Loading...
3 results
Search Results
Now showing 1 - 3 of 3
- Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature EngineeringPublication . Zdravevski, Eftim; Lameski, Petre; Trajkovik, Vladimir; Kulakov, Andrea; Chorbev, Ivan; Goleva, Rossitza; Pombo, Nuno; Garcia, Nuno M.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 classi cation models. From the originally recorded time series and some newly generated time series [i.e., magnitudes, rst 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 classi cation models are trained and evaluated on an independent test set. The proposed method was evaluated on ve publicly available data sets, and on all of them, it yielded better accuracy than when using hand-tailored features. The bene ts of the proposed systematic feature engineering method are quickly discovering good feature sets for any given task than manually nding ones suitable for a particular task, selecting a small feature set that outperforms manually determined features in both execution time and accuracy, and identi cation 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.
- Android Library for Recognition of Activities of Daily Living: Implementation Considerations, Challenges, and SolutionsPublication . Pires, Ivan; Teixeira, Maria Cristina Canavarro; Pombo, Nuno; Garcia, Nuno M.; Flórez-Revuelta, Francisco; Spinsante, Susanna; Goleva, Rossitza; Zdravevski, EftimBackground: Off-the-shelf-mobile devices have several sensors available onboard that may be used for the recognition of Activities of Daily Living (ADL) and the environments where they are performed. This research is focused on the development of Ambient Assisted Living (AAL) systems, using mobile devices for the acquisition of the different types of data related to the physical and physiological conditions of the subjects and the environments. Mobile devices with the Android Operating Systems are the least expensive and exhibit the biggest market while providing a variety of models and onboard sensors. Objective: This paper describes the implementation considerations, challenges and solutions about a framework for the recognition of ADL and the environments, provided as an Android library. The framework is a function of the number of sensors available in different mobile devices and utilizes a variety of activity recognition algorithms to provide a rapid feedback to the user. Methods: The Android library includes data fusion, data processing, features engineering and classification methods. The sensors that may be used are the accelerometer, the gyroscope, the magnetometer, the Global Positioning System (GPS) receiver and the microphone. The data processing includes the application of data cleaning methods and the extraction of features, which are used with Deep Neural Networks (DNN) for the classification of ADL and environment. Throughout this work, the limitations of the mobile devices were explored and their effects have been minimized. Results: The implementation of the Android library reported an overall accuracy between 58.02% and 89.15%, depending on the number of sensors used and the number of ADL and environments recognized. Compared with the results available in the literature, the performance of the library reported a mean improvement of 2.93%, and they do not differ at the maximum found in prior work, that based on the Student’s t-test. Conclusion: This study proves that ADL like walking, going upstairs and downstairs, running, watching TV, driving, sleeping and standing activities, and the bedroom, cooking/kitchen, gym, classroom, hall, living room, bar, library and street environments may be recognized with the sensors available in off-the-shelf mobile devices. Finally, these results may act as a preliminary research for the development of a personal digital life coach with a multi-sensor mobile device commonly used daily.
- Recognition of Activities of Daily Living and Environments Using Acoustic Sensors Embedded on Mobile DevicesPublication . Pires, Ivan; Marques, Gonçalo; Garcia, Nuno M.; Pombo, Nuno; Flórez-Revuelta, Francisco; Spinsante, Susanna; Teixeira, Maria Canavarro; Zdravevski, EftimThe identification of Activities of Daily Living (ADL) is intrinsic with the user’s environment recognition. This detection can be executed through standard sensors present in every-day mobile devices. On the one hand, the main proposal is to recognize users’ environment and standing activities. On the other hand, these features are included in a framework for the ADL and environment identification. Therefore, this paper is divided into two parts—firstly, acoustic sensors are used for the collection of data towards the recognition of the environment and, secondly, the information of the environment recognized is fused with the information gathered by motion and magnetic sensors. The environment and ADL recognition are performed by pattern recognition techniques that aim for the development of a system, including data collection, processing, fusion and classification procedures. These classification techniques include distinctive types of Artificial Neural Networks (ANN), analyzing various implementations of ANN and choosing the most suitable for further inclusion in the following different stages of the developed system. The results present 85.89% accuracy using Deep Neural Networks (DNN) with normalized data for the ADL recognition and 86.50% accuracy using Feedforward Neural Networks (FNN) with non-normalized data for environment recognition. Furthermore, the tests conducted present 100% accuracy for standing activities recognition using DNN with normalized data, which is the most suited for the intended purpose.