Implementation of Hybrid Ionospheric TEC Forecasting Algorithm Using PCA-NN Method

Mallika, I. Lakshmi; Ratnam, D. Venkata; Ostuka, Y.; Sivavaraprasad, G.; Raman, Saravana

doi:10.1109/jstars.2018.2877445

Cited by 50 publications

(21 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Forecasting the ionospheric space weather is important to mitigate its effect on global navigation and communication systems and power grids. However, developing a comprehensive and accurate ionospheric forecasting model is a challenge as the physical drivers are complex across the different regions and seasons (Mallika et al., 2018). Ionospheric TEC is a key parameter in describing the state of the ionosphere and accurate forecasting of it is crucial for ionospheric space weather characterization and mitigation.…”

Section: Summary and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Accepted Articlementioning

confidence: 99%

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Besides, a great deal of studies have indicated that data-driven single ML models, especially for highdimensional data, don't have the competitive advantages in nonlinear approximation tasks. Principal component analysis (PCA) is viewed as a feasible solution for this issue [23]- [25]. In theory, it can achieve covariance-matrixbased dimensionality reduction for given correlated variables, thereby providing more favorable input for regression.…”

Section: Introductionmentioning

confidence: 99%

Multivariate Seawater Quality Prediction Based on PCA-RVM Supported by Edge Computing Towards Smart Ocean

Sun

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Seawater quality prediction has a tremendous potential of enabling future smart ocean. However, this time-sensitive application puts forward a strict delay requirement, thus easily leading to overwhelmed networks. Edge computing is emerging as an effective means of solving network overload, due to its edge-based distributed processing. Therefore, we develop a hybrid multivariate prediction model for seawater quality assessment in an edge computing environment, considering the combination of principal component analysis (PCA) and relevance vector machine (RVM). The PCA method is employed for dimension reduction of ten seawater quality factors in advance. Six principal components are extracted from multiple features, used as input variables of the subsequent predictor. Finally, a RVM is developed to predict the future trends of dissolved oxygen and pH, measuring seawater quality. Experimental results on the real-world ocean sensor data show that our PCA-RVM based multivariate prediction model outperforms single RVM, SVM and its extended version in prediction accuracy and efficiency, meanwhile statistical testings confirm this finding. INDEX TERMS Edge computing, PCA-RVM, water quality, multivariate prediction, smart ocean.

show abstract

“…Bouya et al [10] proposed a hybrid principal component analysis (PCA)–ANN model to forecast the ionospheric signal delays in the Australian region. Mallika et al [11] implemented the PCA–ANN model to forecast the ionospheric signal delays in the Japan region. However, there is still a need for more robust solutions to efficiently analyse and predict the ionospheric time delays predominantly in low‐latitude regions like India and Brazil.…”

Section: Introductionmentioning

confidence: 99%

Implementation of storm‐time ionospheric forecasting algorithm using SSA–ANN model

Dabbakuti

Peesapati

Yarrakula

et al. 2020

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

Implementation of Hybrid Ionospheric TEC Forecasting Algorithm Using PCA-NN Method

Cited by 50 publications

References 43 publications

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

Data‐Driven Forecasting of Low‐Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods

Multivariate Seawater Quality Prediction Based on PCA-RVM Supported by Edge Computing Towards Smart Ocean

Implementation of storm‐time ionospheric forecasting algorithm using SSA–ANN model

Contact Info

Product

Resources

About