Road traffic accidents claim more than 1.25 million lives a year, which costs most countries about 3% of their GDP and remains the leading cause of death of people between the ages of 15 and 29, a report by World Health Organization (WHO) claims.
The WHO has undertaken a mighty initiative to halve the number of deaths and injuries from road traffic crashes by 2020. This goal seems achievable with massive advancements in automotive technology and big data.
Today, one of the biggest use cases of big data and advanced analytics in the automobile and transport industry is to leverage data to improve the safety of vehicles and on the road. And this use case is also being quickly adopted by industries that extensively employ drivers – waste management, fire safety, etc.
Big data and Telematics synergistically play an important role in creating a safe driving environment. While Big Data involves the analysis of data to draw insights, telematics is the science behind extracting vehicular data and synthesizing insights from them. Telematics devices which are employed in a vehicle’s onboard computer network, have been extensively used to track vehicle parameters, maintenance issues, and driver behaviors.
Data captured on driver’s behavior can be used to alter and optimize vehicle parameters like speed, power, and torque and create safe driving conditions. One of the earliest inventions to control vehicular performance were governors, that controlled the speed of the engine by altering fuel injection to the engines. A similar effect can be achieved through digital means by using data to set up a continuous feedback loop that controls the vehicle’s performance. This is essential to prevent drivers from speeding, avert rash driving behavior and ensure drivers wear seat belts.
Predictive analytics can be used to identify potential crash location and areas prone to accidents. This is done by gathering data on crashes that detail the location, cause and time of accidents.
In 2013, a program to predict road accidents was launched in Tennessee, where algorithms were developed to predict areas of fatal accidents by analyzing data from historic crash reports and traffic citations. The results saw a 33% drop in crash response time by the highway patrol between 2012 and 2016. The response time was reduced from 37 minutes to 25 minutes and fatalities dropped by 3%.
Another successful implementation of a crash prediction solution was done for a UK based waste management company by Acuvate.
Acuvate helps a large waste management company leverage data and machine learning to improve the safety of drivers.
Our client, UK’s second-largest integrated waste management and recycling company wanted to implement a machine learning solution to predict the probability of drivers having incidents by integrating telematics and tachograph infringement data.
The client’s executive team wanted to improve the safety of drivers by reducing the number of incidents and in turn reduce the payout of the insurance. In addition, an overall solution to predict the probability of incidents and their causes well beforehand was to be formulated as well.
This solution would enable them to train their drivers better on reducing infringements and improve their driving style.
Acuvate implemented a machine learning solution to predict the probability of drivers having incidents by integrating telematics and tachograph infringement data with a plan to integrate weather data in the next phase.
The machine learning solution helped identify the probability of drivers with a high risk of having an incident and the factors based on which it would happen so that the drivers could get safety training for the same.
This resulted in reduced no of accidents, increased safety of drivers and reduced insurance payout.
Infrastructure has paramount importance is ensuring the safety of drivers and pedestrians as well. Big data is being used along with telematics to control the timing of signals to achieve well-coordinated and smooth traffic flow that can reduce the risk of accidents and fatalities at junctions. Telematics is used to synthesize insights on traffic conditions in the surrounding and accident-prone areas by capturing details from vehicles like braking pattern, speed, location, the direction of motion and driver’s responses to varying conditions.
This data is useful in providing insights to government officials in charge of infrastructure planning to make critical decisions on investing in improving infrastructure and driving conditions.
Big Data is a key driver in improving the safety of autonomous cars. Tesla, one of the biggest manufacturers of autonomous cars, primarily uses big data in their self-driven cars to make vehicular decisions. Tesla’s self-driven cars use machine learning fueled by high volumes of data to predict the most feasible and appropriate action the autopilot is going to make in any given scenario.
Data is also used to generate highly data-dense maps that provide every minute detail like the average increase of traffic speed on the route and locations of hazards that cautions the autopilot to make smart and safe decisions.
With the number of road traffic mishaps rising, there is an urgent need to address this issue and big data is emerging as a powerful technology. Along with the loss of human life, the monetary losses of accidents are also very high. Car crashes have a huge impact on the U.S. economy, costing around $871 billion per year. Significant results have already been achieved by leveraging big data for the effective functioning of automobiles and improving drivers’ performance. And the prognosis seems promising in achieving safer driving environments and smarter vehicles that can make our lives safer on the road.
If you’d like to learn more about this topic, please feel free to get in touch with one of our big data and AI experts for a personalized consultation. You may also be interested in exploring our business intelligence and advanced analytics solutions.