BME 530 Statistics and Machine Learning Final project This is a group project for a team of 2-3 people. Each team chooses to work on one dataset to complete the final project. The details on each...

1 answer below »
I need help with final project using unsupervised machine learning in R


BME 530 Statistics and Machine Learning Final project This is a group project for a team of 2-3 people. Each team chooses to work on one dataset to complete the final project. The details on each dataset can be found on the website in the URL and references herein. You may also use your research data or other datasets in a public repository. 1) Diabetic Retinopathy Debrecen Data Set https://archive.ics.uci.edu/ml/datasets/Diabetic+Retinopathy+Debrecen+Data+Set 2) Quality Assessment of Digital Colposcopies Data Set http://archive.ics.uci.edu/ml/datasets/Quality+Assessment+of+Digital+Colposcopies 3) LSVT Voice Rehabilitation data set http://archive.ics.uci.edu/ml/datasets/LSVT+Voice+Rehabilitation# 4) Smartphone-Based Recognition of Human Activities and Postural Transitions Data Set http://archive.ics.uci.edu/ml/datasets/Smartphone- Based+Recognition+of+Human+Activities+and+Postural+Transitions. 5) Student Performance Data Set https://archive.ics.uci.edu/ml/datasets/Student+Performance 6) Cervical cancer (Risk Factors) data set https://archive.ics.uci.edu/ml/datasets/Cervical+cancer+%28Risk+Factors%29 7) Parkinson Dataset with replicated acoustic features Data Set https://archive.ics.uci.edu/ml/datasets/Parkinson+Dataset+with+replicated+acoustic+fea tures+ 8) HCC Survival Data Set https://archive.ics.uci.edu/ml/datasets/HCC+Survival 9) Drug consumption (quantified) Data Set https://archive.ics.uci.edu/ml/datasets/Drug+consumption+%28quantified%29 10) SCADI Data Set http://archive.ics.uci.edu/ml/datasets/SCADI 11) Gene expression cancer RNA-Seq Data Set http://archive.ics.uci.edu/ml/datasets/gene+expression+cancer+RNA-Seq https://archive.ics.uci.edu/ml/datasets/Diabetic+Retinopathy+Debrecen+Data+Set http://archive.ics.uci.edu/ml/datasets/Quality+Assessment+of+Digital+Colposcopies http://archive.ics.uci.edu/ml/datasets/LSVT+Voice+Rehabilitation http://archive.ics.uci.edu/ml/datasets/Smartphone-Based+Recognition+of+Human+Activities+and+Postural+Transitions http://archive.ics.uci.edu/ml/datasets/Smartphone-Based+Recognition+of+Human+Activities+and+Postural+Transitions https://archive.ics.uci.edu/ml/datasets/Student+Performance https://archive.ics.uci.edu/ml/datasets/Cervical+cancer+%28Risk+Factors%29 https://archive.ics.uci.edu/ml/datasets/Parkinson+Dataset+with+replicated+acoustic+features+ https://archive.ics.uci.edu/ml/datasets/Parkinson+Dataset+with+replicated+acoustic+features+ https://archive.ics.uci.edu/ml/datasets/HCC+Survival https://archive.ics.uci.edu/ml/datasets/Drug+consumption+%28quantified%29 http://archive.ics.uci.edu/ml/datasets/SCADI http://archive.ics.uci.edu/ml/datasets/gene+expression+cancer+RNA-Seq Tasks to perform: Task 1: Perform relevant exploratory data analysis to reveal the relationship among features and the potential hidden structure (but only include the relevant ones in the report). Use dimension reduction methods to visualize the dataset in 2D or 3D. Task 2. Use at least two unsupervised machine learning methods to review the group structures in the dataset. Describe the rationale for determining the number of clusters in your approach. Discuss how the parameters in the clustering methods are determined. Present the clustering accuracy using the true labels. Task 3. Use supervised machine learning models to construct the classification models (each group member should work on one). You also will need to incorporate at least one feature selection technique in your model. Task 4: Evaluate and compare the classification models using appropriate criteria and draw your conclusion based on the computational evaluation of your models. Presentation requirements (10 minutes). Presentation time is strict. Please structure your presentation by including • Intro to the problem • Methods • Experimental protocols • Results • Conclusion What to submit 1. Report (typed, font size 12pt, double spaced). The report should include subsections of Introduction, methods, results, conclusion and cited references. Contribution of each group member to the project should be indicated in the final paragraph of the report. The report should be no more than 12 pages in length. However, if you wish to include additional figures/tables, please organize them into an appendix. 2. Your group presentation file. 3. Your program used to generate the results (R) and the dataset after cleaning. Submit to Blackboard with all files in a zipper file (BME530 FinalProject.Names). Only one submission from a group member is needed. An identical score will be assigned to the members in a group unless a special reason exists.
Answered 3 days AfterDec 05, 2021

Answer To: BME 530 Statistics and Machine Learning Final project This is a group project for a team of 2-3...

Amar Kumar answered on Dec 09 2021
115 Votes
Algorithm 1
Diabetic Retinopathy with CNN
Identify the diabetes stage in a human retina. Kaggle's Diabetic Retinopathy Detection Repository gave the 150 GB picture information.
To see the model in real life, run the cup application under the Deployed Model envelope.
For testing purposes, test pictures have been saved in the Deployed Model envelope.\
For preparing, the ResNet engineering was employed.\
! [Lingering L
earning] (https://cdn-pictures 1.medium.com/max/1200/1*ByrVJspW-TefwlH7OLxNkg.png)
Convolutional Neural Networks, regularly known as ConvNets, are a sort of profound discovering that is most normally used to dissect picture assortments. \
ConvNets have an assortment of layers that are regularly utilized.
* Convolution layer - This layer performs convolution on a picture with indicated step and cushioning.
* Pooling layer - This layer is utilized to decrease the dimensionality of component maps by first building up a veil and an activity to be done, then, at that point, moving the cover over the entire picture as indicated by the step. In this layer, no loads are learned.
* Completely Connected layer - Traditional neural layers found at the neural organization's terminal stem. Because of the surprising number of boundaries it needs, it is just utilized rarely nowadays.
* Dropout layer - This layer is utilized to lessen over-fitting. During the preparation, it turns down specific neurons at arbitrary.
* Bunch Normalization - This lessens estimation time by normalizing the result esteems. It additionally has a regularization impact.
![Convolution](http://machinelearninguru.com/pictures/points/PC vision/rudiments/convolution/1.JPG)
#### I composed a post [here](https://medium.com/@s.ganjoo96/diabetic-retinopathy-recognition with-resnet50-b621514bd22b) on distinguishing diabetic retinopathy.
## Arrangement
### Clone this store and download the information
* Save this archive to your PC as a clone.
* Utilize the album Diabetic-Retinopathy-Detection-with-CNN to get into the envelope.
*Acquire the information records from Kaggle and save them in this area.
### Setting up the essentials
* requirements.txt for pip introduce
## Appropriateness
* In the Model script.ipynb document, run every cell.
* Save your model in the Deployed Model organizer's subfolder.
* Open the app.py document and run it.
* After the server has completed the process of stacking, open an internet browser and type localhost:5000 into the location bar.
#### You are good to go to go.
## Result
Due to the restricted monetary assets, this model was prepared on the cloud for **only**2 ages and accomplishes a 73 percent exactness.
A Machine Learning Approach for the Diagnosis of Parkinson's Disease via Speech Analysis
Introduction
· Parkinson's sickness, which influences in excess of 10 million individuals internationally, is the second most normal neurological disease after Alzheimer's. Parkinson's sickness is portrayed by a decrease in engine and intellectual capacities.
· There is nobody test that can be utilized to analyze a condition. Specialists should rather do a careful clinical assessment of the patient's clinical history.
· Lamentably, this technique for analysis is very insufficient. As indicated by the National Institute of Neurological Disorders, early analysis (manifestations for under 5 years) is just 53% exact. This isn't obviously superior to taking a blind leap of faith, however early location is fundamental for powerful treatment.
· Due to these difficulties, I use a dataset of various discourse qualities (a non-obtrusive yet unmistakable procedure) from the University of Oxford to concentrate on an AI methodology to appropriately analyze Parkinson's sickness.
· What are the advantages of discourse highlights? Since basically every Parkinson's patient has critical vocal decay (powerlessness to create delayed phonations, quake, and roughness), it's a good idea to use voice to recognize the condition. Voice investigation additionally enjoys the benefit of being non-intrusive, minimal expense, and easy to extricate clinically.
Background
Parkinson's Disease
· Parkinson's sickness is a dynamic neurological illness brought about by the deficiency of...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here