scholarly journals Predicting Road Accident Risk in the City of San Pablo, Laguna: A Predictive Model Using Time Series Forecasting Analysis with Multiplicative Model

2020 ◽  
Vol 8 (4) ◽  
pp. 75-80
Author(s):  
Reymar V. Manaloto ◽  
Ronnel A. Dela Cruz
Keyword(s):  
Time Series ◽  
Predictive Model ◽  
Multiplicative Model ◽  
Road Accident ◽  
Time Series Forecasting ◽  
Accident Risk ◽  
Forecasting Analysis ◽  
The City

The Potential for Rail Transit as a Way to Mitigate Accident Risk

2016 ◽  
pp. 23-39
Author(s):  
Sumeeta Srinivasan
Keyword(s):  
Built Environment ◽  
Urban Development ◽  
Traffic Safety ◽  
Road Accident ◽  
Rail Transit ◽  
Accident Risk ◽  
Road Accidents ◽  
Dependent Variables ◽  
Accident Data ◽  
The City

The city of Chennai has made road accident data available with the address location of road accidents and the total numbers of persons and pedestrians affected in the accident in 2009. These data were geocoded to locate the accidents with respect to the census wards within the Chennai Corporation area. Both the total number of persons as well as pedestrians in accidents as well as the rate of accidents normalized by population in the ward were modeled as dependent variables using Poisson based regression models to see the effect of location characteristics such as road length, vehicle traffic, proximity to existing and proposed transit infrastructure and the percentage of the land developed between 1991-2009. The results from the models suggest that location does indeed affect the risk for accidents in Chennai and that planners in the city may need to better understand the implications of roads, urban development, transit access and the built environment for traffic safety.

Gokuldhaam Society: a case on transportation planning

2018 ◽  
Vol 8 (1) ◽  
pp. 1-20
Author(s):  
Peeyush Pandey ◽  
Tuhin Sengupta
Keyword(s):  
Time Series ◽  
Learning Outcomes ◽  
Operations Research ◽  
Operations Management ◽  
Time Series Forecasting ◽  
Stationary Time Series ◽  
Data Set ◽  
Content Type ◽  
The City ◽  
Forecasting Techniques

Subject area The subject areas are Operations Management, Operations Research, Transportation and Logistics. Study level/applicability The following courses (MBA/Post Graduate level) can use the case as part of their teaching material: Applied Forecasting Techniques; Optimization Methods; Operations Research. Case overview The case details a problem faced by the Gokuldhaam Society. The society was located a great distance from the city, as the majority of the residents who live in the society work in the nearby industrial area. To cater to the daily needs of residents, the society has shuttle buses plying to and from the city at different times during the day. However, due to operational inefficiencies, the administration faced excessive transportation costs. Looking for advice in this regard, the chairman of the society contacted the Head of Department at Operations Management, Indira Institute of Management, Indore hoping to find a way to reduce some of the operational costs. Expected learning outcomes The expected learning outcomes are as follows: to make the students apply two different stationary time series forecasting techniques to a real-life problem and data set; to make the students carefully choose a specific trend-based time series forecasting technique due to the inherent constraints in the availability of data set; and to make students appreciate the importance of application of linear programming in a time series problem. Supplementary materials Teaching Notes are available for educators only. Please contact your library to gain login details or email [email protected] to request teaching notes. Subject code CSS 9 Operations and logistics

scholarly journals Analisis Komparatif ARIMA dan Prophet dengan Studi Kasus Dataset Pendaftaran Mahasiswa Baru

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Cato Chandra ◽  
Setia Budi
Keyword(s):  
Time Series ◽  
Regression Model ◽  
Test Data ◽  
Moving Average ◽  
Data Preprocessing ◽  
Time Series Forecasting ◽  
Autoregressive Integrated Moving Average ◽  
Marketing Data ◽  
Forecasting Analysis ◽  
New Student

This research presents all studies, methodologies, and results about testing the accuracy of predictions on new student marketing data by region using the Prophet and Autoregressive Integrated Moving Average (ARIMA) methods. The dataset selected for this study uses 26 years of actual data that has an annual interval. The data was prepared for time series forecasting analysis, therefore, several numbers of data preprocessing were applied such as log transformation and resampling. To get efficient variables, the best variables will be sought to improve the accuracy of predictions. Both models will conduct training and test data to produce values that can be compared using the metric regression model. Based on the training conducted, Prophet has better performance than ARIMA.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

Sign in / Sign up

Export Citation Format

Share Document