China
Africa
Explore chapters and articles related to this topic
Big Data Analysis on Smart Tools and Techniques
Published in Gautam Kumar, Dinesh Kumar Saini, Nguyen Ha Huy Cuong, Cyber Defense Mechanisms, 2020
Jabar H. Yousif, Dinesh Kumar Saini
The following are explanation of some of Big Data tools and their main features: Rapid Miner is open-source software for predictive analysis system, which is implemented in a wide range of business, commercial, and educational applications.Weka is a free ML software with user-friendly GUI, which is used for data mining analysis and visualization. Also, it has algorithms for regression and predicting the results of the future based on the intake data.Orange is open-source software for data mining and ML. Orang offers many features for data visualization and forecasting. Also, it utilizes different pre-processing methods and evaluation algorithms for predictive modeling.KNIME is an open-source software, which has a combination of ML algorithms and data mining analytics and reporting tools. It is effectively implemented in various applications such as customer and financial data analysis and business intelligence.
Cheminformatics—The promising future: Managing change of approach through ICT emerging technology
Published in A. K. Haghi, Lionello Pogliani, Devrim Balköse, Omari V. Mukbaniani, Andrew G. Mercader, Applied Chemistry and Chemical Engineering, 2017
KNIME (Konstanz Information Miner) is one of the modern, open-source workflow-driven cheminformatics platforms for data analytics. It is a fully open library shared with and accessible to the community. One of the features available is a plug-in feature which is better suited for efficient and easy use, and it enables researchers to automate the routine task and data analysis and also enables building additional nodes; data analysis pipelines from defined components that work well, combined with the existing molecule presentation. KNIME allows you to execute complex statistics and data mining by using tools, such as clustering and machine learning and even plotting and chart tools on the data to examine trends and forecast possible results.
A Shifting Paradigm of a Chemistry Methods Approach: Cheminformatics
Published in Alexander V. Vakhrushev, Omari V. Mukbaniani, Heru Susanto, Chemical Technology and Informatics in Chemistry with Applications, 2019
Heru Susanto, Ching Kang Chen, Teuku Beuna Bardant, Arief Amier Rahman Setiawan
Konstanz Information Miner (KNIME): workflow-driven Cheminformatics is one of modern data analytics platforms, which is open-source library and enables sharing and exposing the commodity. One of the features available is plug-in feature, which is efficient and easy to use and better suited, whereby enabling researcher to automate the routine task and data analysis and also enabling building additional nodes and data analysis pipelines from defined components that work well when combined with the existing molecule presentation. KNIME allows you to execute complex statistics and data mining by using tools, such as clustering and machine learning and even plotting and chart tools on the data to examine trends and forecast possible results.
Improving the reproducibility of geospatial scientific workflows: the use of geosocial media in facilitating disaster response
Published in Journal of Spatial Science, 2021
V. Cerutti, C. Bellman, A. Both, M. Duckham, B. Jenny, R. L. G. Lemmens, F. O. Ostermann
This paper uses the KNIME analytics platform (Berthold et al. 2009) to create scientific workflows that replicate the selected published studies. KNIME is an open source platform based on Eclipse, designed for data analysis, predictive analytics and modelling. It has a graphical user interface, making it intuitive and user-friendly. Additionally, it provides a broad range of functions including geospatial ones, which is uncommon in other SWMS (Scheider et al. 2017), and a large community of users that continue to develop extensions. For example, with the recently developed Open Spatial Analytics (OSA) plugin (Bellman et al. 2018), KNIME supports a typical CGSM processing pipeline, i.e. it allows connection to the Twitter Streaming/Search API, supports text processing, location extraction/geocoding using a gazetteer and has DBSCAN, k-means, and self-organising map algorithms already implemented in it. In addition, non-standard components can be added using R or Python scripting.
Content-based fake news classification through modified voting ensemble
Published in Journal of Information and Telecommunication, 2021
Data were analysed, and we developed all models using KNIME Analytics Platform version 4.3.2 and Python 3.8.5 (on Anaconda distribution version 4.9.2). Data were analysed using KNIME v. 4.3.2. We have used the Chi-Square statistical test for significance evaluation and ROC curves to evaluate its usefulness