Enhancing Sustainable Public Transport Through Business Intelligence

1. Introduction

As urban settlements expand, with increased density, strain in terms of environment, and high consumption of energy, efficient, environmentally friendly, and social access networks of transport in smart settlements’ direction through optimized mobility have a growing demand [1]. Through smart interventions in terms of information and communications technology (data and smart infrastructure), smart settlements try to develop efficient, environmentally friendly, and social access networks of transport [2]. Greenhouse gas emissions and congestion in terms of traffic and improvement in living standards in urban life, and alternative use of transportation, become its most important objectives [3].

Public transport occupies a backbone in urban life in an environmentally friendly manner. In smart settlements, smart interventions such as passengers’ real-time information, contactless payments, and smart scheduling integrate with public transport for its improvement in operations [4]. With such development, passengers have real-time information and make efficient trip planning, and commuting through public transport can become a convenient and preferred manner of commuting. Analysis of real-time information plays a key role in regulating urban networks of transportation in smart urban environments. High-tech administration of traffic, smart lights, pricing for congestion, and routing algorithms for optimized routes ease driving and make driving less congested, and in consequence, make transportation efficient and effective [5,6].

Utilization of technology such as Business Intelligence (BI), assists in optimizing operations in public transportation networks. With such technology, transportation providers can evaluate big datasets in real-time, and with it, operational efficiency and asset management can be increased [7]. With BI in public transportation networks can maximize operational efficiency, minimize impact, and effectively utilize a model for sustainable transportation. Integration of technology is a key in developing a cleaner, efficient, and smarter urban driving environment, in enhancing service quality, and in minimizing the footprint of public driving networks [8].

Business Intelligence technology and tools present tools and technology for effective collection, storing, processing, and analysis of information in terms of business processes [9]. Business Intelligence tools, such as cheap and free tools such as WEKA software for machine learning and KNIME software for mining, allow one to implement improvements and modifications, and respond to specific requirements for a specific use. With existing technology, these two tools allow one to implement any improvement one wants and adapt them according to individual requirements.

The following part of the article presents relevant studies of the use of software for machine learning, i.e., WEKA, and software for mining, i.e., KNIME, and it is a starting point for developing a smart tool for supporting innovative processes. With its purpose, the tool will contribute to attaining a Business Intelligence system for supporting companies in taking correct and well-informed decisions.

In an attempt to develop a new Business Intelligence system for managing complexity in transportation, such as forecasting demand for tickets and scheduling coaches and trains, and for scheduling workers’ shifts, the paper [10] is a relevant contribution.The paper [10] optimizes reading and use of a prototype in terms of construction and proposes new methodologies in data mining. It utilizes data in WEKA in an Advanced Manufacturing Analytics platform in revealing hidden trends in terms of construction processes, with increased productivity and efficiency in work in construction. Study [11] takes into consideration analysis of information through techniques in machine learning with use of WEKA, with an objective of finding faults in availability of an aircraft fleet. It estimates the availability of spare tools and formulates an intelligent system for minimizing spare tool expense, with increased efficiency and use of resources. The paper [12] formulates a systemic model for forecasting maintenance expense for highway construction equipment, with discussion of processes involved in information collection, analysis, model development, and information testing. It takes into consideration development and improvement in variety of types of models, with a comparison of seven algorithms through use of software for mining in WEKA. In paper [13], a data mining algorithm for changing maintenance processes in Greek rails is proposed. Algorithms are utilized in a platform in KNIME, in which future faults can be uncovered and grouped effectively, and accuracy in forecasting is assured. Furthermore, article [14] compares the performance of an industrial project for integration of KNIME data mining tools in Enterprise Service Bus (ESB) platform. It concludes that the web service and data mining engine of KNIME can integrate with present information systems and adapt to Industry 4.0, and companies can use information for improvement in processes of a business. Paper [15] addresses the development and use of predictive maintenance technology for farm machines, using analysis of past information for prediction of future failure in machines. Promotion of technology was conducted using free software, i.e., software of KNIME. The article [16] addresses models for improvement in processing documents. In proposed model, information retrieval and extraction of excerpts have been conducted using machine learning techniques. Implementation of model utilized software, i.e., software for KNIME, for processing documents.

Subsequently, the computer programs WEKA and KNIME have become key tools for comparative analysis and supporting sustained development. Article [17] proposes a new model for solid waste management that involves methodologies using P-graph and machine learning approaches supported through WEKA. In this investigation, 160 scenarios emerged, with a conclusion that the best model is that of the J48 algorithm, characterized by its efficiency, less consumption of time, and its adaptability in many sectors. Sustained development in future studies is expected to include consideration of both economic and environmental factors. Article [18], entitled promotes a single, open-source platform for simulations in smart cities with a rich variety of tools for machine learning to drive urban sustainability. In addition, article [19], entitled proposes a model for big data integration through the use of KNIME for supporting sustained development.

The next part of this paper will discuss the scientific bases of Business Intelligence by analyzing the characteristics of data mining and machine learning. At the same time, it outlines the key features of sustainable development along with overcoming the environmental issues of public transport, emphasizing innovative machine learning and data mining technology options with open-source software.

2. Research Context

2.1. Business Intelligence: Overview and Implications

Business Intelligence is the advanced computer technology used to support the discovery of data relevant to businesses, which could include revenues, products sold, costs incurred, sales revenues [20]. Organizations (specialized transportation project production) companies hope BI can be used in the provision of actionable information for better strategic and operational performance [21]. While its core functionality has BI delivering systematic conclusions based upon structured data, this procedure does entail several limitations. The use of structured data very often limits analysis to only one type of “closed” trajectory and not the complete range of dynamic business requirements [22,23]. Sometimes, there will be much time and labor involved in obtaining an overall view, especially in complex and multilevel scenarios. At the initial stage, the raw historic data are located and at the final is the making of the final decisions as shown in Figure 1.

Despite these challenges, BI offers significant advantages. Its most notable strength is its ability to grant near-instant access to data insights that would otherwise demand extensive manual research [24]. This positioning makes BI an indispensable tool for tracking and response towards emerging trends and market transportation projects [25]. The speed and efficiency of BI allows businesses to adapt to decision-making processes, facilitate competitiveness, and adaptability within an increasingly changing marketplace [26,27]. In conclusion, although Business Intelligence has its limitations, its ability to streamline data analysis and deliver timely insights renders it a critical asset for modern organizations seeking to harness the power of data in their strategic pursuit.

2.2. Smart Tools Business Intelligence

2.2.1. Machine Learning Tool – WEKA

WEKA is an open-source software platform for machine learning, developed at the University of Waikato in New Zealand, and is under terms of the GNU General Public License. The software contains a variety of algorithms for use in machine learning for use with structured datasets, and these can be loaded in through files and generated through simple queries in a database. The algorithms enable one to build decision trees, and in this manner, streamline decision processes through predefined default values. In addition, WEKA enables flexible processing workflows for processing personalized information, and when paired with graphical representations of algorithms, proves efficient for predictive maintenance processes [28,29].

2.2.2. Data Mining Tool – KNIME

KNIME was developed in 2004 through a consortium of software developers at the University of Konstanz in Germany. The software is open-source, analytic in purpose, and is placed under the terms of use of the GNU General Public License. As a tool for business intelligence, KNIME possesses a full-fledged development environment and an extendable plugin infrastructure. With the use of the platform offered through KNIME, rapid and efficient processing, transformation, analysis, and visualization of information can be accomplished through its rich feature suite. It can work with big datasets with no restriction in terms of the number of data rows and computation during analysis. KNIME can run under all significant operating platforms, including Linux, Windows, and macOS, through its Java platform base. User-friendly graphical interfaces make it accessible to people with no background in programming. Frameworks for development and architecture in KNIME enable integration with disparate sources of information and allow for creating full workflows, with high-quality output in analysis [30,31].

2.3. Sustainability

Sustainability embodies the concept of satisfying present generations’ requirements in such a manner that future generations can satisfy their requirements in a similar manner [32]. Despite its widespread use and sometimes its simplification to a buzzword, sustainability is an important basis for dealing with worldwide concerns in terms of environment, economy, and society [33].

2.3.1. Definition of Sustainability

The 1987 Bruntland Report brings a broadly acknowledged definition of sustainable development:

“Meeting present and future generations’ needs, not at the expense of future generations’ capacity for satisfying their own needs.” [34].

To a considerable extent, sustainability involves a thorough grasp of interdependence between humanity, the planet, and life-support processes and systems. According to the report, economies’ and society’s welfare depend a lot on living organism and planet processes’ vigor [35,36]

2.3.2. Principles of Sustainability

The key fundamentals, which form the basis of sustainability and must become a part of any system designed to tackle concerns and develop and implement practices for sustainable development, include:

• Environmental integrity: It is about prudent conservation and use of planet processes and natural assets in a manner allowing future generations to access them.
• Economic Balance: It involves developing economies satisfying humans’ wants and requirements in a manner that does not exhaust planet assets.
• Social Equity: It involves providing fair access for groups and people to basic assets and opportunities, therefore allowing them to contribute at a full and effective level in a fair and equitable society [37,38,39].

As shown in Figure 2, all three pillars are equally important and interdependent on each other to achieve sustainable development at a holistic level.

2.3.2.1. Unsustainable Practices and Consequences

Existing consumption trends seen in humanity at present times are actually unsustainable in the current form. In case these trends continue, degradation and exhaustion of planet processes, emerging as a consequence, will become irreparable. In such a case, it will mean:

• Food Insecurity: Degraded lands will not produce enough food provisions.
• Climate Displacement: Climate change will displace millions and destroy livelihoods.
• Resource Conflicts: Inadequacies in such key requirements, including water and arable lands, can ignite discord.
• Biodiversity Loss: Ecosystem degradation can cause extinction of many species, compromising with delicate harmony of overall environmental balance at a global level [40,41].

2.3.2.2. Sustainability in Action

The principle of sustainability must, therefore, be wholistic in its application, using cutting-edge problem-solving approaches and mandating a long-term outlook. Transition to renewable sources of energy, creation of circular economies, conservation of habitats, and establishment of social structures with a view towards equity and resilience are important [48]. Sustainability involves not only environmental factors but is in fact closely tied to humanity’s survival and welfare [43]. By embracing such principles of sustainability, it is then feasible to have a planet in which humans and environment harmoniously coexist and co-thrive together [44].

2.4. Smart Public Transport: Sustainable and Ecological Cities

Public transportation forms an integral part of city planning for smart and sustainable cities, offering a pragmatic and environmentally friendly alternative to private car use, such as bus, trams, and similar ones [45]. Despite numerous challenges, urban mobility programs work towards resolving them, and in consequence, provide equitable and accessible options for everyone, including factors such as overcrowded roads, pollution, and greenhouse emissions [46]. Public transportation’s positive impact towards urban sustainability comes in terms of reduced use of private forms of conveyances. Eliminating such use reduces jams, curtails pollution, and promotes connectivity, and in consequence, enables urban economy growth in a city in question. With ongoing improvement in public transportation, its effectiveness will serve in supporting environment objectives, such as reduced consumption of energy and increased use of renewable sources [47,48]. The anticipated path of public transportation will witness considerable change through integration with cutting-edge technology and environmentally friendly operational processes. Greater operational efficiency, with reduced emissions, will be attained through the use of electric-powered buses, development of smart transportation infrastructure, and real-time analysis of information [49]. Progress in such direction will require coordination between government departments, urban planning departments, and transportation departments through public-private partnerships for strengthening infrastructure and operations of public transportation [50].

Public transportation forms a critical part of a future city with a sustainable urban ecosystem, resolving key social and environment-related concerns. Successful examples of efficient bus networks, such as in Singapore and TransMilenio in Bogotá, illustrate that careful planning and technological advancement form key requirements for developing efficient and ecologically friendly transportation networks [51,52]. Thus, investment in public transportation infrastructure is about to become a key driving force for creating a sustainable, accessible, and resilient urban environment.

3. Problems and Solutions for Urban Transportation Using Smart Tools ΒΙ

Public transportation providers experience significant hurdles when attempting to make their business models profitable. These hurdles originate from the environment, the economy, society, and the field of technology. This chapter discusses these hurdles and illustrates how solution providers can assist through the use of Data Intelligence (BI), WEKA, and KNIME. Both tools can be downloaded for free and utilized for free. This is beneficial for providers, particularly those with limited capital. These solution providers can streamline their processes, reduce their carbon footprint, and make passengers happier, resulting in superior and sustainable mobility. This chapter illustrates through real-life scenarios the benefits data analysis has for urban mobility.

3.1. Problems Facing the Public Transport Organizations

Public transportation providers experience various issues that influence their improvement over the years. These issues influence their efficiency, the environment, and the public. One significant challenge for the environment is the high emission from the majority of the publicly available motor vehicles using fuels from fossils emitting carbon gas [53,54,55,56]. Energy consumption is also an issue since we need to incorporate cleaner energy and energy efficiency like the use of electricity and alternative fuels [57,58,59]. Increased traffic increases the consumption of fuels and emission levels and also decreases the efficiency level of transportation [60,61]. Proper waste handling is also essential, whereby the cars and the infrastructure require structures for handling waste like tires, lubricants, and batteries [62,63]. Economic problems also involve high investment costs for switching over to clean technologies [64]. Switchovers from traditional cars to clean cars are very costly [65]. Having the support and financing for clean growth is essential, but the funds are not necessarily available [66]. Even the operation and upkeep of clean technologies can also involve high expenses and specialized skills [67]. Social barriers comprise the acceptance by the populace of the adoption of new forms of mobility, such as interoperability of public transport [68,69,70]. Accessible public transport is essential for sustainability, where everyone can travel, and the costs remain affordable [71]. Transforming the habits of individuals is also one of the greatest challenges, where rewards and transparent communication need to assist them in adopting the adoption of new mobility [72].

Effective management, study, and implementation of sophisticated Business Intelligence tools have the potential to significantly contribute towards improving the transportation industry, while also encouraging the maximum usage of resources. The following sections describe ways through which intelligent and economical business intelligence tools need to be used for making digital and non-digital changes within the organizations dealing with the provision of transport services.

3.2. Using KNIME and WEKA for Environment Friendly Transportation Solutions for the City

The use of Business Intelligence (BI) tools such as the WEKA machine learning tool and the KNIME data mining tool can significantly help public transport systems and transport companies by solving various issues. Using the WEKA software tool, route control, passenger needs analysis and road analysis can be carried out. This improves the routing process and reduces fuel consumption. The new system will be able to provide better routes to save energy and reduce emissions.

KNIME helps collect and analyze data from various sources such as GPS sensors, databases, and real-time road and weather data. This increases the efficiency of the transportation and also decreases the costs.

In capacity forecasting and forecasting demands, WEKA applies machine learning for forecasting the passengers by day, by time, and by season. This assists the fleets and helps avoid the waste of resources. KNIME, however, analyzes high levels of data from ticket machines, sensors, and portable devices for providing data for optimizing the mode of transport. For energy conservation and emission of less carbon, classification and regression by WEKA determine the cars and routes using the highest levels of fuel, optimizing the mode of transport. KNIME also optimizes sensor data for the consumption of fuel and its environment impact for the support of greener options and emission reduction of CO₂.

WEKA offers predictive abilities for when maintenance is required and for reducing the expenses. These models analyze the deterioration and failures of the parts over the past and recommend the prevention of the failures, thus the cost of the repairs is reduced. Analyzing the work previously performed, including the failures, can avoid sudden breakdowns of the cars, and this is simplified using KNIME. The supply of useful information, via the datamining process, leads to making the right decisions so as to optimize the maintenance as shown in Figure 3 and the goals set case by case.

Analyzing data from passengers, their movements, and their feedback assists the improvement of the passengers’ experience and motivates passengers to travel using public mode. Data from the online networks, online reservations, and the cell phones are merged and analyzed using KNIME, thus providing customized services for the passengers.

In decision-making and policymaking, WEKA facilitates the building of models for forecasting the impact the use of environmentally friendly innovations, such as cars and interoperability of public transport, has on the economy and the returns from them. KNIME analyzes various economic indicators, environment-focused study, and regulations for sustainability to enable informed data-driven decisions. Both KNIME and WEKA make the handling of vast data by the transport sector easier, informed decision-making, and transition towards sustainable development, as shown in the flowchart in Figure 4. These entities can make their processes faster, minimize their carbon print, save resources, and improve the satisfaction of passengers using data mining and machine learning.

4. Analysis and Potential Directions

4.1. Discourse

The application of Business Intelligence (BI) in public transportation is emerging as a key factor in advancing sustainability, improving efficiency, and optimizing urban mobility. The ability to collect, analyze, and utilize vast amounts of data enables transportation organizations to enhance service quality while simultaneously reducing environmental impacts. The integration of advanced analytical tools, including machine learning and artificial data mining, allows transport companies to make better-informed decisions, optimize resource management, and achieve higher levels of operational efficiency. Table 1 below illustrates concrete examples of the impact of business intelligence on public transport.

The adoption of open-source tools such as WEKA and KNIME further enhances the potential of BI in the public transportation sector. These platforms provide transport companies with powerful data analysis capabilities without requiring significant financial investments. By utilizing these tools, organizations can analyze historical and real-time data, predict future demand trends, and implement data-driven strategies to improve operational efficiency. Open-source solutions are particularly beneficial for public transport authorities and organizations with limited financial resources, as they offer a cost-effective approach to implementing BI solutions. Table 2 presents the economic advantages of using open-source software provided free of charge such as WEKA and KNIME.

Additionally, both KNIME and WEKA also promote the cause for environmental sustainability by helping the operators of transport reduce energy consumption and emissions. Organizations can improve the efficiency of fuels, find opportunities for using less energy-consuming forms of transport, and transition towards using environment-friendlier forms of tech like hybrids and electric cars by applying data mining and machine learning processes. Ultimately, the adoption of business intelligence data into the formulation of policies and operating strategies helps ensure that sustainability remains the core emphasis for the improvement of urban mobility solutions.

4.2. Future Directions

To further improve effectiveness, public transport can be made more efficient with the aid of Business Intelligence by following various strategies that are oriented towards the future directions as shown in Table 3. These directions can guide the principles to shape the applications of the sector into the future.

It is clear that deployment of transport with the incorporation of next-generation technologies like AI, IoT, big data, and cloud computing will provide wiser and prudent decision-making capabilities, improve passengers’ travel experiences, and automate major functions to the best levels of performance.

5. Conclusions

The integration of Business Intelligence (BI), Machine Learning (ML), and Data Mining technologies into public transportation systems represents a transformative approach to addressing urban mobility challenges, sustainability, and operational efficiency. By leveraging low-cost open-source tools such as WEKA and KNIME, public transport providers can optimize routes, reduce energy consumption, predict passenger demand, and enhance service quality while minimizing environmental impacts. These technologies enable real-time data analysis, predictive maintenance, and dynamic decision-making, which are critical for developing smarter, more sustainable urban transport networks. Application of platforms such as WEKA and KNIME, operated through an open-source platform, will bestow high-tech analysis capabilities in operators with little financial resources, and in the process, will enable even small operators to access the value that BI can produce.

The future direction of public transportation in future years will be characterized through continued integration of digital technology, such as artificial intelligence, Internet of Things (IoT), and big data analysis, with a view towards increased operational efficiency and comfort for passengers.

In summary, effective use of Business Intelligence, Machine Learning, and Data Mining in public transportation networks creates a path towards smarter, environmentally friendly, and efficient urban mobility platforms. By leveraging such technology metropolitan areas can tackle urbanization-related problems, promote environment-friendliness, and maximize resource efficiency, enhancing citizens’ living standards and supporting development towards a cleaner and environmentally friendly.