scholarly journals Efficient Ultra-Elastic Resource Provisioning through Hyper-Converged Cloud Infrastructure using Hybrid Machine Learning Techniques.

2020 ◽  
Vol 8 (6) ◽  
pp. 4367-4374
Keyword(s):  
Machine Learning ◽  
Resource Provisioning ◽  
Machine Learning Techniques ◽  
Cloud Infrastructure ◽  
Proper Number ◽  
Learning Techniques ◽  
Efficient Resource ◽  
Plant Optimization ◽  
Cloud Framework ◽  
Hybrid Machine

Ultra-flexibility is future asset provisioning method so as to deftly meet the clients' prerequisite in powerful way. Be that as it may, more components are required for execution improvement, for example, CPU and the capacity. It is trying to decide a reasonable edge to effectively scale the assets up or down. In this paper, we propose an efficient resource provisioning using hybrid machine learning techniques (ERP-HML) that emphasis on mutually advance the vitality utilization of servers and system. Here, the proposed asset provisioning is utilized for ultraversatile cloud benefits in hyper-joined cloud framework. In a Hyper-converged Infrastructure the resources such as CPU, storage and Network will be virtualized and software-defined as pools to meet the current demand. The principal commitment is to present an artificial plant optimization algorithm to improve the administration inertness and lessening over-provisioning of flexible cloud administrations. The subsequent commitment is to delineate a deep Q neural network (DQNN) for anticipating the server's preparing load. At that point, an improved hunting search (IHS) calculation is use to register the quantity of assets that must be provisioned dependent on the anticipated burden. The principle target of proposed ERP-HML strategy is precisely foresee the handling heap of a conveyed server and gauge the proper number of assets that must be provisioned to decrease vitality utilization. At last, the presentation of the proposed ERPHML strategy is contrast and the current condition ofcraftsmanship strategies as far as energy consumption, infrastructure costs and QoS.

scholarly journals Optimization of Distribution Control System in Oil Refinery by applying Hybrid Machine Learning Techniques

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Al Jlibawi A. Hussein ◽  
Mohammad Lutfi Othman ◽  
Aris Ishak ◽  
Bahari S. Moh Noor ◽  
Al Huseiny M. Sattar Sajitt
Keyword(s):  
Machine Learning ◽  
Control System ◽  
Oil Refinery ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Hybrid Machine

scholarly journals PROJECT DISPUTE PREDICTION BY HYBRID MACHINE LEARNING TECHNIQUES

2013 ◽  
Vol 19 (4) ◽  
pp. 505-517 ◽  
Author(s):  
Jui-Sheng Chou ◽  
Chih-Fong Tsai ◽  
Yu-Hsin Lu
Keyword(s):  
Machine Learning ◽  
Characteristic Curve ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Type I ◽  
Classification Techniques ◽  
Learning Techniques ◽  
Multiple Classification ◽  
Clustering And Classification ◽  
Hybrid Machine

This study compares several well-known machine learning techniques for public-private partnership (PPP) project dispute problems. Single and hybrid classification techniques are applied to construct models for PPP project dispute prediction. The single classification techniques utilized are multilayer perceptron (MLP) neural networks, decision trees (DTs), support vector machines, the naïve Bayes classifier, and k-nearest neighbor. Two types of hybrid learning models are developed. One combines clustering and classification techniques and the other combines multiple classification techniques. Experimental results indicate that hybrid models outperform single models in prediction accuracy, Type I and II errors, and the receiver operating characteristic curve. Additionally, the hybrid model combining multiple classification techniques perform better than that combining clustering and classification techniques. Particularly, the MLP+MLP and DT+DT models perform best and second best, achieving prediction accuracies of 97.08% and 95.77%, respectively. This study demonstrates the efficiency and effectiveness of hybrid machine learning techniques for early prediction of dispute occurrence using conceptual project information as model input. The models provide a proactive warning and decision-support information needed to select the appropriate resolution strategy before a dispute occurs.

scholarly journals Financial Distress Prediction Using Hybrid Machine Learning Techniques

2020 ◽  
pp. 1-12
Author(s):  
Suduan Chen ◽  
Zong-De Shen
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Financial Distress ◽  
Machine Learning Techniques ◽  
Financial Variables ◽  
Financial Distress Prediction ◽  
Learning Techniques ◽  
Distress Prediction ◽  
Hybrid Machine ◽  
Financially Distressed

The purpose of this study is to establish an effective financial distress prediction model by applying hybrid machine learning techniques. The sample set is 262 financially distressed companies and 786 non-financially distressed companies, listed on the Taiwan Stock Exchange between 2012 and 2018. This study deploys multiple machine learning techniques. The first step is to screen out important variables with stepwise regression (SR) and the least absolute shrinkage and selection operator (LASSO), followed by the construction of prediction models, as based on classification and regression trees (CART) and random forests (RF). Both financial variables and non-financial variables are incorporated. This study finds that the financial distress prediction model built with CART and variables screened by LASSO has the highest accuracy of 89.74%.

Sign in / Sign up

Export Citation Format

Share Document