Posted on

Team Status Report for 4/30

This week, our team presented our final presentation in class. Following a good presentation, we continued to focus our efforts on bringing together the various parts of our project. After struggling to integrate certain pieces of the mirror together, we changed focus, and decided to create a server that allows us to access parts of our project through the internet. This allows both the mirror and the application we are creating to access the server and relay information accordingly. We also worked on integrating the mirror UI to be able to activate the mirror and connect to the other parts of the project.

As we are coming closer to the end of the project, we find ourselves more in need of connecting the final pieces of the project. In the next week we will focus on getting our mirror fully prepared and functional, and also finishing our final poster and final report. Overall we are on track as we enter the final stretch to get the various parts of the mirror together and test them for success.

Posted on

Ramzi’s Status Report for 4/30

This week I worked on connecting the outfit recommendation algorithms with our Google Spreadsheets API that we are using as a database for our user’s wardrobe. This allows the our application and device to connect to the same server for our wardrobe.  I also tested the full outfit recommendation time, and found that we were way over the mark of where we want to be in recommendation time. I think otherwise we are on schedule, and this next week we will be focusing on connecting all the parts together and wrapping everything up in preparation for our final report and demo.

Posted on

Ramzi’s Status Report for 4/23

This week, I improved the weather tags recommendation algorithm, and put together the outfit recommendation algorithm. I altered the weather algorithm and its tags to accommodate a wider variety of clothing, mainly formal clothing, such as suits and dresses, and synchronized it to the format of the database and the user’s input form. We now have an outfit recommendation algorithm that takes in various outputs, and provides the user with the 5 best options for them to pick and choose from based on a weighted point system. It also has an internal system for analyzing what accessories would be appropriate depending on weather conditions.

As we are coming closer to the final presentation and demo, I think we are on track with what we need to be getting done. Next week I will be focusing on putting together our final report, and integrating what remaining parts of our prototype are still waiting to be put together.

Posted on

Yun’s Status Report for 4/16

This week, I worked on the mirror UI using Electron, HTML, and JavaScript. The mirror is supposed to interact with Jetson and the app. The diagram(Figure 1) below illustrates a general idea of how mirror UI would look like.

Figure 1: Mirror UI diagram

As illustrated in the diagram, the mirror UI(desktop app) is supposed to make transitions from one screen to another based on the app and Jetson request/responses. However, as we have not finished the integration of this part yet, I made the app to ack upon buttons such as “Get recommendation” and “Done”. This will later be updated along with the integration. Here is a screen recording of how the desktop app looks so far.

(raw link: https://drive.google.com/file/d/1_uZXitU8aZ5DF-yaDiu9o0ppms_jQQFj/view?usp=sharing)

In terms of the schedule, I think we are on schedule, as we planned to start the integration today after finishing the individual parts. Although modular parts need to be more sophisticated, they are all working. I think we can start integrating everything from today, which was what we planned.

Next week, I will work on connecting Jetson and the Mirror UI, so that the UI can act according to the user input.

 

 

Posted on

Yun’s Status Report for 4/10

Last week I worked on categoritizing outfits and coming up with relevant tags. In order to do so, I did research through multiple popular clothing brands such as Zara and H&M that many students use and that sell various ranges of clothes. With the research, I came up with a few tags that can categorize clothings and tags that are relevant for outfit recommendations. The following Figure 1 demonstrates an abstract idea for tags and categorizations. Beside, I did more research on outfit recommendation algorithm, and I decided to hardcode weather based and also color based recommendation based on the color and weather coordination chart below (Figure 2, 3).

I think we are a week behind the very original schedule; however, because the rest are integration of modular tasks we have already accomplished and because we have done ramping-up, if we spend a few intensive days in the project, we will soon be on track.

This week, I will be working on wrapping up the recommendation systems and test it out to see if the result align with our expectations.

Posted on

Ramzi’s Status Report for 4/2

Unfortunately, I was preoccupied with illnesses throughout the week which greatly hampered my progress. I brought forth concerns with my teammates about support for the bluetooth components of the project, and we ultimately decided to switch over to utilizing a wifi system in order to transfer data to and from the mirror. This is bound to create a multitude of security concerns, however we think it should be fine as long as we will address aforementioned security concerns in the future.