Machine learning to predict kidney disease
Budget: £20 – £250 GBP
I am looking for a machine learning expert to develop a model that can accurately predict Chronic Kidney Disease (CKD) with above 95% accuracy. The main source of data for this project will be Kaggle datasets.
Skills and experience needed:
- Strong background in machine learning and data analysis including CNN and visual transformer
- Experience working with medical datasets and Electronic Health Records
- Familiarity with Kaggle and ability to extract and preprocess data from this platform
- Proficiency in programming languages such as Python and libraries like scikit-learn and TensorFlow
The dataset is available including almost 12000 data in four classes, tumor, cyst, normal, and stone. The steps should focus on preprocessing, feature selection and classification. I want you to use one of the visual transformers such as vision transformer and CNN models including Resnet, and VGG-19, and also one ensemble learning model. The Python must be used. The delivery time is 9 days. Accuracies including auc, F1 score, specificity, sensitivity, confusion matrix, precision and ROC curve should be obtained. Their plots (confusion matrix and roc curver) must be plotted. 80 percent of data are used for training and 20 percent are used for testing data. 50 to 100 if possible epoch should be used to well train the model. Perfect visualizations should be presented and the outputs should be put into the word file or whatsoever suit that.
Skills and experience needed:
- Strong background in machine learning and data analysis including CNN and visual transformer
- Experience working with medical datasets and Electronic Health Records
- Familiarity with Kaggle and ability to extract and preprocess data from this platform
- Proficiency in programming languages such as Python and libraries like scikit-learn and TensorFlow
The dataset is available including almost 12000 data in four classes, tumor, cyst, normal, and stone. The steps should focus on preprocessing, feature selection and classification. I want you to use one of the visual transformers such as vision transformer and CNN models including Resnet, and VGG-19, and also one ensemble learning model. The Python must be used. The delivery time is 9 days. Accuracies including auc, F1 score, specificity, sensitivity, confusion matrix, precision and ROC curve should be obtained. Their plots (confusion matrix and roc curver) must be plotted. 80 percent of data are used for training and 20 percent are used for testing data. 50 to 100 if possible epoch should be used to well train the model. Perfect visualizations should be presented and the outputs should be put into the word file or whatsoever suit that.