Strike Velocity Prediction of Stick Blunt Instruments Based on Backpropagation Neural Network

doi:10.12116/j.issn.1004-5619.2020.401108

Abstract

Abstract:

Objective To analyze and predict the striking velocity range of stick blunt instruments in different populations, and to provide basic data for the biomechanical analysis of blunt force injuries in forensic identification. Methods Based on the Photron FASTCAM SA3 high-speed camera, Photron FASTCAM Viewer 4.0 and SPSS 26.0 software, the tester’s maximum striking velocity of stick blunt instruments and related factors were calculated and analyzed, and inputed to the backpropagation （BP） neural network for training. The trained and verified BP neural network was used as the prediction model. Results A total of 180 cases were tested and 470 pieces of data were measured. The maximum striking velocity range was 11.30-35.99 m/s. Among them, there were 122 female data, the maximum striking velocity range was 11.63-29.14 m/s; there were 348 male data, the maximum striking velocity range was 20.11-35.99 m/s. The maximum striking velocity of stick blunt instruments increased with the increase of weight and height, but there was no obvious increase trend in the male group; the maximum striking velocity decreased with age, but there was no obvious downward trend in the female group. The maximum striking velocity of stick blunt instruments has no significant correlation with the material and strike posture. The root mean square error （RMSE）, the mean absolute error （MAE） and the coefficient of determination （R²） of the prediction results by using BP neural network were 2.16, 1.63 and 0.92, respectively. Conclusion The prediction model of BP neural network can meet the demand of predicting the maximum striking velocity of different populations.

Key words: forensic medicine, biomechanics, finite element analysis, blunt instrument, strike, back propagation neural networks

CLC Number:

DF795.1

Hai-yan LI, Hai-fang LI, Jian-yu PAN, Shi-hai CUI, Guang-long HE, Li-juan HE, Wen-le LÜ. Strike Velocity Prediction of Stick Blunt Instruments Based on Backpropagation Neural Network[J]. Journal of Forensic Medicine, 2022, 38(5): 573-578.

Figures/Tables 9

References 22

1	邵煜，邹冬华，刘宁国，等. 有限元方法在法医学颅脑损伤分析中的应用[J].法医学杂志，2010，26（6）：449-453. doi：10.3969/j.issn.1004-5619.2010.06.013 .
	SHAO Y， ZOU D H， LIU N G， et al. Application of finite element method in evaluation of craniocerebral trauma[J]. Fayixue Zazhi，2010，26（6）：449-453.
2	YOGANANDAN N， PINTAR F A， SANCES A JR， et al. Biomechanics of skull fracture[J]. J Neurotrauma，1995，12（4）：659-668. doi：10.1089/neu.1995.12.659 .
3	马竞. 棍棒类工具致伤颅骨的分析与研究[J].中国人民公安大学学报（自然科学版），2017，23（2）：17-20.
	MA J. Analysis and study of calvaria injured by stick tools[J]. Zhongguo Renmin Gongan Daxue Xuebao （Natural sciences），2017，23（2）：17-20.
4	ALCANTARA A L， ROSZLER M H， GUYOT A M， et al. Blunt head trauma： Comparison of various weapons with intracranial injury and neurologic outcome[J]. J Trauma，1994，37（4）：521-524.
5	LI K， YANG Y Q， WANG L J， et al. Establishment of a blunt impact-induced brain injury model in rabbits[J]. Chin J Traumatol，2012，15（2）：100-104. doi：10.3760/cma.j.issn.1008-1275.2012.02.007 .
6	LI K， WANG J W， LIU S X， et al. Biomechanical behavior of brain injury caused by sticks using finite element model and Hybrid-III testing[J]. Chin J Traumatol，2015，18（2）：65-73. doi：10.1016/j.cjtee.2015.03.004 .
7	HUANG J， PENG Y， YANG J K， et al. A study on correlation of pedestrian head injuries with physical parameters using in-depth traffic accident data and mathematical models[J]. Accid Anal Prev，2018，119：91-103. doi：10.1016/j.aap.2018.07.012 .
8	TRINH T X， HEINKE S， RODE C， et al. Maximum striking velocities in strikes with steel rods-the influence of rod length， rod mass and volunteer parameters[J]. Int J Leg Med，2018，132（2）：499-508. doi：10.1007/s00414-017-1734-z .
9	曹云星. 颅脑损伤及其成伤机制研究[D].沈阳：中国医科大学，2011.
	CAO Y X. Study on craniocerebral injury and its mechanism[D]. Shenyang： China Medical University，2011.
10	孙曙光，张铁成. 木棒他杀致颅骨骨折的法医学研究（附44例分析）[J].锦州医学院学报，1988，9（2）：131-132.
	SUN S G， ZHANG T C. Forensic study on skull fracture caused by stick homicide （analysis of 44 cases）[J]. Jinzhou Yixueyuan Xuebao，1988，9（2）：131-132.
11	高刘伟，张徐军，周义夕，等. BP神经网络在道路交通伤害预测应用的研究进展[J].伤害医学（电子版），2019，8（1）：53-57. doi：10.3868/j.issn.2095-1566.2019.01.010 .
	GAO L W， ZHANG X J， ZHOU Y X， et al. Research progress of BP neural network in prediction of road traffic injury[J]. Shanghai Yixue （Electronic version），2019，8（1）：53-57.
12	OMAR T， ESKANDARIAN A， BEDEWI N. Vehicle crash modelling using recurrent neural networks[J]. Math Comput Model，1998，28（9）：31-42. doi：10.1016/S0895-7177（98）00143-5 .
13	LANZI L C， BISAGNI C， RICCI S. Neural network systems to reproduce crash behavior of structural components[J]. Comput Struct，2004，82（1）：93-108. doi：10.1016/j.compstruc.2003.06.001 .
14	KOENIG K， MITCHELL N D， HANNIGAN T E， et al. The influence of moment of inertia on baseball/softball bat swing speed[J]. Sports Eng，2004，7（2）：105-117. doi：10.1007/BF02915922 .
15	KOIKE S， MIMURA K. Main contributors to the baseball bat head speed considering the generating factor of motion-dependent term[J]. Procedia Eng，2016，147：197-202. doi：10.1016/j.proeng.2016.06.213 .
16	ZHANG N， SHEN S L， ZHOU A N， et al. Investigation on performance of neural networks using quadratic relative error cost function[J]. IEEE Access，2019，7：106642-106652. doi：10.1109/ACCESS.2019.2930520 .
17	BAS E， USLU V R， EGRIOGLU E. Robust learning algorithm for multiplicative neuron model artificial neural networks[J]. Expert Syst Appl，2016，56：80-88. doi：10.1016/j.eswa.2016.02.051 .
18	MÜLLER K R， SMOLA A J， RÄTSCH G， et al. Predicting time series with support vector machines[M]//Nugent R. Lecture Notes in Computer Science. Heidelberg： Springer，2005：999-1004.
19	KRSTAJIC D， BUTUROVIC L J， LEAHY D E， et al. Cross-validation pitfalls when selecting and assessing regression and classification models[J]. J Cheminformatics，2014，6（1）：10. doi：10.1186/1758-2946-6-10 .
20	PILLONETTO G， DE NICOLAO G. Pitfalls of the parametric approaches exploiting cross-validation for model order selection[J]. IFAC Proc Vol，2012，45（16）：215-220. doi：10.3182/20120711-3-BE-2027.00147 .
21	SHI G， ZHANG J S， LI H R， et al. Enhance the performance of deep neural networks via L2 regularization on the input of activations[J]. Neural Process Lett，2019，50（1）：57-75. doi：10.1007/s11063-018-9883-8 .
22	PAROT A， MICHELL K， KRISTJANPOLLER W D. Using artificial neural networks to forecast exchange rate， including VAR-VECM residual analysis and prediction linear combination[J]. Intell Sys Acc Fin Mgmt，2019，26（1）：3-15. doi：10.1002/isaf.1440 .

钝器	材料	外径/mm	内径/mm	长度/mm	质量/g
木棍	木	35	-	600	460
薄壁钢管	钢	30	28	600	420

钝器	材料	外径/mm	内径/mm	长度/mm	质量/g
木棍	木	35	-	600	460
薄壁钢管	钢	30	28	600	420

年龄/岁	男性	女性
15~<25	83	17
25~<35	29	12
35~<45	8	9
45~<55	9	11
55~<65	1	1

年龄/岁	男性	女性
15~<25	83	17
25~<35	29	12
35~<45	8	9
45~<55	9	11
55~<65	1	1

性别	身高/cm	例数
男性	160~<170	22
	170~<180	70
	180~<190	36
	190~<200	2
女性	156~<160	1
	160~<165	13
	165~<170	25
	170~<175	11