Sensor-Based Activity Recognition

By Liming Luke Chen, Jesse Hoey, C. Nugent, Diane Joyce Cook, Zhiwen Yu. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2012

1,044 citations recorded by the source corpus.

Research on sensor-based activity recognition has, recently, made significant progress and is attracting growing attention in a number of disciplines and application domains. However, there is a lack of high-level overview on this topic that can inform related communities of the research state of the art. In this paper, we present a comprehensive survey to examine the development and current status of various aspects of sensor-based activity recognition. We first discuss the general rationale and distinctions of vision-based and sensor-based activity recognition. Then, we review the major approaches and methods associated with sensor-based activity monitoring, modeling, and recognition from which strengths and weaknesses of those approaches are highlighted. We make a primary distinction in this paper between data-driven and knowledge-driven approaches, and use this distinction to structure our survey. We also discuss some promising directions for future research.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9e605d72ab39f7a37a13e912556ee034c0d06133

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A survey of depth and inertial sensor fusion for human action recognition (2015, background): “…there exist several survey papers for human action recognition using depth sensors alone (e.g., [2, 19, 31, 76]) or inertial sensors alone (e.g., [5, 11, 30, 40]), there exists no survey article on the simultaneous utilization of these two differing modality sensors for human action recognition.”
Human Activity Recognition Using Recurrent Neural Networks (2017, background): “Among them, activity recognition in Smart Homes with the use of simple and ubiquitous sensors, has gained a lot of attention in the ﬁeld of ambient intelligence and assisted living technologies for enhancing the quality of life of the residents within the home environment [2].”
Smart Cities: A Survey on Data Management, Security, and Enabling Technologies (2017, methodology): “care applications, sensor networks need to be combined with technologies such as activity recognition [58], [59], behavioral pattern discovery [60], [61], anomaly detection [62] and”
A Survey of Online Activity Recognition Using Mobile Phones (2015, background): “Human activity recognition has enabled novel applications in different areas, such as, healthcare, security and entertainment [1,2].”
Window Size Impact in Human Activity Recognition (2014, background): “Here, only the acceleration data is considered for the study, since this proves to be the most prevalent sensor modality in previous activity recognition contributions [71,72].”
LSTM-CNN Architecture for Human Activity Recognition (2020, background): “Moreover, these sensors have the characteristics of low cost, low power consumption, high capacity, miniaturization, and less dependence on surroundings [15].”
A Survey on Ambient Intelligence in Health Care (2013, neutral): “activity recognition [35], [36] that vary depending on the underlying sensor technologies that are used to monitor”
Combining emerging patterns with random forest for complex activity recognition in smart homes (2018, background): “This approach is also known as dense sensing [4, 5, 22, 23].”
Ensembles of Deep LSTM Learners for Activity Recognition using Wearables (2017, background): “We argue that HAR can now safely be considered common knowledge and thus refer to seminal papers and tutorials such as [Bulling et al. 2014; Chen et al. 2012; Avci et al. 2010].”
Transition-Aware Human Activity Recognition Using Smartphones (2016, background): “Ambient and wearable sensors have been actively exploited for HAR [1].”