10 March 2025 in Discover Internet of Things
17 January 2022 in BioMed Research International
Brain computer interface (BCI) requires an online and real‐time processing of EEG signals. Hence, the accuracy of the recording system is improved by nullifying the developed artifacts. The goal of this proposal is to develop a hybrid model for recognizing and minimizing ocular artifacts through an improved deep learning scheme. The discrete wavelet transform (DWT) and Pisarenko harmonic decomposition are used for decomposing the signals. Then, the features are extracted by principal component analysis (PCA) and independent component analysis (ICA) techniques. After collecting the features, an optimized deformable convolutional network (ODCN) is used for the recognition of ocular artifacts from EEG input signals. When artifacts are sensed, the moderation method is executed by applying the empirical mean curve decomposition (EMCD) followed by ODCN for noise optimization in EEG signals. Conclusively, the spotless signal is reconstructed by an application of inverse EMCD. The proposed method has achieved a higher performance than that of conventional methods, which demonstrates a better ocular artifact reduction by the proposed method.
14 March 2025 in Discover Sustainability
This study explores the efficacy of Automated Machine Learning (AutoML) tools in enhancing linear regression models across industries, focusing on insurance and agriculture. We assessed six widely used AutoML libraries—AutoKeras, AutoGluon, Hyperopt, MLJAR, LightAutoML, and H2O—on a Kaggle-sourced insurance dataset to evaluate their performance in predictive accuracy and operational efficiency. Additionally, we employed TPOT for crop prediction using a Kaggle-based agricultural dataset, demonstrating its application in supporting Sustainable Development Goals (SDGs) related to agriculture. The results showed that AutoML tools vary in effectiveness, with AutoGluon exhibiting superior performance on the insurance dataset due to its low Mean Squared Error (MSE). Similarly, TPOT excelled in optimizing crop yield predictions by automating machine learning pipelines. These findings underscore the versatility of AutoML in handling diverse data contexts, significantly improving model accuracy and reducing manual effort through automation. This study highlights the potential of AutoML to streamline predictive analytics across sectors, enabling data-driven decision-making in industries such as insurance for risk assessment and customer segmentation, as well as in agriculture for sustainable practices and crop optimization. Using datasets from Kaggle reinforces the accessibility and replicability of this research, providing a robust framework for further exploration in diverse industry applications.
12 December 2024 in SN Computer Science