http://www.ronpub.com/publications/search.php?journal=ALL&author=Anne+H.+Ngu&exactauthor=on&title=&abstract=&volume=&issue=&year1=&year2=&searchtype=advanced This feed contains the result of an user-defined search in RonPub publications en-us https://www.ronpub.com/ojiot/OJIOT_2018v4i1n07_Ngu.html http://nbn-resolving.de/urn:nbn:de:101:1-2018080519304951282148 This paper proposes using only the streaming accelerometer data from a commodity-based smartwatch (IoT) device to detect falls. The smartwatch is paired with a smartphone as a means for performing the computation necessary for the prediction of falls in realtime without incurring latency in communicating with a cloud server while also preserving data privacy. The majority of current fall detection applications require specially designed hardware and software which make them expensive and inaccessible to the general public. Moreover, a fall detection application that uses a wrist worn smartwatch for data collection has the added benefit that it can be perceived as a piece of jewelry and thus non-intrusive. We experimented with both Support Vector Machine and Naive Bayes machine learning algorithms for the creation of the fall model. We demonstrated that by adjusting the sampling frequency of the streaming data, computing acceleration features over a sliding window, and using a Naive Bayes machine learning model, we can obtain the true positive rate of fall detection in real-world setting with 93.33% accuracy. Our result demonstrated that using a commodity-based smartwatch sensor can yield fall detection results that are competitive with those of custom made expensive sensors. https://www.ronpub.com/ojiot/OJIOT_2019v5i1n11_Mauldin.html http://nbn-resolving.de/urn:nbn:de:101:1-2019092919352344146661 This paper presents an experimental study of Ensemble Deep Learning (DL) techniques for the analysis of time series data on IoT devices. We have shown in our earlier work that DL demonstrates superior performance compared to traditional machine learning techniques on fall detection applications due to the fact that important features in time series data can be learned and need not be determined manually by the domain expert. However, DL networks generally require large datasets for training. In the health care domain, such as the real-time smartwatch-based fall detection, there are no publicly available large annotated datasets that can be used for training, due to the nature of the problem (i.e. a fall is not a common event). Moreover, fall data is also inherently noisy since motions generated by the wrist-worn smartwatch can be mistaken for a fall. This paper explores combing DL (Recurrent Neural Network) with ensemble techniques (Stacking and AdaBoosting) using a fall detection application as a case study. We conducted a series of experiments using two different datasets of simulated falls for training various ensemble models. Our results show that an ensemble of deep learning models combined by the stacking ensemble technique, outperforms a single deep learning model trained on the same data samples, and thus, may be better suited for small-size datasets.