A Machine Learning Approach to Predict the Average Localization Error With Applications to Wireless Sensor Networks

Singh, Aviral; Kotiyal, Vaibhav; Sharma, Sandeep; Nagar, Jaiprakash; Lee, Cheng‐Chi

doi:10.1109/access.2020.3038645

Cited by 70 publications

(24 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is considered a non-linear sensitivity analysis that disaggregates the averaging effects and evaluates the model at each instance. The average of all the ICE lines provides the PDP plot [94][95][96]. The averaging effect of PDP conceals any heterogeneous relationship present at any particular instance.…”

Section: Feature Sensitivitymentioning

confidence: 99%

Machine Learning to Estimate Surface Roughness from Satellite Images

et al. 2021

Self Cite

View full text Add to dashboard Cite

We apply the Support Vector Regression (SVR) machine learning model to estimate surface roughness on a large alluvial fan of the Kosi River in the Himalayan Foreland from satellite images. To train the model, we used input features such as radar backscatter values in Vertical–Vertical (VV) and Vertical–Horizontal (VH) polarisation, incidence angle from Sentinel-1, Normalised Difference Vegetation Index (NDVI) from Sentinel-2, and surface elevation from Shuttle Radar Topographic Mission (SRTM). We generated additional features (VH/VV and VH–VV) through a linear data fusion of the existing features. For the training and validation of our model, we conducted a field campaign during 11–20 December 2019. We measured surface roughness at 78 different locations over the entire fan surface using an in-house-developed mechanical pin-profiler. We used the regression tree ensemble approach to assess the relative importance of individual input feature to predict the surface soil roughness from SVR model. We eliminated the irrelevant input features using an iterative backward elimination approach. We then performed feature sensitivity to evaluate the riskiness of the selected features. Finally, we applied the dimension reduction and scaling to minimise the data redundancy and bring them to a similar level. Based on these, we proposed five SVR methods (PCA-NS-SVR, PCA-CM-SVR, PCA-ZM-SVR, PCA-MM-SVR, and PCA-S-SVR). We trained and evaluated the performance of all variants of SVR with a 60:40 ratio using the input features and the in-situ surface roughness. We compared the performance of SVR models with six different benchmark machine learning models (i.e., Gaussian Process Regression (GPR), Generalised Regression Neural Network (GRNN), Binary Decision Tree (BDT), Bragging Ensemble Learning, Boosting Ensemble Learning, and Automated Machine Learning (AutoML)). We observed that the PCA-MM-SVR perform better with a coefficient of correlation (R = 0.74), Root Mean Square Error (RMSE = 0.16 cm), and Mean Square Error (MSE = 0.025 cm2). To ensure a fair selection of the machine learning model, we evaluated the Akaike’s Information Criterion (AIC), corrected AIC (AICc), and Bayesian Information Criterion (BIC). We observed that SVR exhibits the lowest values of AIC, corrected AIC, and BIC of all the other methods; this indicates the best goodness-of-fit. Eventually, we also compared the result of PCA-MM-SVR with the surface roughness estimated from different empirical and semi-empirical radar backscatter models. The accuracy of the PCA-MM-SVR model is better than the backscatter models. This study provides a robust approach to measure surface roughness at high spatial and temporal resolutions solely from the satellite data.

show abstract

Section: Feature Sensitivitymentioning

confidence: 99%

Machine Learning to Estimate Surface Roughness from Satellite Images

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this way, we can reduce the hardware on each sensor node, which would reduce the entire network’s cost. The localisation algorithms aim to estimate the accurate positions of the unknown nodes at the earliest [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

ECS-NL: An Enhanced Cuckoo Search Algorithm for Node Localisation in Wireless Sensor Networks

Kotiyal

Singh

Sharma

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Node localisation plays a critical role in setting up Wireless Sensor Networks (WSNs). A sensor in WSNs senses, processes and transmits the sensed information simultaneously. Along with the sensed information, it is crucial to have the positional information associated with the information source. A promising method to localise these randomly deployed sensors is to use bio-inspired meta-heuristic algorithms. In this way, a node localisation problem is converted to an optimisation problem. Afterwards, the optimisation problem is solved for an optimal solution by minimising the errors. Various bio-inspired algorithms, including the conventional Cuckoo Search (CS) and modified CS algorithm, have already been explored. However, these algorithms demand a predetermined number of iterations to reach the optimal solution, even when not required. In this way, they unnecessarily exploit the limited resources of the sensors resulting in a slow search process. This paper proposes an Enhanced Cuckoo Search (ECS) algorithm to minimise the Average Localisation Error (ALE) and the time taken to localise an unknown node. In this algorithm, we have implemented an Early Stopping (ES) mechanism, which improves the search process significantly by exiting the search loop whenever the optimal solution is reached. Further, we have evaluated the ECS algorithm and compared it with the modified CS algorithm. While doing so, note that the proposed algorithm localised all the localisable nodes in the network with an ALE of 0.5–0.8 m. In addition, the proposed algorithm also shows an 80% decrease in the average time taken to localise all the localisable nodes. Consequently, the performance of the proposed ECS algorithm makes it desirable to implement in practical scenarios for node localisation.

show abstract

“…As cloud heights and thicknesses vary, the cloud detection uncertainty also varies depending on the position of the sun or satellite (Ghonima et al, 2012). In general, cloud cover estimation using satellite data differs from the approach used for human-eye observation data, because the wide grid data around the central grid are averaged or calculated as fractions (Alonso-Montesinos, 2020;Sunil et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Twenty-four-hour cloud cover calculation using a ground-based imager with machine learning

2021

View full text Add to dashboard Cite

Abstract. In this study, image data features and machine learning methods were used to calculate 24 h continuous cloud cover from image data obtained by a camera-based imager on the ground. The image data features were the time (Julian day and hour), solar zenith angle, and statistical characteristics of the red–blue ratio, blue–red difference, and luminance. These features were determined from the red, green, and blue brightness of images subjected to a pre-processing process involving masking removal and distortion correction. The collected image data were divided into training, validation, and test sets and were used to optimize and evaluate the accuracy of each machine learning method. The cloud cover calculated by each machine learning method was verified with human-eye observation data from a manned observatory. Supervised machine learning models suitable for nowcasting, namely, support vector regression, random forest, gradient boosting machine, k-nearest neighbor, artificial neural network, and multiple linear regression methods, were employed and their results were compared. The best learning results were obtained by the support vector regression model, which had an accuracy, recall, and precision of 0.94, 0.70, and 0.76, respectively. Further, bias, root mean square error, and correlation coefficient values of 0.04 tenths, 1.45 tenths, and 0.93, respectively, were obtained for the cloud cover calculated using the test set. When the difference between the calculated and observed cloud cover was allowed to range between 0, 1, and 2 tenths, high agreements of approximately 42 %, 79 %, and 91 %, respectively, were obtained. The proposed system involving a ground-based imager and machine learning methods is expected to be suitable for application as an automated system to replace human-eye observations.

show abstract

A Machine Learning Approach to Predict the Average Localization Error With Applications to Wireless Sensor Networks

Cited by 70 publications

References 44 publications

Machine Learning to Estimate Surface Roughness from Satellite Images

Machine Learning to Estimate Surface Roughness from Satellite Images

ECS-NL: An Enhanced Cuckoo Search Algorithm for Node Localisation in Wireless Sensor Networks

Twenty-four-hour cloud cover calculation using a ground-based imager with machine learning

Contact Info

Product

Resources

About