After 5 weeks of excitement and learning, we finally made it to the end of it. We have learned a lot about machine learning, we helped each other. My teammates showed support and they were helpful.
Joining PATHS- UP was a great experience I was lucky when Allen emailed me at the last minute before the start of the program to let me know about this opportunity.
There are great teachers every year who apply for this program and I was one of the lucky ones to get selected to join this program.
Also, Allen showed professionalism during the program and understanding I would like to be part of other programs in the future and participate in.
On Friday we all presented what we have learned even I was so nervous I was so close to stop presenting and leave but if I was not nervous I would have totally nailed it.
On the other hand, Micheal, Alonzo, Ms.Sheryl, Daniel, Derek, and Al did an amazing job presenting and summarizing their journey in a form of a slide deck; I have enjoyed listening to them and learning from them during their presentations. Also, i want to thank our mentor Tianyi she helped up a lot and gave us so many ideas on how to complete the research about machine learning.
Experiments
Getting closer to the end….
Really kicked into overdrive this week as we approach the end of SWITCH 2021 Research Experience for Teachers. My main focus was trying out some different experiments with the Wisconsin Breast Cancer data, including reducing the number of features included in my models to only three by looking at those with the highest correlation to the diagnosis. I visualized this using the heatmap function in seaborn and chose to look at radius, perimeter, and concave points as they had the best correlation when looking at the three features which fall under each category: mean, se, and worst. Then I trained seven machine learning models on each set of three features(mean, se, and worst) associated with each category (radius, perimeter, and concave points) and calculated the training and testing accuracy for each. I found that linear SVM had the highest performance for each with only a marginal reduction from utilizing all 31 features included in the total dataset to train the models, where the Random Forest Classifier had the best testing performance. I believe it is possible to get an adequately accurate model for detecting breast cancer even with a significantly reduced number of features in the training and testing dataset given that those specific features are highly correlated with the diagnosis.
I also really got deep into using the seaborn python package to visualize not only data correlation but also to visualize the individual support vectors for my trained SVM models that support drawing the hyperplane to adequately create the maximum margin for separation of features within the dataset. I found using seaborn to have some advantages compared to matplotlib due to the more functional syntax that it implements. I also find the 3D plots produced by seaborn to be more visually appealing. The downside to these visualizations though is when you are using more than two features as getting the 3D model oriented correctly to be able to see adequate separation is somewhat difficult and in some cases not really possible based on the research and work I have done with it so far.
Faculty talks
We also attended a presentation on Designing Effective Posters presented by Dr. Stephen Perry which was very enlightening. He showed many examples and guidelines for creating an engaging, stand-alone poster that tells a story while being informative and attention grabbing. I learned many strategies that not only helped me in designing my poster for the SWITCH presentation but will also be great information I can pass on to my students when they are working on Science Fair or other academic posters. I am confident that Dr. Perry’s presentation is one that I will continue to reference for quite some time.
We also attended a talk from Dr. Dino Di Carlo, faculty at UCLA, on “Lab on a Particle” technology, which involves creating tiny assays for running many tests simultaneously through 3D fabricated particle-sized “flasks”. This technology also has the potential to leverage existing laboratory technology in production and in application. These 3D structures are like a compartment for containing droplets within a larger sample utilizing oil emulsions with the sample to create “dropicles”. This talk was incredibly interesting and also discussed many challenges in the creation and implementation of “Lab on a Particle”. I am excited to see the future applications of Dr. Di Carlo’s work.
As I started the 4th week with PATHS-UP, Rice University the research department. After working on Breast cancer detection using machine learning. Everything became more clear about the program. We started the week by learning about the perfect poster training. We learned about why designing effective research posters is important and how an effective poster is to share the knowledge of what we learned and it should contain visual representation to attract the audience .
What makes a poster visually appealing?
What makes a poster visually appealing is to be concise and informative and it should attract and engage with the subject.
How to present a poster?
Presenting a poster should be summarizing the experience completing it and very quick using a limited time.
There are 4 keys characteristics about any effective poster:
-Easy to understand.
-Visually appealing.
– Tell a story.
-Strategically designed.
Time-Of-Flight-Diffuse Optical by Yongyi Zhao
On the Second day Yongyi Zhao, Graduate Student Presentation explained a very interesting topic about Time-Of-Flight-Diffuse Optical which is Translation of the image activity in the brain. (BCI) Applications of the brain that it interfaces with prosthetics and mobility.
-Imaging through a strongly diffusive medium remains an outstanding challenge, in particular in applications in biological and medical imaging. Here, a method based on a single-photon time-of-flight camera allows, in combination with computational processing of the spatial and full temporal photon distribution data.
The technique is contactless and requires 1 s acquisition times, thus allowing Hz frame rate imaging. The imaging depth corresponds to several centimetres of human tissue and allows us to perform deep-body imaging as a proof of principle.
Lab on particle technology
By Dr.DiCarlo
On the third day of the PATHS- UP learning journey I came across another interesting topic Which is:
Lab on particle technology
During this presentation Dr.DiCarlo talked about Micro and nanotechnologies designed to operate at micrometer length scales that are uniquely suited to sense and manipulate single cells and single molecules. Concerning diagnostics, these approaches promise to lay the foundation for continuously monitoring health through minute quantities of biomarkers indiscernible by present-day technologies, a revolution that will lead to detecting and re-defining the concept of disease to be unique to each individual. Those molecules are made in different shapes and the dropicles are filled with water and oil.
On the last day of this week,I attended the young scholars’ presentation. They showed their intelligence and their hard work completing the research. It was very inspiring and interesting.This week was exhausting and full of work and information but at the end i enjoyed so many aha moments that i have encountered.
