skip to main content
10.1145/3123024.3123095acmconferencesArticle/Chapter ViewAbstractPublication PagesubicompConference Proceedingsconference-collections
research-article

Recognition of multiple overlapping activities using compositional CNN-LSTM model

Published: 11 September 2017 Publication History

Abstract

This paper introduces a new task, a recognition of multiple overlapping activities in the context of activity recognition. We propose a compositional CNN+LSTM algorithm. The experimental results show on the artificial dataset that it improved the accuracy from 27% to 43%.

References

[1]
Sozo Inoue, Naonori Ueda, Yasunobu Nohara, and Naoki Nakashima, "Mobile Activity Recognition for a Whole Day: Recognizing Real Nursing Activities with Big Dataset", UbiComp, pp.1269--1280, 2015.
[2]
James Robert Lloyd, David Duvenaud, Roger Grosse, Joshua B. Tenenbaum, Zoubin Ghahramani, "Automatic Construction and Natural-Language Description of Nonparametric Regression Models", AAAI, pp.1242--1250, 2014.
[3]
Francisco Javier Ordonez, Daniel Roggen. "Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors 16:115, 2016.
[4]
Daniel Roggen, Alberto Calatroni, Mirco Rossi, Thomas Holleczek, Gerhard Troster, Paul Lukowicz, Gerald Pirkl, David Bannach, Alois Ferscha, Jakob Doppler, Clemens Holzmann, Marc Kurz, Gerald Holl, Ricardo Chavarriaga, Hesam Sagha, Hamidreza Bayati, and Jose del R. Millan. "Collecting complex activity data sets in highly rich networked sensor environments", INSS10, pp.233--240, 2010
[5]
La The Vinh, Sungyoung Lee, Hung Xuan Le, Hung Quoc Ngo, Hyoung II Kim, Manhyung Han, and Young-Koo Lee, "Semi-Markov conditional random fields for accelerometer-based activity recognition", Springer, pp.226--241, 2011.
[6]
Shuochao Yao, Shaohan Hu, Yiran Zhao, Aston Zhang, Tarek Abdelzaher. "DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing". arXiv:1611.01942v1, 2016.

Cited By

View all

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
UbiComp '17: Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers
September 2017
1089 pages
ISBN:9781450351904
DOI:10.1145/3123024
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 September 2017

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. activity recognition
  2. deep learning

Qualifiers

  • Research-article

Conference

UbiComp '17

Acceptance Rates

Overall Acceptance Rate 764 of 2,912 submissions, 26%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)13
  • Downloads (Last 6 weeks)0
Reflects downloads up to 15 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)Exploring Score-Level and Decision-Level Fusion of Inertial and Video Data for Intake Gesture DetectionIEEE Access10.1109/ACCESS.2021.311925313(643-655)Online publication date: 2025
  • (2023)Using ARIMA to Predict the Growth in the Subscriber Data UsageEng10.3390/eng40100064:1(92-120)Online publication date: 1-Jan-2023
  • (2022)Multitemporal Sampling Module for Real-Time Human Activity RecognitionIEEE Access10.1109/ACCESS.2022.317660610(54507-54515)Online publication date: 2022
  • (2022)Predicting Subscriber Usage: Analyzing Multidimensional Time-Series Using Convolutional Neural NetworksCyber Security, Cryptology, and Machine Learning10.1007/978-3-031-07689-3_20(259-269)Online publication date: 23-Jun-2022
  • (2021)Activity Knowledge Graph Recognition by Eye Gaze: Identification of Distant Object in Eye Sight for Watch ActivityAdjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers10.1145/3460418.3479351(334-339)Online publication date: 21-Sep-2021
  • (2021)Deep Learning for Sensor-based Human Activity RecognitionACM Computing Surveys10.1145/344774454:4(1-40)Online publication date: 24-May-2021
  • (2021)Human activity recognition with deep learning: overview, challenges and possibilitiesCCF Transactions on Pervasive Computing and Interaction10.1007/s42486-021-00063-5Online publication date: 9-Apr-2021
  • (2020)MobDL: A Framework for Profiling Deep Learning Models: A Case Study using Mobile Digital Health ApplicationsMobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services10.1145/3448891.3448896(405-414)Online publication date: 7-Dec-2020
  • (2020)Improving Cross-Subject Activity Recognition via Adversarial LearningIEEE Access10.1109/ACCESS.2020.29938188(90542-90554)Online publication date: 2020
  • (2019)On-Device Deep Learning Inference for Efficient Activity Data CollectionSensors10.3390/s1915343419:15(3434)Online publication date: 5-Aug-2019
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media