SisFall: A Fall and Movement Dataset
<p>Device used for acquisition. The self-developed embedded device included two accelerometers and a gyroscope. It was fixed to the waist of the participants.</p> "> Figure 2
<p>Example of processing and classification. The features are computed after the filtering process of the raw data. (<b>a</b>) ADL D11 gives <math display="inline"> <semantics> <msub> <mi>C</mi> <mn>8</mn> </msub> </semantics> </math> values below threshold <math display="inline"> <semantics> <msub> <mi>T</mi> <mn>1</mn> </msub> </semantics> </math> (horizontal <b>red</b> line); (<b>b</b>) Feature <math display="inline"> <semantics> <msub> <mi>C</mi> <mn>8</mn> </msub> </semantics> </math> crosses the threshold when the fall in activity F05 is detected.</p> "> Figure 3
<p>Accuracy obtained in validation after a 10-fold cross-validation without (raw data) and with preprocessing (filtered). Features <math display="inline"> <semantics> <msub> <mi>C</mi> <mn>2</mn> </msub> </semantics> </math> and <math display="inline"> <semantics> <msub> <mi>C</mi> <mn>8</mn> </msub> </semantics> </math> achieved 95.0% and 96.1% of accuracy when the filter was applied, respectively. However, not all features improved their performance after filtering.</p> "> Figure 4
<p>Maximum value per activity obtained with <math display="inline"> <semantics> <msub> <mi>C</mi> <mn>8</mn> </msub> </semantics> </math>. Most <math display="inline"> <semantics> <msub> <mi>T</mi> <mn>1</mn> </msub> </semantics> </math> threshold crossings (horizontal <b>red</b> line) are contained in activities D04, D18 and F11.</p> ">
Abstract
:1. Introduction
2. Related Public Datasets
- MobiFall [15]: twenty-four volunteers (22 to 42 years old) performed nine types of ADLs and four of falls using a Samsung Galaxy smartphone, Samsung, Seoul, South Korea. Nine subjects performed falls and ADLs, while 15 performed only falls (three trials each).
- tFall [16]: ten participants between 20 and 42 years old. They recorded eight types of falls (503 total recordings with two smartphones), and one week of continuous ADL recordings with all participants carrying smartphones in the pockets and a handbag. The ADL trials were not identified by activity.
- DLR [17]: sixteen subjects (23 to 50 years old). They recorded six types of ADLs, and the authors did not specify the conditions of the falls (they belong to a single group). The files are too short for some types of analysis.
- Project gravity [18]: three participants (ages 22, 26, and 32) performed 12 types of falls and seven types of ADLs with a smartphone in the pocket.
3. Materials and Methods
3.1. Selection of Activities
3.2. Participants
3.3. Experimental Set-Up
3.4. Fall Detection Algorithms
3.4.1. Preprocessing Stage
3.4.2. Feature Extraction
3.4.3. Classification
3.4.4. Cross-Validation
4. Results
4.1. Effect of Filtering as the Preprocessing Stage
4.2. Training with Young vs. Elderly People
4.3. Zero False Negatives
5. Discussion
6. Conclusions
Supplementary Materials
- SisFall movement and fall dataset. Text files with all recorded activities and a Readme with particular information of all subjects and recordings.
- Video recordings of all activities. Each activity included in the SisFall dataset was video recorded and included in this material.
- Tables and figures with results of all features. The same experiments shown along the paper with only five features were performed with the 14 selected for this work.
Acknowledgments
Author Contributions
Conflicts of Interest
References
- Masdeu, J.; Sudarsky, L.; Wolfson, L. Gait Disorders of Aging. Falls and Therapeutic Strategies; Lippincot-Raven: Philadelphia, PA, USA, 1997. [Google Scholar]
- Lord, S.; Sherrington, C.; Menz, H. Falls in Older People: Risk Factors and Strategies for Prevention, 1st ed.; Cambridge University Press: Cambridge, UK, 2001. [Google Scholar]
- Vellas, B.; Wayne, S.; Romero, L.; Baumgartner, R.; Garry, P. Fear of falling and restriction of mobility in elderly fallers. Age Ageing 1997, 26, 189–193. [Google Scholar] [CrossRef] [PubMed]
- Delbaere, K.; Crombez, G.; Vanderstraeten, G.; Willems, T.; Cambier, D. Fear-related avoidance of activities, falls and physical frailty. A prospective community-based cohort study. Age Ageing 2004, 33, 368–373. [Google Scholar] [CrossRef] [PubMed]
- Lord, S.; Ward, J.; Williams, P.; Anstey, K. An epidemiological study of falls in older community-dwelling women: The Randwick falls and fractures study. Aust. J. Public Health 1993, 17, 240–245. [Google Scholar] [CrossRef] [PubMed]
- Igual, R.; Medrano, C.; Plaza, I. Challenges, issues and trends in fall detection systems. BioMed. Eng. OnLine 2013, 12, 1–24. [Google Scholar] [CrossRef] [PubMed]
- Brownsell, S.; Bradley, D.; Bragg, R.; Catlin, P.; Carlier, J. Do community alarm users want telecare? J. Telemed. Telecare 2000, 6, 199–204. [Google Scholar] [CrossRef] [PubMed]
- Bagala, F.; Becker, C.; Cappello, A.; Chiari, L.; Aminian, K.; Hausdorff, J.M.; Zijlstra, W.; Klenk, J. Evaluation of Accelerometer-Based Fall Detection Algorithms on Real-World Falls. PLoS ONE 2012, 7, e37062. [Google Scholar] [CrossRef] [PubMed]
- Pannurat, N.; Thiemjarus, S.; Nantajeewarawat, E. Automatic fall monitoring: A review. Sensors 2014, 14, 12900–12936. [Google Scholar] [CrossRef] [PubMed]
- Shany, T.; Redmond, S.J.; Narayanan, M.R.; Lovell, N.H. Sensors-Based Wearable Systems for Monitoring of Human Movement and Falls. IEEE Sens. J. 2012, 12, 658–670. [Google Scholar] [CrossRef]
- Habib, M.A.; Mohktar, M.S.; Kamaruzzaman, S.B.; Lim, K.S.; Pin, T.M.; Ibrahim, F. Smartphone-Based Solutions for Fall Detection and Prevention: Challenges and Open Issues. Sensors 2014, 14, 7181–7208. [Google Scholar] [CrossRef] [PubMed]
- Casilari, E.; Luque, R.; Morón, M.J. Analysis of Android Device-Based Solutions for Fall Detection. Sensors 2015, 15, 17827–17894. [Google Scholar] [CrossRef] [PubMed]
- Yuan, J.; Tan, K.K.; Lee, T.H.; Koh, G.C.H. Power-Efficient Interrupt-Driven Algorithms for Fall Detection and Classification of Activities of Daily Living. IEEE Sens. J. 2015, 15, 1377–1387. [Google Scholar] [CrossRef]
- O’Neill, T.; Varlow, J.; Silman, A.; Reeve, J.; Reid, D.; Todd, C.; Woolf, A. Age and sex influences on fall characteristics. Ann. Rheum. Dis. 1994, 53, 773–775. [Google Scholar] [CrossRef] [PubMed]
- Vavoulas, G.; Pediaditis, M.; Chatzaki, C.; Spanakis, E.; Tsiknakis, M. The MobiFall Dataset: Fall Detection and Classification with a Smartphone. Int. J. Monit. Surveill. Technol. Res. 2014, 2, 44–56. [Google Scholar] [CrossRef]
- Medrano, C.; Igual, R.; Plaza, I.; Castro, M. Detecting Falls as Novelties in Acceleration Patterns Acquired with Smartphones. PLoS ONE 2014, 9, e94811. [Google Scholar] [CrossRef] [PubMed]
- Frank, K.; Vera, M.J.; Robertson, P.; Pfeifer, T. Bayesian Recognition of Motion Related Activities with Inertial Sensors. In Proceedings of the 12th ACM International Conference on Ubiquitous Computing (UbiComp), Copenhagen, Denmark, 26–29 September 2010; pp. 445–446.
- Vilarinho, T.; Farshchian, B.; Bajer, D.G.; Dahl, O.H.; Egge, I.; Hegdal, S.S.; Lones, A.; Slettevold, J.N.; Weggersen, S.M. A combined smartphone and smartwatch fall detection system. In Proceedings of the IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, UK, 26–28 October 2015.
- Igual, R.; Medrano, C.; Plaza, I. A comparison of public datasets for acceleration-based fall detection. Med. Eng. Phys. 2015, 37, 870–878. [Google Scholar] [CrossRef] [PubMed]
- Reyna, R.; Palomera, E.; Gonzalez, R.; de Alba, S.G.; Clifford, M. Human Fall Detection Using 3-Axis Accelerometer; Technical Report; Freescale Semiconductor: Austin, TX, USA, 2005. [Google Scholar]
- Tuck, K. Motion and Freefall Detection Using the MMA8451, 2, 3Q; Technical Report AN4070; Freescale Semiconductor: Austin, TX, USA, 2011. [Google Scholar]
- SISTEMIC: SisFall Dataset. Available online: http://sistemic.udea.edu.co/investigacion/proyectos/english-falls/?lang=en (accessed on 18 January 2017).
- Xue, Y.; Jin, L. A Naturalistic 3D Acceleration-based Activity Dataset and Benchmark Evaluations. In Proceedings of the IEEE International Conference on Systems Man and Cybernetics (SMC), Istanbul, Turkey, 10–13 October 2010; pp. 4081–4085.
- Cleland, I.; Kikhia, B.; Nugent, C.; Boytsov, A.; Hallberg, J.; Synnes, K.; McClean, S.; Finlay, D. Optimal Placement of Accelerometers for the Detection of Everyday Activities. Sensors 2013, 13, 9183–9200. [Google Scholar] [CrossRef] [PubMed]
- López, J.D.; Ocampo, C.; Sucerquia, A.; Vargas-Bonilla, F. Analyzing multiple accelerometer configurations to detect falls and motion. In Proceedings of the Latin American Congress on Biomedical Engineering, Santander, Colombia, 26–28 October 2016.
- Noury, N.; Fleury, A.; Rumeau, P.; Bourke, A.; Laighin, G.; Rialle, V.; Lundy, J. Fall detection—Principles and Methods. In Proceedings of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, France, 22–26 August 2007; pp. 1663–1666.
- Noury, N.; Rumeau, P.; Bourke, A.; ÓLaighin, G.; Lundy, J. A proposal for the classification and evaluation of fall detectors. IRBM 2008, 29, 340–349. [Google Scholar] [CrossRef]
- Klenk, J.; Becker, C.; Lieken, F.; Nicolai, S.; Maetzler, W.; Alt, W.; Zijlstra, W.; Hausdorff, J.; van Lummel, R.; Chiari, L.; et al. Comparison of acceleration signals of simulated and real-world backward falls. Med. Eng. Phys. 2011, 33, 368–373. [Google Scholar] [CrossRef] [PubMed]
- Koshmak, G.A.; Linden, M.; Loutfi, A. Evaluation of the Android-Based Fall Detection System with Physiological Data Monitoring. In Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, 3–7 July 2013; pp. 1164–1168.
Code | Activity | Trials | Duration |
---|---|---|---|
F01 | Fall forward while walking caused by a slip | 5 | 15 s |
F02 | Fall backward while walking caused by a slip | 5 | 15 s |
F03 | Lateral fall while walking caused by a slip | 5 | 15 s |
F04 | Fall forward while walking caused by a trip | 5 | 15 s |
F05 | Fall forward while jogging caused by a trip | 5 | 15 s |
F06 | Vertical fall while walking caused by fainting | 5 | 15 s |
F07 | Fall while walking, with use of hands in a table to dampen fall, caused by fainting | 5 | 15 s |
F08 | Fall forward when trying to get up | 5 | 15 s |
F09 | Lateral fall when trying to get up | 5 | 15 s |
F10 | Fall forward when trying to sit down | 5 | 15 s |
F11 | Fall backward when trying to sit down | 5 | 15 s |
F12 | Lateral fall when trying to sit down | 5 | 15 s |
F13 | Fall forward while sitting, caused by fainting or falling asleep | 5 | 15 s |
F14 | Fall backward while sitting, caused by fainting or falling asleep | 5 | 15 s |
F15 | Lateral fall while sitting, caused by fainting or falling asleep | 5 | 15 s |
Code | Activity | Trials | Duration |
---|---|---|---|
D01 | Walking slowly | 1 | 100 s |
D02 | Walking quickly | 1 | 100 s |
D03 | Jogging slowly | 1 | 100 s |
D04 | Jogging quickly | 1 | 100 s |
D05 | Walking upstairs and downstairs slowly | 5 | 25 s |
D06 | Walking upstairs and downstairs quickly | 5 | 25 s |
D07 | Slowly sit in a half height chair, wait a moment, and up slowly | 5 | 12 s |
D08 | Quickly sit in a half height chair, wait a moment, and up quickly | 5 | 12 s |
D09 | Slowly sit in a low height chair, wait a moment, and up slowly | 5 | 12 s |
D10 | Quickly sit in a low height chair, wait a moment, and up quickly | 5 | 12 s |
D11 | Sitting a moment, trying to get up, and collapse into a chair | 5 | 12 s |
D12 | Sitting a moment, lying slowly, wait a moment, and sit again | 5 | 12 s |
D13 | Sitting a moment, lying quickly, wait a moment, and sit again | 5 | 12 s |
D14 | Being on one’s back change to lateral position, wait a moment, and change to one’s back | 5 | 12 s |
D15 | Standing, slowly bending at knees, and getting up | 5 | 12 s |
D16 | Standing, slowly bending without bending knees, and getting up | 5 | 12 s |
D17 | Standing, get into a car, remain seated and get out of the car | 5 | 25 s |
D18 | Stumble while walking | 5 | 12 s |
D19 | Gently jump without falling (trying to reach a high object) | 5 | 12 s |
Sex | Age | Height (m) | Weight (kg) | |
---|---|---|---|---|
Elderly | Female | 62–75 | 1.50–1.69 | 50–72 |
Male | 60–71 | 1.63–1.71 | 56–102 | |
Adult | Female | 19–30 | 1.49–1.69 | 42–63 |
Male | 19–30 | 1.65–1.83 | 58–81 |
Type | Code | Feature | Equation |
---|---|---|---|
Amplitude | Sum vector magnitude | ||
Sum vector magnitude on horizontal plane | |||
Maximum peak-to-peak acceleration amplitude | |||
Orientation | Angle between z-axis and vertical | ||
Orientation of person’s trunk | |||
Orientation change in horizontal plane | |||
Time | Jerk (rate of acceleration change) | ||
Statistics | Standard deviation magnitude on horizontal plane | ; with | |
Standard deviation magnitude | |||
Area | Signal magnitude area | ||
Signal magnitude area on horizontal plane | |||
Activity signal magnitude area | |||
Activity signal magnitude area on horizontal plane | |||
Velocity (approx.) |
Feature | Young | Elderly | ||||
---|---|---|---|---|---|---|
SE | SP | AC | SE | SP | AC | |
94.28 | 96.13 | 95.21 | 77.33 | 97.67 | 87.49 | |
98.53 | 80.50 | 89.51 | 84.00 | 96.42 | 90.21 | |
95.54 | 96.38 | 95.96 | 85.33 | 98.10 | 91.72 | |
97.79 | 80.70 | 89.25 | 88.00 | 96.42 | 92.21 | |
92.56 | 94.41 | 93.49 | 62.67 | 95.19 | 78.93 |
Feature | AC (%) with Elderly | Threshold | ||
---|---|---|---|---|
Test 1 | Test 2 | Test 1 | Test 2 | |
87.49 | 90.45 ± 5.89 | 1.07 ± 0.029 | 0.97 ± 0.012 | |
90.21 | 90.85 ± 7.25 | 1.48 ± 0.017 | 1.23 ± 0.024 | |
91.72 | 92.36 ± 6.80 | 0.40 ± 0.004 | 0.36 ± 0.003 | |
92.21 | 92.58 ± 7.10 | 0.43 ± 0.009 | 0.36 ± 0.002 | |
78.93 | 80.73 ± 5.62 | 0.08 ± 9.35 × | 0.07 ± 0.002 |
Feature | SP | AC |
---|---|---|
32.97 ± 6.46 | 66.43 ± 3.06 | |
59.04 ± 5.56 | 79.49 ± 2.70 | |
38.34 ± 5.58 | 69.14 ± 2.71 | |
67.97 ± 2.86 | 83.96 ± 1.37 | |
37.80 ± 3.42 | 68.88 ± 1.69 |
© 2017 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sucerquia, A.; López, J.D.; Vargas-Bonilla, J.F. SisFall: A Fall and Movement Dataset. Sensors 2017, 17, 198. https://doi.org/10.3390/s17010198
Sucerquia A, López JD, Vargas-Bonilla JF. SisFall: A Fall and Movement Dataset. Sensors. 2017; 17(1):198. https://doi.org/10.3390/s17010198
Chicago/Turabian StyleSucerquia, Angela, José David López, and Jesús Francisco Vargas-Bonilla. 2017. "SisFall: A Fall and Movement Dataset" Sensors 17, no. 1: 198. https://doi.org/10.3390/s17010198