NIML: non‐intrusive machine learning‐based speech quality prediction on VoIP networks

Alkhawaldeh, Rami S.; Khawaldeh, Saed; Pervaiz, Usama; Alawida, Moatsum; Alkhawaldeh, Hamzah

doi:10.1049/iet-com.2018.5430

Cited by 14 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning methods have been applied as contemporary technologies in a variety of fields [93,94]. Additionally, other studies [95][96][97][98][99][100][101] used triangulation methods such as these to validate and verify the results in addition to SEM.…”

Section: Machine Learning Techniques Validation and Predictionmentioning

confidence: 99%

“…The research [102] used 19 machine learning techniques. Five Machine Learning (ML) classification methods are evaluated in this research, which transform inherited data from a dataset's input into the required output pattern [93,103]. The five ML models used to develop and evaluate models for e-learning dataset application are: Artificial Neural Network (ANN) [104], Linear Regression [105], Sequential Minimal Optimization algorithm (SMO) for Support Vector Machine (SVM) [106], Bagging using REPTree model [107], and Random Forest [108].…”

Section: Machine Learning Techniques Validation and Predictionmentioning

confidence: 99%

See 1 more Smart Citation

An Empirical Study of Factors Influencing the Perceived Usefulness and Effectiveness of Integrating E-Learning Systems during the COVID-19 Pandemic Using SEM and ML: A Case Study in Jordan

et al. 2022

Self Cite

View full text Add to dashboard Cite

The purpose of this research paper is to identify and test the factors influencing the perceived usefulness and perceived effectiveness of adopting an e-learning system from the perspective of teachers in public and private schools as well as the United Nations Relief and Works Agency for Palestinian Refugees in the Near East (UNRWA) in Jordan during the first wave of the COVID-19 pandemic in the academic year 2019/2020. Based on the findings and best practices, the study intends to make appropriate recommendations to decision-makers. Its significance stems from the use of scientific tools of research and investigation, and it aims to ensure the quality and effectiveness of Jordanian schools’ e-learning systems. The study’s hypotheses were verified by electronically collecting 551 questionnaires from teachers in Jordan. To test the study hypotheses, the empirical validity of the research model was set up, and the data were analyzed with SPSS version 21.0. Structural equation modeling (SEM), confirmatory factor analysis (CFA), and machine learning (ML) methods were used to test the study hypotheses and validate the properties of the instrument items. Nineteen variables and one mediating variable were studied. The study found that independent variables pertaining to technology (relative advantage, compatibility, top management support, communication technologies, competitive pressure, technology competence, information intensity, and work flexibility) and moderating variables pertaining to the teacher’s personal income and those pertaining to school (school size, education program, and work sector) had a positive effect on teachers’ perceived usefulness of adopting e-learning systems during the COVID-19 pandemic. On the other hand, independent variables pertaining to technology (complexity and collaboration technology), moderating variables pertaining to the teacher (age, education level, and gender), and moderating variables pertaining to school (educational stage, number of students) were not supported.

show abstract

Section: Machine Learning Techniques Validation and Predictionmentioning

confidence: 99%

Section: Machine Learning Techniques Validation and Predictionmentioning

confidence: 99%

An Empirical Study of Factors Influencing the Perceived Usefulness and Effectiveness of Integrating E-Learning Systems during the COVID-19 Pandemic Using SEM and ML: A Case Study in Jordan

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The training set has these features as input where the wind blade failure is considered as output (label). There are different approaches for extracting characteristics for distinct applications that require high performance (Alkhawaldeh, 2019;Alkhawaldeh et al, 2019). Figure 8 shows a framework that involves building the ML models.…”

Section: Feature Engineering and Extractionmentioning

confidence: 99%

Appraising machine learning classifiers for discriminating rotor condition in 50W–12V operational wind turbine for maximizing wind energy production through feature extraction and selection process

Dhanraj

Alkhawaldeh

et al. 2022

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

Wind energy is one of nature’s most valuable green energy assets, as well as one of the most reliable renewable energy supplies. Wind turbine blades convert wind energy into electric energy. Wind turbine blades range in size from 25 to 120 m, depending on the demands and efficiency necessary. Owing to ambient influences and wide structures, the blades are subject to various friction forces that might harm the blades. As a result, the generation of power and the shutdown of turbines are both affected. Downtimes are reduced when blades are detected on a regular basis, according to structural health management. On the 50-W, 12-V wind turbine, this research investigates the use of vibration signals to anticipate deterioration. The machine learning (ML) method establishes a nonlinear relationship between selected important damage features and the related uniqueness measures. The learning algorithm was trained and tested based on the excellent state of the edge. To forecast blade faults, classifier models, such as naive Bayes (NB), multilayer perceptron (MLP), linear support vector machine (linear_SVM), one-deep convolutional neural network (1DCNN), bagging, random forest (RF), XGBoosts, and decision tree J48 (DT) were used, and the results were compared according to their parameters to propose a better fault diagnostics model.

show abstract

“…it may be used to estimate the risk and reward potential of a certain financial asset. In [24], they employ long short-term memory models (LSTM) and deep neural networks (DNN) as in [25,26] to predict the volatility of stock indices in US stock market. S&P 500 Index, Dow Jones Industrial Average Index, and NASDAQ Composite Index represent the three samples.…”

Section: Plos Onementioning

confidence: 99%

Hybrid fuzzy inference rules of descent method and wavelet function for volatility forecasting

et al. 2022

Self Cite

View full text Add to dashboard Cite

This research employs the gradient descent learning (FIR.DM) approach as a learning process in a nonlinear spectral model of maximum overlapping discrete wavelet transform (MODWT) to improve volatility prediction of daily stock market prices using Saudi Arabia’s stock exchange (Tadawul) data. The MODWT comprises five mathematical functions and fuzzy inference rules. The inputs are the oil price (Loil) and repo rate (Repo) according to multiple regression correlation, and the Engle and Granger Causality test Engle RF, (1987). The logarithm of the stock market price (LSCS) in Tadawul reflects the output variable. The correlation matrix reveals that there is no collinearity between the input variables, and the causality test demonstrates that the input variables significantly influence the outcome variable. According to the multiple regression, there is a substantial negative influence between Loil and LSCS but a significant positive effect between Repo and output. For the 80% dataset under ME (0.000005), MAE (0.003214), and MAPE (0.064497), the MODWT-LA8 (ARIMA(1,1,0) with drift) for the LSCS variable performs better than other WT functions. In the novel hybrid model MODWT-FIR.DM, each function’s approximation coefficient (LSCS) is applied with input variables (Loil and Repo). We evaluate the performance of the proposed model (MODWT-LA8-FIR.DM) using different statistical measures (ME, RMSE, MAE, MPE) and compare it to two established models: the original FIR.DM and other MODWT-FIR.DM functions for forecasting 20% of datasets. The outcomes show that the MODWT-LA8-FIR.DM performs better than the traditional models based on lower ME (3.167586), RMSE (3.167638), MAE (3.167586), and MPE (80.860849). The proposed hybrid model may be a potential stock market forecasting model.

show abstract

NIML: non‐intrusive machine learning‐based speech quality prediction on VoIP networks

Cited by 14 publications

References 18 publications

An Empirical Study of Factors Influencing the Perceived Usefulness and Effectiveness of Integrating E-Learning Systems during the COVID-19 Pandemic Using SEM and ML: A Case Study in Jordan

An Empirical Study of Factors Influencing the Perceived Usefulness and Effectiveness of Integrating E-Learning Systems during the COVID-19 Pandemic Using SEM and ML: A Case Study in Jordan

Appraising machine learning classifiers for discriminating rotor condition in 50W–12V operational wind turbine for maximizing wind energy production through feature extraction and selection process

Hybrid fuzzy inference rules of descent method and wavelet function for volatility forecasting

Contact Info

Product

Resources

About