Analysis of Public Datasets for Wearable Fall Detection Systems

Casilari, E.; Santoyo-Ramón, José Antonio; Cano-García, José Manuel

doi:10.3390/s17071513

Cited by 118 publications

(80 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Sitting down and Standing up from sitting activities have been performed with a chair without armrests; the Lying down from standing and Standing up from laying have been performed on a sofa. The duration of the actives are on average similar to those reported in [52] that reviews a set of public datasets for wearable fall detection systems.…”

Section: Protocolssupporting

confidence: 64%

UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones

2017

View full text Add to dashboard Cite

Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, there are only a few publicly available data sets, which often contain samples from subjects with too similar characteristics, and very often lack specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new dataset of acceleration samples acquired with an Android smartphone designed for human activity recognition and fall detection. The dataset includes 11,771 samples of both human activities and falls performed by 30 subjects of ages ranging from 18 to 60 years. Samples are divided in 17 fine grained classes grouped in two coarse grained classes: one containing samples of 9 types of activities of daily living (ADL) and the other containing samples of 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL performed, the age, the gender, and so on. Finally, the dataset has been benchmarked with four different classifiers and with two different feature vectors. We evaluated four different classification tasks: fall vs. no fall, 9 activities, 8 falls, 17 activities and falls. For each classification task, we performed a 5-fold cross-validation (i.e., including samples from all the subjects in both the training and the test dataset) and a leave-one-subject-out cross-validation (i.e., the test data include the samples of a subject only, and the training data, the samples of all the other subjects). Regarding the classification tasks, the major findings can be summarized as follows: (i) it is quite easy to distinguish between falls and ADLs, regardless of the classifier and the feature vector selected. Indeed, these classes of activities present quite different acceleration shapes that simplify the recognition task; (ii) on average, it is more difficult to distinguish between types of falls than between types of activities, regardless of the classifier and the feature vector selected. This is due to the similarity between the acceleration shapes of different kinds of falls. On the contrary, ADLs acceleration shapes present differences except for a small group. Finally, the evaluation shows that the presence of samples of the same subject both in the training and in the test datasets, increases the performance of the classifiers regardless of the feature vector used. This happens because each human subject differs from other subjects in performing activities even if she shares with them the same physical characteristics.

show abstract

Section: Protocolssupporting

confidence: 64%

UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones

2017

View full text Add to dashboard Cite

show abstract

“…There is no standard framework for defining ADLs and fall activities, which is a critical limitation of the research done in this domain. This is also recognized in the analysis done by Casilari-Perez et al [14]. Our contributions on detecting irregular patterns in streaming data can serve as a benchmark for future researchers.…”

Section: Human Activitiessupporting

confidence: 56%

Detecting Irregular Patterns in IoT Streaming Data for Fall Detection

Mahfuz

Isah

Zulkernine

et al. 2018

2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)

View full text Add to dashboard Cite

Detecting patterns in real time streaming data has been an interesting and challenging data analytics problem. With the proliferation of a variety of sensor devices, real-time analytics of data from the Internet of Things (IoT) to learn regular and irregular patterns has become an important machine learning problem to enable predictive analytics for automated notification and decision support. In this work, we address the problem of learning an irregular human activity pattern, fall, from streaming IoT data from wearable sensors. We present a deep neural network model for detecting fall based on accelerometer data giving 98.75 percent accuracy using an online physical activity monitoring dataset called "MobiAct", which was published by Vavoulas et al. The initial model was developed using IBM Watson studio and then later transferred and deployed on IBM Cloud with the streaming analytics service supported by IBM Streams for monitoring real-time IoT data. We also present the systems architecture of the real-time fall detection framework that we intend to use with Mbientlab's wearable health monitoring sensors for real time patient monitoring at retirement homes or rehabilitation clinics.

show abstract

“…Using shimmer2 wearable sensor device primary mHealth data was generated by Banos, et.al [1]. This work mHealth data is used as secondary data for human activity recognition [7][8]. After we have selected the mHealth data sets for Activity Recognition (AR) we can setup new Human Activity Recognition (HAR) system which can divide 70% of train data and 30% of test data for extracting features.…”

Section: Methodsmentioning

confidence: 99%

Data Analysis and Classification of mHealth Shimmer2 Sensor Data sets for Human Physical Activities Recognition

2019

IJRTE

View full text Add to dashboard Cite

 Abstract: Human physical activity recognition is one of the important attributes for well being of human health and activity recogni-tion field. A physical signal with respect to time based directed toward recognizes human activity events is projected, in the view of this work usage wearable accelerometer sens-ing devices were implanted taking place the human body lo-cation on the upper body Chest Sensor (CS), Left Ankle Sen-sor (LAS) and Right Lower Arms Sensor (RLAS). Accelerome-ter feature extracted based acceleration signals with respect to time, physical appearance of the accelerometer x, y, and z dimension values reported/recorded using shimmer2 weara-ble sensor device is recommended at the categorization of the 10 different users was performed 12 different types human activities, including vigorous and moderate activities. User ages between 24 to 29 years and human body weight (HBW) are 53 to 83 Kg=m2. Results were on view a large validity per-formance precision and recall were getting 95 for each human activities. The whole classifiers accuracy results for all combi-nation of the feature set of all sensors is 98%. The considered work could be used to observe the human body motion of different body location of users and to perform data analysis and classification.

show abstract

Analysis of Public Datasets for Wearable Fall Detection Systems

Cited by 118 publications

References 42 publications

UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones

UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones

Detecting Irregular Patterns in IoT Streaming Data for Fall Detection

Data Analysis and Classification of mHealth Shimmer2 Sensor Data sets for Human Physical Activities Recognition

Contact Info

Product

Resources

About