Search results

In rotary machines, the bearing failure is one of the major causes of the breakdown of machinery. The bearing degradation monitoring is a great anxiety for the prevention of bearing failures. This paper aims to present a combination of the stationary wavelet decomposition and extra-trees regression (ETR) for the evaluation of bearing degradation.

The higher order cumulants features are extracted from the bearing vibration signals by using the stationary wavelet decomposition (stationary wavelet transform [SWT]). The extracted features are then subjected to the ETR for obtaining normal and failure state. A dominance level curve build using the dissimilarity data of test object and retained as health degradation indicator for the evaluation of bearing health.

Experiment conducts to verify and assess the effectiveness of ETR for the evaluation of performance of bearing degradation. To justify the preeminence of recommended approach, it is compared with the performance of random forest regression and multi-layer perceptron regression.

The experimental results indicated that the presently adopted method shows better performance for detecting the degradation more accurately at early stage. Furthermore, the diagnostics and prognostics have been getting much attention in the field of vibration, and it plays a significant role to avoid accidents.

The purpose is twofold. First, this study aims to establish that black box tree-based machine learning (ML) models have better predictive performance than a standard linear regression (LR) hedonic model for rent prediction. Second, it shows the added value of analyzing tree-based ML models with interpretable machine learning (IML) techniques.

Data on Belgian residential rental properties were collected. Tree-based ML models, random forest regression and eXtreme gradient boosting regression were applied to derive rent prediction models to compare predictive performance with a LR model. Interpretations of the tree-based models regarding important factors in predicting rent were made using SHapley Additive exPlanations (SHAP) feature importance (FI) plots and SHAP summary plots.

Results indicate that tree-based models perform better than a LR model for Belgian residential rent prediction. The SHAP FI plots agree that asking price, cadastral income, surface livable, number of bedrooms, number of bathrooms and variables measuring the proximity to points of interest are dominant predictors. The direction of relationships between rent and its factors is determined with SHAP summary plots. In addition to linear relationships, it emerges that nonlinear relationships exist.

Rent prediction using ML is relatively less studied than house price prediction. In addition, studying prediction models using IML techniques is relatively new in real estate economics. Moreover, to the best of the authors’ knowledge, this study is the first to derive insights of driving determinants of predicted rents from SHAP FI and SHAP summary plots.

The purpose of this study is to select the appropriate forecasting model at the retail stage for selected vegetables on the basis of performance analysis.

Various forecasting models such as the Box–Jenkins-based auto-regressive integrated moving average model and machine learning-based algorithms such as long short-term memory (LSTM) networks, support vector regression (SVR), random forest regression, gradient boosting regression (GBR) and extreme GBR (XGBoost/XGBR) were proposed and applied (i.e. modeling, training, testing and predicting) at the retail stage for selected vegetables to forecast demand. The performance analysis (i.e. forecasting error analysis) was carried out to select the appropriate forecasting model at the retail stage for selected vegetables.

From the obtained results for a case environment, it was observed that the machine learning algorithms, namely LSTM and SVR, produced the better results in comparison with other different demand forecasting models.

The results obtained from the case environment cannot be generalized. However, it may be used for forecasting of different agriculture produces at the retail stage, capturing their demand environment.

The implementation of LSTM and SVR for the case situation at the retail stage will reduce the forecast error, daily retail inventory and fresh produce wastage and will increase the daily revenue.

The demand forecasting model selection for agriculture produce at the retail stage on the basis of performance analysis is a unique study where both traditional and non-traditional models were analyzed and compared.

Excessive tool wear is responsible for damage or breakage of the tool, workpiece, or machining center. Thus, it is crucial to examine tool conditions during the machining process to improve its useful functional life and the surface quality of the final product. AI-based tool wear prediction techniques have proven to be effective in estimating the Remaining Useful Life (RUL) of the cutting tool. However, the model prediction needs improvement in terms of accuracy.

This paper represents a methodology of fusing a feature selection technique along with state-of-the-art deep learning models. The authors have used NASA milling data sets along with vibration signals for tool wear prediction and performance analysis in 15 different fault scenarios. Multiple steps are used for the feature selection and ranking. Different Long Short-Term Memory (LSTM) approaches are used to improve the overall prediction accuracy of the model for tool wear prediction. LSTM models' performance is evaluated using R-square, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) parameters.

The R-square accuracy of the hybrid model is consistently high and has low MAE, MAPE and RMSE values. The average R-square score values for LSTM, Bidirection, Encoder–Decoder and Hybrid LSTM are 80.43, 84.74, 94.20 and 97.85%, respectively, and corresponding average MAPE values are 23.46, 22.200, 9.5739 and 6.2124%. The hybrid model shows high accuracy as compared to the remaining LSTM models.

The low variance, Spearman Correlation Coefficient and Random Forest Regression methods are used to select the most significant feature vectors for training the miscellaneous LSTM model versions and highlight the best approach. The selected features pass to different LSTM models like Bidirectional, Encoder–Decoder and Hybrid LSTM for tool wear prediction. The Hybrid LSTM approach shows a significant improvement in tool wear prediction.

This study aims to analyze Kickstarter data along with social media data from a data mining perspective. Kickstarter is a crowdfunding financing plataform and is a form of fundraising and is increasingly being adopted as a source for achieving the viability of projects. Despite its importance and adoption growth, the success rate of crowdfunding campaigns was 47% in 2017, and it has decreased over the years. A way of increasing the chances of success of campaigns would be to predict, by using machine learning techniques, if a campaign would be successful. By applying classification models, it is possible to estimate if whether or not a campaign will achieve success, and by applying regression models, the authors can forecast the amount of money to be funded.

The authors propose a solution in two phases, namely, launching and campaigning. As a result, models better suited for each point in time of a campaign life cycle.

The authors produced a static predictor capable of classifying the campaigns with an accuracy of 71%. The regression method for phase one achieved a 6.45 of root mean squared error. The dynamic classifier was able to achieve 85% of accuracy before 10% of campaign duration, the equivalent of 3 days, given a campaign with 30 days of length. At this same period time, it was able to achieve a forecasting performance of 2.5 of root mean squared error.

The authors carry out this research presenting the results with a set of real data from a crowdfunding platform. The results are discussed according to the existing literature. This provides a comprehensive review, detailing important research instructions for advancing this field of literature.

Cobalt-based alloys exhibit a unique combination of wear resistance, strength and corrosion resistance. Localized corrosion of such alloys in seawater system can be several orders of magnitude faster than general corrosion, and direct experimental evidence of the local activation process is still lacking, which makes the accurate prediction for properties difficult, especially for long-term corrosion. The purpose of this study is revealing the relationship between multiple environments and corrosion properties to predict the corrosion of cobalt-based alloys.

A data-driven method for the prediction of the corrosion behavior of cast and hot isostatic-pressed CoCrMo/W alloys in seawater is proposed. The gradient boosting regression models calculate mean relative errors (MREs) of 0.160 and 0.435 by evaluating a hold-out set for breakdown potential (E_b) and maximum current density (i_max), respectively, considering various compositions, synthesis methods and corrosion environments.

The models can be used to estimate the “unseen” cobalt-based alloy after immersion in 3.5 Wt.% NaCl solution for one, two, four and eight months to obtain high precision with MREs of 7.8% and 9.8% for E_b and i_max, respectively.

Machine learning method provides novel and promising insights for the prediction of localized corrosion properties.

Indoor air quality monitoring is extremely important in urban, industrial areas. Considering the devastating effect of declining quality of air in major part of the countries like India and China, it is highly recommended to monitor the quality of air which can help people with respiratory diseases, children and elderly people to take necessary precautions and stay safe at their homes. The purpose of this study is to detect air quality and perform predictions which could be part of smart home automation with the use of newer technology.

This study proposes an Internet-of-Things (IoT)-based air quality measurement, warning and prediction system for ambient assisted living. The proposed ambient assisted living system consists of low-cost air quality sensors and ESP32 controller with new generation embedded system architecture. It can detect Indoor Air Quality parameters like CO, PM2.5, NO2, O3, NH3, temperature, pressure, humidity, etc. The low cost sensor data are calibrated using machine learning techniques for performance improvement. The system has a novel prediction model, multiheaded convolutional neural networks-gated recurrent unit which can detect next hour pollution concentration. The model uses a transfer learning (TL) approach for prediction when the system is new and less data available for prediction. Any neighboring site data can be used to transfer knowledge for early predictions for the new system. It can have a mobile-based application which can send warning notifications to users if the Indoor Air Quality parameters exceed the specified threshold values. This is all required to take necessary measures against bad air quality.

The IoT-based system has implemented the TL framework, and the results of this study showed that the system works efficiently with performance improvement of 55.42% in RMSE scores for prediction at new target system with insufficient data.

This study demonstrates the implementation of an IoT system which uses low-cost sensors and deep learning model for predicting pollution concentration. The system is tackling the issues of the low-cost sensors for better performance. The novel approach of pretrained models and TL work very well at the new system having data insufficiency issues. This study contributes significantly with the usage of low-cost sensors, open-source advanced technology and performance improvement in prediction ability at new systems. Experimental results and findings are disclosed in this study. This will help install multiple new cost-effective monitoring stations in smart city for pollution forecasting.

From a technological determinist perspective, machine learning (ML) may significantly contribute towards sustainable development. The purpose of this study is to synthesize prior literature on the role of ML in promoting sustainability and to encourage future inquiries.

This study conducts a systematic review of 110 papers that demonstrate the utilization of ML in the context of sustainable development.

ML techniques may play a vital role in enabling sustainable development by leveraging data to uncover patterns and facilitate the prediction of various variables, thereby aiding in decision-making processes. Through the synthesis of findings from prior research, it is evident that ML may help in achieving many of the United Nations’ sustainable development goals.

This study represents one of the initial investigations that conducted a comprehensive examination of the literature concerning ML’s contribution to sustainability. The analysis revealed that the research domain is still in its early stages, indicating a need for further exploration.

GraphQL is a new Open API specification that allows clients to send queries and obtain data flexibly according to their needs. However, a high-complexity GraphQL query may lead to an excessive data volume of the query result, which causes problems such as resource overload of the API server. Therefore, this paper aims to address this issue by predicting the response data volume of a GraphQL query statement.

This paper proposes a GraphQL response data volume prediction approach based on Code2Vec and AutoML. First, a GraphQL query statement is transformed into a path collection of an abstract syntax tree based on the idea of Code2Vec, and then the query is aggregated into a vector with the fixed length. Finally, the response result data volume is predicted by a fully connected neural network. To further improve the prediction accuracy, the prediction results of embedded features are combined with the field features and summary features of the query statement to predict the final response data volume by the AutoML model.

Experiments on two public GraphQL API data sets, GitHub and Yelp, show that the accuracy of the proposed approach is 15.85% and 50.31% higher than existing GraphQL response volume prediction approaches based on machine learning techniques, respectively.

This paper proposes an approach that combines Code2Vec and AutoML for GraphQL query response data volume prediction with higher accuracy.

This study aims to propose a more precise method for robust design optimization of mechanical structures with black-box problems, while also considering the efficiency of uncertainty analysis.

The method first introduces a dual adaptive chaotic flower pollination algorithm (DACFPA) to overcome the shortcomings of the original flower pollination algorithm (FPA), such as its susceptibility to poor accuracy and convergence efficiency when dealing with complex optimization problems. Furthermore, a DACFPA-Kriging model is developed by optimizing the relevant parameter of Kriging model via DACFPA. Finally, the dual Kriging model is constructed to improve the efficiency of uncertainty analysis, and a robust design optimization method based on DACFPA-Dual-Kriging is proposed.

The DACFPA outperforms the FPA, particle swarm optimization and gray wolf optimization algorithms in terms of solution accuracy, convergence speed and capacity to avoid local optimal solutions. Additionally, the DACFPA-Kriging model exhibits superior prediction accuracy and robustness contrasted with the original Kriging and FPA-Kriging. The proposed method for robust design optimization based on DACFPA-Dual-Kriging is applied to the motor hanger of the electric multiple units as an engineering case study, and the results confirm a significant reduction in the fluctuation of the maximum equivalent stress.

This study represents the initial attempt to enhance the prediction accuracy of the Kriging model using the improved FPA and to combine the dual Kriging model for uncertainty analysis, providing an idea for the robust optimization design of mechanical structure with black-box problem.