One Day to Meet The Google Cloud
Last week, several colleagues from Google came to my office to make an interesting event, a Google Cloud Day. They booked the highest floor on the building to decorate it with a good ambiance.
There were many interesting agendas throughout the day, including Infra & Apss Dev, IoT Platform, Digital Marketing, etc.
I couldn’t attend all the agendas due to the limited time, so I choose to be included in the most interesting topic “IoT Enabled for Industrial Solutions”. Markku Lepistö, a Solution Architect from Google Cloud Platform JAPAC, handled this topic. He delivered the advantage of using Google Cloud as an IoT Platform.
He said that Google Cloud IoT is a complete set of tools to connect, process, store, and analyze data both at the edge and in the cloud. The platform consists of scalable, fully-managed cloud services; an integrated software stack for edge/on-premises computing with machine learning capabilities for all your IoT needs. This platform can accelerate business agility and decision making with IoT data, Improve operational efficiency, and enhance the IoT solution with location intelligence.
I was amazed when Markku demonstrated the Edge TPU, the development board for AI inference and Machine Learning accelerator. He set it up with the Raspberry Pi to make an AutoML model with several functions. For example, in this first video, He used it to detect the object automatically by calling the Vision API on the GoogleCloud to the EdgeTPU. After that, He used Text to Speech API to the speaker and added another feature by calling the Translation API. I suggest you watch the video to get it clearly :D.
In the second video, Markku showed the customize ML Model for Air Asia application. It is used for detecting the variation of vehicles in the airport area.
It was a good day to know the Google Cloud and its advantage for me as a learning medium. Thank you Google Cloud & XL Axiata for the good event. Hope it will be a sustainable event and bring more joy in the future.
Originally published at https://www.linkedin.com.
