<abstract><p>Rainfall prediction includes forecasting the occurrence of rainfall and projecting the amount of rainfall over the modeled area. Rainfall is the result of various natural phenomena such as temperature, humidity, atmospheric pressure, and wind direction, and is therefore composed of various factors that lead to uncertainties in the prediction of the same. In this work, different machine learning and deep learning models are used to (a) predict the occurrence of rainfall, (b) project the amount of rainfall, and (c) compare the results of the different models for classification and regression purposes. The dataset used in this work for rainfall prediction contains data from 49 Australian cities over a 10-year period and contains 23 features, including location, temperature, evaporation, sunshine, wind direction, and many more. The dataset contained numerous uncertainties and anomalies that caused the prediction model to produce erroneous projections. We, therefore, used several data preprocessing techniques, including outlier removal, class balancing for classification tasks using Synthetic Minority Oversampling Technique (SMOTE), and data normalization for regression tasks using Standard Scalar, to remove these uncertainties and clean the data for more accurate predictions. Training classifiers such as XGBoost, Random Forest, Kernel SVM, and Long-Short Term Memory (LSTM) are used for the classification task, while models such as Multiple Linear Regressor, XGBoost, Polynomial Regressor, Random Forest Regressor, and LSTM are used for the regression task. The experiment results show that the proposed approach outperforms several state-of-the-art approaches with an accuracy of 92.2% for the classification task, a mean absolute error of 11.7%, and an R2 score of 76% for the regression task.</p></abstract>
The rapid development of computing devices and automation in various fields drastically increased the growth of data, which promotes the usage of machine learning (ML) techniques to get insights from the generated data. However, data processed by ML algorithms lead to several privacy issues, including leakage of users' biometric data while sharing it through the network to train the object detection model. Therefore, federated learning (FL) was introduced, in which the models are trained locally; only model parameters are shared between central authority (CA) and end nodes. They will eventually maintain a common model for all the participating devices. However, many problems are associated with FL, such as the difference in data consumption rate, training capabilities, geographical challenges, and storage capacity. These problems might lead to differences in the common global model and thus an inefficient FL approach. Moreover, the presence of a CA results in a single point of failure and is vulnerable to various attacks. Motivated by the aforementioned discussion, in this article, we propose a blockchain‐based object detection scheme using FL that eliminates the CA by using distributed InterPlanetary File System (IPFS). Global models can be aggregated periodically when several local model parameters are uploaded on the IPFS. Nodes can fetch the global model from the IPFS. The global aggregated object detection model has been evaluated for various scenarios such as human face detection, animal detection, unsafe content detection, noteworthy vehicle detection, and performance evaluation parameters such as accuracy, precision, recall, and end‐to‐end latency. Compared to traditional models, the proposed model achieved an average accuracy of 92.75% on the object detection scenarios mentioned above.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.