This paper addresses a novel topic in ski injury research - how a ski group size indicates the risk of ski injury. There is evidence in research literature that people ski in groups. However, the relationship between group size and the risk of injury has remained unexplored. Based on ski lift entrance data, we use the density-based clustering algorithm OPTICS to identify groups of skiers and discuss the advantages of using this algorithm. We show that the ski group size can be used to improve the identification of skiers who experience ski injury. The results of the identification of ski groups at Mt. Kopaonik Ski Resort in Serbia show that skiing alone is most susceptible to ski injury, while skiing in couples or in bigger groups reduces the risk of injury by 46%. In addition, it is confirmed that ski injuries are an early failure event phenomena. Based on the CHAID decision tree analysis, spending a small amount of time at the ski resort and skiing alone are associated with the: 6 times greater ski injury risk than the average ski injury risk.
Nadine Cooper . Correlative study into injury epidemiology, use of protective equipment and r taking among adolescent participants in alpine snow sports. In: Skiing Trauma and safety: 17th Volume. ASTM International, 2009.
2.
ShepherdHR.The structure of perception: how networks shape ideas of norms. Sociol Forum2017; 32: 72–93.
3.
TekeşBErkuşULajunenT. Does the group membership shape evaluations on other drivers? The role of symbolic cues in traffic. Transp Res Part F Traffic Psychol Behav2019; 63: 216–225.
4.
LaurentV.International report on Snow and Mountain Tourism. Overview of the key industry figures for ski resorts. Laurent Vanat, 2018.
5.
DelibašićBRadovanovićSJovanovićMŠ, et al. Improving decision-making in ski resorts by analysing ski lift transportation—a review. In: MladenovićNSifalerasAKuzmanovićM (eds) Advances in operational research in the Balkans. Belgrade: Springer. 2020, pp.265–273.
6.
RadovanovicSDelibasicBSuknovicM, et al. Where will the next ski injury occur? A system for visual and predictive analytics of ski injuries. Oper Res2019; 19(4): 973–992.
7.
AnkerstMBreunigMMKriegelHP, et al. OPTICS: ordering points to identify the clustering structure. ACM SIGMOD Rec1999; 28(2): 49–60.
8.
XuDTianY.A comprehensive survey of clustering algorithms. Ann Data Sci2015; 2(2): 165–193.
9.
GreveMWYoungDJGossAL, et al. Skiing and snowboarding head injuries in 2 areas of the United States. Wilderness Environ Med2009; 20(3): 234–238.
10.
KassGV.An exploratory technique for investigating large quantities of categorical data. Appl Stat1980; 29(2): 119–127.
11.
DelibašićBRadovanovićSJovanovićM, et al. Ski injury predictive analytics from massive ski lift transportation data. Proc I Mech Eng, Part P: Journal of Sports Engineering and Technology2018; 232(3): 208–217.
12.
AleixVMaximilianoBRojasJT, et al. Evolution of injury rates in skiers and snowboarders from a single ski resort: A 23 years Overview. EC Orthopaedics2018; 9: 182–186.
13.
BarthMPlatzerHPGigerA, et al. Acute on-snow severe injury events in elite alpine ski racing from 1997 to 2019: the Injury Surveillance System of the Austrian Ski Federation. Br J Sports Med2021; 55(11): 589–595.
14.
CarusLCastilloI.Injury prevention: Individual factors affecting adult recreational snowboarders’ actual and estimated speeds on regular slopes. PLoS One2021; 16(2): e0246931.
15.
RuedlGBenedettoKPFinkC, et al. Factors associated with self-reported failure of binding to release among recreational skiers: an epidemiological study. Curr Issues Sport Sci (CISS)2016; 1: 1–8.
16.
Steidl-MüllerLHildebrandtCMüllerE, et al. Limb symmetry index in competitive alpine ski racers: Reference values and injury risk identification according to age-related performance levels. J Sport Health Sci2018; 7(4): 405–415.
17.
OwensBDNaccaCHarrisAP, et al. Comprehensive review of skiing and snowboarding injuries. J Am Acad Orthop Surg2018; 26(1): e1–e10.
18.
TøstesenGLangsethT.Freeride Skiing-risk-taking, recognition, and moral boundaries. Front Sports Active Living2021; 3: 650564.
19.
EkelandASulheimSRodvenA.Injury rates and injury types in alpine skiing, telemarking, and snowboarding. J ASTM Int2005; 2: 1–9.
20.
DuMLiuNHuX.Techniques for interpretable machine learning. Commun ACM2019; 63(1): 68–77.
21.
RadovanovićSPetrovićADelibašićB, et al. Ski injury predictions with explanations. In: International conference on ICT innovations, pp. 148–160. Springer, 2019.
22.
SpörriJKröllJGilgienM, et al. How to prevent injuries in alpine ski racing: what do we know and where do we go from here?Sports Med2017; 47(4): 599–614.
23.
KriegelHKrögerPSanderJ, et al. Density-based clustering. WIREs Data Mining Knowl Discovery2011; 1(3): 231–240.
24.
VukićevićMKirchnerKDelibašićB, et al. Finding best algorithmic components for clustering microarray data. Knowl Inf Syst2013; 35(1): 111–130.
25.
McArdleGTahirABertolottoM.Spatio-temporal clustering of movement data: an application to trajectories generated by human-computer interaction. ISPRS Ann Photogramm Remote Sens Spatial Inf Sci2012; I-2: 147–152.
26.
GuangshuoC.Human Habits Investigation: from mobility reconstruction to mobile traffic prediction. Université Paris-Saclay (ComUE). PhD Thesis, 2018.
27.
LiuQYangJDengM, et al. SNN_flow: a shared nearest-neighbor-based clustering method for inhomogeneous origin-destination flows. Int J Geogr Inf Sci2022; 36(2): 253–279.
28.
AndrienkoGAndrienkoNFuchsG, et al. Revealing patterns and trends of mass mobility through spatial and temporal abstraction of origin-destination movement data. IEEE Trans Vis Comput Graph2017; 23(9): 2120–2136.
29.
WestinMHarringeMLEngströmB, et al. Risk factors for anterior cruciate ligament injury in competitive adolescent alpine skiers. Orthop J Sports Med2018; 6(4): 2325967118766830.
30.
TarkaMCDaveyALonzaGC, et al. Alpine ski racing injuries. Sports Health2019; 11: 265–271.
31.
ProbstPBoulesteixA-L.To tune or not to tune the number of trees in random forest. J Mach Learn Res2017; 18(1): 6673–6690.
32.
TrevorHTibshiraniRFriedmanJH. The elements of statistical learning: data mining, inference, and prediction, vol. 2. New York: Springer, 2009.
