Open AccessProceedings Article10.1145/1931344.1931382

Child-activity recognition from multi-sensor data

- 24 Aug 2010

- pp 38

TL;DR: The obtained experimental results for the recognition of 7 activities based on a limited data set are promising and show the potential of the proposed method.

Abstract: The automatic recognition of child activity using multi-sensor data enables various applications such as child-development monitoring, energy-expenditure estimation, child-obesity prevention, child safety in and around the home, etc. We formulate the activity recognition task as a classification problem based on multiple sensors embedded in a wearable device. The approach we propose in this paper isto apply spectral analysis techniques of multiple sensor data for activity recognition. Quadratic Discriminant Analysis (QDA) classifieris then trained using manually annotated data and applied for activity recognition. The obtained experimental results for the recognition of 7 activities based on a limited data set are promising and show the potential of the proposed method.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions mentioned in the paper "Child-activity recognition from multi-sensor data" ?

The approach the authors propose in this paper is to apply spectral analysis techniques of multiple sensor data for activity recognition.. The obtained experimental results for the recognition of 7 activities based on a limited data set are promising and show the potential of the proposed method.

2. What have the authors stated for future works in "Child-activity recognition from multi-sensor data" ?

As future work, both the extension towards more activities, as well as the validation of the results on a larger data set are required to better quantify the benefits of the proposed approach compared to state-of-the-art methods.

Figure 3. The magnitude of the acceleration is plotted together with obtained classification results. The magnitude was scaled to be able to plot both classification as well as sensor data.

Figure 2. Normalized confusion matrix for 7 activities obtained with the proposed features.

Table 1. List of considered activities and corresponding labels.

Citations

Journal Article•10.1016/J.COMCOM.2016.02.011

Using barometric pressure data to recognize vertical displacement activities on smartphones

Salvatore Vanini, +3 more

- 01 Aug 2016

- Computer Communications

TL;DR: A novel, efficient methodology for the automatic recognition of major vertical displacements in human activities based exclusively on barometric pressure measured by sensors commonly available on smartphones and tablets is introduced.

...read moreread less

Journal Article•10.1016/J.PATREC.2011.06.025

Improving the classification accuracy of streaming data using SAX similarity features

Pekka Siirtola, +4 more

- 01 Oct 2011

- Pattern Recognition Letters

TL;DR: The results show that the recognition rates calculated using SAX similarity features together with traditional features are much better than those obtained employing traditional features only.

...read moreread less

•Journal Article•10.1016/J.PROCS.2014.05.507

Implementation of a Wearable Sensor Vest for the Safety and Well-being of Children

Mirjami Jutila, +3 more

- 01 Jan 2014

TL;DR: A prototype wearable vest for improving the safety and well-being of children in nurseries, daycare centres and primary schools built around the LilyPad Arduino and Adafruit Flora platforms with Xbee radio module, GPS, temperature and accelerometer sensors.

...read moreread less

•Journal Article•10.1155/2020/8617430

Feature Selection Using Genetic Algorithms for the Generation of a Recognition and Classification of Children Activities Model Using Environmental Sound

Antonio García-Domínguez, +7 more

- 13 Feb 2020

- Mobile Information Systems

TL;DR: The use of environmental sound data is proposed to generate a recognition and classification of children activities model through automatic learning techniques, optimized for application on mobile devices, and the best performance is presented by the five-feature model developed through RF.

...read moreread less

Proceedings Article•10.1109/ICPR48806.2021.9412822

A Detection-based Approach to Multiview Action Classification in Infants

Carolina Pacheco, +4 more

- 10 Jan 2021

TL;DR: In this paper, a multiview action classification system based on Faster R-CNN and LSTM networks was proposed for infant action classification in a pediatric rehabilitation environment in which not only infants but also robots and adults are present, with the smallest actor in the scene.

...read moreread less

...

Expand

References

•Book Chapter•10.1007/978-3-540-24646-6_1

Activity recognition from user-annotated acceleration data

Ling Bao, +1 more

- 21 Apr 2004

TL;DR: This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves, and suggests that multiple accelerometers aid in recognition.

...read moreread less

3.5K

•Proceedings Article

Activity recognition from accelerometer data

Nishkam Ravi, +3 more

- 09 Jul 2005

TL;DR: This paper reports on the efforts to recognize user activity from accelerometer data and performance of base-level and meta-level classifiers, and Plurality Voting is found to perform consistently well across different settings.

...read moreread less

1.6K

Proceedings Article•10.1109/BSN.2006.6

Activity recognition and monitoring using multiple sensors on different body positions

U. Maurer, +3 more

- 03 Apr 2006

TL;DR: The design of an activity recognition and monitoring system based on the eWatch, multi-sensor platform worn on different body positions, is presented and the tradeoff between recognition accuracy and computational complexity is analyzed.

...read moreread less

800

•Book

Sensor Networks

Ivan Stojmenovic

- 01 Nov 2005

TL;DR: To get the location information of the elderly person in the smart house, Ultra High Frequency (915 MHz) RFID readers will be used and when it founds the location area ofThe elderly person, by using an antenna with narrow beamwidth the robot will turn to the elderlyperson.

...read moreread less

400

Journal Article•10.1249/MSS.0B013E31818896F4

Energy cost in children assessed by multisensor activity monitors.

Daniel Arvidsson, +3 more

- 01 Mar 2009

- Medicine and Science in Sports and Exerc...

TL;DR: Overall, the IDEEA showed the highest ability to assess energy cost in this study, but SWA may be more feasible for use in children under free-living conditions.

...read moreread less

Child-activity recognition from multi-sensor data

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions mentioned in the paper "Child-activity recognition from multi-sensor data" ?

2. What have the authors stated for future works in "Child-activity recognition from multi-sensor data" ?

Figures

Citations

Using barometric pressure data to recognize vertical displacement activities on smartphones

Improving the classification accuracy of streaming data using SAX similarity features

Implementation of a Wearable Sensor Vest for the Safety and Well-being of Children

Feature Selection Using Genetic Algorithms for the Generation of a Recognition and Classification of Children Activities Model Using Environmental Sound

A Detection-based Approach to Multiview Action Classification in Infants

References

Activity recognition from user-annotated acceleration data

Activity recognition from accelerometer data

Activity recognition and monitoring using multiple sensors on different body positions

Sensor Networks

Energy cost in children assessed by multisensor activity monitors.

Related Papers (5)

Activity recognition from user-annotated acceleration data

Activity recognition from accelerometer data

Detection of posture and motion by accelerometry : a validation study in ambulatory monitoring

Sensor Positioning for Activity Recognition Using Wearable Accelerometers

Classification model for multi-sensor data fusion apply for Human Activity Recognition