Inferring activities from interactions with objects

By Matthai Philipose, Kenneth P. Fishkin, Mike Perkowitz, Donald J. Patterson, Dieter Fox, Henry A. Kautz, Dirk Hähnel. IEEE pervasive computing, 2004

823 citations recorded by the source corpus.

A key aspect of pervasive computing is using computers and sensor networks to effectively and unobtrusively infer users' behavior in their environment. This includes inferring which activity users are performing, how they're performing it, and its current stage. Recognizing and recording activities of daily living is a significant problem in elder care. A new paradigm for ADL inferencing leverages radio-frequency-identification technology, data mining, and a probabilistic inference engine to recognize ADLs, based on the objects people use. We propose an approach that addresses these challenges and shows promise in automating some types of ADL monitoring. Our key observation is that the sequence of objects a person uses while performing an ADL robustly characterizes both the ADL's identity and the quality of its execution. So, we have developed Proactive Activity Toolkit (PROACT).

Subfields: Computer Vision and Pattern Recognition, Information Systems and Management, Surgery

View Paper: https://www.semanticscholar.org/paper/a106cd5537886f2920aaa1d214cf46865e424f7f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems and Management

In Surgery

Citations in the corpus

Figure-ground segmentation improves handled object recognition in egocentric video (2010, background): “Many studies have shown that recognizing handled objects provides rich context information and is the basis for user activity recognition [15, 26].”
Design of an RFID-Based Battery-Free Programmable Sensing Platform (2008, background): “The implementation of an environment augmented with RFID to enhance the quality of life and independence of elderly citizens is discussed in [3].”
Human Activity Detection from RGBD Images (2011, background): “However, this may require subjects to wear RFID sensors in an environment labeled with RFID tags, as was shown in (Philipose et al., 2004; Patterson et al., 2005), or highly engineered and task speciﬁc visual recognition procedures (Mihailidis et al., 2003).”
Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors (2005, neutral): “Recently, researchers at Intel Research Seattle have used scores of radio frequency identification tags to recognize dozens of ADLs [24].”
From participatory sensing to Mobile Crowd Sensing (2014, methodology): “extracted the activity-relevant objects from the Web (Wikis, HowtoDos), which is then used in RFID-based human activity recognition [25].”
A Survey on Ambient Intelligence in Health Care (2013, positive): “In response, researchers have explored the usage of RFID tags [53], [54] and accelerometers or shake sensors [55] for tagging these objects and using the data for activity recognition.”
Fine-grained activity recognition by aggregating abstract object usage (2005, methodology): “[15] looked at the problem of detecting 65 activities of daily living (ADLs), from 14 classes such as cooking, cleaning, and doing laundry, and used data from a wearable RFID tag reader deployed in a home with tagged objects.”
SVM-Based Multimodal Classification of Activities of Daily Living in Health Smart Homes: Sensors, Algorithms, and First Experimental Results (2010, background): “Moreover, with the increase of life expectancy, diseases such as Alzheimer’s are more and more prevalent.”
Unsupervised Activity Recognition Using Automatically Mined Common Sense (2005, background): “Although the above challenges have long been recognized by the perception community, recent work (Philipose et al. 2004; Tapia, Intille, & Larson 2004) has suggested an interesting direction in addressing them.”
Mobility Detection Using Everyday GSM Traces (2006, background): “Smart spaces containing cameras, RFID tags, and the like, have been used to detect fine-grained user activities [3, 15, 25].”
BodyScope: a wearable acoustic sensor for activity recognition (2012, background): “employed radio frequency identification (RFID) tags to determine which objects the user interacts with, and used this information to infer the activity [27].”
Detecting activities of daily living in first-person camera views (2012, background): “There has been a fair amount of work on everyday activity-recognition from the ubiquitous computing community [31, 39, 29] , much of it addressed from a “lifelogging” perspective [2, 30] .”
A Survey on Ambient-Assisted Living Tools for Older Adults (2013, background): “the sequential nature of data, including Markov chains [72], Dynamic Bayesian network [73]–[75], hidden Markov model (HMM) [71], and conditional random fields (CRFs) [76], [77].”
Intelligent Assistive Technology Applications to Dementia Care: Current Capabilities, Limitations, and Future Challenges (2009, methodology): “48 Objects in a research home were instrumented with 108 RF identiﬁcation tags, and the RF signals transmitted by these tags were recorded and analyzed by a prototype glove worn by the study participants.”
Assessing the Quality of Activities in a Smart Environment (2009, background): “Other approaches have been considered for activity recognition; however, these often depend on the participants wearing customized devices [6].”
Transfer Learning for Activity Recognition: A Survey (2013, background): “In response, researchers have explored the usage of RFID tags and shimmer sensors for tagging these objects and using the data for activity recognition [45,52].”