Multiscale Data Analysis Using Binning, Tensor Decompositions, and Backtracking

Leggas, Dimitri; Henretty, Thomas; Ezick, James; Baskaran, Muthu Manikandan; Hofe, Brendan von; Cimaszewski, Grace; Langston, M. Harper; Lethin, Richard

doi:10.1109/hpec43674.2020.9286171

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the dataset variables are discretized to ensure the values are present within a specified range. The proposed work follows the binning 41 processes to discretize the data. The data samples are partitioned in the binning process by placing them in different bins.…”

Section: Proposed Methodologymentioning

confidence: 99%

Hybrid bidirectional long short term memory with black widow optimization for crop yield prediction using data mining

Joseph

Ramasamy

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryCrop yield prediction is highly significant in the agricultural sector. It helps to understand the growth rate of major food crops and identify measures to improve the overall yield. The article proposes a hybrid strategy called bidirectional long short term memory with black widow optimization (Bi‐LSTM‐BWO) for predicting the annual yield produced with improved accuracy. Initially, data augmentation is performed for the collected dataset to increase the size of the dataset and to reduce the data scarcity problem. Then, the dataset is preprocessed to improve the data's quality and remove the noise and irrelevant information. The data is cleaned, transformed, and discretized in the preprocessing stage using various techniques. Then, the preprocessed data is clustered using an enhanced K‐means clustering technique. To enhance the clustering technique, the proposed technique utilized the rain optimization algorithm that automatically computes the initial centroids to improve the clustering outcome. Finally, the prediction process is performed using the proposed Bi‐LSTM‐BWO prediction scheme. The proposed prediction strategy efficiently predicts the annual yield with a high accuracy rate and minimizes loss. The proposed technique achieves a 99.18%, 99.81% and 99.01% accuracy rates for the summer, autumn and winter yield prediction, respectively.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%