Activity Recognition for the Smart Hospital

Abstract

A lthough researchers have developed robust approaches for estimating, location, and user identity, estimating user activities has proven much more challenging. Human activities are so complex and dynamic that it's often unclear what information is even relevant for modeling activities. Robust approaches to recognize user activities will require identifying the relevant information to be sensed and the appropriate sensing technologies.In our effort to develop an approach for automatically estimating hospital-staff activities, we trained a discrete hidden Markov model (HMM) to map contextual information to a user activity. (For other approaches to estimating work activities, see the related sidebar.) We trained the model and evaluated it using data captured from almost 200 hours of detailed observation and documentation of hospital workers. Here, we discuss our approach, the results, and how activity recognition could empower our vision of the hospital as a smart environment. The iHospitalThe iHospital is our vision of a highly interactive smart environment saturated with heterogeneous computing devices. These devices range from handheld computers that can capture and access limited amounts of information, to PCs that can be used at fixed sites for longer time periods, to conveniently located semipublic displays that let users share and discuss information. The iHospital staff can interact with the environment using a set of specialized services that account for contextual information. To help realize this vision, we have developed several ubiquitous and context-aware applications such as a context-aware mobile communication system, a context-aware map, and an activity-based application that support the following functionalities. 1,2 Awareness of people and artifactsHospital staff must navigate hospital premises to gather the information they need to conduct their work; this navigation is time-consuming. We developed and incorporated into the iHospital a contextaware application aimed at saving the staff time by making them aware of the presence, location, and status of artifacts and people, either using a digital floor map or an automatically updated list of people and artifacts. To introduce location awareness, we use a component that estimates users' positions throughout the hospital. 3 Context-aware communicationHospital staff can use contextual information as a trigger to retrieve or send messages. For example, a nurse can send a message to the physician responsible for a patient in the next shift when the patient's laboratory results are ready. The sender doesn't need to know which physician will be attending the patient or when the laboratory results will be ready. The application, on the basis of contextual information, automatically sends the message.In addition, hospital staff can transfer information from public spaces to personal devices, share

Activity Recognition with Multi-tapeFuzzy Finite Automata

“…Among them, the Hidden Markov Model (HMM) is the most commonly used. Sanchez, D. et al [1] trained a discrete HMM to map contextual information to a user activity. The model was trained and evaluated using data captured from 200 hours of detailed observation and documentation of hospital workers.…”

“…The ability to recognize human activities automatically and unobtrusively in a smart environment has a number of applications varying from essential services such as healthcare and security to luxurious services such as automatically adjusting room ambience and ergonomics [1][2] [3]. A smart environment usually has a large number of different types of sensors embedded in almost every possible component of the environment.…”

Interaction Modeling and Prediction in Smart Spaces: A Bio-Inspired Approach Based on Autobiographical Memory

“…The learned rules relate two sets of state variables, regarding respectively sensors and actuators, acquired simultaneously, without considering their temporal consequentiality. In [36], the authors propose an activity recognition method for Smart Hospitals. The system is based on multiple Hidden Markov Models (HMMs) which interpret the interactions between hospital staff, clinical objects, and patients.…”

Dynamic sensor data segmentation for real-time knowledge-driven activity recognition

“…Existing literature provides a number of modelling approaches that fall in two main categories: datadriven and knowledge-driven activity modelling. In data-driven activity modelling [1][2][3], activity models are learnt from pre-existing activity datasets. In knowledge-driven activity modelling [4][5][6], knowledge engineers and/or domain experts employ knowledge engineering techniques to specify activity models explicitly.…”