Role of Big Data in The Safety of Public Transport and Crime Prevention

Crime prevention in public transport has become one of prime importance. With the advent of technological advancements like GPS and AFC card data, WiFi probe data and more, you can gather valuable resources about public transportation operations. A fairly recent idea is the implementation of big data technology to obtain passenger intelligent controls, passenger analysis, training operation systems and more.

Several factors have been worrisome concerning public operations. The optimisation of operations, increasing revenue and cutting costs are points of hindrance, hence the officials are trying to ensure future success with big data technology. There is less financial leeway in public transportation between customer orientation and cost pressure. This is due to budgetary constraints and subsidy cuts by the German government. However, transportation companies cannot lose sight of their customer’s needs. To focus on high quality and standard services, they are utilising big data technology to cut costs besides analysing historical data to strengthen the customer base and reduce the incidence of crimes.

With regards to public transportation safety, big data is offering multiple solutions to overcome these challenges. Comprehensive real-time incident database, weather forecasts and congestion reports through data analytics, clever algorithms and historical data have enabled remarkable improvements in this segment. Most importantly, information gathering about public transport has helped with crime prevention, therefore ensuring that it is highly safe to travel on roads.

How Does Big Data Work?

Big Data is characterised by the three V’s -

• A large VOLUME of data in a different environment from different sources like IoT

• Wide VARIETY of data to store in extensive systems, in a numeric, traditional database or structured form

• VELOCITY of data generation, collection and processing, data streaming at an unprecedented rate

Big data has now become a label for new modified data sets utilised to inform decisions and solve problems. It has improved policing with the capability to identify patterns and behavioural offences. Consequently, the gathering of real-time information has enabled the officials to make quick and agile decisions in the aspect of crime prevention in public transports.

A recent report by the World Health Organisation mentioned that road accidents claim nearly 1.25 million lives every year, costing the country almost 3% of their GDP to manage the. Today, big data analytics leverage data in the automobile and transportation sector to improve road and vehicle safety. Big data and telematics synergistically play a pivotal role in creating a safe driving environment. Big data analyses data to draw valuable insights while telematics performs the science behind the extraction of vehicular data and data synthesis. The officials place this device on the vehicle’s onboard computer network to track parameters, driver behaviour, maintenance issues etc.

The Emergence of Big Data in Public Transportation

A good example is the Automatic Vehicular Location system which tracks the position of buses and other vehicles to gather a constant stream of information.

Smart fare collection systems can capture travel patterns among transit users. Employee tracking is done to find out the rate of absenteeism, safety incidents, time management etc.

Big Data for Operations Maintenance

Officials are using big data principles for operations optimisation and maintenance. In a recent study, one of the members disclosed how they are bringing about disparate data sources in a single place to better analyse issues related to the state of good repair. For example, systems like AWS are allowing predictive modelling on asset conditions. As a result, they are able to focus on problems like vehicle breakdown and remove them before creating congestions on the road. It is also cost-saving.

Keeping public transportation in focus, the operatives are encouraging the drivers to install different data-gathering tools, like GPS, sensors and cameras. The reason behind this is simple.

The big data engineers heavily benefit from capturing these real-time insights, from which they extract data and combine it together to provide services for operational maintenance. It also enables the telematic-service-providing companies and car insurers to rightfully predict vehicular movement. Big data, therefore, plays a major role in enhancing the operational efficiency of public transport.

A good basis is the path planning algorithm used by the public transport vehicles. The Automatic Vehicle Location (AVL) allow a suitable comparison of different paths available for the public vehicles to use. As the study says, “The algorithm is evaluated on a large-scale tracking survey, collected from GPS data and automatic mode and vehicle detection, obtaining high precision both in terms of coverage (more than 94%) and model estimation (high R2 and reasonable parameters).”

They also evaluate the “size and relevance of a path; the assumed walking distance; trips with transfers; ..... namely representing public transport stages as sequences of vehicles, or lines”. A short and quick transport route, therefore, provides confidence to the people about a safe journey.

With effective operational management of public vehicles, the travel fear of people reduces considerably. Any lack of reassuring safety measures puts women’s lives in danger of criminal victimisation. With proper data accumulation through Big Data technology, vehicular tracking and monitoring, these issues have been addressed significantly. They can therefore rely on public transportation as a safe means of travel, through enhanced punctuality and operational efficiency.

Big Data to Improve Driver Safety

The emergence of Big Data technology and the data surrounding the public driver’s behaviour is utilised to alter vehicular parameters like speed, power, torque. This creates a safer driving zone for all. Furthermore, they use this data to set continuous feedback loops to control the vehicle’s performance. This way, the officials ensure to avert rash driving behaviour. They also check if the drivers are wearing seatbelts etc.

A recent program by the Tennesse Highway Patrol was called (CRASH), which could analyse data related to the weather patterns, locations where crashes are most likely to happen due to some special event etc. This enabled law enforcement to predict the location of places selling more alcohol to determine if there are potentials for a road accident. Once after discovering such locations, highway patrol sent troopers to control the traffic condition of those places. Consequently, they monitored road safety over a large area. According to data, the inception of the big data analysis CRASH program has lowered car accidents by 5 per cent.

Data Analytics to Reduce Road Accidents

The applications integrated with data analytics force the drivers of cars, buses and any other transportation system to develop safety habits. These applications can successfully track metrics like overtaking, driving speed, manoeuvring etc. The driver should undertake corrective actions if they detect any abnormality in driver data. This will inculcate a change in driving habits and prevent severe mishaps from happening. Data analytics can also determine whether the driver is maintaining strict road instructions. Additionally, data analytics also assist in roadway queue management to manage overall highway safety.

Even automated cars like Tesla use big data analytics in combination with machine learning as part of their sense-plan-act-program. The autopilot version takes high volume data capable of predicting the outcome of actions in different scenarios. Tesla is seen as a successful company that pioneers in artificial intelligence with help from big data engineers.

Insights From Big Data for Crime Prevention on Road

While most of us complain that constant camera surveillance takes away privacy, it has a prominent role to play here. Many citizens feel uneasy from this ubiquitous scrutiny, however, it helps the officials spot people committing crimes.

The Chicago Police Department has started applying predictive analysis and machine learning for crime arrests. Sensor influenced cameras combined with IoT and real-time historical data can detect gunshots on public roads. This way, they can effectively pinpoint problem locations where a crime can flourish. HunchLab, a geographic prediction tool, relies on data modelling to identify at-risk areas within the city.

Another application by IBM named IBM i2 Coplink consolidates disparate data like mugshots, arrest records, gang affiliations in a single dashboard for the police from different locations to access information securely.

Conclusion

Accurate implementation of big data, machine learning and artificial intelligence can predict abnormal driver behaviour to minimise road accidents through telematics and tachograph. AI and IoT integrated software tools, computer-aided dispatch, and criminal databases help real-time tracking of raw data, leading to actionable consequences. The goal is to leverage the big data architecture through high standard effectiveness so that the challenges related to public transportation, road safety and crime prevention issues can be eliminated.

FAQ Block

1. What is Big Data Analytics?

It is the use of advanced analytics techniques against a vast and diverse set of structured and or unstructured data. The data can range from terabytes to zettabytes. It is further driven by artificial intelligence, the Internet of Things, social media and more. Consequently, it enables better and faster decision making.

2. Does Big Data help in preventing road accidents and safety?

This helps in improving road safety in varied ways. For example, the state of Tennessee introduced a CRASH program to predict weather conditions and potential accident zones, thus lowering the likelihood of a vehicle crash.

3. Does Big Data facilitate public crime prevention?

Predictive analysis and Big Data play a responsible role in preventing crimes, thus making law enforcement more proactive. In addition, the centralisation of multiple data in a single integrated database enhances security features. One such example is the road surveillance camera, which collects vast data through analysis and uses it to prevent crimes.