If you are pursuing the Master degree or PHD Research paper writing then you first get the task to write project proposal before submitting final project. If you don't have an idea or not have time to write this then don't worry. We have experience team of big data and machine learning that can do your project proposal writing work as per your given requirements.
Below the few samples of project proposals:
Project Proposal 1:
Title Page:
---------------------------------------------------
Project Proposal: Average Age of NFL Players Over the Previous Twenty Years
Your Name
University Name
Semester
-------------------------------------------------------------
Table of Contents:
Project Proposal: Average Age of NFL Players Over the Previous Twenty Years............ 1
Project Overview ................................................................................................................ 3
Major Objectives................................................................................................................. 3
Data Resource ..................................................................................................................... 3
Literature Review................................................................................................................ 3
Methods............................................................................................................................... 4
Year-By-Year Average Per Team .................................................................................. 4
Year-By-Year Average Overall...................................................................................... 4
Year-By-Year Average by Position................................................................................ 4
Significance......................................................................................................................... 4
References........................................................................................................................... 7
----------------------------------------------------------------
Project Overview:
I have been a big fan of the New York Giants football team ever since I was in middle school. In my time watching football, I have seen countless players enter and leave the National Football League (NFL) for various reasons. Some players, however, seem to remain in the league for quite some time. Eli Manning just finished his sixteenth and final season with the New York Giants in 2019. In all sixteen years, Manning remained injury free. Most players, especially in positions other than quarterback, tend to have a much harder time staying competitive in the league as they age. A recent example, Victor Cruz, was a very talented wide receiver for the New York Giants. His career was cut short after an injury and Cruz was only able to play four seasons with the Giants. Many of my all-time favorite players, such as Eli Manning, are beginning to retire and as they are being replaced by younger players, I thought it would be interesting to visualize the average player age over the last twenty years and compare the average ages of different positions.
-------------------------------------------------
Major Objective:
Divide players up by team and position
Determine average ages by year
Visualize data using graphs
------------------------------------------------------
Data Resource:
The data I will use for this project comes from:
https://www.dolthub.com/repositories/Liquidata/nfl-play-by-play/data/master/teams.
I found this source through one of the data repositories provided on Blackboard
(https://github.com/awesomedata/awesome-public-datasets).
The dataset is very comprehensive and includes data about each team, play, as well as each player. The data provided for each player includes (but is not limited to): the season they played, the team they played for, the player’s name, the player’s status that season, the player’s position, and the player’s birth date.
There are many more columns of data, but I believe these six columns are the most relevant to this project.
--------------------------------------------------------
Literature Review:
To prepare for this project, I researched the effect of age in other professional sports. One article I found, which conducted a similar study with European football teams, discusses how age relates to European football and the recruitment of professional players. The article found that some positions, such as midfielders and defenders, have a harder time staying in the league than players in other positions. I have a theory that the same is true in American football, and that positions such as quarterback have a longer average career than running backs. Quarterbacks have the benefit of being protected in every play by the offensive line. Running backs, however, get hit in nearly every play that they touch the ball. I believe that the increased protection that quarterbacks receive contributes greatly to their longevity. The article also found that player “recruitment and selection processes came influenced” (Yagüe et al., 2018, p. 413) by age.
Management of teams in the NFL have a lot of tough decisions relating to player contracts and I believe that age has an effect here as well. Free agents (active players not currently signed to a team in the NFL) may have a harder time getting signed to a team as they age. It may be difficult for a free agent to convince a team to sign them when they only have a few good years left, as opposed to a younger player who might give the team more years. Aging players might also be more prone to injury than younger, less expensive players. These factors may come into play when team managers make contract decisions. The article did a good job preforming this study on the European football league; however, I was unable to find such a study, or even a similar one, relating to American football. I believe my project can help fill in this gap in
information.
---------------------------------------------------
Methods
I believe implementation for this project would be relatively simple. First, the project needs to be divided up into different sections: year-by-year average per team, year-by-year average in the league overall, and year-by-year average per position. Dividing the project into these sub-sections will allow me to determine age trends among different teams or positions. If a small number of teams or positions are greatly impacting the results, I will be able to take that information into account when viewing overall averages.
------------------------------------------------------
Year-By-Year Average Per Team
To accomplish this task, the mapper needs to do the following. For each player, emit the key-value pair: (CONCAT(year, team_name), player_birth_date). The data should be sorted before passing through the reducer. The reducer shall take the sorted key-value pairs and compute the average player age for each year and emit the key-value pair: (year_team, avg_player_age). This program will produce numYears*numTeams key-value pairs.
Year-By-Year Average Overall
For the overall average, the mapper function can be a bit simpler than the previous one. For each player, the mapper does not need to perform any concatenation and can simply emit the following key-value pair: (year, player_birth_date). Similar to the team average, this data also needs to be sorted by year before being passed to the reducer function. The reducer shall take the sorted data and compute the average player age for each year and emit the key-value pair: (year, avg_player_age). This program will produce numYears key-value pairs.
Year-By-Year Average by Position
For the position average, the functions will act nearly identical to that of the team average, with the only major change being the key-value pairs produced. The mapper function will emit the following key-value pair: (CONCAT(year, position), player_birth_date). Once again, the data must be sorted prior to the reduce step. The reduce function shall take in the sorted data and compute the average player age for each year by position and emit the following key-value pair: (year_position, avg_player_age). This program will produce numYears*numPositions key-value pairs.
-------------------------------------------
References
Yagüe, J. M., de la Rubia, A., Sánchez-Molina, J., Maroto-Izquierdo, S., & Molinero, O. (2018). The relative age effect in the 10 best leagues of male professional football of the Union of European Football Associations (UEFA). Journal of Sports Science and Medicine, 17(3), 409-416.
-------------------------------------------------------------------------------------------------------------------------------
Project Proposal 2:
Project Title
---------------------------------------------------------------
Cyber Attack Analysis Using UNSW-NB 15 dataset
----------------------------------------------------------------------
Data Set
The raw network packets of the UNSW-NB 15 dataset was created by the IXIA PerfectStorm tool in the Cyber Range Lab of UNSW Canberra for generating a hybrid of real modern normal activities and synthetic contemporary attack behaviours. The tcpdump tool was utilised to capture 100 GB of the raw traffic (e.g., Pcap files). This dataset has nine types of attacks, namely, Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnaissance, Shellcode and Worms. The Argus, Bro-IDS tools are used and twelve algorithms are developed to generate totally 49 features with the class label.
These features are described in UNSW-NB15_features.csv file
The shape of dataset, 9 rows and 49 columns.
-------------------------------------------------------------------
Project Idea
Describe what you plan to achieve? What big data model or tool are you going to use?
In this project perform data analysis task perform to analyse the UNSW Canberra Cyber dataset. In this Nine types of attacks are given that happening i.e. Fuzzers, Analysis, Backdoors, DoS, Exploits, Genetic, Reconnaissance, Shellcode and Worms.
In this project I perform the traditional machine learning algorithms like: Binary Classification and Multi- Classification. In project I archive many important and necessary points like, (1) how to handle big data using Pyspark tool. (2) How to merge features and dataset file. (3) How to visualize the features. (4) And applying algorithms
In this I use the Python tool using PySpark library that use to handle big data. In this I use the Jupyter notebook data analysis editor.
-----------------------------------------------------------------------
Data Source
https://research.unsw.edu.au/projects/unsw-nb15-dataset
-----------------------------------------------------------------------
References
---------------------------------------------------------------
https://spark.apache.org/docs/latest/api/python/getting_started/install.html
https://research.unsw.edu.au/projects/unsw-nb15-dataset
https://www.datacamp.com/tracks/big-data-with-pyspark
To get any help Related project proposal Writing you can send your requirement details at:
realcode4you@gmail.com
コメント