云和县公交安全驾驶报警分析数据

公交司机肩负着保障乘客生命安全和城市交通顺畅的重要职责，而违规驾驶是导致公交交通事故的重要隐患之一。打电话、疲劳驾驶等违规驾驶会导致司机注意力不集中、反应速度下降、判断能力减弱，极易引发追尾、碰撞等交通事故，严重威胁乘客和道路上其他人员的生命财产安全。通过DSM系统实时监控、分析公交司机动作（闭眼、打哈欠、分神等）违规驾驶持续时间，结合当前车速报警阈值判断是否达到报警条件。通过ADAS高级驾驶辅助系统能够识别和追踪静态与动态物体，出现异常时发出报警，构建完善的公交司机驾驶风险预警模型，能够有效降低违规驾驶引发的交通事故风险，为市民的出行安全保驾护航，同时也有助于提升公交行业的整体管理水平。1、数据采集：通过DSM系统实时监控和ADAS高级驾驶辅助系统等多种传感器和设备收集公交司机驾驶行为以及车辆运行等相关数据，传送给公交调度中心系统。2、基于采集到的数据，运用大数据分析和人工智能算法构建驾驶风险预警模型。该模型通过量化报警事件中的关键风险因素（如报警等级、报警项、报警车速、持续时间），计算综合风险得分，评估报警事件的紧急程度和风险等级。权重基于公交运营安全管理经验设定。综合风险得分 =0.4× 报警等级得分 +0.2× 报警项得分 +0.2×(报警车速 / 最高限速) +0.2× 报警持续时间 1.报警等级: 一级 = 1 分，二级 = 2 分，三级 = 3 分 2.报警项:（DSM报警=6分，ADAS报警=5分，车辆报警=4分，围栏报警=3分，盲区报警=2分，胎压报警=1分） 3.线路最高限速为 60km/h 4.报警持续时间：直接取持续时间（单位：秒，时间越长风险越高） 0＜得分＜＝1为低风险， 1＜得分＜＝3为中等风险，需优先处理；得分＞3分为高风险，需立即处理。

Bus drivers bear the critical responsibility of safeguarding passengers' lives and ensuring smooth urban traffic flow. Violating driving regulations is one of the major hidden hazards that lead to bus traffic accidents. Behaviors such as making phone calls and fatigued driving cause drivers to lose focus, experience slowed reaction speeds, and weakened judgment, which easily trigger traffic accidents like rear-end collisions and crashes, severely threatening the lives and property of passengers and other road users.

The DSM (Driver Monitoring System) can conduct real-time monitoring and analysis of bus drivers' movements (such as eye closure, yawning, distracted driving, etc.) and the duration of violating driving behaviors, and determine whether an alarm condition is met by combining the current vehicle speed alarm threshold. The ADAS (Advanced Driver Assistance System) can identify and track both static and dynamic objects, and issue alarms when abnormalities are detected. Establishing a comprehensive bus driver driving risk early warning model can effectively reduce the risk of traffic accidents caused by violating driving, protect the travel safety of citizens, and help improve the overall management level of the public transport industry.

1. Data Collection: Collect relevant data including bus drivers' driving behaviors and vehicle operation status through various sensors and devices such as the DSM system and ADAS advanced driving assistance system, and transmit the collected data to the bus dispatching center system.

2. Risk Early Warning Model Construction: Based on the collected data, use big data analysis and artificial intelligence algorithms to build a driving risk early warning model. This model quantifies the key risk factors in alarm events (including alarm level, alarm item, alarm vehicle speed, and duration), calculates the comprehensive risk score, and evaluates the urgency and risk level of the alarm event. The weights of each factor are set based on the accumulated experience of bus operation safety management.

The formula for the comprehensive risk score is:
Comprehensive Risk Score = 0.4 × Alarm Level Score + 0.2 × Alarm Item Score + 0.2 × (Alarm Vehicle Speed / Maximum Speed Limit) + 0.2 × Alarm Duration

Specific parameter definitions are as follows:
1. Alarm Level: Level 1 = 1 point, Level 2 = 2 points, Level 3 = 3 points
2. Alarm Item: (DSM Alert = 6 points, ADAS Alert = 5 points, Vehicle Alert = 4 points, Fence Alert = 3 points, Blind Spot Alert = 2 points, Tire Pressure Alert = 1 point)
3. The maximum speed limit of the route is 60 km/h
4. Alarm Duration: Directly use the duration value (unit: second; the longer the duration, the higher the risk)

Risk classification criteria:
- 0 < Score ≤ 1: Low risk
- 1 < Score ≤ 3: Medium risk, requiring priority handling
- Score > 3: High risk, requiring immediate handling

搜集汇总

背景与挑战

背景概述

该数据集是云和县公交客运有限公司的公交安全驾驶报警分析数据，包含512条记录，涵盖车牌、报警车速、报警项和风险等级等字段，用于实时监控司机驾驶行为。通过DSM和ADAS系统采集数据，并运用算法计算综合风险得分，评估风险等级，以降低交通事故风险，提升公交安全管理水平。