Accurate Model Research Articles

Accurate Modeling and Optimal Rotor Flux Control of a Bearingless Induction Motor With the Specific Pole

Accurate Modeling and Optimal Rotor Flux Control of a Bearingless Induction Motor With the Specific Pole

Accurate Prediction and Modeling of Overbreak Phenomenon in Tunnel Excavation Using Rock Engineering System Method

Accurate Prediction and Modeling of Overbreak Phenomenon in Tunnel Excavation Using Rock Engineering System Method

Pole placement tuning of proportional integral derivative feedback controller for knee extension model

Functional electrical stimulation (FES) has shown potential in rehabilitative exercises for patients recovering from spinal cord injuries. In recent developments, conventional open-loop FES control techniques have evolved into closed-loop systems that employ feedback controllers for automation. However, closed-loop FES systems often face challenges due to muscle non-linear effects, such as fatigue, time delays, stiffness, and spasticity. Therefore, an accurate non-linear knee model is required during the design stage, and precise tuning of the feedback controller parameters is vital. A proportional– integral–derivative (PID) controller is commonly used as a feedback controller due to its simplicity and ease of implementation. However, most PID tuning methods are complex and time consuming. This paper investigates the viability of employing the pole placement technique for tuning a PID controller that regulates the non-linear knee extension model. The pole placement method aims to improve the control and adaptability of the PID controller in closed-loop FES systems, specifically by facilitating knee extension exercises. MATLAB Simulink was used to assess the effectiveness of this tuning approach. Results showed that the PID controller performed satisfactorily without non-linearities, but performance varied with the inclusion of specific non-linearities. The pole placement tuning method facilitated preliminary assessments of PID controller performance, preceding highly advanced optimization.

Sensitivity and feature importance of climate factors and evaluation of different machine learning models for predicting fire hotspots in Kalimantan, Indonesia

<p>Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still little research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares several machine learning methods to predict hotspots in Kalimantan. Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Some of the machine learning methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, several measures of sensitivity and feature importance used are variance-based, density-based, and distribution-based sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the ML model concluded that the Bayesian linear regression model outperformed other ML models, based on RMSE and explained variance score. Meanwhile, tree-based models, such as random forest and gradient boosting, are indicative of overfit. Based on the results of sensitivity analysis and feature importance, the number of dry days is the most important feature for the Bayesian linear regression model in predicting the number of hotspots in Kalimantan.</p>

Development of a fed-batch-scale anaerobic co-digestion control system based on multivariable output error state space and model predictive control

This paper describes a feeding control system for fed-batch-scale anaerobic co-digestion. The proposed system is based on the multivariable output error state space and uses model predictive control to regulate the biogas flow output of anaerobic co-digestion. This control system combines predictive modeling, receding-horizon optimization, and state feedback. An accurate linear model of anaerobic co-digestion is obtained through the multivariable output error state space method using experimental data, and the accuracy of the model is evaluated using a goodness-of-fit index and the root mean square error. After augmenting the model, a predictive control system is established. The system states are observed through a Kalman filter, and the constrained receding-horizon optimization problem is solved using quadratic programming. Finally, the stability of the control system is demonstrated from both open- and closed-loop perspectives. The control system is then constructed and used in actual experiments, with the target flow output set at 100 NmL/h. The final flow output indicates that the control system achieves good control performance. This research enables the biogas output of anaerobic co-digestion to be controlled from a linear perspective through a concise control algorithm with strong practical application prospects.

ProkDBP: Toward more precise identification of prokaryotic DNA binding proteins.

Prokaryotic DNA binding proteins (DBPs) play pivotal roles in governing gene regulation, DNA replication, and various cellular functions. Accurate computational models for predicting prokaryotic DBPs hold immense promise in accelerating the discovery of novel proteins, fostering a deeper understanding of prokaryotic biology, and facilitating the development of therapeutics targeting for potential disease interventions. However, existing generic prediction models often exhibit lower accuracy in predicting prokaryotic DBPs. To address this gap, we introduce ProkDBP, a novel machine learning-driven computational model for prediction of prokaryotic DBPs. For prediction, a total of nine shallow learning algorithms and five deep learning models were utilized, with the shallow learning models demonstrating higher performance metrics compared to their deep learning counterparts. The light gradient boosting machine (LGBM), coupled with evolutionarily significant features selected via random forest variable importance measure (RF-VIM) yielded the highest five-fold cross-validation accuracy. The model achieved the highest auROC (0.9534) and auPRC (0.9575) among the 14 machine learning models evaluated. Additionally, ProkDBP demonstrated substantial performance with an independent dataset, exhibiting higher values of auROC (0.9332) and auPRC (0.9371). Notably, when benchmarked against several cutting-edge existing models, ProkDBP showcased superior predictive accuracy. Furthermore, to promote accessibility and usability, ProkDBP (https://iasri-sg.icar.gov.in/prokdbp/) is available as an online prediction tool, enabling free access to interested users. This tool stands as a significant contribution, enhancing the repertoire of resources for accurate and efficient prediction of prokaryotic DBPs.

An advanced approach for accurate pneumonia detection using combined deep convolutional neural networks

Pneumonia, a lung infection caused by viral or bacterial agents, poses a significant health risk by affecting one or both lungs in humans. Accurate diagnosis, particularly in pediatric cases, is crucial for timely intervention. chest X-rays (CXRs) are a common and non-invasive diagnostic tool to detect pneumonia-related abnormalities. Nonetheless, the minimal radiation exposure suitable for pediatric diagnosis poses a challenge in accurately detecting pneumonia in children. This work proposes a concatenation model that combines two pre-trained convolutional neural networks (CNNs) depending on the transfer learning (TL) technique and optimizes the training parameters to build a highly accurate model for detecting pediatric pneumonia from CXR images. The concatenated extracted features from the two pre-trained CNNs are passed through a convolutional layer to select more valuable semantic features to reduce the extracted features, which helps reduce the model parameters and execution time. Experimental results demonstrate that the feature concatenation technique, along with optimization of training parameters, surpasses the performance of individual CNNs and several state-of-the-art methods. The proposed method achieves a classification accuracy of 98.5%, precision of 99.5%, sensitivity of 98.4%, and F1 score of 99.1%. The primary objective of the proposed approach is to aid radiologists in achieving accurate pneumonia diagnosis in real-time.

Analysis of the Electromagnetic Effects on the Large Floating Roof Oil Tanks by nearby Lightning Strike Based on TLM

Lightning fire is one of the biggest dangers for chemical and petrochemical storage tank farms, particularly in floating roof oil tanks (FROTs). To improve the lightning protection of FROTs, the process of floating roof tanks affected by lightning is analyzed. Lightning inductive effects can result in the undesired operation of the above-ground storage tank equipment and endanger exploitation safety. The time domain finite element analysis based on the transmission line model (TLM) method is regarded as a numerical technique to solve field problems by implementing circuit equivalents. This study aims to analyze lightning strike characteristics using the Heidler current function and simulate electromagnetic field strength (EMFS) distribution and surface current density (SCD). Calculation of minimum possible effective strike distance and shielding effectiveness (SE) is performed. Parametric modeling ensures accurate modeling of the roof's bypass conductor to the shell. By utilizing the Parameter Sweep technique, multiple simulations can be carried out with varying structure parameter values. This approach ensures optimal efficiency and accuracy in the results obtained.

Predicting mortality within 1 year of ART initiation in children and adolescents living with HIV in sub-Saharan Africa: a retrospective observational cohort study

Differentiated service delivery (DSD) for children and adolescents living with HIV can improve targeted resource use. We derived a mortality prediction score to guide clinical decision making for children and adolescents living with HIV. Data for this retrospective observational cohort study were evaluated for all children and adolescents living with HIV and initiating antiretroviral therapy (ART); aged 0-19 years; and enrolled at Baylor clinics in Eswatini, Malawi, Lesotho, Tanzania, and Uganda between 2005 and 2020. Data for clinical prediction, including anthropometric values, physical examination, ART, WHO stage, and laboratory tests were captured at ART initiation. Backward stepwise variable selection and logistic regression were performed to develop predictive models for mortality within 1 year of ART initiation. Probabilities of mortality were generated, compared with true outcomes, internally validated, and evaluated against WHO advanced HIV criteria. The study population included 16 958 children and adolescents living with HIV and initiated on ART between May 18, 2005, and Dec 18, 2020. Predictive variables for the most accurate model included: age, CD4 percentage, white blood cell count, haemoglobin concentration, platelet count, and BMI Z score as continuous variables, and WHO clinical stage and oedema, abnormal muscle tone and respiratory distress on examination as categorical variables. The area under the curve (AUC) of the predictive model was 0·851 (95% CI 0·839-0·863) in the training set and 0·822 (0·800-0·845) in the test set, compared with 0·606 (0·595-0·617) for the WHO advanced HIV criteria (p<0·0001). This study evaluated a large, multinational population to derive a mortality prediction tool for children and adolescents living with HIV. The model more accurately predicted clinical outcomes than the WHO advanced HIV criteria and has the potential to improve DSD for children and adolescents living with HIV in high-burden settings. National Institute of Health Fogarty International Center.

Modeling realistic synaptic inputs of CA1 hippocampal pyramidal neurons and interneurons via Adaptive Generalized Leaky Integrate-and-Fire models

Computational models of brain regions are crucial for understanding neuronal network dynamics and the emergence of cognitive functions. However, current supercomputing limitations hinder the implementation of large networks with millions of morphological and biophysical accurate neurons. Consequently, research has focused on simplified spiking neuron models, ranging from the computationally fast Leaky Integrate and Fire (LIF) linear models to more sophisticated non-linear implementations like Adaptive Exponential (AdEX) and Izhikevic models, through Generalized Leaky Integrate and Fire (GLIF) approaches. However, in almost all cases, these models are tuned (and can be validated) only under constant current injections and they may not, in general, also reproduce experimental findings under variable currents. This study introduces an Adaptive GLIF (A-GLIF) approach that addresses this limitation by incorporating a new set of update rules. The extended A-GLIF model successfully reproduces both constant and variable current inputs, and it was validated against the results obtained using a biophysical accurate model neuron. This enhancement provides researchers with a tool to optimize spiking neuron models using classic experimental traces under constant current injections, reliably predicting responses to synaptic inputs, which can be confidently used for large-scale network implementations.

An online battery–state of charge estimation method using the varying forgetting factor recursive least square - unscented Kalman filter algorithm on electric vehicles

Accurate and fast estimation of the state of charge is important for the battery management system of electric vehicles. This paper proposes a method to estimate the state of charge of Lithium-ion batteries by the &lt;span lang="EN-US"&gt;variable&lt;/span&gt; forgetting factor recursive least square (VFFRLS) – unscented Kalman filter (UKF) algorithm in real-time without the off-line battery testing data. Since the state observation requires an accurate model, an equivalent circuit model was constructed. Then, the VFFRLS algorithm is used to identify online the battery model parameters based on voltage and current measurements. An advantage of this algorithm is that it requires less initial information and shorter identification time than offline parameter identification. After the model parameters are well identified, the unscented Kalman filter estimates the state of charge and minimizes noise characteristics and uncertainty in the parameter identification process. The VFFRLS algorithm applied in this paper has shown a good result with the model output error of less than 1%, and the identification achieves real-time response. The state of charge obtained by the UKF algorithm has shown satisfactory estimation results with fast convergence speed and small errors. The UKF filter provides the results with a 1.5% error from the reference and converges after 10 cycles.

Phishing Website Detection

Abstract: Phishing is an online threat where an attacker impersonates an authentic and trustworthy organization to obtain sensitive information from a victim. One example of such is trolling, which has long been considered a problem. However, recent advances in phishing detection, such as machine learning-based methods, have assisted in combatting these attacks. Therefore, this paper develops and compares four models for investigating the efficiency of using machine learning to detect phishing domains. It also compares the most accurate model of the four with existing solutions in the literature. The work carried out in this study is an update in the previous systematic literature surveys with more focus on the latest trends in phishing detection techniques. This study enhances readers' understanding of different types of phishing website detection techniques, the data sets used, and the comparative performance of algorithms used. Our findings show that the model based on the K means clustering is the most accurate of the other four techniques and outperforms other solutions in the literature.

Computational modelling of tyre behavior on concrete and sandy soil surfaces using solid works software

Tyres are integral components of vehicles, crucial for controlling movement, supporting vehicle weight, and providing traction. Consequently, there's a growing need for accurate tyre modelling to optimize performance under varying conditions. While extensive literature exists on tyre-soil interaction, information is scarce regarding tyre behaviour across different soil types. This study aims to address this gap by employing computational modelling techniques to analyse tyre behaviour on two distinct surfaces: concrete and sandy soil. Utilizing SolidWorks software, a comprehensive investigation was conducted to evaluate tyre performance under varying road conditions. The study focused on analysing shear forces, soil resistances, and partial soil resistant forces exerted on the tyres. The findings indicate that tyres exhibit superior performance on concrete surfaces compared to sandy soil. The computational simulations predicted shear forces of 0.6 kN, soil resistances of 0.2 kN, and partial soil resistant forces of 0.25 kN for the concrete surfaces. These results were notably higher than those observed on sandy soil surfaces. This study sheds light on the intricate dynamics of tyre behaviour under different road conditions and underscores the importance of computational modelling in understanding and optimizing tyre performance. The insights gained from this research have significant implications for vehicle design, road engineering, and the development of more efficient and durable tyres tailored to specific environmental conditions.

Estimation of the mean effective pressure of a spark ignition internal combustion engine using a neural network, considering the wall-wetting dynamics

The management and development of internal combustion engines stand as critical pursuits within the automotive and related industries. Utilizing cylinder pressure as feedback, engine controllers rely on intricate systems to regulate performance. However, due to the inherent complexity and nonlinearity of engines, direct measurement of cylinder pressure through pressure sensors is costly and computationally demanding. Consequently, the need for accurate and detailed engine models becomes paramount. Neural networks offer a promising avenue for simulating internal combustion engines, combining speed and precision. By treating the engine as an enigmatic entity, neural networks can construct detailed models. This study aims to employ two types of neural networks—multilayer perceptron and radial basis functions—to train and build a model of an internal combustion engine. These networks will simulate and estimate the engine's mean suitable pressure, allowing for a comparison of their effectiveness. Prior to implementing the neural network architecture, an engine model was constructed in MATLAB to gather necessary training data. This preliminary step ensured a robust foundation for subsequent network design and implementation. In summary, this research focuses on leveraging neural networks to model internal combustion engines, utilizing both multilayer perceptron and radial basis functions to simulate engine behavior and estimate mean suitable pressure.

Utilities for Complications Associated with Type 2 Diabetes: A Review of the Literature.

Utility values are used in health economic modeling analyses of type 2 diabetes (T2D) to quantify the effect of acute and long-term complications on quality of life (QoL). For accurate modeling projections, it is important that the utility values used are up to date, accurate and representative of the simulated model cohort. A literature review was performed to identify utility values for health states representing acute and chronic T2D-related complications including cardiovascular complications, stroke, renal disease, ophthalmic complications, neuropathy, diabetic foot, amputation and hypoglycemia. Searches were performed using the PubMed, Embase and Cochrane Library databases and limited to articles published since 2010. Supplementary searches were performed to identify data published at congresses in 2019-2023. A total of 54 articles were identified that reported utility values for T2D-related complications. The most frequently used elicitation method/instrument was the EQ-5D (n = 42 studies) followed by the Short Form-6 dimensions (n = 6), time tradeoff (n = 5), the Health Utilities Index Mark 2 or Mark 3 (n = 2), 15D (n = 1), visual analog scale (n = 1) and standard gamble (n = 1). Stroke and amputation were consistently associated with the largest decrements in QoL. There is a lack of published data that distinguishes between severity of several complications including renal disease, retinopathy and neuropathy. Diabetes-related complications can have a profound impact on QoL; therefore, it is important that these are captured accurately and appropriately in health economic models. Recently published utility values for diabetes-related complications that can be used to inform health economic models are summarized here.

An in-depth analysis of data reduction methods for sustainable deep learning

In recent years, Deep Learning has gained popularity for its ability to solve complex classification tasks, increasingly delivering better results thanks to the development of more accurate models, the availability of huge volumes of data and the improved computational capabilities of modern computers. However, these improvements in performance also bring efficiency problems, related to the storage of datasets and models, and to the waste of energy and time involved in both the training and inference processes. In this context, data reduction can help reduce energy consumption when training a deep learning model. In this paper, we present up to eight different methods to reduce the size of a tabular training dataset, and we develop a Python package to apply them. We also introduce a representativeness metric based on topology to measure how similar are the reduced datasets and the full training dataset. Additionally, we develop a methodology to apply these data reduction methods to image datasets for object detection tasks. Finally, we experimentally compare how these data reduction methods affect the representativeness of the reduced dataset, the energy consumption and the predictive performance of the model.

Normscan: open-source Python software to create average models from CT scans.

Age-matched average 3D models facilitate both surgical planning and intraoperative guidance of cranial birth defects such as craniosynostosis. We aimed to develop an algorithm that accepts any number of CT scans as input and generates highly accurate, average models with minimal user input that are ready for 3D printing and clinical use. Using a compiled database of 'normal' pediatric computed tomography (CT) scans, we report Normscan, an open-source platform built in Python that allows users to generate normative models of CT scans through user-defined landmarks. We use the basion, nasion, and left and right porions as anatomical landmarks for initial correspondence and then register the models using the iterative closest points algorithm before downstream averaging. Normscan is fast and easy to use via our user interface and also creates highly accurate average models of any number of input models. Additionally, it is highly repeatable, with coefficients of variance for the surface area and volume of the average model being less than 3% across ten independent trials. Average models can then be 3D printed and/or visualized in augmented reality. Normscan provides an end-to-end pipeline for the creation of average models of skulls. These models can be used for the generation of databases of specific demographic anatomical models as well as for intraoperative guidance and surgical planning. While Normscan was designed for craniosynostosis repair, due to the modular nature of the algorithm, Normscan has many applications in other areas of surgical planning and research.

Research on wind resistance principles and design of super high-rise buildings

Due to the high and flexible characteristics of super high-rise buildings, the structure is very sensitive to wind loads, and wind vibration effects and comfort are issues that cannot be ignored in the structural design of super high-rise buildings. The paper mainly introduces the problems in wind resistance design of super high-rise buildings. Including wind load values, wind vibration effects, and vibration control methods and applications. The result show that the wind induced vibration effect and comfort of the structure are often determined through wind tunnel tests. For super high-rise buildings with complex structural forms. There are two methods for controlling wind-induced vibration in high-rise buildings: Optimizing structural form through architectural methods; Take structural control measures. At the same time, with the cost of high-performance materials and engineering technologies, it is a challenge to find building materials and technologies that can meet wind resistance requirements while keeping costs in check. However, as computational technology continues to evolve, the wind-resistant design of tall buildings will benefit from more accurate wind-tunnel simulations and computational modelling, which will help to better predict and address wind-resistance challenges. Scientists and engineers will continue to research novel materials and structural designs to improve the wind resistance of tall buildings and reduce costs.

Evaluating nomogram models for predicting survival outcomes in gastric gastrointestinal stromal tumors with SEER database analysis

Gastrointestinal stromal tumors (GISTs) predominantly develop in the stomach. While nomogram offer tremendous therapeutic promise, there is yet no ideal nomogram comparison customized specifically for handling categorical data and model selection related gastric GISTs. (1) We selected 5463 patients with gastric GISTs from the SEER Research Plus database spanning from 2000 to 2020; (2) We proposed an advanced missing data imputation algorithm specifically designed for categorical variables; (3) We constructed five Cox nomogram models, each employing distinct methods for the selection and modeling of categorical variables, including Cox (Two-Stage), Lasso-Cox, Ridge-Cox, Elastic Net-Cox, and Cox With Lasso; (4) We conducted a comprehensive comparison of both overall survival (OS) and cancer-specific survival (CSS) tasks at six different time points; (5) To ensure robustness, we performed 50 randomized splits for each task, maintaining a 7:3 ratio between the training and test cohorts with no discernible statistical differences. Among the five models, the Cox (Two-Stage) nomogram contains the fewest features. Notably, at Near-term, Mid-term, and Long-term intervals, the Cox (Two-Stage) model attains the highest Area Under the Curve (AUC), top-1 ratio, and top-3 ratio in both OS and CSS tasks. For the prediction of survival in patients with gastric GISTs, the Cox (Two-Stage) nomogram stands as a simple, stable, and accurate predictive model with substantial promise for clinical application. To enhance the clinical utility and accessibility of our findings, we have deployed the nomogram model online, allowing healthcare professionals and researchers worldwide to access and utilize this predictive tool.

Investigating Dual-Source Satellite Image Data and ALS Data for Estimating Aboveground Biomass

Accurate estimation of above-ground biomass (AGB) in forested areas is essential for studying forest ecological functions, surface carbon cycling, and global carbon balance. Over the past decade, models that harness the distinct features of multi-source remote sensing observations for estimating AGB have gained significant popularity. It is worth exploring the differences in model performance by using simple and fused data. Additionally, quantitative estimation of the impact of high-cost laser point clouds on satellite imagery of varying costs remains largely unexplored. To address these challenges, model performance and cost must be considered comprehensively. We propose a comprehensive assessment based on three perspectives (i.e., performance, potential and limitations) for four typical AGB-estimation models. First, different variables are extracted from the multi-source and multi-resolution data. Subsequently, the performance of four regression methods is tested for AGB estimation with diverse indicator combinations. Experimental results prove that the combination of multi-source data provides a highly accurate AGB regression model. The proposed regression and variables rating approaches can flexibly integrate other data sources for modeling. Furthermore, the data cost is discussed against the AGB model performance. Our study demonstrates the potential of using low-cost satellite data to provide a rough AGB estimation for larger areas, which can allow different remote sensing data to meet different needs of forest management decisions.