Comparative Analysis Of Models Research Articles

Predictive Modelling of Postpartum Haemorrhage Using Early Risk Factors: A Comparative Analysis of Statistical and Machine Learning Models.

Postpartum haemorrhage (PPH) is a significant cause of maternal morbidity and mortality worldwide, particularly in low-resource settings. This study aimed to develop a predictive model for PPH using early risk factors and rank their importance in terms of predictive ability. The dataset was obtained from an observational case-control study in northern Rwanda. Various statistical models and machine learning techniques were evaluated, including logistic regression, logistic regression with elastic-net regularisation, Random Forests, Extremely Randomised Trees, and gradient-boosted trees with XGBoost. The Random Forest model, with an average sensitivity of 80.7%, specificity of 71.3%, and a misclassification rate of 12.19%, outperformed the other models, demonstrating its potential as a reliable tool for predicting PPH. The important predictors identified in this study were haemoglobin level during labour and maternal age. However, there were differences in PPH risk factor importance in different data partitions, highlighting the need for further investigation. These findings contribute to understanding PPH risk factors, highlight the importance of considering different data partitions and implementing cross-validation in predictive modelling, and emphasise the value of identifying the appropriate prediction model for the application. Effective PPH prediction models are essential for improving maternal health outcomes on a global scale. This study provides valuable insights for healthcare providers to develop predictive models for PPH to identify high-risk women and implement targeted interventions.

Multiphysics performance evaluation of thermoelectric generator arrays

Thermoelectric generators (TEGs) are widely used nowadays in heat recovery and power generation applications. TEGs are connected in series and/or parallel configurations in an array to meet the voltage and/or current requirements of electric load. Therefore, it is necessary to examine the electrical performance of different TEG array configurations employed in TEG systems. In the present study, an experimentally validated hydro-thermoelectric multiphysics computational model is employed by integrating the computational fluid dynamics (CFD) approach with the TEG model to test the electrical performance of various TEG array configurations and determined load voltage, current, associated power, and conversion efficiency. Each TEGs array configuration’s performance is evaluated by varying the hot water temperature from 27 °C to 42 °C as well as hot and cold water flowrate from 0.5 L/min to 2 L/min. Various configurations including series and a combination of series and parallel connections were designed. The findings show that the series configuration of the TEGs array generates higher electric power than series and parallel combined configurations whereas the latter achieves the maximum power point at a higher electric current than the series configuration. The comparative analysis of CFD model with the experimental results indicates a maximum discrepancy of 7 %. For thermoelectric power-generating systems, the proposed model might serve as a benchmark for optimizing TEGs array configurations according to the electric load requirements.

Towards a Practical Study: Unraveling Job Satisfaction Through Models and Measurement Tools

Towards a Practical Study: Unraveling Job Satisfaction Through Models and Measurement Tools

Enhanced Diabetic Retinopathy Diagnosis: A Comparative Analysis of models with an Ensemble classifier and Deep Q Learning

- A novel method that combines the strengths of different classifiers such as Naive Bayes, Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM) is introduced in this paper. This method tackles the urgent need for cutting-edge diagnostic methods in the field of ophthalmology, mainly for the identification of diabetic retinopathy (DR). The approach is ensemble-based. Classical methods in retinal analysis of images often fail as they are static and are unable to adjust to the unique details that each distinct image presents. This constraint results in less accurate and precise diagnostic results, highlighting the urgent need for more adaptable and dynamic methods. The suggested model differs significantly from previous methods. Through the use of an ensemble approach, it capitalizes on the distinct advantages of each classifier: the MLP process's sophisticated feature extraction skill, Naive Bayes' probabilistic analysis, and SVM's non-linear pattern recognition capacity. By combining these techniques, the inherent drawbacks of utilizing a single strategy are addressed, guaranteeing a more thorough examination of retinal samples and images. The core of this idea is the system using Deep Q Learning (DQL) for adaptive classifier selection. Using learned Q Values for various contexts, this reinforcement learning technique selects the best classifier adaptively for each unique retinal image, hence optimizing the ensemble. This approach not only advances diagnosis accuracy and precision but also guarantees ongoing learning and adaptation to keep up with changing data patterns and advances in imaging technology. Extensive experiments on the IDRiD & EyePACS Dataset show the effectiveness of this model with a 5.5% increase in overall accuracy with other performance metrics, the results show a significant improvement over the current method. They represent a significant advancement in the timely and accurate identification of diabetic retinopathy, which will ultimately benefit patients and lessen the strain on healthcare systems. Thus, this work represents a major step forward in patient care as well as a technological advance, opening the door to more efficient supervision and treatment of retinal illnesses.

Diagnostic and comparative analysis of dark energy models with q(z) parametrizations

Diagnostic and comparative analysis of dark energy models with q(z) parametrizations

Advancements in predicting scour depth induced by turbulent wall jets: A comparative analysis of mathematical formulations and machine learning models

This study examines the scour depth induced by turbulent wall jets and proposes novel mathematical formulations to predict the depth of scouring. Through a comprehensive gamma test, key parameters influencing the scour depth are identified, including the apron length, densimetric Froude number, median sediment size, tailwater level, Reynolds number, and Froude number of the jet. Regression analysis is subsequently conducted to establish relationships between the dependent parameter and the aforementioned independent variables. A comparative analysis is then undertaken between the measured scour depths and those predicted by existing equations from previous studies. Furthermore, predictive models leveraging the support vector machine, artificial neural network with particle swarm optimization, M5 tree algorithm, gene expression programming, and adaptive neuro-fuzzy inference system (ANFIS) are developed using the collected data. Statistical metrics are employed to evaluate the performance of each model and the regression equation. The effectiveness of each model in predicting scour depth is demonstrated. Notably, ANFIS yields a coefficient of determination of 0.809 and a root mean square error (RMSE) of 1.585. Multi-nonlinear regression analysis exhibits a coefficient of determination of 0.752 and an RMSE of 0.421, while the M5 tree achieves a coefficient of determination of 0.739 and an RMSE of 1.874, demonstrating superior performance compared to other machine learning techniques and regression equations employed in this study.

Evaluating Deep Learning Techniques for Detecting Aneurysmal Subarachnoid Hemorrhage: A Comparative Analysis of Convolutional Neural Network and Transfer Learning Models

Machine learning (ML) and deep learning (DL) techniques offer a promising multidisciplinary solution for subarachnoid hemorrhage (SAH) detection. The novel transfer learning approach mitigates the time constraints associated with the traditional techniques and demonstrates a superior performance. This study aims to evaluate the effectiveness of convolutional neural networks (CNNs) and CNN-based transfer learning models in differentiating between aneurysmal subarachnoid hemorrhage (aSAH) and nonaneurysmal subarachnoid hemorrhage (naSAH). Data from Istanbul Ümraniye Training and Research Hospital, which included 15,600 DICOM images from 123 patients with aSAH and 7,793 images from 80 patients with naSAH, were used. The study employed four models: Inception-V3, EfficientNetB4, single-layer CNN, and three-layer CNN. Transfer learning models were customized by modifying the last three layers and using the Adam optimizer. The models were trained on Google Collaboratory and evaluated based on metrics such as F-score, precision, recall, and accuracy. EfficientNetB4 demonstrated the highest accuracy (99.92%), with a better F-score (99.82%), recall (99.92%), and precision (99.90%) than the other methods. The single- and three-layer CNNs and the transfer learning models produced comparable results. No overfitting was observed, and robust models were developed. CNN-based transfer learning models can accurately diagnose the etiology of SAH from CT images and is a valuable tool for clinicians. This approach could reduce the need for invasive procedures such as digital subtraction angiography, leading to more efficient medical resource utilization and improved patient outcomes.

Predicting Liquefaction Susceptibility in North-East Morocco: Comparative Analysis of Semi-empirical Methods and UBC3D-PLM Model

Predicting Liquefaction Susceptibility in North-East Morocco: Comparative Analysis of Semi-empirical Methods and UBC3D-PLM Model

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models

BackgroundAdvances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive. ObjectiveThis study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database. MethodsWe conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT. ResultsOur multimodal model achieved a lead time of at least 12 h ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT. ConclusionOur study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

Comparative Analysis Of Machine Learning And Deep Learning Models Integrated With Altman Z-Score For Financial Distress Prediction In Companies Listed On The Indonesia Stock Exchange (IDX)

Financial distress is a condition in which a company experiences a decline in its financial situation, which is typically temporary. However, financial distress can worsen if not promptly addressed, leading to bankruptcy. Early identification of potential financial distress in a company is crucial for stakeholders such as investors, creditors, and regulators. In practice, predicting financial distress in a company is not an easy task. One of the methods commonly used to identify early symptoms of financial distress is the method introduced by Altman in 1986. Altman's research model, known as the Z-Score, determines a value based on standard calculations of financial ratios to indicate the likelihood of a company experiencing bankruptcy. The use of artificial intelligence, such as deep learning, can enhance the scope of research on the analysis and prediction of financial distress. This study aims to conduct a comparative analysis of machine learning models, such as the K-Nearest Neighbor Classifier and Random Forest Classifier, and deep learning models, such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). This analysis is carried out to evaluate the success rate of the proposed deep learning models in predicting financial distress in companies operating in Indonesia. Based on the conducted research, the K-Nearest Neighbor Classifier algorithm achieved an accuracy of 77.42% during testing and 88.89% during validation, the Random Forest Classifier algorithm achieved an accuracy of 87.09% during testing and 95.24% during validation, the CNN model achieved an accuracy of 95.16% during testing and 96.83% during validation, and the RNN model achieved an accuracy of 93.55% during testing and 96.83% during validation. Based on these results, the deep learning method has a higher average success rate than machine learning models in predicting financial distress.

Comparative analysis and implementation of a transformative business and supply chain model for the FMCG sector in Africa and the USA

This paper conducts a comparative analysis of business and supply chain models in the Fast Moving Consumer Goods (FMCG) sector between Africa and the USA, aiming to identify transformative strategies for enhancing efficiency, sustainability, and market penetration. The FMCG sector serves as a critical component of both economies, contributing significantly to GDP and employment. However, stark differences in infrastructure, consumer behavior, and regulatory environments between Africa and the USA necessitate tailored approaches to business and supply chain management. Drawing on empirical data and case studies, this study examines key elements of successful FMCG models in each region, including distribution networks, inventory management, technology adoption, and market dynamics. It explores how factors such as urbanization, income levels, and cultural preferences influence consumer demand and supply chain strategies. Moreover, the analysis delves into the impact of emerging trends such as e-commerce, sustainability, and digitalization on FMCG operations in both regions. The findings reveal opportunities for mutual learning and adaptation between Africa and the USA. While the USA boasts mature infrastructure and advanced technological capabilities, Africa offers potential for innovative solutions tailored to its unique challenges and opportunities. Through cross-regional knowledge exchange and strategic partnerships, FMCG companies can develop hybrid models that combine the best practices from both regions to drive growth, reduce costs, and enhance resilience. The study concludes by proposing actionable recommendations for FMCG companies seeking to implement transformative business and supply chain models in Africa and the USA, emphasizing the importance of flexibility, agility, and stakeholder collaboration in navigating diverse market landscapes and driving sustainable growth.

A comparative analysis of feature selection models for spatial analysis of floods using hybrid metaheuristic and machine learning models.

The research aims to propose a feature selection model for hydraulic analysis as such a model has not been proposed previously. For this purpose, hybrids of three metaheuristic algorithms, particle swarm optimization (PSO), ant colony optimization (ACO), and genetic algorithm (GA) with two machine learning models which are support vector machine (SVM) and K-nearest neighbor (KNN) are employed. The dataset considered was hydraulic having an association with flood and possessed topographic, geo-environmental, and human-induced variables. The dataset considered had multicollinearity heteroscedasticity and autocorrelation problems. The metaheuristic algorithms were evaluated by varying the number of population size. Among them, PSO performed better by providing an appropriate number of features with a lower number of iterations. We have analyzed the performance of SVM with different kernels; linear, radial basis function (RBF), sigmoid, and polynomial, as the original SVM is designed only for linear datasets but the hydraulic dataset possesses non-linear characteristics as well. The performance of different kernels in terms of their accuracies is evaluated and recorded. This study showed that RBF performed the best and sigmoid showed the least accuracy for GA, PSO, and ACO algorithms. The performance of KNN is evaluated in terms of accuracies by varying the K-values. It was found that KNN shows low accuracy with a small K-value which then attained a maximum level by increasing K-values, and it finally started decreasing, explicitly, by further enhancing K-values. While comparing the performance of hybrids of GA, PSO, and ACO with SVM and KNN, it was analyzed that KNN performed better with these meta-heuristics with PSO-KNN which performed the best among the baseline models. Thus, the study proposes that PSO-KNN can be utilized as a feature selection technique to obtain optimal data subsets for hydraulic modeling and analysis.

Comparative Analysis of Generic and Fine-Tuned Large Language Models for Conversational Agent Systems

In the rapidly evolving domain of conversational agents, the integration of Large Language Models (LLMs) into Chatbot Development Platforms (CDPs) is a significant innovation. This study compares the efficacy of employing generic and fine-tuned GPT-3.5-turbo models for designing dialog flows, focusing on the intent and entity recognition crucial for dynamic conversational interactions. Two distinct approaches are introduced: a generic GPT-based system (G-GPT) leveraging the pre-trained model with complex prompts for intent and entity detection, and a fine-tuned GPT-based system (FT-GPT) employing customized models for enhanced specificity and efficiency. The evaluation encompassed the systems’ ability to accurately classify intents and recognize named entities, contrasting their adaptability, operational efficiency, and customization capabilities. The results revealed that, while the G-GPT system offers ease of deployment and versatility across various contexts, the FT-GPT system demonstrates superior precision, efficiency, and customization, although it requires initial training and dataset preparation. This research highlights the versatility of LLMs in enriching conversational features for talking assistants, from social robots to interactive chatbots. By tailoring these advanced models, the fluidity and responsiveness of conversational agents can be enhanced, making them more adaptable and effective in a variety of settings, from customer service to interactive learning environments.

Air Quality Index Prediction using Bi-LSTM

Air quality prediction plays a vital role in safeguarding public health and guiding environmental policy. Traditional single-model approaches often struggle to accurately forecast air quality fluctuations. In response, this study introduces a robust prediction system leveraging advanced machine learning techniques. We present a comparative analysis of several models including Support Vector Regression (SVR), Genetic Algorithm-Enhanced Extreme Learning Machine (GA-KELM), and Deep Belief Network with Back-Propagation (DBN-BP). Additionally, we propose the integration of Bidirectional Long Short-Term Memory (BiLSTM), a deep learning architecture, to further enhance prediction accuracy. Through comprehensive experimentation and evaluation, we demonstrate that BiLSTM outperforms existing models, exhibiting lower Root Mean Square Error (RMSE) and Mean Squared Error (MSE) values. Furthermore, by incorporating GA-KELM, we optimize the performance of BiLSTM, enhancing its predictive capabilities even further. The proposed hybrid model not only offers improved accuracy in air quality forecasting but also contributes to informed decision-making for pollution control strategies and public health interventions. This research underscores the significance of exploring innovative techniques to address pressing environmental challenges and underscores the potential of machine learning in advancing air quality management.

A Comparative Study on the Results of College English Grade 4 Based on Multi-model Prediction

Predictive analytics improves educational outcomes by offering insights into student performance and influencing targeted interventions. In this work, we undertake a detailed comparative analysis of predictive models for projecting College English Grade 4 exam results, to contribute to the improvement of educational predictive analytics. We compare the predicted accuracy and interpretability of several modeling approaches, including ensemble learning methods like Random Forests, interpretable models like Decision Trees, and Support Vector Machines (SVM). We evaluate each model's performance using important metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2) coefficients. Our results show that Random Forests have greater prediction accuracy, beating other models in terms of MSE, RMSE, and MAE. Despite its slightly lower R2 coefficients, Decision Trees perform competitively and provide useful insights into crucial variables. In contrast, SVM shows limitations in prediction accuracy for College English Grade 4 exam results. We highlight the relevance of these findings for educators and administrators, emphasizing the need to make educated decisions when selecting predictive models and implementing targeted interventions to promote student achievement. This work advances the field of educational predictive analytics by giving empirical evidence for the efficacy of various modeling methodologies and emphasizing the importance of model interpretability in understanding student performance determinants. More study is needed to improve predictive analytics methods and enhance their applicability in educational settings.

Detecting health misinformation: A comparative analysis of machine learning and graph convolutional networks in classification tasks

In the digital age, the proliferation of health-related information online has heightened the risk of misinformation, posing substantial threats to public well-being. This research conducts a meticulous comparative analysis of classification models, focusing on detecting health misinformation. The study evaluates the performance of traditional machine learning models and advanced graph convolutional networks (GCN) across critical algorithmic metrics. The results comprehensively understand each algorithm's effectiveness in identifying health misinformation and provide valuable insights for combating the pervasive spread of false health information in the digital landscape. GCN with TF-IDF gives the best result, as shown in the result section.•The research method involves a comparative analysis of classification algorithms to detect health misinformation, exploring traditional machine learning models and graph convolutional networks.•This research used algorithms such as Passive Aggressive Classifier, Random Forest, Decision Tree, Logistic Regression, Light GBM, GCN, GCN with BERT, GCN with TF-IDF, and GCN with Word2Vec were employed. Performance Metrics: Accuracy: for Passive Aggressive Classifier: 85.75 %, Random Forest: 86 %, Decision Tree: 81.30 %, Light BGM: 83.29 %, normal GCN: 84.53 %, GCN with BERT: 85.00 %, GCN with TR-IDF: 93.86 % and GCN with word2Vec: 81.00 %•Algorithmic performance metrics, including accuracy, precision, recall, and F1-score, were systematically evaluated to assess the efficacy of each model in detecting health misinformation, focusing on understanding the strengths and limitations of different approaches. The superior performance of Graph Convolutional Networks (GCNs) with TF-IDF embedding, achieving an accuracy of 93.86 %

Integrating Machine Learning and MLOps for Wind Energy Forecasting: A Comparative Analysis and Optimization Study on Türkiye’s Wind Data

This study conducted a detailed comparative analysis of various machine learning models to enhance wind energy forecasts, including linear regression, decision tree, random forest, gradient boosting machine, XGBoost, LightGBM, and CatBoost. Furthermore, it developed an end-to-end MLOps pipeline leveraging SCADA data from a wind turbine in Türkiye. This research not only compared models using the RMSE metric for selection and optimization but also explored in detail the impact of integrating machine learning with MLOps on the precision of energy production forecasts. It investigated the suitability and efficiency of ML models in predicting wind energy with MLOps integration. The study explored ways to improve LightGBM algorithm performance through hyperparameter tuning and Docker utilization. It also highlighted challenges in speeding up MLOps development and deployment processes. Model performance was assessed using the RMSE metric, conducting a comparative evaluation across different models. The findings revealed that the RMSE values among the regression models ranged from 460 kW to 192 kW. Focusing on enhancing LightGBM, the research decreased the RMSE value to 190.34 kW. Despite facing technical and operational hurdles, the implementation of MLOps was proven to enhance the speed (latency of 9 ms), reliability (through Docker encapsulation), and scalability (using Docker swarm) of machine learning endeavors.

Comparative Analysis of Machine Learning Models for Predicting Diabetes: Unveiling the Superiority of Advanced Ensemble Methods

This study presents a comprehensive analysis of various machine learning models to predict diabetes. The research evaluates and compares the predictive performance of advanced ensemble techniques Extra Trees Classifier and LightGBM with traditional machine learning algorithms and simpler deep neural network (DNN) architectures. The dataset comprises numerous features pertinent to diabetes diagnosis, such as glucose concentration, BMI, and insulin levels, among others. A methodology, including polynomial feature transformation and ten-fold cross-validation, was employed to ensure the study's reliability and the models' capability to generalize. The advanced ensemble models, Extra Trees and LightGBM, achieved stellar predictive metrics, with the former attaining a near-perfect ROC AUC, accuracy, precision, and an F1 score close to 1. LightGBM followed closely, demonstrating the high efficacy of ensemble methods in complex data settings. These results were contrasted with significantly lower performance metrics from DNNs and respectable, albeit lower, scores from traditional models like Decision Trees, Random Forest, KNN, and XGBoost.

Research on cable dynamic response of a catenary anchor leg mooring system based on ANCF

This paper presents a dynamic analysis model for a catenary anchor leg mooring (CALM) system based on the absolute nodal coordinate formulation (ANCF) method, combined with continuum mechanics and finite element theory. This model uses absolute slope coordinates instead of traditional angle coordinates to better describe the large deformation and large displacement of the cables. The paper derives the element mass matrix, generalized stiffness matrix, and the element external load matrix, including the Morison force transformed into the ANCF framework, based on the virtual work principle. The accuracy and reliability of the ANCF program are validated using static and dynamic beam models, as well as submerged tether models. Furthermore, a comparative analysis of the ANCF mooring cable model with OpenFAST and MoorDyn accentuates the program's practical value in real engineering applications. Finally, we systematically analyzed the dynamic characteristics of a CALM single-point mooring system, revealing that the mooring forces in the cables significantly influence the high-frequency motion of the buoy. Additionally, the reduction in the length of the mooring cables, to an appropriate extent, enhances the stability of the system, which further attests to the effectiveness and practicality of the ANCF model that has been developed.

Predicting Corporate Bankruptcy: A Comparative Analysis of Machine Learning Models

Predicting Corporate Bankruptcy: A Comparative Analysis of Machine Learning Models