Evaluation and Comparison of Selected Machine Learning Methods for Improving Maintenance Processes

Purpose In today's competitive industries, the selection of best suitable maintenance strategy is dependent on large number of quantitative and qualitative factors, and it becomes an extensively difficult problem for maintenance engineers. Over the years, a diverse range of solution methodologies have been developed for solving this multi-criteria decision-making (MCDM) problem. In this paper, the authors have presented a comprehensive review of latest maintenance strategy paradigms and solution approaches proposed for the selection of an appropriate strategy in various industries. It would provide a systematic mapping of developments in this field and identify some research gaps to explore further studies. Design/methodology/approach A systematic state-of-the-art comprehensive literature review on maintenance strategy paradigms and selection approaches is presented in this study. In this study, 87 research articles published in peer-reviewed journals, since year 2012, are reviewed. Findings For the selection of a suitable maintenance strategy, a variety of criteria are considered to better evaluate the alternatives. In this study, contemporary strategies are discussed, and their applications in different industries are also depicted. Moreover, through the analysis of extant literature, critical criteria are selected and classified in six major categories (namely, economic, technical, safety, environmental, feasibility and social) and further sub-categorized in quantitative and qualitative classes. These clusters of criteria can be helpful as an initial set of criteria for survey and then case- or industry-specific criteria can be shortlisted for further alternative evaluation. Practical implications From the perspective of maintenance managers, maintenance management can be a very difficult task, considering the numerous factors affecting the decision-making process. In order to help in the decision-making process, this study presents the contemporary maintenance strategies in a systematic manner. In a previous study (Kothamasu et al ., 2006), these strategies were classified into repair and prevent classes only. With the developments of autonomous maintenance and design out maintenance (DOM), it was fair to include continuous improvement class. It will help managers and practitioners to identify, according to organization policy, appropriate maintenance strategy alternatives for the asset. A benchmark set of state-of-the-art maintenance strategies are laid out with their applications. The industrial case studies discussed in this study summarizes the optimal maintenance strategies for respective industries. Also, most critical criteria are identified from the existing studies for various industries that can help maintenance practitioners in acknowledging the critical factors and making appropriate decisions. Evaluation parameters for the maintenance strategy selection (MSS) generally conflict with each other, and considering the difficulty of quantifying the qualitative measures, it is a challenging task to determine the optimal trade-off. In order to overcome these challenges, popular MCDM approaches, demonstrating effective results across different industries are discussed with their limitations and applications. Decision-makers can refer this study to identify best suitable decision-making technique for the MSS problem in the industry of their choice. Maintenance managers and engineers can refer the case studies illustrated in Tables 1 and 2 to analyse the MSS techniques proposed by previous studies with industry-specific applications. Social implications This study is an attempt to provide a reference point for research scholars interested in the field of maintenance management and/or development of maintenance strategy framework. This study provides a critical state-of-the-art review of efforts made in the field of MSS. The prominent maintenance strategies being implemented in contemporary industries are discussed with respective case studies. Interested researchers and academicians can familiarize themselves with these strategies and their distinct features in this study. In order to guide future studies and provide a reference point for academicians, MSS critical criteria used in extant literature are identified and classified into a comprehensive benchmark framework. Moreover, the industrial case studies are discussed with the most critical criteria of MSS for different industries and which strategy is most suitable for the respective industries based on these criteria. Table 1 presents different MCDM techniques and their hybrid applications for solving MSS problem that can help researchers in identifying research gaps. Future research can be directed at addressing the limitation of MCDM approach employed in existing studies and comparing the differences in results obtained by the proposed approach. Different industrial case studies with considered maintenance strategy alternatives are presented in Table 2, which can help researchers in identifying the industries that have not been studied yet. Moreover, not all of the existing studies are carried out by considering all the presented benchmark strategies, which can be addressed in future studies by interested researchers. More detailed discussion on research gaps is presented in the following section. Originality/value From the analysis of the extant literature, the authors could observe that the decision-making process adopted in numerous studies was limited to the classical maintenance strategies and not inclusive of aggressive maintenance strategy alternatives. To overcome these limitations and help maintenance managers in the decision-making, this study depicts the contemporary maintenance strategies, critical evaluation criteria and MCDM frameworks (employed to solve the MSS problem with industrial case studies) in a structured manner.

Purpose– This paper aims to synthesize and categorize the published literatures related to maintenance strategies formulation, selection and implementation in various industries. The purpose of this paper is to develop a conceptual framework based on literature review for formulation of maintenance strategies, selection and the implementation of selected strategies. Further, to study on impact of maintenance strategies implementation in maintenance function.Design/methodology/approach– A literature review has been carried out to identify the existing frameworks related to maintenance strategies formulation, selection of maintenance strategy and implementation of maintenance strategy in the industry. Literature support for all the conceptual constructs referred in the framework has been discussed to establish a logical sequence.Findings– A conceptual framework for maintenance strategies formulation, selection and implementation and its impact in maintenance function has been developed. Further, constructs and sub-constructs which form the basis for maintenance strategies formulation, selection and implementation have been identified from the literatures. In addition, propositions have also been formulated to support the conceptual framework and these propositions provide the logical relationship among the maintenance strategies formulation, selection among the formulated strategies and the implementation of these strategies.Research limitations/implications– The conceptual framework developed in this paper for maintenance strategy formulation and selection is yet to be empirically tested. The proposed framework can be tested in various industries.Practical implications– Literature study on maintenance strategy formulation and selection has so far been very limited. Maintenance strategy selection is a critical decision-making problem for the maintenance managers working in the process plant, manufacturing companies, etc. The conceptual framework proposed in this paper will help maintenance managers to asses, formulate, select suitable maintenance strategy and implement for their organization.Originality/value– The paper provides comprehensive study on maintenance strategy problem which will be useful to researchers, maintenance managers and other professionals in various industries such as process industry, manufacturing industry, etc., to understand maintenance strategy selection problem and implementation of maintenance strategy.

This research aims to categorize survey data to determine the level of satisfaction with the services provided by the village government as a public service provider. Villages or sub-districts currently offer services in response to community demand, although only partially or as efficiently as possible. The data collection technique used was distributing questionnaires to the village community. The method used for classification is the machine learning method. Before the classification process, feature selection is carried out at the data pre-processing stage using Particle Swarm Optimization (PSO), which has been proven to increase the accuracy of the classification values. The classification methods employed include Decision Tree (DT), Naive Bayes, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms for classification purposes. This study achieves the maximum level of accuracy in decision tree classification, attaining an accuracy rate of 97.74%. Subsequently, the KNN algorithm achieved an accuracy of 77.90%, the Nave Bayes algorithm achieved 64.4%, and the SVM algorithm, which yielded the lowest accuracy value, achieved 59.90%. Following the application of Particle Swarm Optimization (PSO) for optimization, the accuracy of the SVM and KNN algorithms improved to 98.3%. The Decision Tree algorithm achieved a value of 97.77%, while the Naive Bayes technique yielded a value of 69.30%.

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent-based learning — in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.

Integrated phenology and climate in rice yields prediction using machine learning methods

Predicting academic performance associated with physical fitness of primary school students using machine learning methods

Machine learning methods are widely used in automated technologies. Classification prediction is a machine learning based on data mining. Today, many technological devices can make new predictions by gaining experience from past data with machine learning methods. Machine learning is widely studied in two types, supervised and unsupervised. The limits of the objectives in supervised learning are predetermined. In unsupervised learning, there are no predetermined targets. In this learning, the machines are required to determine the targets automatically. Prediction process is one of the basic components of machine learning. Machines need to use some algorithms in order to perform the prediction process on the basis of data mining. k nearest neighbor (kNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) algorithms are used mostly. k nearest neighbor (kNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) algorithms are used mostly. These algorithms can be applied with the help of some tools on data sets. In this study, kNN algorithm was used to estimate Iris data set classification using Orange tool. The success of the KNN algorithm depends on using the correct attribute and changing the optimum k value. As a result of the tests, it was determined that when the k neighbor value was selected as 15, it was the most suitable k neighbor value, providing 98.67% classification prediction success in the Iris dataset.

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India

Prediction of chronic kidney disease (CKD) has emerged as a useful technique for early detection of at-risk persons and the introduction of appropriate management strategies. Machine learning and data-driven methods have been used in predictive modeling to examine massive databases of patient demographics, medical histories, test findings, and genetic information. These cutting-edge methods allow for the profiling of high-risk patients and the tailoring of healthcare administration approaches. Patient outcomes, complication rates, and healthcare system efficiency may all benefit greatly from CKD screening and prediction. Responsible use of CKD prediction algorithms, however, requires resolving issues with data availability, integration, and ethics. The area of medicine has benefited greatly from the use of Machine Learning (ML) methods, which have played an increasingly central role in illness prediction. In this study, we use a strategy that makes use of ML methods to construct effective tools for predicting the development of CKD. Multiple ML models are trained, and their results are compared using a variety of criteria. We applied five ML methods such as logistic regression (LR), Decision tree (DT), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). The LR and KNN have the highest accuracy with 99%.

Biomarkers are known to be the key driver behind targeted cancer therapies by either stratifying the patients into risk categories or identifying patient subgroups most likely to benefit. However, the ability of a biomarker to stratify patients relies heavily on the type of clinical endpoint data being collected. Of particular interest is the scenario when the biomarker involved is a continuous one where the challenge is often to identify cut-offs or thresholds that would stratify the population according to the level of clinical outcome or treatment benefit. On the other hand, there are well-established Machine Learning (ML) methods such as the Support Vector Machines (SVM) that classify data, both linear as well as non-linear, into subgroups in an optimal way. SVMs have proven to be immensely useful in data-centric engineering and recently researchers have also sought its applications in healthcare. Despite their wide applicability, SVMs are not yet in the mainstream of toolkits to be utilised in observational clinical studies or in clinical trials. This research investigates the very role of SVMs in stratifying the patient population based on a continuous biomarker across a variety of datasets. Based on the mathematical framework underlying SVMs, we formulate and fit algorithms in the context of biomarker stratified cancer datasets to evaluate their merits. The analysis reveals their superior performance for certain data-types when compared to other ML methods suggesting that SVMs may have the potential to provide a robust yet simplistic solution to stratify real cancer patients based on continuous biomarkers, and hence accelerate the identification of subgroups for improved clinical outcomes or guide targeted cancer therapies.

PurposeInjuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention.MethodsA search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle–Ottawa Scale. Study quality was evaluated using the GRADE working group methodology.ResultsEleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%). ConclusionsCurrent ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.

Deep learning (DL) and machine learning (ML) methods have recently contributed to the advancement of models in the various aspects of prediction, planning, and uncertainty analysis of smart cities and urban development. This paper presents the state of the art of DL and ML methods used in this realm. Through a novel taxonomy, the advances in model development and new application domains in urban sustainability and smart cities are presented. Findings reveal that five DL and ML methods have been most applied to address the different aspects of smart cities. These are artificial neural networks; support vector machines; decision trees; ensembles, Bayesians, hybrids, and neuro-fuzzy; and deep learning. It is also disclosed that energy, health, and urban transport are the main domains of smart cities that DL and ML methods contributed in to address their problems.

Due to the similar chemical composition and matrix effect, the accurate identification of mineral pigments on wall paintings has brought great challenges. This work implemented an identification study on three mineral pigments with similar chemical compositions by combining LIBS technology with the K-nearest neighbor algorithm (KNN), random forest (RF support vector machine (SVM), back propagation artificial neural network (Bp-ANN) and convolutional neural network (CNN) to find the most suitable identification method for mural research. Using the SelectKBest algorithm, 300 characteristic lines with the largest difference among the three pigments were determined. The identification models of KNN, RF, SVM, Bp-ANN and CNN were established and optimized. The results showed that, except for the KNN model, the identification accuracy of other models for mock-up mural samples was above 99%. However, only the identification accuracy of 2D-CNN models reached above 94% for actual mural samples. Therefore, the 2D-CNN model was determined as the most suitable model for the identification and analysis of mural pigments.

The key to achieving optimum ship system reliability and safety is to have a sound maintenance management system in place for mitigating or eliminating equipment/component failures. Maintenance has three key elements; risk assessment, maintenance strategy selection and the process of determining the optimal interval for the maintenance task. The optimisation of these three main elements of maintenance is what constitute a sound maintenance management system. One of the challenges that marine maintenance practitioners are faced with is the problem of maintenance selection for each equipment item of the ship machinery system. The decision making process involves utilising different conflicting decision criteria in selecting the optimum maintenance strategy from among multiple maintenance alternatives. In tackling such decision making problems the application of a multi-criteria decision making (MCDM) method is appropriate. Hence in this paper two hybrid MCDM methods; Delphi-AHP and Delphi-AHP-PROMETHEE, are presented for the selection of appropriate maintenance strategies for ship machinery systems and other related ship systems. A case study of a ship machinery system maintenance strategy selection problem is used to demonstrate the suitability of the proposed methods.

The support vector machine (SVM) combined with the K-nearest neighbor (KNN) algorithm is applied to the 3D image recognition algorithm to cope with the issues of 3D image recognition in the image processing process. In this paper, the KNN algorithm is used to extend the eigenvalues of the residual network from frequency to complex plane according to the eigenvalues of 3D images, and the relevant data are extracted from the images by using the corresponding separation rules of the SVM. Subsequently, a sparse observation model is established based on the SVM combined with the KNN, and the 3D image processing issue is converted to a residual network visualization issue of 3D image recognition by establishing a parameterized database. Meanwhile, detection of high-resolution distance of 3D images is conducted, and the variational inference method is used to visualize and analyze the 3D images accordingly. Finally, through the experimental study, it can be known that the method of SVM combined with the KNN algorithm can reach an accuracy of up to 94.18% in the dataset of the Princeton 3D polygonal models. After comparison with the existing SVM-KNN method and deep learning, it can be concluded that the method put forward in this paper has a higher recognition rate and stronger anti-interference capacity, and the algorithm has a superior convergence speed with less adjustment parameters.