SisFall: A Fall and Movement Dataset

Sucerquia, Angela; López, José David; Vargas-Bonilla, Jesús Francisco

doi:10.20944/preprints201610.0096.v1

Cited by 54 publications

(122 citation statements)

References 10 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…The third data set used for experimental result is the Sis-Fall [8,26], selecting data related to the waist sensor point. It was generated with 38 participants performing repetitions of 19 ADL and 15 fall types.…”

Section: Resultsmentioning

confidence: 99%

Event Detection in Complex Environments: An Effective and Efficient Machine-Learning-Based Framework (S)

Cuzzocrea¹,

Mumolo²

2019

International Conferences on Distributed Multimedia Systems

View full text Add to dashboard Cite

In this paper we describe a falls detection and classification algorithm for discriminating falls from daily life activities using a MEMS accelerometer. The algorithm is based on a shallow Neural Network with three hidden layers, used as fall/non fally classifier, trained with daily life activities features and fall features. The novelty of this algorithm is that synthetic falls are generated as multivariate random Gaussian features, so only real daily life features must be collected during some day of normal living. Moreover, the features related to synthetic fall events are generated as complement of normal features. First of all, the features acquired during daily life are clustered by Principal Component Analysis and no Fall activities shall be recorded. The complement set of the normal features is found and used as a mask for Monte Carlo generation of synthetic fall. The two feature sets, namely the features recorded from daily life activities and those artificially generated are used to train the Neural Network. This approach is suitable for a practical utilization of a Neural Network based fall detection characterized by high Recall-Precision rate.

show abstract

Section: Resultsmentioning

confidence: 99%

Event Detection in Complex Environments: An Effective and Efficient Machine-Learning-Based Framework (S)

Cuzzocrea¹,

Mumolo²

2019

International Conferences on Distributed Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…All signals from the three Physilog® sensors will be synchronized by wireless transmission and recorded on a micro SD card inside the IMU before being transferred to a computer. The waist-worn sensor data will be filtered using a 4-th order infinite impulse response (IIR) low-pass Butterworth filter with a cut-off frequency of 5 Hz [42].…”

Section: Process A: Biomechanical Analysismentioning

confidence: 99%

Dual-task training with progression from variable- to fixed-priority instructions versus dual-task training with variable-priority on gait speed in community-dwelling older adults: A protocol for a randomized controlled trial

et al. 2020

View full text Add to dashboard Cite

Background: Functional independence and safe mobility, especially in older people, mostly rely on the ability to perform dual tasks, particularly during activities with variable-and fixed-priority attention. The aim of this study is to compare the dual-task training with progression from variable-to fixed-priority instructions versus dual-task training with variable-priority on gait speed in community-dwelling older adults. Methods: This is an assessor-and participant-blinded, two-arm, randomized controlled trial with 60 communitydwelling male and female older adults between the ages of 60 and 80 years old. Participants will be randomly allocated into either the intervention group or the control group using a computer-generated permuted block randomization schedule. The intervention group will undertake a progressive dual-task training in which the participants will be progressively submitted to dual-task walking and postural balance exercises with variable-to fixed-priority instructions. The control group will be submitted to dual-task training with variable-priority attention exercises. Both groups will receive 48 sessions lasting for 60 min each over 24 weeks. The primary outcome will be the gait speed under single-and dual-task conditions. Secondary outcomes will include spatiotemporal gait parameters, functional balance, executive function, falls, quality of life, and depression symptoms. All the analyses will be based on the intention-to-treat principle.

show abstract

“…Musci et al used 14 characteristics to extract features from the dataset [16]. Among the extracted features, best results were observed for the characteristics coded C2, C3, C8, C9 and C13 as given below.…”

Section: B Data Preprocessing A) Mobiactmentioning

confidence: 99%

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

SisFall: A Fall and Movement Dataset

Cited by 54 publications

References 10 publications

Event Detection in Complex Environments: An Effective and Efficient Machine-Learning-Based Framework (S)

Event Detection in Complex Environments: An Effective and Efficient Machine-Learning-Based Framework (S)

Dual-task training with progression from variable- to fixed-priority instructions versus dual-task training with variable-priority on gait speed in community-dwelling older adults: A protocol for a randomized controlled trial

Detecting Irregular Patterns in IoT Streaming Data for Fall Detection

Contact Info

Product

Resources

About