Evaluating Machine Learning Techniques for Demand Forecasting in Supply Chains Using MOORA Method

PurposeThe findings of this paper throw light on the focal research areas within RFID in the supply chain, which serves as an effective guideline for future research in this area. This research, therefore, contributes to filling the gap by carrying out an SLR of contemporary research studies in the area of RFID applications in supply chains. To date, SLR augmented with BA has not been used to study the developments in RFID applications in supply chains.Design/methodology/approachWe analyze 556 articles from years 2001 to date using Systematic Literature Review (SLR). Contemporary bibliometric analysis (BA) tools are utilized. First, an exploratory analysis is carried, out revealing influential authors, sources, regions, among other key aspects. Second, a co-citation work analysis is utilized to understand the conceptual structure of the literature, followed by a dynamic co-citation network to reveal the evolution of the field. This is followed by a multivariate analysis is performed on top-100 cited papers, and k-means clustering is carried out to find optimal groups and identify research themes. The influential themes are then pointed out using factor analysis.FindingsAn exploratory analysis is carried out using BA tools to provide insights into factors such as influential authors, production countries, top-cited papers and frequent keywords. Visualization of bibliographical data using co-citation network analysis and keyword co-occurrence analysis assisted in understanding the groups (communities) of research themes. We employed k-means clustering and factor analysis methods to further develop these insights. A historiographical direct citation analysis also unveils potential research directions. We observe that RFID applications in the supply chain are likely to benefit from the Internet of Things and blockchain Technology along with the other machine learning and visualization approaches.Originality/valueAlthough several researchers have researched RFID literature in relation to supply chains, these reviews are often conducted in the traditional manner where the author(s) select paper based on their area of expertise, interest and experience. Limitation of such reviews includes authors’ selection bias of studies to be included and limited or no use of advanced BA tools for analysis. This study fills this research gap by conducting an SLR of RFID in supply chains to identify important research trends in this field through the use of advanced BA tools.

Machine Learning or the ability of a machine to learn automatically has garnered a lot of interest in the last years. It has proven to be a valuable tool for aiding decision makers and improving the productivity of enterprise processes, thanks to its ability to learn and find interesting patters in data. Thereby, supply chains can take advantage from Machine Learning to improve their productivity thanks to the better forecasts. As such, this paper examines multiple algorithms of Machine Learning and explores their applications for the various supply chain processes.

The Cyber Supply Chain (CSC) system is a multifaceted system with multiple subsystems carrying out distinct functions. The inherent vulnerabilities and threats from any portion of the system that can be exploited at any point in the supply chain make supply chain security difficult. This can cause a severe disruption on the overall business continuity. Thus, it is critical for organizations to comprehend and assess the risks in order to implement the appropriate supply chain security management measures. In order to analyse and forecast the risks based on the features of Cyber Threat Intelligence (CTI), we have combined CTI with Machine Learning (ML) approaches. To demonstrate the applicability of our approach, CTI data is gathered and a number of ML algorithms, i.e., Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF) and Decision Tree (DT), are used to develop predictive analytics using the Microsoft Malware Prediction dataset. KEYWORDS: Cyber Supply Chain, Malware, Cyber Threat Intelligence, Machine Learning.

Machine learning classifiers are increasingly used to create predictive models for pathological complete response (pCR) in breast cancer after neoadjuvant therapy (NAT). Few studies have compared the effectiveness of different ML classifiers. This study evaluated radiomics models based on pre- and post-contrast first-phase T1 weighted images (T1WI) in predicting breast cancer pCR after NAT and compared the performance of ML classifiers. This retrospective study enrolled 281 patients undergoing NAT from the Duke-Breast-Cancer-MRI dataset. Radiomic features were extracted from pre- and post-contrast first-phase T1WI images. The Synthetic Minority Oversampling Technique (SMOTE) was applied, then the dataset was randomly divided into training and validation groups (7:3). The radiomics model was built using selected optimal features. Support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were classifiers. Receiver operating characteristic curves were used to assess predictive performance. LightGBM performed best in predicting pCR [area under the curve (AUC): 0.823, 95% confidence interval (CI) [0.743-0.902], accuracy 74.0%, sensitivity 85.0%, specificity 67.2%]. During subgroup analysis, RF was most effective in pCR prediction in luminal breast cancers (AUC: 0.914, 95% CI [0.847-0.981], accuracy 87.0%, sensitivity 85.2%, specificity 88.1%). In triple-negative breast cancers, LightGBM performed best (AUC: 0.836, 95% CI [0.708-0.965], accuracy 78.6%, sensitivity 68.2%, specificity 90.0%). The LightGBM-based radiomics model performed best in predicting pCR in patients with breast cancer. RF and LightGBM showed promising results for luminal and triple-negative breast cancers, respectively.

The disease may be an explicit status that negatively affects human health. Cardiopathy is one of the common deadly diseases that is attributed to unhealthy human habits compared to alternative diseases. With the help of machine learning (ML) algorithms, heart disease can be noticed in a short time as well as at a low cost. This study adopted four machine learning models, such as random forest (RF), decision tree (DT), AdaBoost (AB), and K-nearest neighbor (KNN), to detect heart disease. A generalized algorithm was constructed to analyze the strength of the relevant factors that contribute to heart disease prediction. The models were evaluated using the datasets Cleveland, Hungary, Switzerland, and Long Beach (CHSLB), and all were collected from Kaggle. Based on the CHSLB dataset, RF, DT, AB, and KNN models predicted an accuracy of 99.03%, 96.10%, 100%, and 100%, respectively. In the case of a single (Cleveland) dataset, only two models, namely RF and KNN, show good accuracy of 93.437% and 97.83%, respectively. Finally, the study used Streamlit, an internet-based cloud hosting platform, to develop a computer-aided smart system for disease prediction. It is expected that the proposed tool together with the ML algorithm will play a key role in diagnosing heart diseases in a very convenient manner. Above all, the study has made a substantial contribution to the computation of strength scores with significant predictors in the prognosis of heart disease.

Kidneys are the filter of the human body. About 10% of the global population is thought to be affected by Chronic Kidney Disease (CKD), which causes kidney function to decline. To protect in danger patients from additional kidney damage, effective risk evaluation of CKD and appropriate CKD monitoring are crucial. Due to quick and precise detection capabilities, Machine Learning models can help practitioners accomplish this goal efficiently; therefore, an enormous number of diagnosis systems and processes in the healthcare sector nowadays are relying on machine learning due to its disease prediction capability. In this study, we designed and suggested disease predictive computer-aided designs for the diagnosis of CKD. The dataset for CKD is attained from the repository of machine learning of UCL, with a few missing values; those are filled in using "mean-mode" and "Random sampling method" strategies. After successfully achieving the missing data, eight ML techniques (Random Forest, SVM, Naive Bayes, Logistic Regression, KNN, XGBoost, Decision Tree, and AdaBoost) were used to establish models, and the performance evaluation comparisons among the result accuracies are measured by the techniques to find the machine learning models with the highest accuracy. Among them, Random Forest as well as Logistic Regression showed an outstanding 99% accuracy, followed by the Ada Boost, XGBoost, Naive Bayes, Decision Tree, and SVM, whereas the KNN classifier model stands last with an accuracy of 73%.

In today’s dynamic business environment, the accurate prediction of sales orders plays a critical role in optimizing Supply Chain Management (SCM) and enhancing operational efficiency. In a rapidly changing, Fast-Moving Consumer Goods (FMCG) business, it is essential to analyze the sales of the products and accordingly plan the supply. Due to low data volume and complexity, traditional forecasting methods struggle to capture intricate patterns. Domain Adversarial Neural Networks (DANNs) offer a promising solution by integrating transfer learning techniques to improve prediction accuracy across diverse datasets. This study presents a new sales order prediction framework that combines DANN-based feature extraction and various machine learning models. The DANN method generalizes the data, maintaining the data behavior’s originality. The approach addresses challenges like limited data availability and high variability in sales behavior. Using the transfer learning approach, the DANN model is trained on the training data, and this pre-trained DANN model extracts relevant features from unknown products. In contrast, Machine Learning (ML) algorithms are used to build predictive models based on it. The hyperparameter tuning of ensemble models such as Decision Tree (DT) and Random Forest (RF) is also performed. Models like the DT and RF Regressor perform better than Linear Regression and Support Vector Regressor. Notably, even without hyperparameter tuning, the Extreme Gradient Boost (XGBoost) Regressor model outperforms all the other models. This comprehensive analysis highlights the comparative benefits of various models and establishes the superiority of XGBoost in predicting sales orders effectively.

The emergence of artificial intelligence (AI) and its related capabilities has led industries to rethink the existing practices of conventional supply chain management and data analysis. Machine learning (ML), Deep Learning (DL) and their unique ability to predict future data and classify data have led to important research in the supply chain (SC) domain, particularly in identifying and prioritizing supply chain risks. This paper proposes several DL methodologies to exploit the benefit of DL, particularly to identify whether any product will be delivered late due to any unforeseen reason in a complex SC system. Four different DL architectures (Simple-LSTM, Deep-LSTM, 1D-CNN, and TCN-1DSPCNN models) are proposed to extract features, while six variant classifiers: Softmax, random trees (RT), random forest (RF), K-nearest neighbor (KNN), artificial neural network (ANN), and support vector machine (SVM), were used to classify delay or non-delay information. By seamlessly capturing intricate temporal dependencies, these DL models enhance accuracy in robustly identifying supply chain late orders. Leveraging their hierarchical feature learning, these proposed DL models excel in recognizing subtle patterns and correlations, making them ideal for classifying late orders within the supply chain. Their parallel processing prowess facilitates real-time decision support, allowing organizations to address potential delays and allocate resources effectively and proactively. Five-fold cross-validation is presented to avoid over-fitting and to prove the efficiency of the proposed DL models. The total accuracies of the six ML classifiers are 74.03, 75.81, 93.35, 87.72, 93.59, and 95.10, respectively, while the maximum accuracies obtained from four proposed DL methodologies obtained an accuracy of 97.6, 98.63, 100, 100% respectively using the SVM classifier for predicting late orders based on five-fold cross-validation.

Background To assess the feasibility of a machine learning (ML) approach using radiomics features of perfusion defects on rest myocardial perfusion imaging (MPI) to detect the presence of hibernating myocardium. Methodology Data of patients who underwent 99mTc-sestamibi MPI and 18F-FDG PET/CT for myocardial viability assessment were retrieved. Rest MPI data were processed on ECToolbox, and polar maps were saved using theNFile PMap tool. The reference standard for defining hibernating myocardium was the presence of mismatched perfusion-metabolism defect with impaired myocardial contractility at rest. Perfusion defects on the polar maps were delineated with regions of interest (ROIs) after spatial resampling and intensity discretization. Replicable random sampling allocated 80% (257) of the perfusion defects of the patients from January 2017 to September 2022 to the training set and the remaining 20% (64) to the validation set. An independent dataset of perfusion defects from 29 consecutive patients from October 2022 to January 2023 was used as the testing set for model evaluation. One hundred ten first and second-order texture features were extracted for each ROI. After feature normalization and imputation, 14 best-ranked features were selected using a multistep feature selection process including the Logistic Regression and Fast Correlation-Based Filter. Thirteen supervised ML algorithms were trained with stratified five-fold cross-validation on the training set and validated on the validation set. The ML algorithms with a Log Loss of <0.688 and <0.672 in the cross-validation and validation steps were evaluated on the testing set. Performance matrices of the algorithms assessed included area under the curve (AUC), classification accuracy (CA), F1 score, precision, recall, and specificity. To provide transparency and interpretability, SHapley Additive exPlanations (SHAP) values were assessed and depicted as beeswarm plots. Results Two hundred thirty-nine patients (214 males; mean age 56 ± 11 years) were enrolled in the study. There were 371 perfusion defects (321 in the training and validation sets; 50 in the testing set). Based on the reference standard, 168 perfusion defects had hibernating myocardium (139 in the training and validation sets; 29 in the testing set). On cross-validation, six ML algorithms with Log Loss <0.688 had AUC >0.800. On validation, 10 ML algorithms had a Log Loss value <0.672, among which six had AUC >0.800. On model evaluation of the selected models on the unseen testing set, nine ML models had AUC >0.800 with Gradient Boosting Random Forest (xgboost) [GB RF (xgboost)] achieving the highest AUC of 0.860 and could detect the presence of hibernating myocardium in 21/29 (72.4%) perfusion defects with a precision of 87.5% (21/24), specificity 85.7% (18/21), CA 78.0% (39/50) and F1 Score 0.792. Four models depicted a clear pattern of model interpretability based on the beeswarm SHAP plots. These were GB RF (xgboost), GB (scikit-learn), GB (xgboost), and Random Forest. Conclusion Our study demonstrates the potential of ML in detecting hibernating myocardium using radiomics features extracted from perfusion defects on rest MPI images. This proof-of-concept underscores the notion that radiomics features capture nuanced information beyond what is perceptible to the human eye, offering promising avenues for improved myocardial viability assessment.

The diagnostic process for Autism Spectrum Disorder (ASD) typically involves time-consuming assessments conducted by specialized physicians. To improve the efficiency of ASD screening, intelligent solutions based on machine learning have been proposed in the literature. However, many existing ML models lack the incorporation of medical tests and demographic features, which could potentially enhance their detection capabilities by considering affected features through traditional feature selection approaches. This study aims to address the aforementioned limitation by utilizing a real dataset containing 45 features and 983 patients. To achieve this goal, a two-phase methodology is employed. The first phase involves data preparation, including handling missing data through model-based imputation, normalizing the dataset using the Min-Max method, and selecting relevant features using traditional feature selection approaches based on affected features. In the second phase, seven ML classification techniques recommended by the literature, including Decision Trees (DT), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost, Gradient Boosting (GB), and Neural Network (NN), are utilized to develop ML models. These models are then trained and tested on the prepared dataset to evaluate their performance in detecting ASD. The performance of the ML models is assessed using various metrics, such as Accuracy, Recall, Precision, F1-score, AUC, Train time, and Test time. These metrics provide insights into the models' overall accuracy, sensitivity, specificity, and the trade-off between true positive and false positive rates. The results of the study highlight the effectiveness of utilizing traditional feature selection approaches based on affected features. Specifically, the GB model outperforms the other models with an accuracy of 87%, Recall of 87%, Precision of 86%, F1-score of 86%, AUC of 95%, Train time of 21.890, and Test time of 0.173. Additionally, a benchmarking analysis against five other studies reveals that the proposed methodology achieves a perfect score across three key areas. By considering affected features through traditional feature selection approaches, the developed ML models demonstrate improved performance and have the potential to enhance ASD screening and diagnosis processes.

Early detection of defects in steel plates is essential to ensure structural integrity and product quality in the metal manufacturing industry. This study compares the performance of five machine learning algorithms Support Vector Classifier (SVC), Nu-Support Vector Classifier (NuSVC), Decision Tree (DT), Random Forest (RF), and CatBoost (CB) to classify seven categories of steel plate defects using 26 technical features from a publicly available dataset on Kaggle. The preprocessing pipeline included outlier detection (IQR method), class imbalance correction using SMOTE, and feature normalization via StandardScaler. The models were evaluated using classification metrics such as Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Log Loss. Results revealed that the CatBoost algorithm achieved the most balanced and consistent performance, with an AUC of 0.93, accuracy of 68.3%, and the lowest Log Loss value (0.786). In contrast, the Decision Tree showed severe overfitting with perfect training performance but poor generalization (Log Loss = 15.72). This study highlights the promise of CatBoost as an interpretable and efficient solution for automated defect detection in steel manufacturing, while also offering transparent reproducibility pathways for further research.

Emotion recognition plays a pivotal role in advancing Human-Computer Interaction (HCI) by enabling systems to understand and respond to human emotional states. Among various modalities, Speech Emotion Recognition (SER) stands out as a non-invasive, cost-effective, and temporally efficient approach for detecting emotions. This study leverages the RAVDESS dataset, which provides high-quality audio recordings for emotion classification. The proposed methodology involves preprocessing audio signals to remove noise, extracting temporal and spectral features in both time and frequency domains, and implementing machine learning models for multi-class emotion classification. The study evaluates and compares the performance of several classification models, including Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Decision Trees (DT). Experimental results demonstrate promising accuracy levels, highlighting the potential of these machine learning techniques in SER. This research contributes to the integration of SER within Brain-Computer Interfaces (BCI) and other emotion-aware applications, paving the way for enhanced interactive systems. Keywords – Speech Emotion Recognition -Machine Learning - Random Forest -Multilayer Perceptron - Support Vector Machine - Convolutional Neural Networks - Decision Tree - RAVDESS Dataset

Fake online reviews hinder internet marketing efforts to build businesses and brands in a competitive market with changing consumer expectations. This helps brands attract clients, making fake online reviews hard to uncover. Hence, fake reviews and websites are extensively examined. AI models like the Generalized Additive2 Model (GA2M) and its ensemble with the Elastic-net Classifier model have been studied using Log-Loss metric. This research, analysis, and depiction help demarcate bogus hotel reviews and websites from genuine entities. The paper uses ML classifiers (Decision Tree, Logistic Regression, Naïve Bayes) and ensemble models (Random Forest, Gradient Boosting) to identify legitimate websites using binary classification. This article compares ML classifiers and ensemble models by accuracy, precision, recall, f1-score, and ROC-AUC to evaluate their pros and downsides. Elastic-Net Classifier (L2 / Binomial Deviance) with score of 0.2879 outperformed GA2M model by 0.66% in LogLoss holdout score on Hotel dataset. LogLoss predicts values better than ROC-AUC due to its closer proximity to predicting actual values. Elastic-Net Classifier (L2 / Binomial Deviance) surpassed GA2M in F1 score, precision, and accuracy by 0.4%, 1.84%, and 0.63%. Ensemble techniques outperform ML classifiers in the Fraudulent and Legitimate Online Shops dataset with ROC-AUC scores of 0.71%, 1.73%, 0.76%, 1.10%, and 0.63% using 50% to 90% training datasets and 50% to 10% holdout datasets.

Online games are hazardous to one's health and well-being. Addiction to video games has now become a concern to Bangladeshi youth. Our lives are negatively impacted by online gaming. We must keep an eye on our country's youth to ensure that they do not become addicted to any kind of internet gaming. We must refrain from playing games in order to avoid being hooked on them. Machine learning will be used to forecast the likelihood of becoming addicted to video games. We begin by reviewing relevant studies, journals, and internet publications, and then we speak with online gaming addictions. We discovered certain common elements that are linked to gaming addiction and Lemmen’s gaming addiction scale to measure the whether a person is addicted or not. Then, based on those criteria, such as age, gender, mental pressure, and so on, we collect data. We gather information from both addicts and nonaddicts. There are two possible outcomes: We processed all of the data once it was collected and developed a processed dataset. On our processed dataset, we used machine learning techniques. In different predictions and detection systems, machine learning, artificial intelligence and deep learning are applied. KNN (K-Nearest Neighbor), LR (Logistic Regression), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Random Forest (RF), Adaptive Boosting (ADA Boosting), Decision Tree (DT), XGBOOST and Gradient Boosting (GB) classifier are some of the methods we utilize. Adaptive Boosting outperformed the other nine methods in our study. All the nine classifiers predict with high accuracy and among them, Adaptive Boosting (ADA Boosting) gives the maximum accuracy which is 93.00%.

The importance of supply chain management to business operations and social growth cannot be overstated. Today's supply chains are very different from those of a few years ago and continually change in a highly competitive climate. Investing in technology that can handle the sheer complexity of dynamic supply chain operations is necessary. Current supply chain solutions cannot completely mitigate the risks of inefficiencies at various supply chain stages. Several functional supply chain applications based on Machine Learning (ML) have appeared in recent years; however, few studies have analyzed data-driven logistics and supply chain management applications. Robotics, machine learning, and natural language processing are potential supply chain transformation enablers. This paper offers a thorough and up-to-date literature review that examines what researchers have done regarding data-driven techniques in the supply chain context and identifies what needs further exploration. We reviewed 135 research articles published between 2008 and 2022 on the Scopus database and created a classification of the research material on data-driven logistics and supply chain management. This comprehensive literature evaluation will enable researchers and business administrators to undertake innovation initiatives better and redirect money and human resource efforts.