[AI] Human Activity Recognition

這兩篇可以參考看看
https://github.com/markdregan/K-Nearest-Neighbors-with-Dynamic-Time-Warping
https://becominghuman.ai/deep-learning-for-sensor-based-human-activity-recognition-970ff47c6b6b

[NLP] NLP ABC

https://blog.insightdatascience.com/how-to-solve-90-of-nlp-problems-a-step-by-step-guide-fda605278e4e?imm_mid=0faff0

[Linux] access the webcam at the same time

找了一陣子終於看到了
https://askubuntu.com/questions/165727/is-it-possible-for-two-processes-to-access-the-webcam-at-the-same-time

$ git clone https://github.com/umlaeute/v4l2loopback.git
$ cd v4l2loopback
$ make
$ sudo make install

$ sudo depmod -a

$ sudo modprobe v4l2loopback devices=2

gst-launch-1.0 v4l2src device=/dev/video0 ! tee name=t ! queue ! v4l2sink device=/dev/video1 t. ! queue ! v4l2sink device=/dev/video2

[Tips] 流量

每次都要找在哪裡
https://www.alexa.com/siteinfo
https://www.alexa.com/find-similar-sites

[Audio] echo cancellation

被歧視了 QQ
http://wiki.seeedstudio.com/ReSpeaker_2_Mics_Pi_HAT/
https://github.com/respeaker/mic_hat
https://github.com/voice-engine/voice-engine
https://github.com/Kitt-AI/snowboy

還沒解決，但參考這幾篇想想看
https://tinkerboarding.co.uk/wiki/index.php/Google-Assistant-SDK
http://lac.linuxaudio.org/2013/download/slides.pdf
https://gist.github.com/aflaxman/6300595

=>  https://github.com/respeaker/respeaker_for_raspberrypi

順便看一下 alsa 的 config 意義
http://www.sabi.co.uk/Cfg/ALSA/asound_simple.conf

ReSpeaker 的設定參考
https://github.com/wzpan/dingdang-robot/wiki/respeaker-2-mics-pi-hat

[待辦] Tangram

去中華電信問到的
http://tangram.pingguohe.net/

生產力中心不知道會不會用到？ 不過好像只是 Android UI

我錯了 QQ，應該要看的是這個
https://www.tangram.tw/