Comparing Ensembles Of Decision Trees And Neural Networks For One-day-ahead Stream Flow Predict

Karakurt, Onur; Erdal, Halil İbrahim; Namlı, Ersin; Yumurtaci-Aydogmus, Hacer; Turkkan, Yusuf Sait

doi:10.9780/23218045/1172013/41

Cited by 7 publications

(4 citation statements)

References 32 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More precisely, the employed ANNs have achieved the best results in solving of considered RPO problem by achieving up to a 6% improvement in average accuracy over the Naive Bayes classifier, up to a 12% over the Multi-Layer Perceptron classifier, and up to a 13% over state-of-the-art ANN for power forecasting. Finally, their evaluation metrics (like Precision, Sensibility, and F-Score) are slightly higher than those obtained from the J48 decision trees, as already observed in several studies where neural networks have been compared with decision trees (Tharaha and Rashika 2017;Karakurt et al 2013;Ahmad et al 2017).…”

Section: Achieved Results and Discussionsupporting

confidence: 54%

Artificial neural networks for resources optimization in energetic environment

2022

View full text Add to dashboard Cite

Resource Planning Optimization (RPO) is a common task that many companies need to face to get several benefits, like budget improvements and run-time analyses. However, even if it is often solved by using several software products and tools, the great success and validity of the Artificial Intelligence-based approaches, in many research fields, represent a huge opportunity to explore alternative solutions for solving optimization problems. To this purpose, the following paper aims to investigate the use of multiple Artificial Neural Networks (ANNs) for solving a RPO problem related to the scheduling of different Combined Heat & Power (CHP) generators. The experimental results, carried out by using data extracted by considering a real Microgrid system, have confirmed the effectiveness of the proposed approach.

show abstract

Section: Achieved Results and Discussionsupporting

confidence: 54%

Artificial neural networks for resources optimization in energetic environment

2022

View full text Add to dashboard Cite

show abstract

“…However, comparative studies on the performance of various ensemble learning models have discovered that bagging outperforms boosting and stacking [16][17]. Bagging can significantly decrease the ML model's prediction error and variance when utilized with a base learner generation [17][18].…”

Section: Background and Related Workmentioning

confidence: 99%

An Optimized Bagging Ensemble Learning Approach Using BESTrees for Predicting Students’ Performance

Evangelista

2023

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Every academic institution's goal is to identify students who require additional assistance and take appropriate actions to improve their performance. As such, various research studies have focused on developing prediction models that can detect correlated patterns influencing students' performance, dropout, collaboration, and engagement. Among the influential predictive models available, the bagging ensemble has captured the interest of researchers seeking to improve prediction accuracy over single classifiers. However, prior work in this area has focused mainly on selecting single classifiers as the base classifier of the bagging ensemble, with little to no further optimization of the proposed framework. This study aims to fill this gap by providing a bagging ensemble framework to optimize its hyperparameters and achieve improved prediction accuracy. The proposed model used the Weka BESTrees data mining tool and Math language course student dataset from UCI Machine Learning Repository. Based on the experiments performed, the proposed bagging optimization technique can effectively increase the accuracy of a traditional bagging ensemble method. It reveals further that the proposed BESTrees framework can achieve an optimized performance when trained with the appropriate hyperparameters and hill climb metrics.

show abstract

“…Decision trees and neural network methods demonstrate good prediction and classification quality compared to such machine learning methods as Random Forest, Support Vector Machine, Naive Bayes, and K Nearest Neighbor. The paper [11] compared ensembles of decision trees and neural networks for one-day-ahead streamflow prediction. The results obtained in this study indicate that ensemble learning models yield better prediction accuracy than a conventional artificial neural network model, such as a multilayer perceptron.…”

Section: Related Workmentioning

confidence: 99%

Visualization of Research Trending Topic Prediction: Intelligent Method for Data Analysis

Charnine

Tishchenko

Kochiev

2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

View full text Add to dashboard Cite

This paper presents the results of a method for the visualization of the long-term prediction of research trending topics. Meaningful topics were identified among the words included in the titles of scientific articles. The title is the most important element of a scientific article and the main indication of the article’s subject and topic. We treated the titles’ words, which occur several times in articles cited in the analyzed collection, as the research trending topics. The longevity of the citation trend growth was the target for the machine learning algorithms. The CatBoost machine learning method, which is one of the best implementations of decision trees, was used. We conducted experiments on a scientific dataset that included 5 million publications from the top conferences in artificial intelligence and data mining areas to demonstrate the effectiveness of the proposed model. The accuracy rate of three-year forecasts for a number of experiments from 1997 to 2014 was about 60%. To visualize the forecast, the t-SNE and Word2Vec methods were used. Clusters of trending keywords on the semantic map helped to accurately identify promising directions. Two examples of forecast visualizations for the topic “Intelligent methods for data and image analysis” are presented. The presented visualizations serve as the analytical method for predicting topic trends and promising directions.

show abstract

Comparing Ensembles Of Decision Trees And Neural Networks For One-day-ahead Stream Flow Predict

Cited by 7 publications

References 32 publications

Artificial neural networks for resources optimization in energetic environment

Artificial neural networks for resources optimization in energetic environment

An Optimized Bagging Ensemble Learning Approach Using BESTrees for Predicting Students’ Performance

Visualization of Research Trending Topic Prediction: Intelligent Method for Data Analysis

Contact Info

Product

Resources

About