English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices arebeing increasingly used to monitor human activities. Data acquired by thehosted sensors are usually processed by machine-learning-based algorithms toclassify human activities. The success of those algorithms mostly depends onthe availability of training (labeled) data that, if made publicly available,would allow researchers to make objective comparisons between techniques.Nowadays, publicly available data sets are few, often contain samples fromsubjects with too similar characteristics, and very often lack of specificinformation so that is not possible to select subsets of samples according tospecific criteria. In this article, we present a new dataset of accelerationsamples acquired with an Android smartphone designed for human activityrecognition and fall detection. The dataset includes 11,771 samples of bothhuman activities and falls performed by 30 subjects of ages ranging from 18 to60 years. Samples are divided in 17 fine grained classes grouped in two coarsegrained classes: one containing samples of 9 types of activities of dailyliving (ADL) and the other containing samples of 8 types of falls. The datasethas been stored to include all the information useful to select samplesaccording to different criteria, such as the type of ADL, the age, the gender,and so on. Finally, the dataset has been benchmarked with four differentclassifiers and with two different feature vectors. We evaluated four differentclassification tasks: fall vs no fall, 9 activities, 8 falls, 17 activities andfalls. For each classification task we performed a subject-dependent andindependent evaluation. The major findings of the evaluation are the following:i) it is more difficult to distinguish between types of falls than types ofactivities; ii) subject-dependent evaluation outperforms thesubject-independent one

UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones