Grading & Assignments

Grading

• Research Paper Summaries - 36%

• Individual Presentation - 10%

• Class Participation - 10%

• Midterm Project Review - 4%

• Final Paper/Project - 30%

• Project Presentation - 10%

Per Dartmouth's Spring term grading rule of credit/no credit (applicable only to undergraduate students), the threshold for gaining credit in this course is 80%.

Weekly Research Paper Summaries

Each week students are expected to read and summarize two research papers from the weekly reading list. These summaries are due every Monday at 11:59pm EST (except during week 1). The purpose of this assignment is to ensure students have read the relevant papers and are prepared to engage in a fruitful class discussion.

Guidelines

• • Limit: For 2 paper summaries, 1.5 - 2 pages, single-spaced, 12 pt. font

  • Title of the paper and your name

  • Address all the below questions in individual/separate subsections:

    1. Objective: What is the objective/contribution?

    2. Problem Space: Why is the problem space interesting/important?

    3. Key Innovations: What are the key innovations? (may not be valid for review papers)

    4. Methodology: Summarize the approach/methodology presented.

    5. Results: What are the key findings/results?

    6. My Question/Thought: What is one primary question or thought that you have on the topic/paper? This will be used as a point for class discussion.

Note: There are 7 weeks of papers on the reading list with one summary due in week 1 and two due every other week, there are a total of 13 paper summaries due. Only 12 will be graded. Hence, each student can choose to omit one summary of their choosing (e.g., one less summary during the week a person is presenting in class).

Individual Presentation

See the home page under "Class Structure" for my information.

Class Participation

Given that this class will be taught remotely, there are two ways to actively participate in the class:

1. Engage in interactive sessions during the class time. Ask questions and share thoughts based on your knowledge and from your readings.

2. Engage in weekly discussion boards via Canvas to ask questions and share thoughts based on your knowledge and from your readings. This option is provided as an alternative for students who cannot attend interactive class sessions.

Final Project

Through the course of the term, students will work on a final project and concurrently write a publishable paper about their work. Every ~2 weeks, a new section of your paper describing progress on the project is due. Students have the option to work on their final project as an individual or in a two-person team (pairing will be done by the students themselves).

Given the timeliness of the course and today's global pandemic, the final project is titled "Learning from Data about Coronavirus (LDC)". Each group can select one of the below datasets for their final project:

• Novel Corona Virus 2019 Dataset

• COVID-19 Open Research Dataset Challenge (CORD-19)

Additionally, students have the option to select any task or challenge posted online in association with the dataset or can define their own challenge which must be approved by the instructor. Acceptable challenges can include data and text mining, modeling, prediction, visualization, etc. to support improved understanding of COVID-19.

Getting Started:

1. First Hour with a Kaggle Challenge by Sentdex. This video is a great starting point for working with the CORD-19 dataset.

2. Exploring Coronavirus Research Publications by Sadrach Pierre

Exception - Learning from Data about [fill-in-the-blank]: In the event that a given student is more passionate about another health domain and would prefer to do their final project in that space, this is acceptable if we can gain access to a fitting dataset for a strong project in the selected space. Some examples that may qualify for this exception are, a student already does research in a given field and they have data for their research, a student can find a publicly-available dataset in their field of interest. A great resource for publicly available datasets is https://www.kaggle.com/datasets.

Final Paper

Every project group (individual or pair) is expected to write a final publishable paper to share their research results and findings. There will be writing milestones due throughout the term (see schedule) to keep teams on task with writing. The primary publication venue is:

• PLOS ONE: Primarily for teams working with an open-source dataset.

However, alternative venues will be considered on a case-by-case basis for each project team, especially those working with non-public datasets (e.g. from a research lab).

Important Notes:

• Manuscript length: At least 6 papers not including references for a single-person team and 10 - 12 pages not including references for a two-person team. This guideline is for teams writing for PLoS ONE for which no page limit is given.

• Organization: Every manuscript must follow instructions provided by the selected publication venue. An example of submission guidelines for PLOS ONE can be found here.

• Template: All papers should use the appropriate template provided by the selected publication venue. An example of such a template for PLOS ONE can be found here.

• LaTex: All final papers should be written using LaTex. Each project team should use Overleaf an online, collaborative LaTex editor.

• Reference Papers: It is always a good idea to have a few examples papers from the selected publication venue that can be used as a reference during the course of writing your own papers. Some example reference papers for PLOS ONE are as follows:

  1. Nyarku et al, "Mobile phones as monitors of personal exposure to air pollution: Is this the future?" PLoS ONE, 2018.

  2. Casilari et al., "Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection," PLoS ONE, 2016.

  3. Brinkler et al., "Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions," PLoS ONE, 2019.

  4. Ali et al., "Novel image retrieval based on visual words integration of SIFT and SURF," PLoS ONE, 2016.

• Actual Publication: Although we will be writing a publishable paper in this course, students/teams have the option to decide whether or not they actually want to submit their final paper for review and potential publication. As we will learn, some teams may have interesting findings while others may not and this will influence the decision. Additionally, we may find that combining two final papers into one may make for a stronger paper to be submitted for publication. If this is the case, such decisions will be made when the time arises.

• Authorship: Given that this is a class project, the instructor will serve as a research advisor for every project team and as such will be listed as the last author (i.e. advisor) on any papers submitted from this course.