# 174: It's Not Weird

- Show: [Embedded.fm](https://hardwarepodcasts.com/podcast/embedded-fm)
- Published: 2016-11-02
- Length: 1h 09m
- Page: https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird
- Listen: https://makingembeddedsystems.libsyn.com/174-its-not-weird

## Summary

Evan Shapiro, CTO and co-founder of Knit Health, explains how his company uses a custom Linux-based camera with an onboard Qualcomm Snapdragon processor and deep learning neural networks to monitor infant sleep and respiration without wearable sensors. He details the engineering challenges of extracting weak respiration signals from noisy video, the decision to process data locally on the edge to preserve privacy and reduce cloud costs, and the rigorous security measures implemented to prevent hacking. Shapiro also discusses the history of neural networks, the 'Wizard of Oz' method used to train their models before having sufficient data, and his background as a professional poker player.

## Chapters

- [0:06](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=6) Introduction and Knit Health Overview
- [8:44](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=524) Computer Vision and Respiration Detection
- [16:09](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=969) Hardware Architecture and Edge Processing
- [19:16](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=1156) Data Privacy and Cloud Strategy
- [30:47](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=1847) History and Mechanics of Neural Networks
- [37:36](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=2256) Training Data and Wizard of Oz Method
- [39:44](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=2384) Linux OS and Security Implementation
- [50:05](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=3005) Professional Poker Background and Game Theory
- [59:07](https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird#t=3547) Kickstarter Campaign and Clinical Validation

## Topics

- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Security & privacy](https://hardwarepodcasts.com/topic/security-and-privacy)
- [Prototyping & iteration](https://hardwarepodcasts.com/topic/prototyping)
- [Crowdfunding & preorders](https://hardwarepodcasts.com/topic/crowdfunding)

## Most relevant to

early-stage companies

## Mentioned

- Knit Health (company)
- Qualcomm (chip)
- Linux (tool)
- Linaro (company)
- TensorFlow (tool)
- Theano (tool)
- Card Runners (other)
- Kickstarter (other)

## Related episodes from other shows

- [Baby Tech Revolution: Nanit and the Future of Infant Monitoring](https://hardwarepodcasts.com/podcast/over-the-air/2024-11-21-baby-tech-revolution-nanit-and-the-future-of-infant-monitoring) (Over the Air)
- [#023: Running Edge AI in Their Sleep: How Elemind Built Embedded Firmware for On-Demand Rest](https://hardwarepodcasts.com/podcast/coredump-sessions/2026-06-25-023-running-edge-ai-in-their-sleep-how-elemind-built-embedded-firmware-for-on-de) (Coredump Sessions)
- [Revolutionizing IoT with Machine Learning at the Edge | Perceive's Steve Teig](https://hardwarepodcasts.com/podcast/iot-for-all-podcast/2020-10-20-revolutionizing-iot-with-machine-learning-at-the-edge-perceives-steve-teig) (IoT For All Podcast)
- [Taming the Wild Edge](https://hardwarepodcasts.com/podcast/ee-times-current/2021-09-17-taming-the-wild-edge) (EE Times Current)
- [Machines That See | Distribution Evolution | Where No TV Show Has Gone Before](https://hardwarepodcasts.com/podcast/ee-times-current/2020-09-04-machines-that-see-distribution-evolution-where-no-tv-show-has-gone-before) (EE Times Current)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/embedded-fm/2016-11-02-174-its-not-weird. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Embedded.fm.