Loading...
5 results
Search Results
Now showing 1 - 5 of 5
- Enhanced Living Environments, Algorithms, Architectures, Platforms, and SystemPublication . Garcia, Nuno M.; Ganchev, Ivan; Dobre, Ciprian; Mavromoustakis, Constandinos X.; Goleva, Rossitza
- 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.
- Keyed User Datagram Protocol: Concepts and Operation of an Almost Reliable Connectionless Transport ProtocolPublication . Garcia, Nuno M.; Gil, Fabio; Matos, Barbara; Yahaya, Coulibaly; Pombo, Nuno; Goleva, RossitzaDeparting from the well-known problem of the excessive overhead and latency of connection oriented protocols, this paper describes a new almost reliable connectionless protocol that uses user datagram protocol (UDP) segment format and is UDP compatible. The problem is presented and described, the motivation, the possible areas of interest and the concept and base operation modes for the protocol named keyed UDP are presented (here called KUDP). Also, discussed are some of the possible manners in which the KUDP can be used, addressing potential problems related with current networking technologies. As UDP is a connectionless protocol, and KUDP allows for some degree of detection of loss and re-ordering of segments received out-of-sequence, we also present a proposal for a stream reconstruction algorithm. This paper ends by mentioning some of the research issues that still need to be addressed.
- 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 Based on Environmental Analyses Using Audio Fingerprinting Techniques: A Systematic ReviewPublication . Pires, Ivan; Santos, Rui; Pombo, Nuno; Garcia, Nuno M.; Flórez-Revuelta, Francisco; Spinsante, Susanna; Goleva, Rossitza; Zdravevski, EftimAn increase in the accuracy of identification of Activities of Daily Living (ADL) is very important for different goals of Enhanced Living Environments and for Ambient Assisted Living (AAL) tasks. This increase may be achieved through identification of the surrounding environment. Although this is usually used to identify the location, ADL recognition can be improved with the identification of the sound in that particular environment. This paper reviews audio fingerprinting techniques that can be used with the acoustic data acquired from mobile devices. A comprehensive literature search was conducted in order to identify relevant English language works aimed at the identification of the environment of ADLs using data acquired with mobile devices, published between 2002 and 2017. In total, 40 studies were analyzed and selected from 115 citations. The results highlight several audio fingerprinting techniques, including Modified discrete cosine transform (MDCT), Mel-frequency cepstrum coefficients (MFCC), Principal Component Analysis (PCA), Fast Fourier Transform (FFT), Gaussian mixture models (GMM), likelihood estimation, logarithmic moduled complex lapped transform (LMCLT), support vector machine (SVM), constant Q transform (CQT), symmetric pairwise boosting (SPB), Philips robust hash (PRH), linear discriminant analysis (LDA) and discrete cosine transform (DCT).