Michael Sung

Wearable feedback systems for rehabilitation

In this paper we describe LiveNet, a flexible wearable platform intended for long-term ambulatory health monitoring with real-time data streaming and context classification. Based on the MIT Wearable Computing Groups distributed mobile system architecture, LiveNet is a stable, accessible system that combines inexpensive, commodity hardware; a flexible sensor/peripheral interconnection bus; and a powerful, light-weight distributed sensing, classification, and inter-process communications software architecture to facilitate the development of distributed real-time multi-modal and context-aware applications. LiveNet is able to continuously monitor a wide range of physiological signals together with the users activity and context, to develop a personalized, data-rich health profile of a user over time. We demonstrate the power and functionality of this platform by describing a number of health monitoring applications using the LiveNet system in a variety of clinical studies that are underway. Initial evaluations of these pilot experiments demonstrate the potential of using the LiveNet system for real-world applications in rehabilitation medicine.

MIThril 2003: applications and architecture

In this paper we describe the MIThril 2003 wearablecomputing research platform. MIThril 2003 is a proven,accessible architecture that combines inexpensive,commodity hardware, a flexible sensor/peripheralinterconnection bus, and a powerful, light-weightdistributed sensing, classification, and inter-processcommunications software layer to facilitate thedevelopment of distributed real-time multimodal andcontext-aware applications.MIThril 2003 extends the previous MIThril modulararchitecture into the domain of large-scale wirelessgroup applications by leveraging the availability ofinexpensive Linux-based PDA hardware combined withinnovative open-source software and custom sensorhardware. We demonstrate the power and functionalityof MIThril 2003 by describing compelling real-worldwearable research applications created using MIThril2003 technology.

Mobile-IT Education (MIT.EDU): M-Learning Applications for Classroom Settings.

In this paper, we describe the Mobile-IT Education (MIT.EDU) system, which demonstrates the potential of using a distributed mobile device architecture for rapid prototyping of wireless mobile multi-user applications for use in classroom settings. MIT.EDU is a stable, accessible system that combines inexpensive, commodity hardware, a flexible sensor/ peripheral interconnection bus, and a powerful, light-weight distributed sensing, classification, and inter-process communications software architecture to facilitate the development of distributed real-time multi-modal and context-aware applications. We demonstrate the power and functionality of this platform by describing a number of MIT.EDU application deployments in educational settings. Initial evaluations of these experiments demonstrate the potential of using the system for real-world interactive m-learning applications.

Shiver motion and core body temperature classification for wearable soldier health monitoring systems

We present a wearable real-time shiver monitor based on the MIThril LiveNet system, a flexible distributed mobile platform that can be used for a variety of proactive healthcare applications. In this exploratory study, we demonstrate that shivering can be accurately determined from continuous accelerometer sensing. Our preliminary results also indicate that shivering characteristics may be correlated with core body temperature, indicating the potential for creating a real-world cold exposure monitoring and classification wearable system.

MIT.EDU: system architecture for real-world distributed multi-user applications in classroom settings

In this paper we describe the MIThril mobile-IT education (MIT.EDU) platform, an innovative architecture that allows for the rapid prototyping of wireless mobile multi-user applications for use in classroom settings. MIT.EDU is a proven, accessible system that combines inexpensive, commodity hardware, a flexible sensor/peripheral interconnection bus, and a powerful, light-weight distributed sensing, classification, and interprocess communications software architecture to facilitate the development of distributed real-time multi-modal and context-aware applications. We demonstrate the power and functionality of the MIT.EDU platform by describing a number of system deployments of real-world applications in a number of educational settings.