Machine Learning-based Approach Research Articles

FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

SURVEY ON FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and Mask R-CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

A Machine Learning-Based Approach for Predicting Installation Torque of Helical Piles from SPT Data

Helical piles are advantageous alternatives in constructions subjected to high tractions in their foundations, like transmission towers. Installation torque is a key parameter to define installation equipment and the final depth of the helical pile. This work applies machine learning (ML) techniques to predict helical pile installation torque based on information from 707 installation reports, including Standard Penetration Test (SPT) data. It uses this information to build three datasets to train and test eight machine-learning techniques. Decision tree (DT) was the worst technique for comparing performances, and cubist (CUB) was the best. Pile length was the most important variable, while soil type had little relevance for predictions. Predictions become more accurate for torque values greater than 8 kNm. Results show that CUB predictions are within 0.71,1.59 times the real value with a 95% confidence. Thus, CUB successfully predicted the pile length using SPT data in a case study. One can conclude that the proposed methodology has the potential to aid in the helical pile design and the equipment specification for installation.

CO2 emission prediction from coal used in power plants: a machine learning-based approach

CO2 emission prediction from coal used in power plants: a machine learning-based approach

DeepAVP-TPPred: identification of antiviral peptides using transformed image-based localized descriptors and binary tree growth algorithm.

Despite the extensive manufacturing of antiviral drugs and vaccination, viral infections continue to be a major human ailment. Antiviral peptides (AVPs) have emerged as potential candidates in the pursuit of novel antiviral drugs. These peptides show vigorous antiviral activity against a diverse range of viruses by targeting different phases of the viral life cycle. Therefore, the accurate prediction of AVPs is an essential yet challenging task. Lately, many machine learning-based approaches have developed for this purpose; however, their limited capabilities in terms of feature engineering, accuracy, and generalization make these methods restricted. In the present study, we aim to develop an efficient machine learning-based approach for the identification of AVPs, referred to as DeepAVP-TPPred, to address the aforementioned problems. First, we extract two new transformed feature sets using our designed image-based feature extraction algorithms and integrate them with an evolutionary information-based feature. Next, these feature sets were optimized using a novel feature selection approach called binary tree growth (BTG) Algorithm. Finally, the optimal feature space from the training dataset was fed to the Deep neural network (DNN) to build the final classification model. The proposed model DeepAVP-TPPred was tested using stringent 5-fold cross-validation and two independent dataset testing methods, which achieved the maximum performance and showed an enhanced efficiency over existing predictors in terms of both accuracy and generalization capabilities. https://github.com/MateeullahKhan/DeepAVP-TPPred. Supplementary data are available at Bioinformatics online.

Abstract PO2-15-06: ctDNA-based DNADX in hormone receptor-positive and HER2-negative (HR+/HER2-) advanced breast cancer following endocrine therapy and CDK4/6 inhibition: a correlative analysis from the randomized phase 2 PARSIFAL trial

Abstract ctDNA-based DNADX in hormone receptor-positive and HER2-negative (HR+/HER2-) advanced breast cancer following endocrine therapy and CDK4/6 inhibition: a correlative analysis from the randomized phase 2 PARSIFAL trial Background: DNADX, a novel machine learning-based approach, utilizes DNA from tumor tissue or plasma ctDNA to identify clinically relevant phenotypic tumor features and classify breast cancer into 4 subtypes (Nat Comm 2023). Here, we evaluated DNADX's ability to predict prognosis and treatment benefit in HR+/HER2- advanced breast cancer following endocrine therapy and a CDK4/6 inhibitor. Methods: DNADX was evaluated centrally in available baseline plasma ctDNA samples from PARSIFAL trial (NCT02491983) which randomized 486 patients (pts) with HR+/HER2- advanced breast cancer to receive (1:1 ratio) first line palbociclib with either fulvestrant or letrozole. Shallow whole genome sequencing was performed on ctDNA, and the 4 DNA-based subtypes (Clusters-1, -2, -3, and -4) were identified if the ctDNA tumor fraction (TF)≥3%. The main objective was to evaluate the association of DNADX subtypes with progression-free survival (PFS) and overall survival (OS). Secondary objective was to identify the subgroup of pts who benefit more from each endocrine treatment. Uni- and multi-variable Cox regression models were used after adjusting for TF, menopausal status, ECOG status, de novo metastasis (vs. recurrence), visceral disease and number of metastatic sites. Results: DNADX was evaluated in plasma ctDNA samples from 122 pts (25.1%). Clinical variables and median PFS (27.6 months) were similar as the overall PARSIFAL population. DNADX identified 56.6% pts with TF of < 3%, 14.8% with Cluster-1, 19.7% with Cluster-2, 5.7% with Cluster-3 and 3.3% with Cluster-4. In terms of PFS, pts classified with TF< 3% had a lower risk of progression compared to Cluster-1, Cluster-2, Cluster-3, Cluster-4 subtypes (pairwise PFS hazard ratios [HRs] of 1.88, 2.02, 3.15, and 5.62, respectively, with a global log-rank test of p=0.010). Similar results were obtained after adjusting for other clinical-pathologic variables. A numerical benefit of fulvestrant in comparison with letrozole was observed in pts classified in Cluster-1 and Cluster-4 (HR=0.42, 95% CI 0.14-1.24) in contrast to the other groups (HR=1.21, 95% CI 0.68-2.18), and the interaction test was statistically significant after adjusting for clinical-pathologic variables (anova p-value=0.037). In terms of OS, pts classified with TF< 3% had a lower risk of death compared to Cluster-1, Cluster-2, Cluster-3, and Cluster-4 subtypes (pairwise OS HRs of 1.90, 4.23, 11.13, and 6.80, respectively, with a global log-rank test of p=0.003). In the multivariable analysis, results were consistent after adjusting for clinical-pathologic variables and TF. Conclusions: Liquid biopsy-based DNADX subtypes predict outcomes in pts with HR+/HER2- advanced breast cancer on endocrine therapy and CDK4/6 inhibitors, potentially identifying the most optimal endocrine treatment for each pt. Citation Format: Fara Brasó-Maristany, Javier Cortés, José Manuel Pérez-García, Rosario Vega-León, Laia Paré, Guillermo Villacampa, Judit Matito, Francisco Pardo, Marina Gomez-Rey, Mario Mancino, Elena Martínez-García, Carmen Mora Gallardo, Leonardo Mina, Florence Dalenc, Meritxell Bellet- Ezquerra, Manuel Ruíz - Borrego, Miguel Gil-Gil, Peter Schmid, Charles M. Perou, Joel S. Parker, Patricia Villagrasa, Ana Vivancos, Aleix Prat, Antonio Llombart-Cussac. ctDNA-based DNADX in hormone receptor-positive and HER2-negative (HR+/HER2-) advanced breast cancer following endocrine therapy and CDK4/6 inhibition: a correlative analysis from the randomized phase 2 PARSIFAL trial [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-15-06.

FRAUD DETECTION AND PREVENTION IN FINANCIAL INSTITUTIONS

Financial fraud, characterized by deceptive practices aimed at securing financial gains, has emerged as a prevalent threat within companies and organizations. Traditional methods like manual verification and inspection are inaccurate, expensive, and time-consuming in identifying fraudulent activities. With the rise of artificial intelligence, machine learning-based approaches offer a promising solution to detect fraudulent transactions through the analysis of vast financial datasets. This paper presents a systematic literature review (SLR) that systematically surveys and consolidates existing literature on machine learning (ML)-based fraud detection. Employing the Kitchenham approach, which employs defined protocols to extract and synthesize relevant articles, this review reports the findings from various studies gathered through specified search strategies from electronic databases. After applying inclusion/exclusion criteria, 93 articles were selected, synthesized, and analyzed. The review outlines popular ML techniques utilized for fraud detection, prevalent fraud types, and evaluation metrics. The surveyed articles indicate that support vector machine (SVM) and artificial neural network (ANN) are commonly employed ML algorithms for fraud detection, with credit card fraud being the most addressed fraud type using ML techniques. Additionally, the paper discusses key issues, gaps, and limitations in financial fraud detection and suggests potential areas for future research. Furthermore, the review identifies challenges like class imbalance in datasets and the dynamic nature of fraud patterns. While SVM and ANN are popular, exploring ensemble methods, deep learning, and anomaly detection techniques shows promise for improving detection accuracy in suitability. Future research should address these limitations and foster collaboration between academia, industry, and regulatory bodies to advance fraud detection methods and safeguard financial transactions.

Two-Stage Machine Learning-Based Approach to Predict Points of Departure for Human Noncancer and Developmental/Reproductive Effects.

Chemical points of departure (PODs) for critical health effects are crucial for evaluating and managing human health risks and impacts from exposure. However, PODs are unavailable for most chemicals in commerce due to a lack of in vivo toxicity data. We therefore developed a two-stage machine learning (ML) framework to predict human-equivalent PODs for oral exposure to organic chemicals based on chemical structure. Utilizing ML-based predictions for structural/physical/chemical/toxicological properties from OPERA 2.9 as features (Stage 1), ML models using random forest regression were trained with human-equivalent PODs derived from in vivo data sets for general noncancer effects (n = 1,791) and reproductive/developmental effects (n = 2,228), with robust cross-validation for feature selection and estimating generalization errors (Stage 2). These two-stage models accurately predicted PODs for both effect categories with cross-validation-based root-mean-squared errors less than an order of magnitude. We then applied one or both models to 34,046 chemicals expected to be in the environment, revealing several thousand chemicals of moderate concern and several hundred chemicals of high concern for health effects at estimated median population exposure levels. Further application can expand by orders of magnitude the coverage of organic chemicals that can be evaluated for their human health risks and impacts.

A physics-driven and machine learning-based digital twinning approach to transient thermal systems

Purpose In this study, the authors propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The purpose of this study is to harness the combined power of deep learning (DL) and physics-based methods (PBM) to create an active virtual replica of the physical system. Design/methodology/approach To achieve this goal, we introduce a deep neural network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is used to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop. Findings The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems. Originality/value The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.

Stock Market Prediction and Visualisation

Abstract: Stock price forecasting is a widely discussed and significant topic in both financial and academic circles. The stock market is inherently unpredictable, lacking clear rules for estimating or predicting share prices. Various methods, including technical analysis, fundamental analysis, time series analysis, and statistical analysis, have been employed to forecast stock prices. However, none of these methods consistently serve as reliable prediction tools. In this paper, we explore the implementation, prediction, and analysis of stock market prices. Artificial Neural Networks and Machine Learning prove effective for forecasting stock prices, returns, and modeling stock behavior. By conducting statistical analyses, we establish relationships between selected factors and share prices, contributing to more accurate predictions. While the stock market remains inherently uncertain, this paper aims to apply data analysis and prediction concepts to forecast stock prices. In the era of global digitization, stock market prediction has undergone significant technological advancements, transforming traditional trading models. As market capitalization continues to rise, stock trading becomes a focal point for financial investors. Analysts and researchers have developed tools and techniques to predict stock price movements, aiding decision-making. Advanced models leverage non-traditional textual data from social platforms for market prediction. Machine learning approaches, including text data analytics and ensemble methods, have significantly improved prediction accuracy. However, analyzing and predicting stock markets remains challenging due to dynamic, erratic, and chaotic data. This study explores machine learning-based approaches for stock market prediction, emphasizing a generic framework. By critically analyzing findings from the last decade (2011–2021) from digital libraries like ACM and Scopus, we provide insights for emerging researchers to delve into this promising area.

DDoS Attack Detection and Classification using Machine Learning Algorithms

Abstract: In the dynamic realm of networking, Software Defined Networking (SDN) emerges as a transformative force, offering centralized control and programmable capabilities that empower network administrators to efficiently manage and secure network infrastructures. However, amidst the ever-present threat of distributed denial-of-service (DDoS) attacks, the need for robust detection mechanisms is imperative. This research proposes a machine learning-based approach to enhance DDoS attack detection and classification within SDN environments. Leveraging the SelectKBest algorithm for feature selection and employing various classifiers such as Decision tree, KMeans++, XGBoost, etc.. with a focus on Random Forest as the most effective, the project aims to bolster detection accuracy and efficiency. Through comprehensive experimentation and comparative analysis, the efficacy of the proposed methodology in identifying DDoS threats is demonstrated, contributing to the ongoing efforts in fortifying cybersecurity defenses against sophisticated adversarial tactics.

Exploring Physics-Informed Neural Networks for the Generalized Nonlinear Sine-Gordon Equation

The nonlinear sine-Gordon equation is a prevalent feature in numerous scientific and engineering problems. In this paper, we propose a machine learning-based approach, physics-informed neural networks (PINNs), to investigate and explore the solution of the generalized non-linear sine-Gordon equation, encompassing Dirichlet and Neumann boundary conditions. To incorporate physical information for the sine-Gordon equation, a multiobjective loss function has been defined consisting of the residual of governing partial differential equation (PDE), initial conditions, and various boundary conditions. Using multiple densely connected independent artificial neural networks (ANNs), called feedforward deep neural networks designed to handle partial differential equations, PINNs have been trained through automatic differentiation to minimize a loss function that incorporates the given PDE that governs the physical laws of phenomena. To illustrate the effectiveness, validity, and practical implications of our proposed approach, two computational examples from the nonlinear sine-Gordon are presented. We have developed a PINN algorithm and implemented it using Python software. Various experiments were conducted to determine an optimal neural architecture. The network training was employed by using the current state-of-the-art optimization methods in machine learning known as Adam and L-BFGS-B minimization techniques. Additionally, the solutions from the proposed method are compared with the established analytical solutions found in the literature. The findings show that the proposed method is a computational machine learning approach that is accurate and efficient for solving nonlinear sine-Gordon equations with a variety of boundary conditions as well as any complex nonlinear physical problems across multiple disciplines.

Deep Fake Detecting System

Abstract: Over the past few decades, there have been rapid breakthroughs in AI, machine learning, and deep learning, which have led to the development of new tools and methodologies for manipulating multimedia. Technology has generally been employed for beneficial purposes, such as education and entertainment, but dishonest users have also exploited it for darker or illicit purposes. For example, incredibly realistic-looking, well-produced fake movies, images, or audio have been made to spread false information, incite political unrest and hatred, or even to harass and blackmail people. The extremely replicated, realistic, and edited videos have been dubbed as "Deepfake" in recent times. Since then, several approaches to resolving the problems raised by Deepfake have been described in length in the literature. We conduct a systematic literature review (SLR) in this work to give a current synopsis of the Deepfake detection research projects. We provide an overview of 112 pertinent publications from 2018 to 2020 that showcased various methodologies. For analysis, we divide them into four categories: deep learning-based approaches, traditional machine learning-based approaches, statistical-based approaches, and blockchain-based approaches. We also evaluate the pattern recognition performance of several algorithms on various datasets, and we find that deep learningbased approaches outperform other approaches in Deepfake detection

Metaheuristic optimization algorithms comparison adopted for the profit maximization of electricity market participants

The electricity market faces numerous challenges due to the growing demand for energy, increasing penetration of renewable energy sources, and the need for grid reliability and efficiency. To address these challenges, optimization algorithms have emerged as essential tools for optimizing various aspects of the electricity market, including generation, transmission, distribution, and demand-side management. The review can be done by providing an overview of the key components and challenges of the electricity market, including generation dispatch, unit commitment, economic dispatch, transmission network optimization, and demand response management. It then systematically examines a wide range of optimization techniques employed in addressing these challenges, including linear programming, mixed-integer linear programming, nonlinear programming, dynamic programming, genetic algorithms, particle swarm optimization, simulated annealing, and machine learning-based approaches. This paper presents a comparison of optimization algorithms, RCEDUMDA (Ring-Cellular Encode-Decode Univariate Marginal Distribution Algorithm) and CL_HC2RCEDUMDA (Hill Climbing to Ring Cellular Encode-Decode Univariate Marginal Distribution Algorithm) for the profit maximization of Electricity Market consumers & prosumers.

Machine Learning-Based Prediction of Reduction Potentials for PtIV Complexes.

Some of the well-known drawbacks of clinically approved PtII complexes can be overcome using six-coordinate PtIV complexes as inert prodrugs, which release the corresponding four-coordinate active PtII species upon reduction by cellular reducing agents. Therefore, the key factor of PtIV prodrug mechanism of action is their tendency to be reduced which, when the involved mechanism is of outer-sphere type, is measured by the value of the reduction potential. Machine learning (ML) models can be used to effectively capture intricate relationships within PtIV complex data, leading to highly accurate predictions of reduction potentials and other properties, and offering significant insights into their electrochemical behavior and potential applications. In this study, a machine learning-based approach for predicting the reduction potentials of PtIV complexes based on relevant molecular descriptors is presented. Leveraging a data set of experimentally determined reduction potentials and a diverse range of molecular descriptors, the proposed model demonstrates remarkable predictive accuracy (MSE = 0.016 V2, RMSE = 0.13 V, R2 = 0.92). Ab initio calculations and a set of different machine learning algorithms and feature engineering techniques have been employed to systematically explore the relationship between molecular structure and similarity and reduction potential. Specifically, it has been investigated whether the reduction potential of these compounds can be described by combining ML models across different combinations of constitutional, topological, and electronic molecular descriptors. Our results not only provide insights into the crucial factors influencing reduction potentials but also offer a rapid and effective tool for the rational design of PtIV complexes with tailored electrochemical properties for pharmaceutical applications. This approach has the potential to significantly expedite the development and screening of novel PtIV prodrug candidates. The analysis of principal components and key features extracted from the model highlights the significance of structural descriptors of the 2D Atom Pairs type and the lowest unoccupied molecular orbital energy. Specifically, with just 20 appropriately selected descriptors, a notable separation of complexes based on their reduction potential value is achieved.

Image-driven machine learning for automatic characterization of grain size and distribution in smart vanadium dioxide thin films

This study focuses on characterizing grain size and distribution in vanadium dioxide (VO2) thin films using Atomic Force Microscope (AFM) images. Traditional segmentation methods face challenges in accurately detecting grains, and this paper addresses these limitations by employing machine learning-based classification approaches, defining three classes: grains, joints or dividing lines, and the background. Various classification methods, including supervised, unsupervised, and thresholding-based approaches, were investigated, demonstrating the superiority of machine learning-based methods over traditional segmentation techniques. Deep Learning (DL) models, such as Convolutional Neural Networks (CNN), Deep Belief Networks (DBN), and Deep Boltzmann Machines (DBM), achieved the best results in accuracy and precision. The DBN algorithm, in particular, outperformed other methods with a 93.66% accuracy in grain detection. This could be attributed to its probabilistic modeling and effective handling of challenging pixels, making it a powerful tool for accurate grain size and distribution analysis.

Positive-unlabeled learning identifies vaccine candidate antigens in the malaria parasite Plasmodium falciparum

Malaria vaccine development is hampered by extensive antigenic variation and complex life stages of Plasmodium species. Vaccine development has focused on a small number of antigens, many of which were identified without utilizing systematic genome-level approaches. In this study, we implement a machine learning-based reverse vaccinology approach to predict potential new malaria vaccine candidate antigens. We assemble and analyze P. falciparum proteomic, structural, functional, immunological, genomic, and transcriptomic data, and use positive-unlabeled learning to predict potential antigens based on the properties of known antigens and remaining proteins. We prioritize candidate antigens based on model performance on reference antigens with different genetic diversity and quantify the protein properties that contribute most to identifying top candidates. Candidate antigens are characterized by gene essentiality, gene ontology, and gene expression in different life stages to inform future vaccine development. This approach provides a framework for identifying and prioritizing candidate vaccine antigens for a broad range of pathogens.

Vitamin Deficiency Detection from eye Using Machine Learning

Vitamin deficiencies affect millions globally, with over two billion people at risk. Early detection is crucial, yet one in three youngsters lacks proper vitamin intake. Addressing this, a novel machine learning-based approach, using eye images instead of blood samples, offers a free desktop application for vitamin deficiency detection. The software, trained to distinguish healthy and deficient eyes, provides users with comprehensive reports. Early identification of deficiencies can prevent anemia, infectious illnesses, and developmental issues. Real-world trials confirm the method's superior efficiency compared to previous approaches, marking a promising advancement in global health. Keywords: Machine Learning, Opthalmology, YOLO, Deep Learning, Image preprocessing , extraction, ultralytics.

Pore Pressure Prediction for High-Pressure Tight Sandstone in the Huizhou Sag, Pearl River Mouth Basin, China: A Machine Learning-Based Approach

A growing number of large data sets have created challenges for the oil and gas industry in predicting reservoir parameters and assessing well productivity through efficient and cost-effective techniques. The design of drilling plans for a high-pressure tight-sand reservoir requires accurate estimations of pore pressure (Pp) and reservoir parameters. The objective of this study is to predict and compare the Pp of Huizhou Sag, Pearl River Mouth Basin, China, using conventional techniques and machine learning (ML) algorithms. We investigated the characteristics of low-permeability reservoirs by observing well-logging data sets and cores and examining thin sections under a microscope. In the reservoir zone, the average hydrocarbon saturation is 55%, and the average effective porosity is 11%. The tight sandstone reservoirs consist of fine- to extremely fine-grained argillaceous feldspathic sandstone. The mean absolute error for reservoir property prediction is 1.3%, 2.2%, and 4.8%, respectively, for effective porosity, shale volume, and water saturation. Moreover, the ML algorithm was employed to cross-check the validity of the prediction of Pp. Combining conventional and ML techniques with the core data demonstrates a correlation coefficient (R2) of 0.9587, indicating that ML techniques are the most effective in testing well data. This study shows that ML can effectively predict Pp at subsequent depths in adjacent geologically similar locations. Compared to conventional methods, a substantial data set and ML algorithms improve the precision of Pp predictions.

A Topic Modeling Approach to Determine Supply Chain Management Priorities Enabled by Digital Twin Technology

Background: This paper examines scientific papers in the field of digital twins to explore the different areas of application in supply chains. Methods: Using a machine learning-based topic modeling approach, this study aims to provide insights into the key areas of supply chain management that benefit from digital twin capabilities. Results: The research findings highlight key priorities in the areas of infrastructure, construction, business, technology, manufacturing, blockchain, and agriculture, providing a comprehensive perspective. Conclusions: Our research findings confirm several recommendations. First, the machine learning-based model identifies new areas that are not addressed in the human review results. Second, while the human review results put more emphasis on practicality, such as management activities, processes, and methods, the machine learning results pay more attention to macro perspectives, such as infrastructure, technology, and business. Third, the machine learning-based model is able to extract more granular information; for example, it identifies core technologies beyond digital twins, including AI/reinforcement learning, picking robots, cybersecurity, 5G networks, the physical internet, additive manufacturing, and cloud manufacturing.