Started the project pipeline for Fake News Detection.
Started working on Fake News Detection
on 2018-08-30
with
No Comments
Weekly Update 1
- Looked for three general areas that I want to do my research in, namely:
- Structure from Motion
- Disaster prep and management
- Parallel Computing
- Searched for some related work that has happened in these areas.
Senior Project Ideas
Ideas:
- Pillow AI: I am thinking of having Arduino device built-in the pillow, which can be charged and have heart-rate sensors to receive heart-rate while the person is sleeping. Having this data, I could determine sleeping patterns and find the Light Sleep phase. After having a light sleep phase, I can send the alarm signal to the phone to wake up a person closest to the time when they set the alarm.
- Signature Recognition: I can use some deep learning algorithms, create a testing dataset and collect signatures of a lot of people. After that, I want to determine if the given signature is fake or a person’s real one.
- Human Development Index: I’ve been working on this project with my Econ professor this summer on the research, but the project turned out to be so exciting I might use it for my senior research project. So the basic idea is that have a platform(website) where people can go and choose their indicators(whatever they think are essential for country’s development) for the Human Development Index and get a new ranking of those countries. Keeping track of all given inputs from users, I can make some cool data analysis with it. Back-end will be python with pandas library, and dataset will be streaming live Restful API from Worldbank database.
Very first draft of thesis ideas
Computer Echolocation
For my project, I would like to do something where I can use both hardware and software. An idea I am interested in that contains the intersection between hardware and software would be creating a robot that uses echolocation to find the walls that define its boundaries. For now, I am thinking of using an EV3 robot and sonar. However, this doesn’t seem like it’ll be enough for a final project, so I am considering using other hardware tools for the robot besides the EV3 robot. I’m still narrowing that part down and need to do a little more research into hardware tools.
Platform for viewing data
I am interested in data, an idea relating to this is be to create my own platform for ingesting and displaying data. Having experimented with D3 recently, I think that would be a tool I would like to use for a large portion of project. During the summer, I used a platform that stored data in a graph form and would display said data, I would like to make something similar to this but with a different data structure for the data. I will be doing research to consider what direction to go with this.
Python Module for Image Processing
My final and least developed idea is to make a python module for image processing. I would make this from scratch, it would be dependant on other modules, but not other image processing modules. Creating a python module from scratch and image processing are two things that
Project Ideas
1)A piece of software that takes aspects of a soccer team and suggests players to sign or release based on statistics found online. This will include physical attributes, such as height, weight, 40 time, as well as statistics like shots on target and passes. This could be improved to search for specific words in scouting reports such as “dynamic” or “intelligent”.
2)Soccer is a dynamic and fluid game with many complexities that make it very difficult to predict. I’m interested in looking at how current predictions are made, such as at fivethirtyeight, and attempting to develop software to predict outcomes of matches.
3)Drones create opportunities to see the world with an unprecedented amount of freedom and flexibility. As they improve they’re able to fly higher and for longer, and cameras also improve to take images of incredible quality even from heights of more than 100 meters. The result is a lot of images. I’m interested in creating a robust piece of software that stitches large sets of images together reliably and quickly into a single 2D image.
To do for the upcoming week – Rei
For the next week, I plan on working on:
- Extract data from the blog and Brown corpora
- Identify which algorithms we’ll be using
- Find where these are available
- Identify parts of work already that that’ll be useful
3 Initial Senior Project Ideas
These are super vague ideas, and I don’t know if they’re doable, but that’s what I came up with:
- App/Game for experiencing different cultures
- Tone analyzer
- Text editor extension for good code-writing habits
Flannery Currin Week 1
This past week I reached out to Dave and he agreed to be my mentor for this project and prepared my presentation slides based on my project proposal. I dug into the NVDA developer’s guide and walked through some basic examples of creating and testing NVDA add-ons, so now I have a better understanding of what developing an add-on looks like. I met with Dave to go over my general approach and strategies to adapt that approach as necessary as time goes on. I also reached out to the director of the program where I worked over the summer to ask her to connect me with a colleague of hers or one of his students who have done more work in this space and who could help me especially at this stage of my project.
In the upcoming week I hope to develop criteria for the types of data visualizations I’ll be focusing on and begin creating examples of those and playing preliminarily with how NVDA digests them. I’d also like to go back over my literature review and begin working on paring it down some and shaping it into a Related Works section of my final paper.