Towards Realizing the Internet-of-Things Vision: In-body, Homes, Cities, and Farms

Опубликовано 20 мая 2019, 15:23

The Internet-of-things (IoT) enables us to connect our physical and digital worlds by embedding computing devices into the environment. Today, there is a huge interest in IoT systems for smart homes, smart cities, digital healthcare, data-driven agriculture, etc. However, for these IoT system to deliver their intended vision we need to address three key challenges: (a) operation under limited resources like power and connectivity, (b) obtaining contextual information, and (c) inference from multi-modal data.

In this talk, I will present three examples of my research that address these challenges. First, I will talk about enabling IoT devices inside the human body, where both power and connectivity are scarce. I will present ReMix, a system that enables communication and localization at zero transmission power. Second, I will discuss our design for context-aware smart homes. Today, individual IoT devices need to be controlled manually because of lack of contextual information, an approach that negates much of their advantage. Ideal smart homes would understand an occupant's needs, habits, and behavior and adapt organically. I will show how we can embed such contextual information into these IoT systems to redefine the smart home experience. Finally, I will present FarmBeats, a system that fuses together data from multiple sensing modalities (sensors, images, videos) to deliver higher level inferences for data-driven agriculture. FarmBeats has been deployed in farms across multiple countries and has already proven beneficial to farmers. I will conclude the talk with future directions in IoT research, both in terms of the core methods as well as applications.

See more at microsoft.com/en-us/research/v...