COVID-19 Machine Learning Analytical Report
In this assignment, you are required to perform a machine learning analysis on COVID-19 datasets. You can choose any methods and algorithms which you feel confident at, the emphasis is on the report. Make sure you follow the outline to write your report carefully.
When you complete the final report please also create a 5-7 pages of ppt slides to present and explain this project report. You can use the dataset uploaded but feel free to use any other sources as you like. You can refer, edit, copy and use those documents uploaded. Those are each small parts that have been worded previously so fa
This report should be 7-9 pages including words, codes and visualizations contains following parts:
-Abstract
-Introduction
1. Project Background and Execute Summary
Project background, needs and importance, targeted project problem, motivations and goals. Planned project approaches and method. Expected project contributions and applications.
2. Project Deliverables
Deliverables include reports, prototypes, development applications, and/or production applications.
-Problem Definition and Data Exploration
1. Data Management Plan
Data collection approaches, management methods, storage methods, and usage mechanisms.
2. Project Development Methodology
Data analytics with intelligent system development cycle; planned development processes and activities.
3. Project Organization Plan
Work
eakdown structure presenting the hierarchical and incremental decomposition of the project into phases, deliverables and work packages.
4. Project Resource Requirements and Plan
Required hardware, software, tools and licenses including specifications, costs and justification.
-Data Processing
1. Data Process
Decide the approaches and steps of deriving raw, training, validation and test datasets in order to enable the models to meet the project requirements.
2. Data Collection
Define the sources, parameters and quantity of raw datasets; collect necessary and sufficient raw datasets; present samples from raw datasets.
3. Data Pre-processing
Pre-process collected raw data with cleaning and validation tools; present samples from pre-processed datasets.
4. Data Transformation
Transform pre-processed datasets to desired formats with tools and scripts; present samples from transformed datasets.
5. Data Preparation
Prepare training, validation and test datasets from transformed datasets; present samples from training, validation and test datasets.
-Model Selection and Development
1. Model Proposals
Propose models to solve targeted problems in detailed terms of concepts, features, algorithms etc.
2. Model Supports
Describe the platform, environment and tools to support the development and execution of each model; provide diagrams of architecture, components, data flows, etc.
3. Model Comparison and Justification
Compare models regarding function and non-functional characteristics including strengths and targeted problems, approaches, data types, limitations; provide justification for each model.
4. Model Evaluation Methods
Present evaluation methods and metrics for each model, e.g., accuracy, loss, ROC/AOC, MSRE, etc.
-Data Analytics
Demonstration of analysis performed in this project
-Results and Visualization
1. Analysis of Model Execution/Evaluation Results
Evaluate whether the output match tagged/labelled targets. Describe the methodology of measuring accuracy/loss, precision
ecall/F-score, or AUC, confusion metrics, etc.
2. Achievements and Constraints
Demonstrate and compare that the problem has been solved, made advances have been made, and/or any limitations have been acknowledged.
3. Quality Evaluation of Model Functions and Performance
Other than the co
ectness of the model, evaluate whether the run-time performance meet timing requirement.
-Conclusion
1. Summary
Explain what the research has achieved; revisit key points in each section and summary of major findings, and implications for the field if any.
2. Experience and Lessons Learned
Discuss and summarize the experience and lessons learned from this project
3. Recommendations for Future Work
Provide recommendations for future project works and extensions.
-References and Appendices
1. Appendix A – System Testing
Present the test results of required use cases in terms of a sequence of GUI screens for each required use case.
2. Appendix B – Project Data Source and Management Store
Upload and Provide the required project data source information in a designated Google Drive Link URL: https:
drive.google.com/drive/u/0/folders/1Ghbhi1qhHYKbEeTC4Lx9gsEDUqD1OwBT
In this report we will try to analyse the data which is best over the Covid patients across the
world. The data has different attributes, and it shows information about the code patients. It
shows the data on the basis of different state in regions from where the information about the
confirm, deaths, recovered patients have been used and it will use date feature also. I selected
this data from the Kaggle website which provides open-source data free of cost. I selected this
data because it has null values also so it will be easier to implement and demonstrate the usage
of exploratory data analysis over the information. The exploratory data analysis is performed
over the data set to make sure that there is no null values from the data set and if there is some
null values then can we move from that help us a different questions over the data set. In this
code I try to find out answer for the 5 different questions. When I was working on the Covid
data the first step was to import the data into the data frame. I imported pandas and NumPy
li
aries the data set was used by calling the file path into the pandas data frame variable. After
importing the data, I selected the head function to show the first 5 rows of the data so that it
ecomes easier to understand what type of values are present in it. End step was to check
whether the data contains null values or not. I called the is null function to check for the null
values and it shows there are 2 null values present in a column. I also used the shape function
to find out the number of rows and column present in the whole data set. Shape gets the number
of rows and columns present in a data set and it will become easier to understand the size of
the data set to perform any other operation over it.
I also wrote the code to check for the total number of null values present in the data set. We
can call the sum function over is null function to get the sum of all the null values present in
the data set. The output shows there are 181 null values present in the state attribute.
The following are the 5 questions over which I analyse the data set and answer was found in
the form of output. The first one is to show the number of all the confirmed, deaths and
ecovered cases present in each region. The second question was to find out the maximum
number of confirmed cases confirmed cases from the region. In the 3rd question we will find
out the minimum number of deaths which were recorded Indian region and it will show the
name of the region along with the minimum number of deaths. The 4th question was to find
out the confirm, deaths and recovered cases from any particular region on the basis of a date.
For this query I selected Pakistan as the region. The last question was to remove all the records
where the confirmed cases were less than 10. For this I found out all the values who were less
than 10 and then removed them from the table.
Analysis of COVID-19 Pandemic Based on Machine Learning Techniques
The development of cyber-infrastructure to advance worldwide collaborations remains
prudent in facilitating the ease with which persons can access and manage COVID-19 related
data. Ongoing efforts to design diagnostic strategies using machine learning algorithms in
esponse to COVID-19 disease accelerate diagnostic accuracy and promise to safeguard the
healthcare of persons (Alimadadi et al XXXXXXXXXXWithin this framework, in a machine learning
analysis of COVID-19, De Felice & Polimeni XXXXXXXXXXestablished evidence regarding the
feasibility of implementing and scaling up networks that promote rapid sharing of data from
China to allow quick assessment and evaluation of fundamental aspects of the disease. For
example, machine learning strategies have allowed for sharing of COVID-19 pathogenesis as
well as further the generation of specific treatments. Machine learning and deep learning
approaches remain instrumental in advancing the early forecasting of COVID-19 spread to allow
for the development and implementation of necessary actions to tackle the disease. Models such
as polynomial regression (PR) have predicted a significant loss of lives without the adoption of
COVID-19 measures such as social distancing and adhering to the lockdown initiative (Punn,
Sonbhadra, & Agarwal, XXXXXXXXXXA robust clinical and societal response backed by intelligence
from machine learning and artificial intelligence supports better utilization of scarce health
esources, accelerates clinical trials, and informs policy directives. At the same time, transfer
learning methods can address the issue of biased models when making predictions about
individuals derived from populations (van der Schaar et al XXXXXXXXXXInternational collaboration
emains critical in yielding large datasets for machine learning training and deployment globally.
The utilization of artificial intelligence models can take advantage of prevailing data
infrastructure such as EHR records, data from airlines, social media, as well as cellular operators.
Results from previous studies remain promising regarding the practicality of machine learning
models in enabling users including physicians, patients, and policymakers to make rational
decisions in mitigating the COVID-19 pandemic.
References
Alimadadi, A., Aryal, S., Manandhar, I., Munroe, P. B., Joe, B., & Cheng, X XXXXXXXXXXArtificial
intelligence and machine learning to fight COVID-19.
De Felice, F., & Polimeni, A XXXXXXXXXXCoronavirus Disease (COVID-19): A Machine learning
ibliometric analysis. in vivo, 34(3 suppl), XXXXXXXXXX.
Punn, N. S., Sonbhadra, S. K., & Agarwal, S XXXXXXXXXXCOVID-19 epidemic analysis using
machine learning and deep learning algorithms. MedRxiv.
van der Schaar, M., Alaa, A. M., Floto, A., Gimson, A., Scholtes, S., Wood, A., ... & Ercole, A.
XXXXXXXXXXHow artificial intelligence and machine learning can help healthcare systems
espond to COVID-19. Machine Learning, 110(1), 1-14.
1
COVID-19 ANALYSIS
1.0 Introduction
The novel Corona Virus also known as Covid-19 was spread extensively throughout China at the
end of 2019. It has infected a huge number of people. While the new virus was disseminating hastily
in other regions, the native epidemic has been efficiently controlled. Europe had become the
vulnerable spot of the then outburst of new pneumonia. In the meantime,