Table 1 Key statistical metrics of the dataset.

From: Design of a dynamic trust management and defense decision system for shared vehicle data based on blockchain and deep reinforcement learning

Metric

Value/distribution characteristics

Total Sample Size

12 million records

Average Daily Requests per User

µ = 1.2, σ = 0.8

Service Duration (minutes)

µ = 12.3, σ = 4.8, Range [1, 60]

Percentage of Harsh Braking Events

68% (labeled data)

Speeding Event Road Distribution

87% on highways, 13% on urban roads

Missing Data Rate (preprocessing)

6.8% (maximum missing rate for “device model” 7.2%)

Outlier Percentage (preprocessing)

4.3% (acceleration/steering angle outliers)

Back to article page