China 
Africa 
Explore chapters and articles related to this topic
Knowledge Discovery with RapidMiner
Published in Richard J. Roiger, Data Mining, 2017
RapidMiner is a well-known commercial data mining and predictive analytics tool developed by a company with the same name. In this chapter, we introduce RapidMiner Studio an easy-to-use, open-source, and code-free version of RapidMiner’s commercial product. RapidMiner uses a workflow paradigm for building models to solve complex problems. RapidMiner’s software platform offers several options for interacting with its interface. We leave exploring these various options to you. Here we concentrate on showing you how to use RapidMiner to design and execute workflows that solve problems with the techniques discussed in this text.
Implementation
Published in Seyedeh Leili Mirtaheri, Reza Shahbazian, Machine Learning Theory to Applications, 2022
Seyedeh Leili Mirtaheri, Reza Shahbazian
RapidMiner is a general-purpose data science software platform designed for Machine Learning, Deep Learning, text mining, predictive analytics, and data preparation [111]. It is a cross-platform framework developed on an open core model written in java. The development of RapidMiner (also known as YALE, Yet Another Learning Environment) started in 2001 at the Artificial Intelligence Unit of the Technical University of Dortmund.Implementation 177
Prediction of Diabetics in the Early Stages Using Machine-Learning Tools and Microsoft Azure AI Services
Published in Sarvesh Tanwar, Sumit Badotra, Ajay Rana, Machine Learning, Blockchain, and Cyber Security in Smart Environments, 2023
Chandrashekhar Kumbhar, Abid Hussain
RapidMiner is a data science platform that can perform essential tasks including data preparation, data visualization, machine learning, data analysis and deep learning. It includes a number of modelling, feature selection, and extraction options. Some machine-learning techniques also apply to these results (Haq et al., 2020).
Enhancing resilience in marine propulsion systems by adopting machine learning technology for predicting failures and prioritising maintenance activities
Published in Journal of Marine Engineering & Technology, 2023
Mohsen Elmdoost-gashti, Mahmood Shafiee, Ali Bozorgi-Amiri
The remainder of the paper is organised as follows. Section 2 reviews the state-of-the-art maintenance strategies and highlights the importance of CBM in maritime industry. It also discusses the role of data mining and ML techniques in solving maintenance decision-making problems and reviews the applications of ML techniques in shipping industry. Section 3 presents the proposed methodology in detail. Section 4 reports the results of applying ML algorithms to a dataset that is publicly available on the repository of the University of California in Irvine (UCI) (Repository 2014). Dataset has been produced from a sophisticated simulator of a gas turbine mounted on a frigate characterised by a COmbined Diesel eLectric And Gas (CODLAG) propulsion plant type. We conduct a classification process with ML algorithms by using RapidMiner software. RapidMiner is a data science software platform that provides an integrated environment to support all steps of the ML process, including data preparation, predictive analytics, data visualisation, and model validation and optimisation. Finally, section 5 concludes the research and provides recommendations for future research.
Modeling the productivity of mechanized CTL harvesting with statistical machine learning methods
Published in International Journal of Forest Engineering, 2020
Eero Liski, Pekka Jounela, Heikki Korpunen, Amanda Sosa, Ola Lindroos, Paula Jylhä
The practical application of the results of the present study is limited by the fact that GBM and SVM do not produce parametric equations. The OLS regression models’ equations can be utilized using non-specialized software (e.g. MS Excel). For GBM and SVM, one option for practical applicability would be to serve the GBM and SVM models in the cloud, where anyone could apply them to their own dataset. However, applying all the models would require data with the same distribution as in the dataset used in the present study. Another solution to apply to GBM and SVM would be to follow the procedures described in this article and apply them to another dataset. For this, however, specific software is needed (e.g. R, R Core Team 2018; RapidMiner, Mierswa et al. 2006; Knime, Python and Weka, Eibe et al. 2016). They all include specialized packages (extensions) for various tasks. They can be used interactively; for example, RapidMiner has extensions for R, Python and Weka. So a fraction of a process can be run concurrently in another software using the same (one) script of the parent software. Currently available machine learning software has more or less the same mainstream functionalities with minor differences in the implementation of algorithms.
Predicting project cost overrun levels in bidding stage using ensemble learning
Published in Journal of Asian Architecture and Building Engineering, 2020
Hyosoo Moon, Trefor P. Williams, Hyun-Soo Lee, Moonseo Park
This section explains the development of the ensemble learning model and the process to select the input data for the project cost overrun prediction model. A stacking ensemble model was developed using the RapidMiner environment (Mierswa et al. 2006). RapidMiner is an open-source software system that allows for the rapid development of data-mining models. The model outputs a prediction of the level of cost overruns that occurs during construction execution. Figure 2 depicts the structure of the developed model.