Silicon Orchard
Silicon Orchard
Objective: Accurately estimating the market value of a house using various data points.
Data Involved:
Methodology:
Outcome:
Objective: To determine the repair costs for damaged vehicles for insurance purposes.
Data Involved:
Methodology:
Outcome:
Objective: To ensure the quality and consistency of pizzas using image analysis.
Data Involved:
Methodology:
Outcome:
Citation: 223
Description:
Machine learning approaches have shown promise in efficiently diagnosing heart disease patients, but challenges with inconsistent and missing data can lead to inaccurate predictions. This paper evaluates eleven ML algorithms and six data scaling methods on a dataset of heart disease patients, finding that CART with RS or QT scaling outperforms other algorithms with 100% accuracy, precision, recall, and F1 score. The study highlights the importance of data scaling methods in model performance.
Citation: 81
Description:
To address the need for initial screening of COVID-19, this study explores the use of deep learning techniques with CT scan and chest X-ray images. Eight models were tested, with NasNetMobile achieving the highest accuracy of 82.94% in CT scan and 93.94% in chest X-ray datasets. The models were able to identify infectious regions and top features, offering potential for distinguishing COVID-19 patients from others.
Citation: 57
Description:
To address the laborious process of conducting COVID-19 tests, this study aims to develop a deep learning-based model that can accurately detect COVID-19 patients using CT scan and chest X-ray images. Eight different deep learning approaches were tested on datasets consisting of 400 CT scan images and 400 chest X-ray images. The study also utilized Local Interpretable Model-agnostic Explanations (LIME) to explain the model's interpretability and identify top features for building a trustworthy AI framework.
