Comparative Modeling Study Research Articles

Comparative Study of Predictive Classification Models on Data with Severely Imbalanced Predictors

Analysing pre-COVID-19 unemployment in West Java is vital for comprehending and tackling Indonesia’s economic challenges. This significance arises not only due to the region’s high unemployment rate, but also from the need to understand unemployment patterns before COVID-19, which has become more relevant now during the country’s post-pandemic recovery phase. This study evaluates four machine learning models (Random Forest, Linear SVM, RBF SVM, and Polynomial SVM) to classify employment status using demographic and job-related variables. The objective is to find the most suitable model, particularly considering the imbalanced nature of the study-case data. Data from the National Labor Force Survey (SAKERNAS) in August 2019 is utilized, comprising 54,429 respondents across districts in West Java. The four models are evaluated using holdout validation with a 70:30 stratified proportion, repeated for 100 times. Results indicate that the random forest model outperforms others in balanced accuracy, F1-score, and computational time. The random forest model also underscores the importance of gender and age in classifying employment status in West Java, suggesting a need for targeted intervention, especially for female citizens and individuals in productive age groups.

Correction: Comparative study of ML models for IIoT intrusion detection: impact of data preprocessing and balancing

Correction: Comparative study of ML models for IIoT intrusion detection: impact of data preprocessing and balancing

Comparative Model of Political Marketing of the Winning Team of Ganjar Pranowo- Taj Yasin with Sudirman Said-Ida Fauziah in the 2018 Central Java Election in Pati Regency

This study is a comparative study of the political marketing model that occurred in the 2018 Central Java regional election competition in Pati Regency. The focus is on how the political marketing models run by candidates and winning teams in winning the competition, then what causes the strong competition in the election in Pati Regency. The findings of this study include four important things that are the main causes of the strong competition in running political marketing between the winning teams of candidates in Pati Regency, causing different political marketing models to be run to gain support from voters. First, the Work Program offered; Second, Campaign Presentation; Third, Political Marketing Media Channels; Fourth, Personal Branding of Candidate Leadership. The method used is a qualitative method.

Advancing hydrogen storage predictions in metal-organic frameworks: A comparative study of LightGBM and random forest models with data enhancement

The escalating consumption of fossil fuels has given rise to a substantial upsurge in greenhouse gas concentrations and global temperatures, which, in turn, has triggered severe climate-related consequences. The critical imperative to reduce CO2 emissions and combat global warming has spurred extensive investigations into clean energy alternatives, with hydrogen emerging as a compelling zero-emission energy source. As a pivotal component of clean energy strategies, hydrogen requires designing compact, lightweight, and efficient storage systems. This study focuses on the development and evaluation of machine learning models for predicting the efficiency of Metal-Organic Frameworks (MOFs) in hydrogen storage, a key aspect of advancing clean energy technologies. MOFs, a class of nanoporous materials, show remarkable potential for hydrogen storage due to their high surface area and porosity. However, selecting the most suitable MOF for this application from a vast array of possible structures is a daunting task. In this context, machine learning algorithms offer an efficient alternative for predicting MOF suitability by considering their structural and chemical properties. We used ensemble learning methods, specifically Light Gradient Boosting Machine (LightGBM) and Random Forest (RF), to predict hydrogen uptake of MOFs based on a dataset of 219 experimentally tested samples. Two modeling scenarios were considered: one using the entire dataset, and the other involving strategic data pre-processing, including outlier removal and feature engineering. The results demonstrate that the measures taken to refine the dataset significantly enhance the predictive performance of the developed models, reducing prediction errors and improving overall goodness of fit. Specifically, the Mean Absolute Error (MAE) values for both the LightGBM and random forest models were reduced from 0.48 and 0.94, respectively, to 0.16 for both models, and the coefficients of determination (R2) increased substantially from 0.84 and 0.72 to 0.95, in both cases. Moreover, feature importance analysis unveiled that pressure-related features make the most significant contributions to the formation of tree ensembles during the model training process. A parametric sensitivity analysis was conducted revealing that H2 uptake in MOFs is most sensitive to changes in adsorption enthalpy, followed by surface area and temperature, while showing lower sensitivity to variations in pressure, consistent with established literature. These results underscore the pivotal role of data enhancement methods in refining machine learning models and can be instrumental in accelerating the development and optimization of MOF materials for clean energy applications.

Comparative Study of Single-Wood Biomass Model at Plot Level Based on Multi-Source LiDAR

Forests play an important role in promoting carbon cycling and mitigating the urban heat island effect as one of the world’s major carbon storages. Scientifically quantifying tree biomass is the basis for assessing tree carbon storage and other ecosystem functions. In this study, a sample plot of Populus tomentosa plantation in the Olympic Forest Park in Beijing was selected as the research object. Point cloud data from three types of laser scanners, including terrestrial laser scanner (TLS), backpack laser scanner (BLS), and handheld laser scanner (HLS), were used to estimate the biomass of single tree trunks, branches, leaves, and aboveground total biomass based on the Allometric Biomass Model (ABM) and Advanced Quantitative Structure Model (AdQSM). The following conclusions were drawn from the estimation results: (1) For the three types of laser scanner point clouds, the biomass estimation values obtained using the AdQSM model were generally higher than those obtained using the Allometric Biomass Model. However, the estimation values obtained using the two models were similar, especially for tree trunks and total biomass. (2) For total biomass and individual biomass components of single trees, the results obtained from handheld and terrestrial laser scanner point clouds are consistent; however, they show some differences from the results obtained from backpack-mounted point clouds. This study further enriches the methodological system for estimating forest biomass, providing a theoretical basis and reference for more accurate estimates of forest biomass and more sustainable forest management.

A Comparative Study of Feature Extraction Models for Image Caption Generation

A Comparative Study of Feature Extraction Models for Image Caption Generation

Exploring the Multifaceted Dynamics of Cartilage: A Comparative Modeling Study

Cartilage numeric models play a vital role in advancing our understanding of cartilage mechanics, disease progression, and the development of clinical interventions. The aim of this study is to investigate the influence of different mathematical models on cartilage mechanical behavior over time. A comparative analysis was conducted across three scenarios: the single-phase, biphasic, and fibril-reinforced poroelastic models. To understand how cartilage behaves over time, a 1000-second ramp relaxation displacement was applied. The findings reveal that the single-phase model falls short of capturing the time-dependent characteristics of cartilage. Conversely, the inclusion of fluid and collagen fibrils within the cartilage model significantly enhances cartilage resilience and enables the cartilage to behave non-linearly. The results presented herein make a substantial contribution to a deeper and more holistic comprehension of cartilage's dynamic behavior under compressive loads, shedding light on the intricate interplay between fluid pressure and fibril reinforcement.

Life expectancy gains from dietary modifications: a comparative modeling study in 7 countries

BackgroundEating healthier is associated with a range of favorable health outcomes. Our previous model estimated the impact of dietary changes on life expectancy gains but did not consider height, weight, or physical activity. ObjectivesWe aimed to estimate the increase in life expectancy resulting from the transition from typical national dietary patterns to longevity-optimizing dietary changes, more feasible dietary modifications, and optimized vegan dietary changes in China, France, Germany, Iran, Norway, the United Kingdom, and the United States. MethodsOur modeling study used data from meta-analyses presenting dose-response relationships between intake of 15 food groups and mortality. Background mortality data were from the Global Burden of Disease Study. We used national food intake data and adjusted for height, weight, and physical activity level. ResultsFor 40-y-olds, estimated life expectancy gains ranged from 6.2 y (with uncertainty interval [UI]: 5.7, 7.5 y) for Chinese females to 9.7 y (UI: 8.1, 11.3 y) for United States males following sustained changes from typical country-specific dietary patterns to longevity-optimized dietary changes, and from 5.2 y (UI: 4.0, 6.5 y) for Chinese females to 8.7 y (UI: 7.1, 10.3 y) for United States males following changes to optimized vegan dietary changes. ConclusionsA sustained change from country-specific typical dietary pattern patterns to longevity-optimized dietary changes, more feasible dietary changes, or optimized vegan dietary changes are all projected to result in substantial life expectancy gains across ages and countries. These changes included more whole grains, legumes, and nuts and less red/processed meats and sugars and sugar-sweetened beverages. The largest gains from dietary changes would be in the United States.

Passive cooling and thermal comfort performance of Passive Downdraught Evaporative Cooling (PDEC) towers in a Saudi library: An on-site study

In the hot arid climate of Saudi Arabia, where air conditioning, primarily fueled by fossil fuels, accounts for a significant portion of energy consumption, the implementation of Passive Downdraught Evaporative Cooling (PDEC) towers presents a sustainable solution. This study conducts an extensive evaluation of PDEC towers in a public library, focusing on their effectiveness in reducing reliance on conventional cooling and enhancing thermal comfort. Through detailed field measurements, the study examines the influence of wind speed on the towers' cooling performance, correlating it with internal environmental conditions. The research extends to a comparative analysis of two prominent thermal comfort models: the Predicted Mean Vote (PMV) and the Adaptive Thermal Comfort (ATC) model. Findings indicate a notable interaction between wind speed and indoor air temperature, where increased wind speeds correspond to higher indoor temperatures. Despite this, the PDEC towers demonstrate a significant reduction in temperature, maintaining cooling effectiveness between 70 % and 75 %. The comparative study of thermal comfort models reveals that the ATC model provides a more relevant assessment of comfort levels in naturally ventilated spaces, with 71 % of the recorded temperatures falling within the comfortable range during the monitoring period. The research highlights the PDEC tower's potential in delivering effective passive cooling, adaptable to wind speed changes, and contributing to a sustainable and energy-efficient building environment in hot arid climates.

A comparative study of soil classification machine learning models for construction management

Prior to the construction of buildings and roads, soil classification plays a vital role to ensure proper project management and durability of the structure. Civil engineers need to possess knowledge about soil behavior and properties of soil classification to construct reliable and long-lasting infrastructures. However, traditional soil classification methods are both expensive and time-consuming. Recently, machine learning (ML) has become increasingly popular in solving complex problems in Geotechnical Engineering, leading to novel approaches for automating soil classification. This research evaluates the effectiveness of various machine learning algorithms, including Multinomial Logistic Regression (MLR), Gaussian Naive Bayes (GNB), Extreme Gradient Boosting (XGBoost), Random Forest, and Artificial Neural Network-Multilayer Layer Perceptron (ANN-MLP), in classifying soils. The paper also implemented Hard and Soft Voting Ensemble models. Each model was quantitatively evaluated and compared using various metrics. The models achieved high scores in multiple performance metrics across the soil classes with accuracies ranging between 87% and 93%, except the Naive Bayes model with a balanced accuracy of 77.6% while the hard-voting model outperformed the others with a balanced accuracy of 93%. The study’s results benefit industry practitioners and academic researchers for integrating and assessing ML algorithms in soil classification.

A comparative study of analytical models of diffuse reflectance in homogeneous biological tissues: Gelatin-based phantoms and Monte Carlo experiments.

Information about tissue oxygen saturation (StO2) and other related important physiological parameters can be extracted from diffuse reflectance spectra measured through non-contact imaging. Three analytical optical reflectance models for homogeneous, semi-infinite, tissue have been proposed (Modified Beer-Lambert, Jacques 1999, Yudovsky 2009) but these have not been directly compared for tissue parameter extraction purposes. We compare these analytical models using Monte Carlo (MC) simulated diffuse reflectance spectra and controlled gelatin-based phantoms with measured diffuse reflectance spectra and known ground truth composition parameters. The Yudovsky model performed best against MC simulations and measured spectra of tissue phantoms in terms of goodness of fit and parameter extraction accuracy followed closely by Jacques' model. In this study, Yudovsky's model appeared most robust; however, our results demonstrated that both Yudovsky and Jacques models are suitable for modeling tissue that can be approximated as a single, homogeneous, semi-infinite slab.

Stereoselective Synthesis and Catalytical Application of Perillaldehyde-Based 3-Amino-1,2-diol Regioisomers.

A library of regioisomeric monoterpene-based aminodiols was synthesised and applied as chiral catalysts in the addition of diethylzinc to benzaldehyde. The synthesis of the first type of aminodiols was achieved starting from (-)-8,9-dihydroperillaldehyde via reductive amination, followed by Boc protection and dihydroxylation with the OsO4/NMO system. Separation of formed stereoisomers resulted in a library of aminodiol diastereoisomers. The library of regioisomeric analogues was obtained starting from (-)-8,9-dihydroperillic alcohol, which was transformed into a mixture of allylic trichloroacetamides via Overman rearrangement. Changing the protecting group to a Boc function, the protected enamines were subjected to dihydroxylation with the OsO4/NMO system, leading to a 71:16:13 mixture of diastereoisomers, which were separated, affording the three isomers in isolated form. The obtained primary aminodiols were transformed into secondary derivatives. The regioselectivity of the ring closure of the N-benzyl-substituted aminodiols with formaldehyde was also investigated, resulting in 1,3-oxazines in an exclusive manner. To explain the stability difference between diastereoisomeric 1,3-oxazines, a series of comparative theoretical modelling studies was carried out. The obtained potential catalysts were applied in the reaction of aromatic aldehydes and diethylzinc with moderate to good enantioselectivities (up to 94% ee), whereas the opposite chiral selectivity was observed between secondary aminodiols and their ring-closed 1,3-oxazine analogues.

Artificial Intelligence in Academic Translation: A Comparative Study of Large Language Models and Google Translate

Purpose. The advent of Large Language Model (LLM), a generative artificial intelligence (AI) model, in November 2022 has had a profound impact on various domains, including the field of translation studies. This motivated this study to conduct a rigorous evaluation of the effectiveness and precision of machine translation, represented by Google Translate (GT), in comparison to Large Language Models (LLMs), specifically ChatGPT 3.5 and 4, when translating academic abstracts bidirectionally between English and Arabic. 
 Methods. Employing a mixed-design approach, this study utilizes a corpus comprising 20 abstracts sourced from peer-reviewed journals indexed in the Clarivate Web of Science, specifically the Journal of Arabic Literature and Al-Istihlal Journal. The abstracts are equally divided to represent both English-Arabic and Arabic-English translation directionality. The study’s design is rooted in a comprehensive evaluation rubric adapted from Hurtado Albir and Taylor (2015), focusing on semantic integrity, syntactic coherence, and technical adequacy. Three independent raters carried out assessments of the translation outputs generated by both GT and LLM models. 
 Results. Results from quantitative and qualitative analyses indicated that LLM tools significantly outperformed MT outputs in both Arabic and English translation directions. Additionally, ChatGPT 4 demonstrated a significant advantage over ChatGPT 3.5 in Arabic-English translation, while no statistically significant difference was observed in the English-Arabic translation directionality. Qualitative analysis findings indicated that AI tools exhibited the capacity to comprehend contextual nuances, recognize city names, and adapt to the target language's style. Conversely, GT displayed limitations in handling specific contextual aspects and often provided literal translations for certain terms.

Enhancing Economic Development through Inventory Management Optimization in Agro-based Industries in Bihar: A Comparative Study of EOQ and EPQ Models

Inventory management is crucial for optimizing operational efficiency and cost-effectiveness in agro-based industries, particularly in regions like Bihar,known for their agricultural resources. This study compares the effectiveness of two inventory management models, the Economic Order Quantity (EOQ) and Economic Production Quantity (EPQ), in addressing the unique challenges faced by Bihar's agro-based industries. Data from Taruwar Agro Industries Private Limited in Ashiyana, Patna, use to calculate EOQ and EPQ values for three product categories: Tomato Chili, Peri Peri, and Punjabi Tadka. The study employs relevant formulas to compute optimal order quantities and total inventory costs, assuming constant demand, quality, price, holding costs, and ordering costs. Both the EOQ and EPQ models offered viable approaches to inventory optimization. EOQ focused on minimizing holding and ordering costs, while EPQ integrated production-related costs to optimize production flow. The study underscored the importance of aligning inventory management strategies with operational capabilities, market demand, and financial objectives. This study contributes to advancing theoretical understanding and practical applications of inventory management in agro-based economies like Bihar. Recommendations for empirical validation, contextual adaptation, technology integration, and long-term impact assessment are provided to enhance inventory management practices. Integration of the BCG matrix into decision-making processes offers a comprehensive approach to prioritizing inventory management strategies and guiding strategic implications.

A Comparative Study of Transformer-based Models for Text Summarization of News Articles

Transformer-based models such as GPT, T5, BART, and PEGASUS have made substantial progress in text summarization, a sub-domain of natural language processing that entails extracting important information from lengthy texts. The main objective of this research was to conduct a comparative analysis of these four transformer-based models based on their performance in text summarization of news articles. In achieving this objective, the transformer models pre-trained on extensive datasets were fine-tuned on the CNN/DailyMail dataset using a low learning rate to preserve the learned representations. The T5 transformer records the highest scores of 35.12, 22.75, 32.82, and 28.59 in ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum respectively, surpassing GPT, BART, and PEGASUS across all ROUGE metrics. The findings deduced from this study establish the proficiency of encoder-decoder models such as T5 in summary generation. Furthermore, the findings also demonstrated that the fine-tuning process's effectiveness in pre-trained models is improved when the pre-training objective closely aligns with the downstream task.

Assessing Column Stability: A Comparative Study of Machine Learning Regression Models for Shear Strength Prediction

This research presents a comprehensive investigation into the accurate estimation of shear strength in rectangular reinforced concrete columns through advanced machine learning (ML) models. The study addresses the intricate challenge posed by shear strength complexity, which is crucial for evaluating column stability and ensuring structural integrity. Building upon a substantial dataset comprising 545 experimental observations sourced from diverse literature, this research establishes a robust foundation for predictive modeling. Four distinct ML regression models, Random Forest, Decision Tree, XGBoost, and LightGBM, are meticulously evaluated for their performance. The evaluation employs established metrics, including R2, RMSE, MAE, and MAPE to quantify their predictive capabilities. The outcomes highlight the models' robustness in capturing nuanced variations in shear strength, with impressive R2 values ranging from 93.6% to 93.9%, showcasing their exceptional ability to elucidate intricate shear behaviors. Furthermore, comparative analysis indicates the slightly superior performance of the Random Forest over the Decision Tree, highlighting the efficacy of ensemble methods in this context. Extending the exploration to include XGBoost and LightGBM, the study showcases their potential as accurate shear strength predictors. The performance of the models is validated through scatter plots and error distribution plots, confirming accurate shear strength predictions across various scenarios. This research contributes significantly to the advancement of structural engineering methodologies by highlighting the potential of ML to improve the accuracy of shear strength estimation. The findings not only underscore the exceptional performance of ML models but also provide valuable insights into their comparative effectiveness, paving the way for enhanced structural assessments in columns.

A comparative study of ensemble machine learning models for compressive strength prediction in recycled aggregate concrete and parametric analysis

A comparative study of ensemble machine learning models for compressive strength prediction in recycled aggregate concrete and parametric analysis

Comparative study of robust optimization model of multimaterial emergency logistics in an uncertain environment

AbstractGiven the significance of objective functions in alleviating human suffering within the humanitarian relief supply chain, it is imperative to consider both logistics costs and the cost of deprivation as ideal targets. This study investigates a multimaterial single‐cycle stochastic mixed integer model, integrating uncertainties about post‐disaster demand, supply survival, and road networks. An innovative heuristic approach is used to solve the stochastic facility location problem, which minimizes unfulfilled requests and response times in lexicographic order. This research also compares the cost‐minimization model of the pre‐positioning problem to an alternative model that maximizes demand satisfaction under resource constraints. Empirical validation through numerous case studies and solutions confirms the effectiveness and feasibility of the alternative model. The results of our experiments consistently demonstrate that the best solution provided by the alternative model not only satisfies the minimum cost model but also surpasses the conventional problem, without compromising performance. Consequently, it is crucial to avoid the cost‐minimization approach at the expense of human suffering.

A Comparative Study of Large Language Models, Human Experts, and Expert-Edited Large Language Models to Neuro-Ophthalmology Questions.

While large language models (LLMs) are increasingly used in medicine, their effectiveness compared with human experts remains unclear. This study evaluates the quality and empathy of Expert + AI, human experts, and LLM responses in neuro-ophthalmology. This randomized, masked, multicenter cross-sectional study was conducted from June to July 2023. We randomly assigned 21 neuro-ophthalmology questions to 13 experts. Each expert provided an answer and then edited a ChatGPT-4-generated response, timing both tasks. In addition, 5 LLMs (ChatGPT-3.5, ChatGPT-4, Claude 2, Bing, Bard) generated responses. Anonymized and randomized responses from Expert + AI, human experts, and LLMs were evaluated by the remaining 12 experts. The main outcome was the mean score for quality and empathy, rated on a 1-5 scale. Significant differences existed between response types for both quality and empathy (P < 0.0001, P < 0.0001). For quality, Expert + AI (4.16 ± 0.81) performed the best, followed by GPT-4 (4.04 ± 0.92), GPT-3.5 (3.99 ± 0.87), Claude (3.6 ± 1.09), Expert (3.56 ± 1.01), Bard (3.5 ± 1.15), and Bing (3.04 ± 1.12). For empathy, Expert + AI (3.63 ± 0.87) had the highest score, followed by GPT-4 (3.6 ± 0.88), Bard (3.54 ± 0.89), GPT-3.5 (3.5 ± 0.83), Bing (3.27 ± 1.03), Expert (3.26 ± 1.08), and Claude (3.11 ± 0.78). For quality (P < 0.0001) and empathy (P = 0.002), Expert + AI performed better than Expert. Time taken for expert-created and expert-edited LLM responses was similar (P = 0.75). Expert-edited LLM responses had the highest expert-determined ratings of quality and empathy warranting further exploration of their potential benefits in clinical settings.

Comparative study of physics-based model and machine learning model for epidemic forecasting and countermeasure

Comparative study of physics-based model and machine learning model for epidemic forecasting and countermeasure