Mean Average Error Research Articles

A Strategy for Predicting the Performance of Supervised and Unsupervised Tabular Data Classifiers

AbstractMachine Learning algorithms that perform classification are increasingly been adopted in Information and Communication Technology (ICT) systems and infrastructures due to their capability to profile their expected behavior and detect anomalies due to ongoing errors or intrusions. Deploying a classifier for a given system requires conducting comparison and sensitivity analyses that are time-consuming, require domain expertise, and may even not achieve satisfactory classification performance, resulting in a waste of money and time for practitioners and stakeholders. This paper predicts the expected performance of classifiers without needing to select, craft, exercise, or compare them, requiring minimal expertise and machinery. Should classification performance be predicted worse than expectations, the users could focus on improving data quality and monitoring systems instead of wasting time in exercising classifiers, saving key time and money. The prediction strategy uses scores of feature rankers, which are processed by regressors to predict metrics such as Matthews Correlation Coefficient (MCC) and Area Under ROC-Curve (AUC) for quantifying classification performance. We validate our prediction strategy through a massive experimental analysis using up to 12 feature rankers that process features from 23 public datasets, creating additional variants in the process and exercising supervised and unsupervised classifiers. Our findings show that it is possible to predict the value of performance metrics for supervised or unsupervised classifiers with a mean average error (MAE) of residuals lower than 0.1 for many classification tasks. The predictors are publicly available in a Python library whose usage is straightforward and does not require domain-specific skill or expertise.

An Approach to Realize Generalized Optimal Motion Primitives Using Physics Informed Neural Networks

Abstract Autonomous manipulation is a challenging problem in field robotics due to uncertainty in object properties, constraints, and coupling phenomenon with robot control systems. Humans learn motion primitives over time to effectively interact with the environment. We postulate that autonomous manipulation can be enabled by basic sets of motion primitives as well, but do not necessitate mimicking human motion primitives. This work presents an approach to generalized optimal motion primitives using physics-informed neural networks. Our simulated and experimental results demonstrate that optimality is notionally maintained where the mean maximum observed final position percent error was 0.564% and the average mean error for all the trajectories was 1.53%. These results indicate that notional generalization is attained using a physics-informed neural network approach that enables near optimal real-time adaptation of primitive motion profiles.

Machine Learning-Based Predictions of Flow and Heat Transfer Characteristics in a Lid-Driven Cavity with a Rotating Cylinder

Machine learning-based predictions of heat transfer characteristics in lid-driven cavities are transforming the field of computational fluid dynamics (CFD). Lid-driven cavities are a fundamental problem in fluid mechanics, characterized by the motion of a fluid inside a square cavity driven by the motion of one of its walls. The goal of this study was to develop multiple machine-learning regression models and highlight the discrepancies between the predicted and actual average Nusselt numbers. Additionally, the study utilized physics-informed neural networks (PINNs) to model the flow and thermal behavior at both low and high Reynolds numbers. The results were compared among actual data from computational fluid dynamics (CFD) simulations, PINN models trained with CFD data, and purely PINN models created without any prior data input. The findings of this study showed that the random forest model exhibited an exceptional stability in its predictions, consistently maintaining low errors even as the Reynolds number increased compared with other machine-learning regression models. Further, the results of this study in terms of flow and thermal behavior within the cavity were found to depend significantly on the PINN method. The data-driven PINN exhibited a much lower mean average errors at both Reynolds numbers, while the physics-based PINN showed lower physics loss.

AI-smartphone markerless motion capturing of hip, knee, and ankle joint kinematics during countermovement jumps.

Recently, AI-driven skeleton reconstruction tools that use multistage computer vision pipelines were designed to estimate 3D kinematics from 2D video sequences. In the present study, we validated a novel markerless, smartphone video-based artificial intelligence (AI) motion capture system for hip, knee, and ankle angles during countermovement jumps (CMJs). Eleven participants performed six CMJs. We used 2D videos created by a smartphone (Apple iPhone X, 4K, 60 fps) to create 24 different keypoints, which together built a full skeleton including joints and their connections. Body parts and skeletal keypoints were localized by calculating confidence maps using a multilevel convolutional neural network that integrated both spatial and temporal features. We calculated hip, knee, and ankle angles in the sagittal plane and compared it with the angles measured by a VICON system. We calculated the correlation between both method's angular progressions, mean squared error (MSE), mean average error (MAE), and the maximum and minimum angular error and run statistical parametric mapping (SPM) analysis. Pearson correlation coefficients (r) for hip, knee, and ankle angular progressions in the sagittal plane during the entire movement were 0.96, 0.99, and 0.87, respectively. SPM group-analysis revealed some significant differences only for ankle angular progression. MSE was below 5.7°, MAE was below 4.5°, and error for maximum amplitudes was below 3.2°. The smartphone AI motion capture system with the trained multistage computer vision pipeline was able to detect, especially hip and knee angles in the sagittal plane during CMJs with high precision from a frontal view only.

Handrim Reaction Force and Moment Assessment Using a Minimal IMU Configuration and Non-Linear Modeling Approach during Manual Wheelchair Propulsion.

Manual wheelchair propulsion represents a repetitive and constraining task, which leads mainly to the development of joint injury in spinal cord-injured people. One of the main reasons is the load sustained by the shoulder joint during the propulsion cycle. Moreover, the load at the shoulder joint is highly correlated with the force and moment acting at the handrim level. The main objective of this study is related to the estimation of handrim reactions forces and moments during wheelchair propulsion using only a single inertial measurement unit per hand. Two approaches are proposed here: Firstly, a method of identification of a non-linear transfer function based on the Hammerstein-Wiener (HW) modeling approach was used. The latter represents a typical multi-input single output in a system engineering modeling approach. Secondly, a specific variant of recurrent neural network called BiLSTM is proposed to predict the time-series data of force and moments at the handrim level. Eleven subjects participated in this study in a linear propulsion protocol, while the forces and moments were measured by a dynamic platform. The two input signals were the linear acceleration as well the angular velocity of the wrist joint. The horizontal, vertical and sagittal moments were estimated by the two approaches. The mean average error (MAE) shows a value of 6.10 N and 4.30 N for the horizontal force for BiLSTM and HW, respectively. The results for the vertical direction show a MAE of 5.91 N and 7.59 N for BiLSTM and HW, respectively. Finally, the MAE for the sagittal moment varies from 0.96 Nm (BiLSTM) to 1.09 Nm for the HW model. The approaches seem similar with respect to the MAE and can be considered accurate knowing that the order of magnitude of the uncertainties of the dynamic platform was reported to be 2.2 N for the horizontal and vertical forces and 2.24 Nm for the sagittal moments. However, it should be noted that HW necessitates the knowledge of the average force and patterns of each subject, whereas the BiLSTM method do not involve the average patterns, which shows its superiority for time-series data prediction. The results provided in this study show the possibility of measuring dynamic forces acting at the handrim level during wheelchair manual propulsion in ecological environments.

A Multivariate Approach to Quantifying Risk Factors Impacting Stereotactic Robotic-Guided Stereoelectroencephalography.

Stereoelectroencephalography (SEEG) is an important method for invasive monitoring to establish surgical candidacy in approximately half of refractory epilepsy patients. Identifying factors affecting lead placement can mitigate potential surgical risks. This study applies multivariate analyses to identify perioperative factors affecting stereotactic electrode placement. We collected registration and accuracy data for consecutive patients undergoing SEEG implantation between May 2022 and November 2023. Stereotactic robotic guidance, using intraoperative imaging and a novel frame-based fiducial, was used for planning and SEEG implantation. Entry-point (EE), target-point (TE), and angular errors were measured, and statistical univariate and multivariate linear regression analyses were performed. Twenty-seven refractory epilepsy patients (aged 15-57 years) undergoing SEEG were reviewed. Sixteen patients had unilateral implantation (10 left-sided, 6 right-sided); 11 patients underwent bilateral implantation. The mean number of electrodes per patient was 18 (SD = 3) with an average registration mean error of 0.768 mm (SD = 0.108). Overall, 486 electrodes were reviewed. Univariate analysis showed significant correlations of lead error with skull thickness (EE: P = .003; TE: P = .012); entry angle (EE: P < .001; TE: P < .001; angular error: P = .030); lead length (TE: P = .020); and order of electrode implantation (EE: P = .003; TE: P = .001). Three multiple linear regression models were used. All models featured predictors of implantation region (157 temporal, 241 frontal, 79 parietal, 9 occipital); skull thickness (mean = 5.80 mm, SD = 2.97 mm); order (range: 1-23); and entry angle in degrees (mean = 75.47, SD = 11.66). EE and TE error models additionally incorporated lead length (mean = 44.08 mm, SD = 13.90 mm) as a predictor. Implantation region and entry angle were significant predictors of error (P ≤ .05). Our study identified 2 primary predictors of SEEG lead error, region of implantation and entry angle, with nonsignificant contributions from lead length or order of electrode placement. Future considerations for SEEG may consider varying regional approaches and angles for more optimal accuracy in lead placement.

Decoding the impact of neighboring amino acids on ESI-MS intensity output through deep learning

Peptide-level quantification using mass spectrometry (MS) is no trivial task as the physicochemical properties affect both response and detectability. The specific amino acid (AA) sequence affects these properties, however the connection between sequence and intensity output remains poorly understood. In this work, we explore combinations of amino acid pairs (i.e., dimer motifs) to determine a potential relationship between the local amino acid environment and MS1 intensity. For this purpose, a deep learning (DL) model, consisting of an encoder-decoder with an attention mechanism, was built. The attention mechanism allowed to identify the most relevant motifs. Specific patterns were consistently observed where a bulky/aromatic and hydrophobic AA followed by a cationic AA as well as consecutive bulky/aromatic and hydrophobic AAs were found important for the prediction of the MS1 intensity. Correlating attention weights to mean MS1 intensities revealed that some important motifs, particularly containing Trp, His, and Cys, were linked with low responding peptides whereas motifs containing Lys and most bulky hydrophobic AAs were often associated with high responding peptides. Moreover, Asn-Gly was associated with low response. The model predicts MS1 response with a mean average percentage error of ∼11 % and a Pearson correlation coefficient of ∼0.64. While dimer representation of peptide sequences did not improve predictive capacity compared to single AA representation in earlier work, this work adds valuable insight for a better understanding of peptide response in MS analysis. SignificanceMass spectrometry is not inherently quantitative, and the response of a compound relies not only on its concentration but also on the molecular composition. For mass spectrometry-based analysis of peptides, such as in bottom-up proteomics, this directly implies that the response cannot be used directly to quantify individual peptides. Moreover, the dependency of the response on the amino acid sequence of individual peptides remains poorly understood. Using a deep learning model based on a recurrent neural network with an attention mechanism, we here investigate how the presence of dimer motifs within a peptide affects the MS1 response through the analysis of intended equimolar peptide pools comprising almost 200,000 unique peptides in total. Not only do we identify certain dimer classes and specific dimers that substantially affect the MS1 response, but the model is also able to predict peptide intensity with low error rates within the independent test subset. The findings not only improve our understanding of the link between sequence and response for peptides but also highlight the potential of utilizing deep learning for developing methods allowing for absolute, label-free peptide quantification.

Hybrid artificial neural networks-based approaches predicting the heat transfer and flow characteristics of manifold microchannels

Aiming at meeting the requirement of high heat flux electronics cooling, the geometric complexity of manifold microchannels as an energy-saving technique has been increasing rapidly. It is well worth exploring optimal prediction models for the heat transfer and flow characteristics of manifold microchannels to reduce computing resources and time costs in the optimization process. In this paper, hybrid prediction approaches based on artificial neural networks are proposed for manifold microchannels. Four optimization algorithms, namely, genetic algorithm, particle swarm optimization algorithm, artificial hummingbird algorithm, and zebra optimization algorithm were adopted to enhance the prediction performance. Initially, all prediction models were trained and tested by a numerical database including six input parameters, and the thermal resistance and pumping power were taken as the target outputs. Compared to the original method, hybrid prediction models show higher accuracy and reliability on the numerical data with regression coefficients beyond 0.987. The prediction model optimized by the artificial hummingbird algorithm shows the best performance with the mean average error for thermal resistance and pumping power decreased by 88.7% and 81.4% respectively. Additionally, the runtime of all prediction models is compared and the model optimized by the zebra optimization algorithm takes the longest time, but is still two orders of magnitude shorter than that of the traditional simulation method. Finally, the generalizability of all prediction models is further validated by a database amassed from six experimental studies on manifold microchannels. The results showed that three hybrid models can provide accurate outputs with regression coefficients beyond 0.84 which differs from the poor prediction of the original method. The model optimized by the zebra optimization algorithm shows superior prediction performance for six individual studies, two fluids, three fin shapes, and wide flow rate conditions. The trained hybrid prediction models in this study perform higher accuracy and can be cost-effective and reliable prediction tools for the rapid optimization process of various manifold microchannel applications.

Electric load prediction using SARIMAX

ABSTRACT Electricity demand variation is one of the prevalent phenomena in Nepal. This variation can cause excess electricity during low-demand periods and a shortage during high-demand periods. An early prediction of electricity demand allows for levelling such fluctuations by introducing dynamic tariffs based on varying demands. This study aims to use Python’s time series models to make predictions about electrical demands and propose a dynamic tariff system. The dataset of Panama City’s hourly electrical load is brought into use. Two models, namely the Seasonal Auto-Regressive Integrated Moving Average with Exogenous Factors (SARIMAX) and the BATS model, are deemed to be the two best time series models. The selection of optimal seasonal and non-seasonal orders in SARIMAX is made by comparing Bayes Information Criterion (BIC). For the SARIMAX model, a daily dataset has been taken by summing the hourly data for each day, whereas for the BATS model, hourly data for the year 2018 has been used. The SARIMAX model resulted in the best fit with the evaluation metrics values: Root Mean Square Error (RMSE) of 975,336.88, Mean Average error (MAE) of 739.09, and R2 score of 0.75. However, SARIMAX’s limitation is that the use of daily data does not allow dynamic tariff prediction, which is possible with the BATS model.

Demand Forecasting in Supply Chain Using Uni-Regression Deep Approximate Forecasting Model

This research presents a uni-regression deep approximate forecasting model for predicting future demand in supply chains, tackling issues like complex patterns, external factors, and nonlinear relationships. It diverges from traditional models by employing a deep learning strategy through recurrent bidirectional long short-term memory (BiLSTM) and nonlinear autoregressive with exogenous inputs (NARX), focusing on regression-based approaches. The model can capture intricate dependencies and patterns that elude conventional approaches. The integration of BiLSTM and NARX provides a robust foundation for accurate demand forecasting. The novel uni-regression technique significantly improves the model’s capability to detect intricate patterns and dependencies in supply chain data, offering a new angle for demand forecasting. This approach not only broadens the scope of modeling techniques but also underlines the value of deep learning for enhanced accuracy in the fluctuating supply chain sector. The uni-regression model notably outperforms existing models in accuracy, achieving the lowest errors: mean average error (MAE) at 1.73, mean square error (MSE) at 4.14, root mean square error (RMSE) at 2.03, root mean squared scaled error (RMSSE) at 0.020, and R-squared at 0.94. This underscores its effectiveness in forecasting demand within dynamic supply chains. Practitioners and decision-makers can leverage the uni-regression model to make informed decisions, optimize inventory management, and enhance supply chain resilience. Furthermore, the findings contribute to the ongoing evolution of supply chain demand forecasting methodologies.

The role of utilizing artificial intelligence and renewable energy in reaching sustainable development goals

Many nations want to use only renewable energy by 2050. Given the recent rapid expansion in RE use in the global energy mix and its progressive impact on the global energy sector, the evaluation and analysis of Renewable Energy's impact on achieving sustainable development goals is insufficient. Wind energy could be renewable. For smart grid supply-and-demand issues, wind power forecasting is critical. One of the biggest challenges of wind energy is its significant fluctuation and intermittent nature, which makes forecasting difficult. This study's goal is to develop data-driven models to predict wind speed and power. This paper uses Machine Learning (ML) and Deep Learning (DL) to improve a wind speed prediction and recommendation system for wind turbine power production using site climatological data. This system optimizes turbine use by selecting the right number of turbines to operate solely based on the required energy, which is related to wind power and speed, and recommends the best power station location to determine the best turbine run time. The Proposed Enhanced Recommendation System (PERS) includes the Wind Speed Prediction Module (WSPM), Wind Speed vs. Power Consumption Calculation (WSPC), and Recommendation Module (RM). Test results showed the suggested method works in run time. The XGBoost or Random Forest regressor predicted 15-day power output with 94 % accuracy and 6 % mean average percentage error.

A monitoring platform based on electrical impedance and AI techniques to enhance the resilience of the built environment

Structural Health Monitoring (SHM) and early warning systems (EWSs) play a pivotal role in enhancing seismic resilience for both buildings and occupants. This paper introduces a monitoring platform that collects electrical impedance data from scaled concrete beams undergoing load and accelerated degradation tests. Artificial Intelligence (AI) algorithms are employed for predictive analysis, scrutinizing historical impedance data, and forecasting future trends. These algorithms adapt to environmental parameters, becoming valuable tools in data-driven decision-making processes. In particular, the study investigates concrete specimens in different test conditions, utilizing a distributed sensor network based on electrical impedance as well as temperature and relative humidity sensors. Real-time data are transmitted to a cloud infrastructure during accelerated degradation tests (both in water and in chloride-rich solution) and in room conditions. An AI-based forecasting approach using Prophet is proposed, ingesting electrical impedance and temperature data, and tested to predict electrical impedance corresponding to approximately 10 % of the time series balancing responsiveness with predictive accuracy, crucial for effective EWS operations and management requirements. The performance of the tested models is evaluated employing metrics such as Mean Average Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and correlation. The proposed approach surpasses statistical methods and deep learning techniques, reporting a MAPE always lower than 3.20 % and a correlation higher than 81.65 % (in wet-dry cycles in water these values are 0.65 Ω and 91.85 %, respectively). This proves to be a promising step towards transparent SHM, which integrates AI models facilitating self-monitoring and early maintenance prediction, thus enhancing the resilience of the built environment.

Predicting sessile droplet evaporation kinetics via cascaded deep networks and tree-based machine learning approach

The intricate nature of sessile droplet evaporation phenomenon makes detailed experimental studies time consuming and requires sophisticated apparatus; while complete numerical simulations are computationally expensive and also time-intensive. In this article, for the first time, we explore the applicability of machine learning (ML) approaches to predict the evaporation kinetics of generalized sessile droplets under various conditions. An in-house dataset, obtained using an experimentally well validated numerical model, is used to develop the ML models: deep artificial neural network (ANN) and decision tree algorithms such as Random Forest (RF) and extreme gradient boosting (XGB). The structures of these models are modified by cascading the output features according to the physics involved. This distinctive approach results in better prediction of the evaporation kinetics than basic ML models. The models are trained by a large set of input parameters for the target variables: viz. droplet evaporation rate, velocity scale, and temperature drop in the solid and liquid domain. Finally, the performance of these ML models is assessed by comparing their predictions with that of physics-based, experimentally validated, numerical models. Results show that the inclusion of additional features obtained using feature engineering significantly improve the prediction performance of ML algorithms, and consistently accurate predictions of droplet evaporation kinetics are obtained. Among various algorithms considered here, the ANN outperforms in term of various error matrices for most of the cases, followed by XGB, and RF models. Also, the highest mean average error (MAE) yield by the ML models for evaporation rate, velocity scale and temperature drop in liquid remains within ∼12.5%. In the case of temperature drop for the solid, the MAE is considerably higher due to large variability of the same target variable. Overall, the work clearly shows that ML algorithms can be used to obtain physically consistent predictions for sessile droplet evaporation parameters.

Adaptive Control Strategies for Enhanced Integration of Solar Power in Smart Grids Using Reinforcement Learning

Integrating solar power into smart grids is challenging because of the variable nature of solar energy. This study focuses on implementing reinforcement learning (RL) using a Deep Q-Network algorithm to enhance the stability and efficiency of a grid. A custom environment was designed using OpenAI Gym, in which real-time simulation of grid operations was conducted using real-time data on solar power, weather, and other grid metrics. The trained RL agent exhibited high predictability in optimally distributing the load and managing the battery storage, with R-squared = 0.886, mean average error = 1,173,046.55 Wh, and root mean squared error = 2,075,515.10 Wh. The model effectively captured the seasonality and daily variations in solar power generation. Forecasting using the proposed model provides insights into future energy trends and uncertainties. The reward function will be further refined and scaled for more complex energy systems by incorporating additional variables and hybrid approaches. This study highlights the potential of RL-based adaptive control strategies for developing more efficient and resilient integration of renewable energy sources into smart grids.

Heat flux partition based on onset of significant void

The thermal log-law Θ+(y+)=β+2.12log(y+) is valid in flow boiling with a value of β that evolves as the flow develops. Using a multiphase flow cross-literature database, this constant is shown to be βOSV=−7 at the point of onset of significant void (OSV). This means that at the OSV the liquid is at saturation temperature up to y+≃30. The OSV predictions using this model have a similar mean average error as the Saha and Zuber 1974 correlation for one less fitted constant for channel, pipe and annular flows for pressure from 1 to 147 bar and Peclet numbers from 3.5⋅103 to 4⋅105. This model is used to build a heat flux partitioning (HFP) inspired from system-scale codes (Lahey 1978). It predicts the distribution of the heat flux between the liquid phase and the evaporation term when the total heat flux is known. It does not give information on the total heat flux as a function of wall temperature and cannot be used to draw a boiling curve. In imposed flux conditions, this partition provides more coherent flux distribution between the evaporation and liquid terms than Kurul and Podowski (1990) based approaches and improves void fraction predictions in high-subcooling regions on the DEBORA database (Garnier et al. 2001) and on experiments by Bartolomei and Chanturiya (1967) and Bartolomei et al. (1982). When the wall temperature is imposed, it must be coupled with an empirical boiling total heat flux correlation to replace a traditional HFP. The prediction of the total heat flux is then as good as that of the correlation.

Forecasting the incidence frequencies of schizophrenia using deep learning

Mental disorders are becoming increasingly prevalent worldwide, and accurate incidence forecasting is crucial for effective mental health strategies. This study developed a long short-term memory (LSTM)-based recurrent neural network model to predict schizophrenia in inpatients in Taiwan. Data was collected on individuals aged over 20 years and diagnosed with schizophrenia between 1998 and 2015 from the National Health Insurance Research Database (NHIRD). The study compared six models, including LSTM, exponential smoothing, autoregressive integrated moving average, particle swarm optimization (PSO), PSO-based support vector regression, and deep neural network models, in terms of their predictive performance. The results showed that the LSTM model had the best accuracy, with the lowest mean absolute percentage error (2.34), root mean square error (157.42), and mean average error (154,831.70). This finding highlights the reliability of the LSTM model for forecasting mental disorder incidence. The study's findings provide valuable insights that can help government administrators devise clinical strategies for schizophrenia, and policymakers can use these predictions to formulate healthcare education and financial planning initiatives, fostering support networks for patients, caregivers, and the public.

Periodically activated physics-informed neural networks for assimilation tasks for three-dimensional Rayleigh–Bénard convection

We apply physics-informed neural networks to three-dimensional Rayleigh–Bénard convection in a cubic cell with a Rayleigh number of Ra=106 and a Prandtl number of Pr=0.7 to assimilate the velocity vector field from given temperature fields and vice versa. With the respective ground truth data provided by a direct numerical simulation, we are able to evaluate the performance of the different activation functions applied (sine, hyperbolic tangent and exponential linear unit) and different numbers of neurons (32, 64, 128, 256) for each of the five hidden layers of the multi-layer perceptron. The main result is that the use of a periodic activation function (sine) typically benefits the assimilation performance in terms of the analyzed metrics, correlation with the ground truth and mean average error. The higher quality of results from sine-activated physics-informed neural networks is also manifested in the probability density function and power spectra of the inferred velocity or temperature fields. Regarding the two assimilation directions, the assimilation of temperature fields based on velocities appears to be more challenging in the sense that it exhibits a sharper limit on the number of neurons below which viable assimilation results cannot be achieved.

Partial reconstruction of sparse and incomplete point clouds applied to the generation of corneal topographic maps of healthy and diseased patients

The presence of unmeasured areas or areas with missing data in corneal topographies greatly affect the quality of digital corneal models. These are more frequent in posterior than in anterior corneal surface. This work seeks to complete and improve digital corneal models generated from incomplete point clouds obtained with commercial tomographic equipment, applying three interpolation/extrapolation techniques based on population data (Polynomial, Biharmonic Splines and Cubic Radial Base Functions). 43 personalized corneal models of patients with different grades of keratoconus were used to test each interpolation method. All interpolation results were compared using the Mean Average Percentage Error (MAPE) index, observing that it is possible to interpolate/extrapolate up to the radius 5.2 mm on the anterior face and up to 4.2 mm on the posterior face in general, but none of the methods stand out above the others for all the situations considered. Consequently, extrapolation method must be chosen carefully.

Study on the key factors affecting the performance of shield scrapers in gravelly soil strata

Gravelly soil strata exhibit heterogeneity and nonlinearity in their physical and mechanical properties, leading to volatile fluctuations of shield scraper force. Understanding the performance of shield scrapers in gravelly soils is significant for the safe and efficient excavation of tunnel boring machines. This paper conducts unconsolidated-undrained triaxial tests to obtain the mechanical properties of gravelly soils with gravel content ranging from 0 % to 30 %. The process of shield scrapers cutting through gravelly soils is analyzed by combining the varying mechanical properties of gravelly soils with the limit equilibrium analysis method. Subsequently, modified models for predicting the scraper force and specific energy in gravelly soils are established. Based on these models, the impact of key factors on the scraper performance is analyzed. Laboratory experiments are further performed on a rotary test bench to validate these models. The experimental results demonstrate that the horizontal cutting force and specific energy of shield scrapers in gravelly soils can be predicted with mean average errors of 8.8 % and 7.3 %, respectively, with the errors of all predicted values falling within ±20 % of the experimental results. These established models can serve as useful references for the structural and operational design of shield scrapers in gravelly soil strata.

SUSCEPTIBLE VACCINATED INFECTED RECOVERED SUSCEPTIBLE MODEL: EQUILIBRIA POINTS AND APPLICATION ON COVID-19 CASE DATA IN INDONESIA

Severe Respiratory Syndrome Coronavirus-2 is the infectious agent that causes COVID-19. A vaccine program is an effort to stop the spread of COVID-19 infections in Indonesia. The susceptible vaccinated infected recovered susceptible (SVIRS) model can be used to represent the spread of infectious diseases. This study aims to construct the SVIRS model, identify the equilibria points thus apply it to COVID-19 case data in Indonesia, and determine transmission patterns, model accuracy, and interpretation. Literature and applications are the research methodologies employed. First-order nonlinear differential equations form the obtained SVIRS model. The model has two equilibrium points: a disease-free equilibrium point, and the other is endemic equilibrium point. The SVIRS model on the spread of COVID-19 in Indonesia was obtained using daily secondary data from January 11 to November 30, 2022. The model is solved by the fourth-order Runge-Kutta method. The model’s accuracy is accurate enough to explain the spread of COVID-19 in Indonesia with a mean average percentage error (MAPE) value of 43%. According to the transmission pattern, the number of COVID-19 cases in Indonesia peaked on July 27, 2022, then decreased to zero, obtaining an equilibrium point when no more cases of the disease were present.