Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering
Ambient-assisted living (AAL) is promising to become a supplement of the current care models, providing enhanced living experience to people within context-aware homes and smart environments. Activity recognition based on sensory data in AAL systems is an important task because 1) it can be used for...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2017-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/7883880/ |
| _version_ | 1818619147728191488 |
|---|---|
| author | Eftim Zdravevski Petre Lameski Vladimir Trajkovik Andrea Kulakov Ivan Chorbev Rossitza Goleva Nuno Pombo Nuno Garcia |
| author_facet | Eftim Zdravevski Petre Lameski Vladimir Trajkovik Andrea Kulakov Ivan Chorbev Rossitza Goleva Nuno Pombo Nuno Garcia |
| author_sort | Eftim Zdravevski |
| collection | DOAJ |
| description | Ambient-assisted living (AAL) is promising to become a supplement of the current care models, providing enhanced living experience to people within context-aware homes and smart environments. Activity recognition based on sensory data in AAL systems is an important task because 1) it can be used for estimation of levels of physical activity, 2) it can lead to detecting changes of daily patterns that may indicate an emerging medical condition, or 3) it can be used for detection of accidents and emergencies. To be accepted, AAL systems must be affordable while providing reliable performance. These two factors hugely depend on optimizing the number of utilized sensors and extracting robust features from them. This paper proposes a generic feature engineering method for selecting robust features from a variety of sensors, which can be used for generating reliable classification models. From the originally recorded time series and some newly generated time series [i.e., magnitudes, first derivatives, delta series, and fast Fourier transformation (FFT)-based series], a variety of time and frequency domain features are extracted. Then, using two-phase feature selection, the number of generated features is greatly reduced. Finally, different classification models are trained and evaluated on an independent test set. The proposed method was evaluated on five publicly available data sets, and on all of them, it yielded better accuracy than when using hand-tailored features. The benefits of the proposed systematic feature engineering method are quickly discovering good feature sets for any given task than manually finding ones suitable for a particular task, selecting a small feature set that outperforms manually determined features in both execution time and accuracy, and identification of relevant sensor types and body locations automatically. Ultimately, the proposed method could reduce the cost of AAL systems by facilitating execution of algorithms on devices with limited resources and by using as few sensors as possible. |
| first_indexed | 2024-12-16T17:32:52Z |
| format | Article |
| id | doaj.art-164f91ce56184d90aa3af1c437550db0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T17:32:52Z |
| publishDate | 2017-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-164f91ce56184d90aa3af1c437550db02022-12-21T22:22:52ZengIEEEIEEE Access2169-35362017-01-0155262528010.1109/ACCESS.2017.26849137883880Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature EngineeringEftim Zdravevski0https://orcid.org/0000-0001-7664-0168Petre Lameski1https://orcid.org/0000-0002-5336-1796Vladimir Trajkovik2Andrea Kulakov3Ivan Chorbev4Rossitza Goleva5Nuno Pombo6Nuno Garcia7Faculty of Computer Science and Engineering, Saints Cyril and Methodius University, Skopje, MacedoniaFaculty of Computer Science and Engineering, Saints Cyril and Methodius University, Skopje, MacedoniaFaculty of Computer Science and Engineering, Saints Cyril and Methodius University, Skopje, MacedoniaFaculty of Computer Science and Engineering, Saints Cyril and Methodius University, Skopje, MacedoniaFaculty of Computer Science and Engineering, Saints Cyril and Methodius University, Skopje, MacedoniaFaculty of Telecommunications, Technical University of Sofia, Sofia, BulgariaDepartment of Informatics, Instituto de Telecomunicações and ALLab Assisted Living Computing and Telecommunications Laboratory, Universidade da Beira Interior, Covilhã, PortugalDepartment of Informatics, Instituto de Telecomunicações and ALLab Assisted Living Computing and Telecommunications Laboratory, Universidade da Beira Interior, Covilhã, PortugalAmbient-assisted living (AAL) is promising to become a supplement of the current care models, providing enhanced living experience to people within context-aware homes and smart environments. Activity recognition based on sensory data in AAL systems is an important task because 1) it can be used for estimation of levels of physical activity, 2) it can lead to detecting changes of daily patterns that may indicate an emerging medical condition, or 3) it can be used for detection of accidents and emergencies. To be accepted, AAL systems must be affordable while providing reliable performance. These two factors hugely depend on optimizing the number of utilized sensors and extracting robust features from them. This paper proposes a generic feature engineering method for selecting robust features from a variety of sensors, which can be used for generating reliable classification models. From the originally recorded time series and some newly generated time series [i.e., magnitudes, first derivatives, delta series, and fast Fourier transformation (FFT)-based series], a variety of time and frequency domain features are extracted. Then, using two-phase feature selection, the number of generated features is greatly reduced. Finally, different classification models are trained and evaluated on an independent test set. The proposed method was evaluated on five publicly available data sets, and on all of them, it yielded better accuracy than when using hand-tailored features. The benefits of the proposed systematic feature engineering method are quickly discovering good feature sets for any given task than manually finding ones suitable for a particular task, selecting a small feature set that outperforms manually determined features in both execution time and accuracy, and identification of relevant sensor types and body locations automatically. Ultimately, the proposed method could reduce the cost of AAL systems by facilitating execution of algorithms on devices with limited resources and by using as few sensors as possible.https://ieeexplore.ieee.org/document/7883880/Feature extractiontime series analysisambient intelligencewearable sensorssensor fusionpattern recognition |
| spellingShingle | Eftim Zdravevski Petre Lameski Vladimir Trajkovik Andrea Kulakov Ivan Chorbev Rossitza Goleva Nuno Pombo Nuno Garcia Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering IEEE Access Feature extraction time series analysis ambient intelligence wearable sensors sensor fusion pattern recognition |
| title | Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering |
| title_full | Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering |
| title_fullStr | Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering |
| title_full_unstemmed | Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering |
| title_short | Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering |
| title_sort | improving activity recognition accuracy in ambient assisted living systems by automated feature engineering |
| topic | Feature extraction time series analysis ambient intelligence wearable sensors sensor fusion pattern recognition |
| url | https://ieeexplore.ieee.org/document/7883880/ |
| work_keys_str_mv | AT eftimzdravevski improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT petrelameski improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT vladimirtrajkovik improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT andreakulakov improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT ivanchorbev improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT rossitzagoleva improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT nunopombo improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering AT nunogarcia improvingactivityrecognitionaccuracyinambientassistedlivingsystemsbyautomatedfeatureengineering |