Agent-based modeling to simulate road travel using Big Data from smartphone GPS: An application to the continental United States

Author(s):  
Sashikanth Gurram ◽  
Vijayaraghavan Sivaraman ◽  
Jonathan T. Apple ◽  
Abdul R. Pinjari
Author(s):  
Gang Zhang ◽  
Hao Li ◽  
Rong He ◽  
Peng Lu

AbstractThe outbreak of COVID-19 has greatly threatened global public health and produced social problems, which includes relative online collective actions. Based on the life cycle law, focusing on the life cycle process of COVID-19 online collective actions, we carried out both macro-level analysis (big data mining) and micro-level behaviors (Agent-Based Modeling) on pandemic-related online collective actions. We collected 138 related online events with macro-level big data characteristics, and used Agent-Based Modeling to capture micro-level individual behaviors of netizens. We set two kinds of movable agents, Hots (events) and Netizens (individuals), which behave smartly and autonomously. Based on multiple simulations and parametric traversal, we obtained the optimal parameter solution. Under the optimal solutions, we repeated simulations by ten times, and took the mean values as robust outcomes. Simulation outcomes well match the real big data of life cycle trends, and validity and robustness can be achieved. According to multiple criteria (spans, peaks, ratios, and distributions), the fitness between simulations and real big data has been substantially supported. Therefore, our Agent-Based Modeling well grasps the micro-level mechanisms of real-world individuals (netizens), based on which we can predict individual behaviors of netizens and big data trends of specific online events. Based on our model, it is feasible to model, calculate, and even predict evolutionary dynamics and life cycles trends of online collective actions. It facilitates public administrations and social governance.


Author(s):  
Peng Lu ◽  
Zhuo Zhang ◽  
Mengdi Li

AbstractUnder the mobile internet and big data era, more and more people are discussing and interacting online with each other. The forming process and evolutionary dynamics of public opinions online have been heavily investigated. Using agent-based modeling, we expand the Ising model to explore how individuals behave and the evolutionary mechanism of the life cycles. The big data platform of Douban.com is selected as the data source, and the online case “NeiYuanWaiFang” is applied as the real target, for our modeling and simulations to match. We run 10,000 simulations to find possible optimal solutions, and we run 10,000 times again to check the robustness and adaptability. The optimal solution simulations can reflect the whole life cycle process. In terms of different levels and indicators, the fitting or matching degrees achieve the highest levels. At the micro-level, the distributions of individual behaviors under real case and simulations are similar to each other, and they all follow normal distributions; at the middle-level, both discrete and continuous distributions of supportive and oppositive online comments are matched between real case and simulations; at the macro-level, the life cycle process (outbreak, rising, peak, and vanish) and durations can be well matched. Therefore, our model has properly seized the core mechanism of individual behaviors, and precisely simulated the evolutionary dynamics of online cases in reality.


2017 ◽  
Vol 185 (9) ◽  
pp. 822-831 ◽  
Author(s):  
Jay V. DePasse ◽  
Kenneth J. Smith ◽  
Jonathan M. Raviotta ◽  
Eunha Shim ◽  
Mary Patricia Nowalk ◽  
...  

2021 ◽  
Vol 5 (4) ◽  
pp. 48
Author(s):  
Damianos P. Sakas ◽  
Nikolaos Th. Giannakopoulos

Rising demand for optimized digital marketing strategies has led firms in a hunt to harvest every possible aspect indicating users’ experience and preference. People visit, regularly through the day, numerous websites using both desktop and mobile devices. For businesses to acknowledge device’s usage rates is extremely important. Thus, this research is focused on analyzing each device’s usage and their effect on airline firms’ digital brand name. In the first phase of the research, we gathered web data from 10 airline firms during an observation period of 180 days. We then proceeded in developing an exploratory model using Fuzzy Cognitive Mapping, as well as a predictive and simulation model using Agent-Based Modeling. We inferred that various factors of airlines’ digital brand name are affected by both desktop and mobile usage, with mobile usage having a slightly bigger impact on most of them, with gradually rising values. Desktop device usage also appeared to be quite significant, especially in traffic coming from referral sources. The paper’s contribution has been to provide a handful of time-accurate insights for marketeers, regarding airlines’ digital marketing strategies.


Author(s):  
Maira A. de C. Gatti ◽  
Marcos R. Vieira ◽  
Joao Paulo F. de Melo ◽  
Paulo Rodrigo Cavalin ◽  
Claudio Santos Pinhanez

Sign in / Sign up

Export Citation Format

Share Document