Demand Forecast Using Data Analytics for the Preallocation of Ambulances

被引：51

作者：

Chen, Albert Y. ^{[1
]}

Lu, Tsung-Yu ^{[2
]}

Ma, Matthew Huei-Ming ^{[3
]}

Sun, Wei-Zen ^{[4
]}

机构：

[1] Natl Taiwan Univ, Dept Civil Engn, Taipei 10617, Taiwan

[2] Natl Taiwan Univ, Dept Transportat Engn, Taipei 10617, Taiwan

[3] Natl Taiwan Univ, Dept Emergency Med, Taipei 10617, Taiwan

[4] Natl Taiwan Univ, Emergency Med Serv Res Ctr, Taipei 10617, Taiwan

来源：

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS | 2016年 / 20卷 / 04期

关键词：

Artificial neural network (ANN); demand forecast; emergency medical services; geographic information system; support vector machine (SVM); ARTIFICIAL NEURAL-NETWORKS; CALL VOLUME PREDICTIONS; EMS; SIMULATION;

D O I：

10.1109/JBHI.2015.2443799

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The objective of prehospital emergency medical services (EMSs) is to have a short response time. By increasing the operational efficiency, the survival rate of patients could potentially be increased. The geographic information system (GIS) is introduced in this study to manage and visualize the spatial distribution of demand data and forecasting results. A flexible model is implemented in GIS, through which training data are prepared with user-desired sizes for the spatial grid and discretized temporal steps. We applied moving average, artificial neural network, sinusoidal regression, and support vector regression for the forecasting of prehospital emergency medical demand. The results from these approaches, as a reference, could be used for the preallocation of ambulances. A case study is conducted for the EMS in New Taipei City, where prehospital EMS data have been collected for three years. The model selection process has chosen different models with different input features for the forecast of different areas. The best daily mean absolute percentage error during testing of the EMS demand forecast is 23.01%, which is a reasonable forecast based on Lewis' definition. With the acceptable prediction performance, the proposed approach has its potential to be applied to the current practice.

引用

页码：1178 / 1187

页数：10

共 29 条

[1]

[Anonymous], P 2 INT C MED BIOM

[2]

[Anonymous], HIST DAIL RAINF DAT

[3]

[Anonymous], 2006, Pattern Recognition and Machine Learning

[4]

[Anonymous], J SERV SCI MANAG

[5]

[Anonymous], 2015, J PEASANT STUD

[6]

[Anonymous], SAFE SECURE CITIES C

[7]

Awad M., 2015, Neural Inf. Process. -Lett. Rev, P67, DOI [DOI 10.1007/978-1-4302-5990-9_4, 10.1007/978-1- 4302-5990-9_4]

[8] Are EMS call volume predictions based on demand pattern analysis accurate? [J].

Brown, Lawrence H. ;

Lerner, E. Brooke ;

Larmon, Baxter ;

LeGassick, Todd ;

Taigman, Michael .

PREHOSPITAL EMERGENCY CARE, 2007, 11 (02) :199-203

[9] Clinical data analysis using artificial neural networks (ANN) and principal component analysis (PCA) of patients with breast cancer after mastectomy [J].

Bucinski, Adam ;

Baczek, Tomasz ;

Krysinski, Jerzy ;

Szoszkiewicz, Renata ;

Zaluski, Jerzy .

REPORTS OF PRACTICAL ONCOLOGY AND RADIOTHERAPY, 2007, 12 (01) :9-17

[10] LIBSVM: A Library for Support Vector Machines [J].

Chang, Chih-Chung ;

Lin, Chih-Jen .

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)

← 1 2 3 →