{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unimib-shar-a-new-dataset-for-human-activity","title":"UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones","arxiv_id":"1611.07688","date":"2016-11-23","proceeding":null,"authors":["Daniela Micucci","Marco Mobilio","Paolo Napoletano"],"abstract":"Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are\nbeing increasingly used to monitor human activities. Data acquired by the\nhosted sensors are usually processed by machine-learning-based algorithms to\nclassify human activities. The success of those algorithms mostly depends on\nthe availability of training (labeled) data that, if made publicly available,\nwould allow researchers to make objective comparisons between techniques.\nNowadays, publicly available data sets are few, often contain samples from\nsubjects with too similar characteristics, and very often lack of specific\ninformation so that is not possible to select subsets of samples according to\nspecific criteria. In this article, we present a new dataset of acceleration\nsamples acquired with an Android smartphone designed for human activity\nrecognition and fall detection. The dataset includes 11,771 samples of both\nhuman activities and falls performed by 30 subjects of ages ranging from 18 to\n60 years. Samples are divided in 17 fine grained classes grouped in two coarse\ngrained classes: one containing samples of 9 types of activities of daily\nliving (ADL) and the other containing samples of 8 types of falls. The dataset\nhas been stored to include all the information useful to select samples\naccording to different criteria, such as the type of ADL, the age, the gender,\nand so on. Finally, the dataset has been benchmarked with four different\nclassifiers and with two different feature vectors. We evaluated four different\nclassification tasks: fall vs no fall, 9 activities, 8 falls, 17 activities and\nfalls. For each classification task we performed a subject-dependent and\nindependent evaluation. The major findings of the evaluation are the following:\ni) it is more difficult to distinguish between types of falls than types of\nactivities; ii) subject-dependent evaluation outperforms the\nsubject-independent one","url_abs":"http://arxiv.org/abs/1611.07688v5","url_pdf":"http://arxiv.org/pdf/1611.07688v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"}],"methods":[],"datasets_introduced":[{"slug":"unimib-shar","name":"UniMiB SHAR","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.07688","atlas_url":"https://app.syntology.ai/?focus=1611.07688","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}