Collaborator: Meijie Hu, Zeshu Zhu
Our common conception of smart home devices is often as such - when human translates the complexity of language and situations into simple commands that device would ‘understand’, it simplifies the commands further into bytes of data that can be easily ‘communicated’ between devices. Just as written in the reading The Dream of The Internet of Things by Alice Benessia and Ângela Guimarães Pereira, technology, particularly in the context of IoT, “experience can be replaced by a series of algorithmic instructions, designed by software and hardware developers”.
While this is a true representation of how connected devices work, it is rather human-centric (and boring) to think that machines cannot think creatively with the information it receives. Especially with the advancement of machine learning, our traditional conception that devices lack imagination is further challenged. Therefore, we recreate a few common smart home sensors such as temperature sensor, light sensor to collect data in the room, and we translate them into dream imageries with GANs and map across the room. The whole smart home system is connected through server and monitored through a central platform.
On the physical end, we recreate a few sensors that are common in smart homes nowadays- smoke detector, light sensors etc to collect sensors data in different rooms in our home, these data will be updated every hour uploaded through HTTP.
On the digital end, we create a website as a virtual representation of the smart home sensors imagine. We will manually translate the sensor data into more descriptive languages (”dry as desert”, “humid as a rainforest”) to feed them into the GANs to generate images of the interior
that sensors “imagine”.
Users can play back the images generated from the sensor data to see how sensors’ imaginaries changes overtime.
