Page 184 - Big Data Analytics for Connected Vehicles and Smart Cities

164 Big Data Analytics for Connected Vehicles and Smart Cities Transportation Use Cases 165

develop strategies for the achievement of the optimum payment channel
use pattern.
• Expected outcome of analyses: Better use of payment channels and optimi-
zation of ticketing strategies that deliver greater efficiency and enhance
the user.
• Success criteria: Maximizing revenue from each payment channel, com-
pared to the cost of operating each channel and identifying and applying
the most appropriate ticketing strategy for each mode.
• Source data examples: Volume of revenue from each payment channel;
ticketing strategy data; and effects of strategies on revenue data.
• Business benefits: Lower cost of payment channel operation; enhanced
user experience; and maximized revenue.
• Challenges: Collecting performance data on each payment channel and
developing a catalog of possible ticketing strategies.

• Analytics that can be applied: Payment channel efficiency, ticketing strat-
egy effectiveness, cost of money collection, relative use of each payment.

Use Case Example 6: Intelligent Sensor–Based Infrastructure
Smart City Service: Intelligent Sensor–Based Infrastructure

• Objectives: To optimize the balance between the cost of intelligent sen-
sor–based infrastructure and the quality of the data delivered and to
promote an integrated approach to data collection that blends together
infrastructure-based sensors and probe vehicle sensors.
• Expected outcome of analyses: Better use of infrastructure-based and vehi-
cle-based sensors in an integrated fashion.
• Success criteria: More efficient data collection, reduced cost of center
operation, better integration of sensor data with other data.
• Source data examples: Sensor-based data including volumes and speeds;
cost of data collection by different means; and quality of data by differ-
ent means.
• Business benefits: Lower cost of data collection; better and more com-
plete data; and better management of investments in infrastructure.
• Challenges: Establishing data quality targets; measuring data quality; and
integrating data from multiple sources.
• Analytics that can be applied: Data quality index, sensor efficiency, cost-
benefit to sensors.