The application of GPS-trackers data to the analysis of spatial behavior patterns of drivers
Driver behavior and its possible application to the tariff policy of insurance companies. Calculation of the price tariff for the driver, depending on his riskiness. Possibilities of measuring the probability of a driver getting into an accident.
| Рубрика | Транспорт |
| Вид | дипломная работа |
| Язык | английский |
| Дата добавления | 10.12.2019 |
| Размер файла | 2,5 M |
Отправить свою хорошую работу в базу знаний просто. Используйте форму, расположенную ниже
Студенты, аспиранты, молодые ученые, использующие базу знаний в своей учебе и работе, будут вам очень благодарны.
References
1. Bhowmik T., Yasmin S., Eluru N. A multilevel generalized ordered probit fractional split model for analyzing vehicle speed //Analytic Methods in Accident Research. - 2018.
2. Jun J., Ogle J., Guensler R. Relationships between crash involvement and temporal-spatial driving behavior activity patterns: use of data for vehicles with global positioning systems //Transportation Research Record: Journal of the Transportation Research Board. - 2007. - №. 2019. - С. 246-255.
3. Hultkrantz L., Nilsson J. E., Arvidsson S. Voluntary internalization of speeding externalities with vehicle insurance //Transportation research part A: policy and practice. - 2012. - Т. 46. - №. 6. - С. 926-937.
4. Jain A. K. Data clustering: 50 years beyond K-means //Pattern recognition letters. - 2010. - Т. 31. - №. 8. - С. 651-666.
5. Hilbe J. M. Logistic regression models. - Chapman and hall/CRC, 2009.
6. Tang F., Ishwaran H. Random forest missing data algorithms //Statistical Analysis and Data Mining: The ASA Data Science Journal. - 2017. - Т. 10. - №. 6. - С. 363-377.
7. Natekin A., Knoll A. Gradient boosting machines, a tutorial //Frontiers in neurorobotics. - 2013. - Т. 7. - С. 21.
8. Dey S. et al. Forecasting to Classification: Predicting the direction of stock market price using Xtreme Gradient Boosting. - Working paper. DOI: 10.13140/RG. 2.2. 15294.48968, 2016.
9. Arrow K. J. Uncertainty and the welfare economics of medical care (American economic review, 1963) //Journal of health politics, policy and law. - 2001. - Т. 26. - №. 5. - С. 851-883.
10. Pauly M. V. Taxation, health insurance, and market failure in the medical economy //Journal of economic literature. - 1986. - Т. 24. - №. 2. - С. 629-675.
11. Pauly M. V. The economics of moral hazard: comment //American economic review. - 1968. - Т. 58. - №. 3. - С. 531-537.
12. Desyllas P., Sako M. Profiting from business model innovation: Evidence from Pay-As-You-Drive auto insurance //Research Policy. - 2013. - Т. 42. - №. 1. - С. 101-116.
13. Wеhlberg A. E. The stability of driver acceleration behavior, and a replication of its relation to bus accidents //Accident Analysis & Prevention. - 2004. - Т. 36. - №. 1. - С. 83-92.
14. Klauer S. G. et al. The impact of driver inattention on near-crash/crash risk: An analysis using the 100-car naturalistic driving study data. - 2006.
15. Vickrey W. Automobile accidents, tort law, externalities, and insurance: an economist's critique //Law & Contemp. Probs. - 1968. - Т. 33. - С. 464.
16. Cummins J. D., Tennyson S. Moral hazard in insurance claiming: evidence from automobile insurance //Journal of Risk and Uncertainty. - 1996. - Т. 12. - №. 1. - С. 29-50.
17. Hultkrantz L., Lindberg G. Pay-as-you-speed An Economic Field Experiment //Journal of Transport Economics and Policy (JTEP). - 2011. - Т. 45. - №. 3. - С. 415-436.
18. Bolderdijk J. W. et al. Effects of Pay-As-You-Drive vehicle insurance on young drivers' speed choice: Results of a Dutch field experiment //Accident Analysis & Prevention. - 2011. - Т. 43. - №. 3. - С. 1181-1186.
19. Ahmed M. M., Abdel-Aty M., Yu R. Assessment of interaction of crash occurrence, mountainous freeway geometry, real-time weather, and traffic data //Transportation Research Record. - 2012. - Т. 2280. - №. 1. - С. 51-59.
20. Edlin A. S., Karaca-Mandic P. The accident externality from driving //Journal of Political Economy. - 2006. - Т. 114. - №. 5. - С. 931-955.
21. Edlin A. S. Per-Mile Premiums for Auto Insurance. Economics for an Imperfect World: Essays in Honor of Joseph Stiglitz. - 2003.
Appendix
Logit results for a shortened dataset with behavioral features:
Current function value: 0.051067
Iterations 11
Results: Logit
=======================
Model: Logit No. Iterations: 11.0000
Dependent Variable: crash Pseudo R-squared: 0.159
Date: 2019-05-06 15:36 AIC: 418.6363
No. Observations: 3531 BIC: 597.5470
Df Model: 28 Log-Likelihood: -180.32
Df Residuals: 3502 LL-Null: -214.51
Converged: 1.0000 Scale: 1.0000
-----------------------------------------------------------------------------
Coef. Std.Err. z P>|z| [0.025 0.975]
-----------------------------------------------------------------------------
min_x_more_mean -0.0048 0.0062 -0.7820 0.4342 -0.0170 0.0073
max_x_more_mean 0.0026 0.0026 0.9687 0.3327 -0.0026 0.0077
min_y_more_mean -0.0033 0.0086 -0.3873 0.6985 -0.0202 0.0135
max_y_more_mean 0.0010 0.0053 0.1933 0.8467 -0.0094 0.0114
min_z_more_mean -0.0043 0.0028 -1.5042 0.1325 -0.0098 0.0013
max_z_more_mean -0.0036 0.0026 -1.3967 0.1625 -0.0087 0.0015
min_x_less_mean -0.0121 0.0056 -2.1421 0.0322 -0.0231 -0.0010
max_x_less_mean 0.0078 0.0060 1.2896 0.1972 -0.0040 0.0196
min_y_less_mean -0.0011 0.0061 -0.1842 0.8539 -0.0131 0.0108
max_y_less_mean -0.0026 0.0064 -0.4079 0.6833 -0.0150 0.0099
mileage -0.0000 0.0014 -0.0020 0.9984 -0.0027 0.0027
speed3_100 -0.4843 0.7705 -0.6285 0.5297 -1.9945 1.0259
acc1_100 0.0365 0.0113 3.2466 0.0012 0.0145 0.0586
acc2_100 -0.0649 0.0563 -1.1528 0.2490 -0.1754 0.0455
acc3_100 -0.2530 0.2827 -0.8949 0.3708 -0.8069 0.3010
drg1_100 -0.0104 0.0384 -0.2715 0.7860 -0.0857 0.0649
drg2_100 0.0329 0.1507 0.2181 0.8274 -0.2625 0.3282
drg3_100 0.5305 0.8509 0.6235 0.5329 -1.1371 2.1982
side1_100 -0.0223 0.0345 -0.6455 0.5186 -0.0900 0.0454
side2_100 0.2229 0.0753 2.9597 0.0031 0.0753 0.3705
side3_100 0.1082 0.2388 0.4531 0.6505 -0.3598 0.5762
avg_daily_business_mileage 0.0016 0.0018 0.8802 0.3787 -0.0019 0.0050
avg_daily_morning_jam_mileage -0.0029 0.0043 -0.6819 0.4953 -0.0113 0.0055
avg_daily_night_mileage -0.0216 0.0129 -1.6645 0.0960 -0.0469 0.0038
avg_speed -0.0191 0.0236 -0.8120 0.4168 -0.0653 0.0271
max_morning_jam_speed 0.0125 0.0058 2.1725 0.0298 0.0012 0.0238
max_evening_jam_speed 0.0129 0.0054 2.3645 0.0181 0.0022 0.0235
max_night_speed 0.0001 0.0091 0.0148 0.9882 -0.0178 0.0181
max_speed 0.0077 0.0047 1.6432 0.1003 -0.0015 0.0168
Appendix 2
Logit results for a shortened dataset with behavioral features and clusters added:
Optimization terminated successfully.
Current function value: 0.048004
Iterations 11
Results: Logit
=======================
Model: Logit No. Iterations: 11.0000
Dependent Variable: crash Pseudo R-squared: 0.210
Date: 2019-05-08 13:55 AIC: 405.0042
No. Observations: 3531 BIC: 608.5923
Df Model: 32 Log-Likelihood: -169.50
Df Residuals: 3498 LL-Null: -214.51
Converged: 1.0000 Scale: 1.0000
-----------------------------------------------------------------------------
Coef. Std.Err. z P>|z| [0.025 0.975]
-----------------------------------------------------------------------------
min_x_more_mean -0.0050 0.0064 -0.7761 0.4377 -0.0175 0.0076
max_x_more_mean 0.0048 0.0032 1.5039 0.1326 -0.0015 0.0110
min_y_more_mean -0.0053 0.0091 -0.5828 0.5601 -0.0232 0.0126
max_y_more_mean 0.0042 0.0059 0.7061 0.4801 -0.0074 0.0157
min_z_more_mean -0.0067 0.0034 -1.9476 0.0515 -0.0134 0.0000
max_z_more_mean -0.0008 0.0029 -0.2681 0.7886 -0.0065 0.0049
min_x_less_mean -0.0143 0.0062 -2.3101 0.0209 -0.0265 -0.0022
max_x_less_mean 0.0096 0.0068 1.4167 0.1566 -0.0037 0.0228
min_y_less_mean -0.0009 0.0097 -0.0935 0.9255 -0.0199 0.0181
max_y_less_mean -0.0033 0.0099 -0.3322 0.7397 -0.0228 0.0162
mileage -0.0006 0.0018 -0.3164 0.7517 -0.0040 0.0029
speed3_100 -0.7482 0.9039 -0.8278 0.4078 -2.5198 1.0234
acc1_100 0.0415 0.0121 3.4218 0.0006 0.0177 0.0653
acc2_100 -0.0606 0.0585 -1.0359 0.3002 -0.1752 0.0540
acc3_100 -0.2691 0.3156 -0.8528 0.3938 -0.8877 0.3494
drg1_100 -0.0431 0.0412 -1.0440 0.2965 -0.1239 0.0378
drg2_100 -0.0161 0.1531 -0.1050 0.9164 -0.3161 0.2840
drg3_100 0.5807 0.8777 0.6616 0.5082 -1.1396 2.3009
side1_100 0.0053 0.0374 0.1412 0.8877 -0.0681 0.0786
side2_100 0.2330 0.0807 2.8886 0.0039 0.0749 0.3911
side3_100 0.1572 0.2590 0.6070 0.5438 -0.3503 0.6647
avg_daily_business_mileage 0.0008 0.0021 0.4081 0.6832 -0.0032 0.0049
avg_daily_morning_jam_mileage -0.0032 0.0047 -0.6826 0.4948 -0.0124 0.0060
avg_daily_night_mileage -0.0204 0.0140 -1.4534 0.1461 -0.0479 0.0071
avg_speed -0.0060 0.0251 -0.2371 0.8126 -0.0552 0.0433
max_morning_jam_speed 0.0116 0.0066 1.7469 0.0807 -0.0014 0.0245
max_evening_jam_speed 0.0129 0.0058 2.2371 0.0253 0.0016 0.0243
max_night_speed 0.0012 0.0118 0.1014 0.9192 -0.0219 0.0243
max_speed -0.0007 0.0079 -0.0854 0.9320 -0.0162 0.0148
cluster_1 1.6007 2.0762 0.7710 0.4407 -2.4686 5.6699
cluster_3 -1.2106 2.2317 -0.5424 0.5875 -5.5847 3.1635
cluster_4 0.9431 2.1051 0.4480 0.6542 -3.1830 5.0691
cluster_5 -1.5525 2.2290 -0.6965 0.4861 -5.9213 2.8163
=======================
Logit results for a full dataset with behavioral features:
Optimization terminated successfully.
Current function value: 0.054320
Iterations 10
Results: Logit
========================
Model: Logit No. Iterations: 10.0000
Dependent Variable: crash Pseudo R-squared: -0.029
Date: 2019-05-08 13:57 AIC: 37338.6222
No. Observations: 343086 BIC: 37693.2315
Df Model: 32 Log-Likelihood: -18636.
Df Residuals: 343053 LL-Null: -18116.
Converged: 1.0000 Scale: 1.0000
------------------------------------------------------------------------------
Coef. Std.Err. z P>|z| [0.025 0.975]
------------------------------------------------------------------------------
min_x_more_mean -0.0032 0.0042 -0.7549 0.4503 -0.0114 0.0051
max_x_more_mean 0.0060 0.0019 3.1877 0.0014 0.0023 0.0097
min_y_more_mean -0.0038 0.0069 -0.5530 0.5803 -0.0173 0.0097
max_y_more_mean 0.0017 0.0038 0.4629 0.6434 -0.0056 0.0091
min_z_more_mean 0.0009 0.0024 0.3703 0.7112 -0.0039 0.0057
max_z_more_mean -0.0028 0.0024 -1.1977 0.2310 -0.0074 0.0018
min_x_less_mean -0.0146 0.0050 -2.8946 0.0038 -0.0245 -0.0047
max_x_less_mean 0.0082 0.0050 1.6377 0.1015 -0.0016 0.0180
min_y_less_mean 0.0022 0.0054 0.4146 0.6784 -0.0084 0.0129
max_y_less_mean -0.0060 0.0054 -1.1182 0.2635 -0.0166 0.0045
mileage -0.0003 0.0001 -1.9818 0.0475 -0.0006 -0.0000
speed3_100 0.2599 0.0651 3.9891 0.0001 0.1322 0.3875
acc1_100 0.0019 0.0004 4.7868 0.0000 0.0011 0.0026
acc2_100 0.0001 0.0004 0.3138 0.7537 -0.0007 0.0010
acc3_100 0.0000 0.0001 0.1355 0.8922 -0.0001 0.0001
drg1_100 -0.0074 0.0013 -5.4798 0.0000 -0.0100 -0.0047
drg2_100 -0.0001 0.0009 -0.1670 0.8673 -0.0019 0.0016
drg3_100 0.0000 0.0002 0.0613 0.9511 -0.0005 0.0005
side1_100 0.0004 0.0005 0.7383 0.4603 -0.0006 0.0014
side2_100 -0.0002 0.0008 -0.2664 0.7899 -0.0017 0.0013
side3_100 -0.0000 0.0002 -0.0794 0.9367 -0.0004 0.0003
avg_daily_business_mileage -0.0005 0.0002 -2.6794 0.0074 -0.0009 -0.0001
avg_daily_morning_jam_mileage 0.0001 0.0005 0.1937 0.8464 -0.0008 0.0010
avg_daily_night_mileage 0.0002 0.0002 0.7911 0.4289 -0.0003 0.0007
avg_speed -0.0175 0.0019 -9.3865 0.0000 -0.0212 -0.0138
max_morning_jam_speed 0.0000 0.0001 0.0663 0.9471 -0.0002 0.0002
max_evening_jam_speed 0.0002 0.0001 2.1822 0.0291 0.0000 0.0004
max_night_speed 0.0001 0.0002 0.7678 0.4426 -0.0002 0.0005
max_speed -0.0060 0.0005 -13.1974 0.0000 -0.0069 -0.0051
cluster_1 -2.2120 0.0828 -26.7008 0.0000 -2.3744 -2.0497
cluster_3 -3.5257 0.0640 -55.0792 0.0000 -3.6512 -3.4003
cluster_4 -2.6399 0.0671 -39.3293 0.0000 -2.7715 -2.5083
cluster_5 -3.2333 0.0650 -49.7221 0.0000 -3.3608 -3.1059
========================
Code
Python code for OSM parsing.
traffic_signal = pd.read_excel('traffic_signal.xlsx', sheetname='Лист1')
traffic_signal = pd.DataFrame(data=traffic_signal)
traffic_signal['lat_r_4']=round(traffic_signal['lat'], 4)
traffic_signal['lon_r_4']=round(traffic_signal['lon'], 4)
traffic_signal['coord'] = traffic_signal[['lat_r_4', 'lon_r_4']].apply(lambda x: ','.join(x.fillna('').map(str)), axis=1)
df = pd.read_table('00400077.mp', names= ('A'))
fileall = open("00400077.mp", "r", encoding='utf-8').read()
allVarsList = []
aalist = []
bblist = []
cclist = []
flist = fileall.split("[END]")
for fl in flist[1:105000]:
try:
aa = re.search('NodeID(.*?)\\n', fl).group(0)
bb = re.search('Data0(.*?)\\n', fl).group(0)
cc = re.search('\\n(.*?)\\n(.*?)POI', fl).group(0)
except BaseException:
aa = 0
bb = 0
cc = 0
print(fl)
else:
aalist.append(aa)
bblist.append(bb)
cclist.append(cc)
df = pd.DataFrame(aalist)
labels = ['NodeID']
df = pd.DataFrame(aalist, columns=labels)
df['N'], df['nodeID'] = df['NodeID'].str.split('=', 1).str
df1 = pd.DataFrame(bblist)
labels = ['data0']
df1 = pd.DataFrame(bblist, columns=labels)
df1['D'], df1['Data0'] = df1['data0'].str.split('=', 1).str
df2 = pd.DataFrame(cclist)
labels = ['geo']
df2 = pd.DataFrame(cclist, columns=labels)
df2['tr'], df2['poi'] = df2['geo'].str.split('[', 1).str
result = pd.concat([df, df1], axis=1)
result= pd.concat([result, df2], axis=1)
result=result.drop(['N', 'NodeID', 'D', 'data0', 'geo', 'poi'], axis=1)
result['tr']=result.tr.apply(lambda x: x.replace('\n',''))
result['tr']=result.tr.apply(lambda x: x.replace(';',''))
result['nodeID']=result.nodeID.apply(lambda x: x.replace('\n',''))
result['Data0']=result.Data0.apply(lambda x: x.replace('\n',''))
result['lat'], result['lon'] = result['Data0'].str.split(',', 1).str
result['lat']=result.lat.apply(lambda x: x.replace('(',''))
result['lon']=result.lon.apply(lambda x: x.replace(')',''))
result['tr1'], result['tr2'] = result['tr'].str.split('=', 1).str
result=result.drop(['tr'], axis=1)
result["lat"] = pd.to_numeric(result["lat"])
result["lon"] = pd.to_numeric(result["lon"])
result['lat_r_4']=round(result['lat'], 4)
result['lon_r_4']=round(result['lon'], 4)
result['coord'] = result[['lat_r_4', 'lon_r_4']].apply(lambda x: ','.join(x.fillna('').map(str)), axis=1)
merged_left_1 = pd.merge(left=my_data,right=result, how='left', left_on='coord', right_on='coord')
filtered_df = merged_left_1[merged_left_1['Data0'].notnull()]
Размещено на Allbest.ru
...Подобные документы
Inspected damages: visual inspection of the aircrafts which are present in the hangar: damages of a fuselage, of an engine, of a wing, of a tail unit, of a landing gear. Accident emergency landings (on ground and on water); emergency water landings.
отчет по практике [7,2 M], добавлен 25.05.2012Construction of zone and flight plan. Modeling of zone in experimental program "Potok". Analysis of main flow direction of modeled airspace. Analysis of modeled airspace "Ivlieva_South" and determination of main flow direction, intensity, density.
курсовая работа [2,0 M], добавлен 21.11.2014Organization of maintenance and repair of rolling stock. Calculation of the production program of maintenance, the number of posts and lines maintenance and repair. Optimal technology Body Repair. Heating Safety in the workplace when the body work.
дипломная работа [467,1 K], добавлен 18.01.2015Business strategy of NAC "Uzbekistan airways technics". Modernization and unification of the fleet, expansion of production capacity for technical servicing of aircraft. Process design aircraft repair of composite panels. Total price of modification.
дипломная работа [1,1 M], добавлен 23.05.2015Diesel fuel is any fuel used in diesel engines. Chemical composition and cetane number. Boiling point and freezing point of representative diesel fuel hydrocarbons. Disadvantages of Diesel Fuel. Environment hazards of sulfur. Fuel value and price.
реферат [39,2 K], добавлен 25.05.2012Discussion of organizational culture. The major theories of personality. Social perception, its elements and common barriers. Individual and organizational influences on ethical behavior. The psychophysiology of the stress response.
контрольная работа [27,7 K], добавлен 19.11.2012Problem of oscillations arising in an elastic base caused by rotor vibrations of an asynchronous driver near the critical angular velocity. The equations of slow motions. Oscillations in the absence of energy dissipation. Damped stationary oscillations.
статья [417,2 K], добавлен 25.03.2011History of application of aluminium. The characteristic, chemical and physical properties of aluminium, industrial production and clarification. Aluminium application in the industry, in household appliances. Prospects of development of manufacture.
реферат [21,6 K], добавлен 11.11.2009Law of nature: "the fittest survive". Price war - one of strategies of companies to become a leader. Determination of a price war, positive and negative effects on firms, customers and the public. Possible tactics. Price war in hotel industry.
реферат [24,9 K], добавлен 27.12.2011A theory of price. Analysis of Markets. Simple Supply and Demand curves. Demand curve shifts. Supply curve shifts. Effects of being away from the Equilibrium Point. Vertical Supply Curve. Other market forms. Discrete Example. Application: Subsidy.
контрольная работа [84,0 K], добавлен 18.07.2009Wireless LANs will provide the first layer of connectivity between mobile users and the global information infrastructure. Wireless application design, data reduction, caching, active documents, dynamic URLs. Interworking units for wireless connectivity.
реферат [23,7 K], добавлен 07.10.2010Unhealthy food, lack of sleep, passive lifestyle, related works. Survey, Passive Lifestyle, Lack Of Sleep, Nutrition. How often pupils have negative feelings. Teachers' complaints. Can we do to reduce these negative displays of pupil’s behavior.
курсовая работа [25,5 K], добавлен 18.05.2015Value and probability weighting function. Tournament games as special settings for a competition between individuals. Model: competitive environment, application of prospect theory. Experiment: design, conducting. Analysis of experiment results.
курсовая работа [1,9 M], добавлен 20.03.2016Formation of intercultural business communication, behavior management and communication style in multicultural companies in the internationalization and globalization of business. The study of the branch of the Swedish-Chinese company, based in Shanghai.
статья [16,2 K], добавлен 20.03.2013Study credit channel using clustering and test the difference in mean portfolio returns. The calculated debt-to-capital, interest coverage, current ratio, payables turnover ratio. Analysis of stock market behavior. Comparison of portfolios’ performances.
курсовая работа [1,5 M], добавлен 23.10.2016Defining cognitive linguistics. The main descriptive devices of frame analysis are the notions of frame and perspective. Frame is an assemblage of the knowledge we have about a certain situation, e.g., buying and selling. Application of frame analysis.
реферат [324,4 K], добавлен 07.04.2012Legislation regulating the application of administrative law enforcement termination. Types of special rules of administrative. Improving the practice of special means of administrative cease-duty law enforcement. Special means of administrative.
реферат [16,0 K], добавлен 08.10.2012Plan of marketing. Absence of a large number of competitors. The emergence of new competitors. Active advertising policy. The absence of a known name in the market. Break even point. The price for advertising. Distribution channels and pricing policy.
презентация [2,6 M], добавлен 15.02.2012The air transport system in Russia. Project on the development of regional air traffic. Data collection. Creation of the database. Designing a data warehouse. Mathematical Model description. Data analysis and forecasting. Applying mathematical tools.
реферат [316,2 K], добавлен 20.03.2016Animal physiology as a branch of the biological sciences life processes, bodily functions and behavior of animals. The history of physiology, its purpose, the main sections, concepts and relationship with other sciences. Basic life processes of animals.
презентация [1,4 M], добавлен 22.12.2014
