outlet flow rate is predicted to be 524 mL/min.

A Novel Early Detection and Prevention of Coronary Heart Disease Framework Using Hybrid Deep Learning Model and Neural Fuzzy Inference System

A Novel Early Detection and Prevention of Coronary Heart Disease Framework Using Hybrid Deep Learning Model and Neural Fuzzy Inference System

Investigations on machinability and evolution of hybrid artificial intelligent tools for contemporary machining of nickel alloy

ABSTRACT Superalloys, also known as nickel alloys, are commonly used in various engineering practices such as the manufacture of chemical processing components and food processing equipment. Due to their properties, such as their high thermal conductivity and strength, they are often deemed hard to machine in conventional methods of material removal processes. As an alternative approach, modern methods are generally developed for the machining of this kind of harder material. Wire Electrical Discharge Machining is one amidst the present-day approach which is employed for machining of harder materials, that is adopted in this present investigation. This article aspires to develop a Grey-based Artificial Neural Network Model (ANN) and Adaptive Neuro Fuzzy Inference System that can be adopted for the prediction of WEDM variables. In order to study the variable inputs of the model, the paper utilizes the ANOVA and design by Taguchi. This model is designed to envisage the various performance characteristics of the process. A comparison of the model’s predicted values with the experimental results has been conducted, and it is noticed that there is a close relation between the experimental and prophesied values. The performance investigation proves the capability of evolved which helps the manufacturer to make effective decisions.

Turbulent convective heat transfer enhancement modeling of water-Al2O3 nanofluid using CFD mixture model and adaptive neural fuzzy inference system

ANFIS and multiphase Mixture model, two different methods from two very distinct engineering domains: Machine Intelligence and Computational Mechanics, have been put into a good amount of use over the past few years for modeling of nanofluids heat transfer enhancement. However, not only the previous investigations using both of these approaches suffer from the use of narrow range of nanofluid and flow properties, but also never have these two particular approaches been juxtaposed to point at a superior approach for specific flow regimes for predicting nanofluids heat transfer enhancement. In this study, water-Al2O3 nanofluid has been simulated using CFD multiphase Mixture model and ANFIS in order to assess the precision of both approaches to predict heat transfer enhancement of water-Al2O3 nanofluid for a very wide range of nanofluid configurations and flow properties, and to suggest the better approach for prediction of heat transfer enhancement for each specific flow regime. The results suggest that almost in every single case ANFIS is able to predict the heat transfer enhancement of nanofluids very efficiently with a maximum error of 0.35%, but the Mixture models’ predictions deviate significantly from the experimental correlation in some cases, though for intermediate nanofluid configurations, yielded results by Mixture model could be reliable with error around 1%.

COVID-19 pandemic dynamics in South Africa and epidemiological characteristics of three variants of concern (Beta, Delta, and Omicron).

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants of concern (VOCs) have been key drivers of new coronavirus disease 2019 (COVID-19) pandemic waves. To better understand variant epidemiologic characteristics, here we apply a model-inference system to reconstruct SARS-CoV-2 transmission dynamics in South Africa, a country that has experienced three VOC pandemic waves (i.e. Beta, Delta, and Omicron BA.1) by February 2022. We estimate key epidemiologic quantities in each of the nine South African provinces during March 2020 to February 2022, while accounting for changing detection rates, infection seasonality, nonpharmaceutical interventions, and vaccination. Model validation shows that estimated underlying infection rates and key parameters (e.g. infection-detection rate and infection-fatality risk) are in line with independent epidemiological data and investigations. In addition, retrospective predictions capture pandemic trajectories beyond the model training period. These detailed, validated model-inference estimates thus enable quantification of both the immune erosion potential and transmissibility of three major SARS-CoV-2 VOCs, that is, Beta, Delta, and Omicron BA.1. These findings help elucidate changing COVID-19 dynamics and inform future public health planning.

Effects of thickness reduction in cold rolling process on the formability of sheet metals using ANFIS

Cold rolling has detrimental effect on the formability of sheet metals. It is, however, inevitable in producing sheet high quality surfaces. The effects of cold rolling on the forming limits of stretch sheets are not investigated comprehensively in the literature. In this study, a through experimental study is conducted to observe the effect of different cold rolling thickness reduction on the formability of sheet metals. Since the experimental procedure of such tests are costly, an artificial intelligence is also adopted to predict effects of cold thickness reduction on the formability of the sheet metals. In this regard, St14 sheets are examined using tensile, metallography, cold rolling and Nakazima’s hemi-sphere punch experiments. The obtained data are further utilized to train and test an adaptive neural network fuzzy inference system (ANFIS) model. The results indicate that cold rolling reduces the formability of the sheet metals under stretch loading condition. Moreover, the tensile behavior of the sheet alters considerably due to cold thickness reduction of the same sheet metal. The trained ANFIS model also successfully trained and tested in prediction of forming limits diagrams. This model could be used to determine forming limit strains in other thickness reduction conditions. It is discussed that determination of forming limit diagrams is not an intrinsic property of a chemical composition of the sheet metals and many other factors must be taken into account.

Study of water resources parameters using artificial intelligence techniques and learning algorithms: a survey

Qualitative analysis of water resources is one of the most widely used topics in water resources research today. Researchers use various analysis methods of water parameters to achieve the desired goals in this field. This research uses artificial intelligence (AI), learning machine (LM), data mining, and mathematical techniques to simulate water behavior and estimate its parametric changes. The proposed model used in this study was a Self-adaptive Extreme learning machine (SAELM) to estimate hydrogeological parameters of the Meghan wetland located in Markazi province in Iran. In addition, SAELM simulation results were compared to Least square support vector machine (LSSVM), Multiple linear regression (MLR), and Adaptive Neuro-fuzzy inference system (ANFIS) models. The simulated parameters were Electrical Conductivity (EC), Total Dissolved Solids (TDS), Groundwater Level (GWL), and salinity. This information was related to sampling for 175 months in the study area. Finally, after simulation operation, four models were introduced as superior models. Mentioned exceptional models were SAELM in GWL modeling, SAELM in modeling the EC, MLR in salinity simulation, and LSSVM in the simulation of TDS parameters. Moreover, by five approaches, the models' performance was evaluated. Suggested strategies were performance evaluation by statistical indicators, Wilson score method uncertainty analysis (WSMUA), response & correlation plots, discrepancy ratio charts, and distribution error diagrams. Based on statistical indicators, the SAELMGWL model was the most accurate model with RMSE, MAPE, and R2 indices equal to 0.1496, 0.0043, and 0.9933, respectively. The ANFIS model had the worst results in simulation.

Development of AI-driven prediction models to realize real-time tumor tracking during radiotherapy

BackgroundIn infrared reflective (IR) marker-based hybrid real-time tumor tracking (RTTT), the internal target position is predicted with the positions of IR markers attached on the patient’s body surface using a prediction model. In this work, we developed two artificial intelligence (AI)-driven prediction models to improve RTTT radiotherapy, namely, a convolutional neural network (CNN) and an adaptive neuro-fuzzy inference system (ANFIS) model. The models aim to improve the accuracy in predicting three-dimensional tumor motion.MethodsFrom patients whose respiration-induced motion of the tumor, indicated by the fiducial markers, exceeded 8 mm, 1079 logfiles of IR marker-based hybrid RTTT (IR Tracking) with the gimbal-head radiotherapy system were acquired and randomly divided into two datasets. All the included patients were breathing freely with more than four external IR markers. The historical dataset for the CNN model contained 1003 logfiles, while the remaining 76 logfiles complemented the evaluation dataset. The logfiles recorded the external IR marker positions at a frequency of 60 Hz and fiducial markers as surrogates for the detected target positions every 80–640 ms for 20–40 s. For each logfile in the evaluation dataset, the prediction models were trained based on the data in the first three quarters of the recording period. In the last quarter, the performance of the patient-specific prediction models was tested and evaluated. The overall performance of the AI-driven prediction models was ranked by the percentage of predicted target position within 2 mm of the detected target position. Moreover, the performance of the AI-driven models was compared to a regression prediction model currently implemented in gimbal-head radiotherapy systems.ResultsThe percentage of the predicted target position within 2 mm of the detected target position was 95.1%, 92.6% and 85.6% for the CNN, ANFIS, and regression model, respectively. In the evaluation dataset, the CNN, ANFIS, and regression model performed best in 43, 28 and 5 logfiles, respectively.ConclusionsThe proposed AI-driven prediction models outperformed the regression prediction model, and the overall performance of the CNN model was slightly better than that of the ANFIS model on the evaluation dataset.

A stacking neuro-fuzzy framework to forecast runoff from distributed meteorological stations

Neuro-fuzzy models have been used to predict runoff from rainfall, a hydrological phenomenon associated with a degree of uncertainty. However, rainfall can be measured from different meteorological stations, and runoff forecasting can be biased. Thus, the aim of this work is to propose a new stacking neuro-fuzzy framework for predicting runoff from physically distributed meteorological stations. As a method to estimate single one-day-ahead runoff and as a stacking approach, the Self-Identification Neuro-fuzzy Inference model (SINFIM) and Self-Organizing Neuro-fuzzy Inference System (SONFIS) were developed, respectively. As a case study, data from two Chilean watersheds (the Diguillín River (Ñuble region) and Colorado River (Maule region)) and average daily runoff and average daily rainfall recorded over eighteen years were collected from the Chilean Directorate of Water Resources (DGA). The experimental results show good adjustment in the single forecasting of runoff with meteorological stations showing adjustment and efficiency indexes of greater than 80% in the validation set and being able to efficiently predict both high and low runoff values. However, better results were obtained with the stacking model with values being higher than single runoff predictions and those of state-of-art approaches. Therefore, the general framework proposed represents a good approach for forecasting runoff since it can improve predictions and generate more accurate runoff values than single models.

Data Analysis and Symbolic Regression Models for Predicting CO and NOx Emissions from Gas Turbines

Predictive emission monitoring systems (PEMS) are software solutions for the validation and supplementation of costly continuous emission monitoring systems for natural gas electrical generation turbines. The basis of PEMS is that of predictive models trained on past data to estimate emission components. The gas turbine process dataset from the University of California at Irvine open data repository has initiated a challenge of sorts to investigate the quality of models of various machine learning methods to build a model for predicting CO and NOx emissions depending on ambient variables and the parameters of the technological process. The novelty and features of this paper are: (i) a contribution to the study of the features of the open dataset on CO and NOx emissions for gas turbines, which will enable one to more objectively compare different machine learning methods for further research; (ii) for the first time for the CO and NOx emissions, a model based on symbolic regression and a genetic algorithm is presented—the advantage of this being the transparency of the influence of factors and the interpretability of the model; (iii) a new classification model based on the symbolic regression model and fuzzy inference system is proposed. The coefficients of determination of the developed models are: R2=0.83 for NOx emissions, R2=0.89 for CO emissions.

Determination of ride comfort thresholds based on international roughness index for asphalt concrete pavements

ABSTRACT The study is aimed to mathematically model the relationship between the amount of whole-body vibration exposed in a passenger car type vehicle and the ride speed of the vehicle in the same section and the International Roughness Index (IRI), which is used as a pavement performance indicator. Vibration measurements were analysed according to the evaluation method determined in the ISO 2631 standard, and frequency-weighted root-mean-square acceleration (aw) values were obtained in the vertical direction. Mathematical relationships between real measurement data performed in 1114 road sections were investigated using regression analysis, artificial neural networks (ANN) and Adaptive Neural Fuzzy Inference System (ANFIS) modelling techniques. The models' performance levels were determined using comparison metrics, and it was determined that ANFIS was the model with the best goodness of fit, with the regression coefficient 0.955, mean absolute error (MAE) 0.013, and root mean squared error (RMSE) 0.020. The threshold values affecting the ride comfort of IRI and the ride comfort values corresponding to the IRI limit values recommended by the Federal Highway Administration (FHWA) were determined through the ANFIS mathematical model. Then, a sensitivity analysis was conducted to determine the effects of a certain increase in the IRI value on discomfort.

Prediction of torrefied biomass properties from raw biomass

The torrefaction process enhances the quality of raw biomass and has gained widespread attention as an effective technique in energy production. Therefore, the estimation of torrefied biomass characteristics at certain operating conditions is critical to obtain desired solid products. In this study, the carbon, hydrogen, oxygen content and higher heating value (HHV) of torrefied biomass were estimated based on the results of proximate analysis (the fixed-carbon, volatile matter and ash values) of raw biomass and experimental conditions (torrefaction temperature and time). A total of 448 input and output sets belonging to lignocellulosic biomass were collected from 61 different works in the literature. Subsequently, the feedforward backpropagation algorithm based artificial neural network (ANN) model and adaptive neuro-fuzzy inference system (ANFIS) were developed as a machine learning approach for modeling the torrefaction process. The estimation capability of the developed models was examined with evaluation indicators such as mean squared error, mean absolute percentage error, and coefficient of determination. The method developed in this study provided acceptable accuracies for both elemental composition and heating value estimates. Moreover, the ANN model provided slightly better performance than ANFIS. The results show that the developed ANN model is a useful tool to obtain the desired torrefied biomass.

Assessment of Data-based Models (ANN, ANFIS and SVR) for Estimation of Exchangeable Sodium Percentage (ESP) of Bafra Plain Soils

ABSTRACT The objective of the present study was to estimate the exchangeable sodium percentage (ESP) of the soil from the Bafra plain utilizing easily determined soil characteristics (EC and pH) with the use of artificial intelligence-based models. A total of 448 soil samples were taken from different points of the study area. Artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector regression (SVR) models were developed and compared. The present database was randomly divided into training and test data sets (70:30). Coefficient of determination (R2), normalized root mean square error (NRMSE), normalized mean absolute error (NMAE), Nash and Sutcliffe model efficiency (NS) and Akaike’s Information Criterion (AIC) were used as statistical performance indicators to assess the accuracy of the models. Present findings revealed that both ANN (R2 = 0.91, NMAE = 0.21, NRMSE = 0.05, NS = 0.91 and AIC = 191.86) and ANFIS (R2 = 0.91, NMAE = 0.21, NRMSE = 0.05, NS = 0.91 and AIC = 195.51) models had greater general estimation performance than SVR (R2 = 0.89, NMAE = 0.49, NRMSE = 0.08, NS = 0.74 and AIC = 334.57) model. Comparative assessments revealed that ANN and ANFIS approaches could successfully be used in estimation of ESP from EC and pH data. It was concluded based on present findings that artificial intelligence-based techniques could reliably be used in estimation of soil ESP as a promising alternative of traditional approaches.

Development of a model-inference system for estimating epidemiological characteristics of SARS-CoV-2 variants of concern

To support COVID-19 pandemic planning, we develop a model-inference system to estimate epidemiological properties of new SARS-CoV-2 variants of concern using case and mortality data while accounting for under-ascertainment, disease seasonality, non-pharmaceutical interventions, and mass-vaccination. Applying this system to study three variants of concern, we estimate that B.1.1.7 has a 46.6% (95% CI: 32.3–54.6%) transmissibility increase but nominal immune escape from protection induced by prior wild-type infection; B.1.351 has a 32.4% (95% CI: 14.6–48.0%) transmissibility increase and 61.3% (95% CI: 42.6–85.8%) immune escape; and P.1 has a 43.3% (95% CI: 30.3–65.3%) transmissibility increase and 52.5% (95% CI: 0–75.8%) immune escape. Model simulations indicate that B.1.351 and P.1 could outcompete B.1.1.7 and lead to increased infections. Our findings highlight the importance of preventing the spread of variants of concern, via continued preventive measures, prompt mass-vaccination, continued vaccine efficacy monitoring, and possible updating of vaccine formulations to ensure high efficacy.

Economic Complexity, Economic Growth, and CO2 Emissions: A Panel Data Analysis

ABSTRACT Reducing global warming effects without jeopardizing economic prosperity demands the analysis of the link between these factors. Environmental degradation and economic growth are thought to be related in a non-linear manner, following an inverted-U pattern called the ‘Environmental Kuznets Curve’ (EKC). Despite the many studies seeking empirical support for this relationship, the literature does not provide conclusive findings. By presenting the Economic Complexity Index (ECI) as an explanatory variable, this paper aims at providing a comprehensive analysis of EKC from 86 countries with different development levels, covering the period between 1971 and 2014. Different statistical estimation techniques were used, including an Adaptive Neuro-Fuzzy Inference System (ANFIS) model, dynamic panel data techniques, and the Sasabuchi–Lind–Mehlum (SLM) test. The results show no clear evidence supporting the idea of EKC, neither for production volumes nor for production sophistication, as captured by ECI. Nonetheless, when ECI increases, pollution levels drop monotonously only for developed countries.