# How to develop a machine learning algorithm a federated learning approach on wearable devices using DL4J?

**URL:** <https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048>\
**Category:** DL4J\
**Created:** [October 23, 2022, 7:05pm UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048 "2022-10-23T19:05:26Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://community.konduit.ai/u/edward)\
**Post date:** [October 23, 2022, 7:05pm UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048/1 "2022-10-23T19:05:26Z")

</div>

Hi all. I’m a student working on a federated learning project to predict atrial fibrillation using wearable technology. However, I am stuck and require your assistance. What I want to do is create a server and two clients that run on a WearOS simulator. I want to use Deeplearning4J to implement both the server and the client. [Here](https://drive.google.com/file/d/1EAyxXtGko_QhU56MYNjlt8LHxdLoVZ_n/view) is what I intend to accomplish in detail under (DEMO SETUP AND PRELIMINARY RESULTS), but I’m having trouble putting it into practice, for example, how to build a WearOS simulator, create clients, and the server. I appreciate your time and thoughtful comments in advance.

---

<div class="post-metadata">

**Author:** ![treo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/treo/32/47_2.png) [@treo](https://community.konduit.ai/u/treo)\
**Post date:** [October 23, 2022, 7:36pm UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048/2 "2022-10-23T19:36:59Z")

</div>

It looks like you are looking for us to write a masters thesis for you.

Unfortunately, we can only help you with things that are directly related to the things that you try doing yourself.

---

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://community.konduit.ai/u/edward)\
**Post date:** [October 23, 2022, 8:20pm UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048/3 "2022-10-23T20:20:22Z")

</div>

Thank you for the prompt response. Well, it’s a group project rather than a master’s thesis. We are a group of three students in our second year, and while we have it implemented in PyTorch, the instructor suggested that we simulate it on mobile devices. Therefore, we are simply figuring out how to do it.

---

<div class="post-metadata">

**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Post date:** [October 23, 2022, 11:40pm UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048/4 "2022-10-23T23:40:41Z")

</div>

@edward  
While we won’t re implement your whole project for you I can tell you that someone in the community did implement this: [Federated Learning. A Machine Learning adventure with… | by Jose Corbacho | ProAndroidDev](https://proandroiddev.com/federated-learning-e79e054c33ef)

If you want to start from there we’d be happy to help you with the basics.

---

<div class="post-metadata">

**Author:** ![edward](https://avatars.discourse-cdn.com/v4/letter/e/90db22/32.png) [@edward](https://community.konduit.ai/u/edward)\
**Post date:** [October 24, 2022, 6:09am UTC](https://community.konduit.ai/t/how-to-develop-a-machine-learning-algorithm-a-federated-learning-approach-on-wearable-devices-using-dl4j/2048/5 "2022-10-24T06:09:40Z")

</div>

Thank your for your valued input. We’ll definitely look into how we can proceed from there.