Growing of smart IoT has generated many major impacts on transportation development, of which one underlying big story is the thriving of big data driven smart transportation nowadays. We are moving from IT to data technology (DT) time, and we are entering a “results driven” era in transportation. As the front and center of the smart IoT transformed mobility, transportation data sets grow rapidly while they are increasingly gathered from more connected sensors, devices, actuators in real-world applications. In 2016, over 823.0 million air trip passengers were reported by U.S. airlines and over 25 million public transit trips was generated daily.  The data traffic associated with mobility and transportation is estimated to be roughly 0.6 exabytes every month by 2020 (about 9 percent of total US wireless data traffic), and will grow to 9.4 exabytes every month by 2030. Although the quantity of the data available is indeed large, that is not the most striking characteristic of “big data” in the smart IoT era concerning transportation. The challenge in big data driven transportation rarely refers to the large volume or size of data; rather, it often refers to extracting value from data with certain innovative methods, i.e. how to analyze the data and to gather meaningful insights that can be used to inform decisions makers.

Many concurrent novel technologies and employments have emerged within the big data driven smart mobility ecosystem, emanating from the transportation needs of different stakeholders for better safety, reliability, sustainability, and automation.

For public transportation, big data analytics have transformed both the plan and operations phases on planning and demand modeling, predictive maintenance, and event response. New big data tech-savvy has brought more personalized services to public transportation users, such as offering ancillary services to providing recommendations about additional destinations to visit as part of an upgrade to the passenger’s journey, etc. The big data driven smart public transportation influences both automated and human decision-making, which has clearly played a big part in re-energizing public transport network, and has offered plenty of opportunities to improve the public transportation experience with improved reliability and safety.

For drivers, real-time traffic sensor data collection, analysis, visualization and optimization of dynamic transportation systems has reduced transportation time and emissions greatly. The latest developments in big data analytics technologies have led to the prevalence of Intelligent Transportation Systems for effective monitoring, real-time decision-making, and agile management of transportation. The state-of-the-art transportation control systems could combine big data analytics with distributed scalable optimization technologies for a significant reduction in transportation time and emission, such as the smart traffic signal control system that has achieved improvements of over 25% reductions in travel times, over 40% reductions in idle time, and a projected reduction in emissions of over 21%. In addition, Yellow-light tweaks supported with big data analytics could make intersections safer. Big data driven future cruise control and big data driven integrated intelligent vehicle management with embedded optimize technologies could brought more environmental and safety features to drivers, which can not only save fuel and reduce emissions, but also be fine-tuned for intelligent vehicle capability with a better safety. Though full automation in real-world is still a few years away, semi-autonomous features have been set in many cars and they’re getting better, cheaper and more widely available every year.

For pedestrian and bicyclists, big data analytics has led to many multimode transportation improvements, where new hierarchical framework classifier has increased the overall accuracy of classifying transportation modes to make pedestrian and bicyclists have better experiences. Corresponding to multimode transportation, data fusion of multiple data sources is important. Although new insights can emerge from the analysis of single data sets, the real potential for new knowledge rests on the improved ability to apply analytical methodologies to multiple data sources.

Moreover, big data analytics has advanced sharing our transportation resources in an emerging multitude of options, from app-powered car-pooling and car sharing to novel modes of parking and driving to new forms of short-distance travel and jitney buses with seats allocated by app or phone.

More and more transportation industry parties are seeking to maximize the potential of all channels in mobility to reach new big data tech-savvy customers far and wide. The cutting edge smart IoT technologies with powerful big data analytics have transformed the way in which people move around in cities. The impacts will continue to strengthen for many years in coming. The transportation industry leaders in near future would be the ones who could jump at the opportunities to combine industry savvy with smart IoT and big data.

User_Account_Avatar_Person_Profile_Login_Persona-128 By Z. Jenipher Wang, Ph.D.  —— The WIOMAX SmartIoT Blog

Big Data Driven Smart Transportation: the Underlying Story of IoT Transformed Mobility

2 thoughts on “Big Data Driven Smart Transportation: the Underlying Story of IoT Transformed Mobility

Comments are closed.