China 
Africa 
Explore chapters and articles related to this topic
Machine Learning Techniques
Published in Neeraj Kumar, Aaisha Makkar, Machine Learning in Cognitive IoT, 2020
Weka is an open source software which is developed for executing machine learning algorithms. Weka contains a variety of tools for classification, regression, association, and clustering. It is licensed under GNU. Initially, Weka was developed for handling agricultural data; later in 1997, it was completely enhanced to support machine learning algorithms. It can also handle multiple file formats such as CSV. The necessary tools are already installed in Weka. The facility of the package manager is also available for installing the required packages and uninstalling the useless packages. Weka is developed in the Waikato University of New Zealand where Waikato Environment for Knowledge Analysis (Weka) is programmed in Java. It is executable on almost every platform and is mainly designed to help researchers.
Supplier Selection with Machine Learning Algorithms
Published in Turan Paksoy, Çiğdem Koçhan, Sadia Samar Ali, Logistics 4.0, 2020
Mustafa Servet Kιran, Engin Eșme, Belkιz Torğul, Turan Paksoy
It is being developed by Waikato University in New Zealand. WEKA which stands for “Waikato Environment for Knowledge Analysis”, is a comprehensive collection of machine learning algorithms employed in data mining tasks. WEKA is coded in java and is open source software released under the GNU General Public License. It can be run on Windows, Macintosh, Linux operating systems and almost all platforms. By connecting to databases via the Java Database Connectivity (JDBC) driver, it can treat a query consequence and store the results of the transaction in the databases.
Smartphone-Based Human Activity Recognition
Published in Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu, Device-to-Device based Proximity Service, 2017
Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu
Nowadays, WEKA is recognized as a landmark system in data mining and machine learning. It has achieved widespread acceptance within academia and business circles and has become a widely used tool for data mining research. It contains implementations of a number of learning algorithms, and it allows to easily evaluating them for a particular dataset using cross validation and random split, among others. WEKA also offers a Java API that facilitates the incorporation of new learning algorithms and evaluation methodologies on top of the pre-existing framework.
Influence of building parameters on energy efficiency levels: a Bayesian network study
Published in Advances in Building Energy Research, 2022
Lakmini Rangana Senarathne, Gaurav Nanda, Raji Sundararajan
For data analyzing and to obtain accurate results, we have used WEKA workbench (Holmes et al., 1994; Keleş et al., 2022) with various machine learning algorithms, including the libraries that facilitate the comparison of performance of algorithms. WEKA is an interactive tool that can do data manipulation, result visualization, database linkage and cross-validation using machine learning models. Supervised machine learning models that learn the relationship between input and output parameters using labelled training data are generally divided into two categories, namely, regression and classification. Regression models predict a continuous output value and calculate errors between the actual and predicted value and try to minimize the error. Similarly, classification models predict the class value, and results are presented as the accuracy of predicted values on the test dataset (Prasetiyo et al., 2019). In this study, we used the Bayesian network, a supervised machine learning algorithm as a classification model for the UCI energy efficiency dataset (Online, 2022).
Determining suitable machine learning classifier technique for prediction of malaria incidents attributed to climate of Odisha
Published in International Journal of Environmental Health Research, 2022
Pallavi Mohapatra, N. K. Tripathi, Indrajit Pal, Sangam Shrestha
Waikato Environment for Knowledge Analysis (WEKA) is a collection of machine learning algorithms that accurately perform data mining tasks (Weka 1994). WEKA contains tools that facilitate data preparation, regression, classification, association rules mining, clustering, and visualization. Through its machine learning platform, WEKA enables the algorithm to learn about data as samples and with or without any other explicit programs (Witten and Frank 2002; Hornick 2009). More detail about the tool is available at https://www.cs.waikato.ac.nz/~ml/weka/. Multilayer Perceptron (MLP)) and J48 classifier techniques in the Weka tool are commonly used to predict malaria incidents (Sharma et al. 2015; Bui et al. 2019; Olayinka and Chiemeke 2019). Researchers around the globe also used it for prediction of dengue (Shakil et al. 2015; Guo et al. 2017; Atulbhai 2017; Mello-Román et al. 2019) and other public health issues such as Cholera (Leo et al. 2019), diabetes (Al Jarullah 2011; Zia and Khan 2017; Mahmud et al. 2018), heart diseases (Dangare and Apte 2012; Sabarinathan and Sugumaran 2014). Both these methods are therefore used in the current study.
Forecasting gasoline consumption using machine learning algorithms during COVID-19 pandemic
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022
Zeynep Ceylan, Derya Akbulut, Engin Baytürk
In this section, the methodology to predict gasoline consumption under the effect of COVID-19 pandemic-related precautions is reported. As it is summarized in Figure 4, firstly, input parameters for the model are preprocessed, and then the data is split into train and test partitions. After the preparation, train data is used to generate prediction models with four different ML methods. The ML algorithms were implemented through Waikato Environment for Knowledge Analysis (WEKA) software. WEKA is a free and open-source software based on Java developed at the Waikato University of New Zealand. Then, the models are used for the prediction of the test data, and their performances are compared over three different metrics. Finally, the best prediction result is obtained for the study.