Paper on "Application of deep and reinforcement learning to boundary control problems"

Recently, I wrote a paper based on my master thesis project, which I had attempted to submit to AAAI conference. However, the attempt was futile as the reviewers did not really like it. It was quite interesting to see that at least some of the comments by the reviewers are contradictory with each other; it looks like I am not the only one who is lazy to read. Anyway, I decided to make it available for the public via arXiv and viXra. The following are the links to the same. Originally, I had only planned on submitting this to arXiv. When I checked the submission portal a couple of hours after the scheduled publishing time, I saw that the article was put "On Hold" from being published. I searched for the reasons for the same, and I read in a few places that sometimes arXiv takes a lot of time to publish them once put on hold, and sometimes they just don't publish them at all. Therefore, I decided to submit it

Smart Containers - An old project during my college days that could make Amazon better

A few months ago, my friend Dhawal shared a page from Amazon Business introducing their product named Dash Smart Shelf. The system enables businesses to manager their inventories by keeping a track of stuffs in the shelves over time and automatically doing the reordering. The principle behind the product is to have a weight-sensing Wi-Fi-enabled smart scale that is placed on a shelf to track the inventory.

The method involved is reasonably simple. A shop owner can have as many of these devices as the different products he/she wishes to store. That would be a lot of sensors.

Dhawal and I had worked on a project that would enable reducing the number of sensors involved in order to do the same. In our setup, there would be just two weight sensors placed at a distance and a platform on top of the sensors. We divide the platform into any number and we can determine where each product is placed and if anything is taken away from it, it would automatically change the values. This could theoretically work for any number of slots there are; just two weight sensors.

That would be a huge reduction in cost, wouldn't it?

We developed this system back in 2017. We had recorded a video talking about this in detail to take part in a compoetition. The following was recorded for that. In the video we explain in detail on how the setup was created, the working principle and gives a quick demo. (I know that the app crashed when we were shooting the video).

The video was recorded from the Hardware Lab in IIT Patna. We had to rush the creation of the video as the deadline for submission was right around the clock.

The app was created in React Native. The assembly has four load cells in a Wheatstone Bridge arrangement for more accurate detection, two such arrangements are made at either ends. The voltage variations from the load cells are picked up by Arduino and the information is interpreted there to know which slot has what weight. The final information is sent to Raspberry Pi, which acts as the server and provides the data to the React Native App through Rest API based calls.

Such simple concepts in physics and engineering could help in cutting down a lot of expenditure. I hope this inspires a lot of people.


Popular posts from this blog

Bought a new domain -

Started a blog under HexHoot

Created a video to help people get started with HexHoot