The relationship between important achievements in soft computing technology with the transportation and logistics industry in Iran: A review
Subject Areas : Application of soft computing in engineering sciences
1 - Department of Industrial Engineering, Central Tehran Branch, Islamic Azad University, Tehran, Iran
Keywords: Soft Computing, Transportation, Logistics, Digital Transformation, Communications.,
Abstract :
The transportation and logistics industry in Iran plays a pivotal role in the nation's economic development, yet it faces significant challenges, including inefficiencies and high operational costs. This review explores the critical relationship between advancements in soft computing technologies-such as fuzzy logic, neural networks, and genetic algorithms and their transformative impact on this sector. The necessity of this study arises from the urgent need for innovative solutions to enhance decision-making processes, optimize resource allocation, and improve overall service delivery within the Iranian transportation and logistics framework. This review synthesizes existing literature and case studies to highlight the novelty of integrating soft computing techniques in addressing complex logistical challenges. By employing a systematic methodology that includes qualitative analysis of recent advancements and their practical applications, this study identifies key trends and successful implementations within the industry. The findings reveal that soft computing technologies significantly enhance predictive modeling, route optimization, and demand forecasting, leading to improved efficiency and reduced costs. This research underscores the importance of embracing these technologies to foster sustainable growth in Iran's transportation and logistics sector, ultimately contributing to the broader economic landscape.
[1] Heidari, A., Jafari Navimipour, N. and Unal, M., 2022. The history of computing in Iran (Persia)-since the achaemenid empire. Technologies, 10(4), p.94.
[2] Herold, D.M., Ćwiklicki, M., Pilch, K. and Mikl, J., 2021. The emergence and adoption of digitalization in the logistics and supply chain industry: an institutional perspective. Journal of Enterprise Information Management, 34(6), pp.1917-1938.
[3] Wu, Z., Liao, H., Lu, K. and Zavadskas, E.K., 2021. Soft computing techniques and their applications in intelligent industrial control systems: A survey. International Journal of Computers Communications & Control, 16(1), p. 4142.
[4] Kharola, S., Ram, M., Mangla, S.K. and Kazancoglu, Y., 2023. Advances in soft computing applications, 1st Edition, New York. River Publishers.
[5] Jauha, S.K. and Pant, M., 2013. Recent trends in supply chain management: A soft computing approach. In Proceedings of Seventh International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA 2012), 2, pp. 465-478.
[6] Li, P., Xue, R., Shao, S., Zhu, Y. and Liu, Y., 2023. Current state and predicted technological trends in global railway intelligent digital transformation. Railway Sciences, 2(4), pp.397-412.
[7] Oladimeji, D., Gupta, K., Kose, N.A., Gundogan, K., Ge, L. and Liang, F., 2023. Smart transportation: an overview of technologies and applications. Sensors, 23(8), p.3880.
[8] Kalsoom, T., Ahmed, S., Rafi-ul-Shan, P.M., Azmat, M., Akhtar, P., Pervez, Z., Imran, M.A. and Ur-Rehman, M., 2021. Impact of IOT on Manufacturing Industry 4.0: A new triangular systematic review. Sustainability, 13(22), p.12506.
[9] Mashayekhy, Y., Babaei, A., Yuan, X.M. and Xue, A., 2022. Impact of Internet of Things (IoT) on inventory management: A literature survey. Logistics, 6(2), p.33.
[10] https://www.deloitte.com/global/en/our-thinking/insights/topics/digital-transformation/industry-4-0/digital-transformation-in-supply-chain.html
[11] Iliopoulou, C. and Kepaptsoglou, K., 2019. Combining ITS and optimization in public transportation planning: state of the art and future research paths. European Transport Research Review, 11, p. 27.
[12] Najafi, M., Keymanesh, M., Moshrefi, R. and Zefreh, M.M., 2019. Impact of Economic Inputs on Production of Transportation Services in Iran. International Journal of Transportation Engineering, 7(1), pp.77-89.
[13] Sumbal, M.S., Ahmed, W., Shahzeb, H. and Chan, F., 2023. Sustainable Technology Strategies for Transportation and Logistics Challenges: An Implementation Feasibility Study. Sustainability, 15(21), p.15224.
[14] Li, X., 2024. Optimization of logistics flow management through big data analytics for sustainable development and environmental cycles. Soft Computing, 28(3), pp.2701-2717.
[15] https://www2.deloitte.com/us/en/insights/focus/transportation/future-of-transport-industry.html
[16] Digital logistics: Technology race gathers momentum, McKinsey’s Operations Practice, 2023. https://www.mckinsey.com/capabilities/operations/our-insights/digital-logistics-technology-race-gathers-momentum#/auth-download/
%2F~%2Fmedia%2Fmckinsey%2Fbusiness%20functions%2Foperations%2Four%20insights%2Fdigital%20logistics%20technology%20race%20gathers%20momentum%2Fdigital-logistics-technology-race-gathers-momentum_final.pdf%3FshouldIndex%3Dfalse
|
Journal of Optimization in Soft Computing (JOSC) Vol. 2, Issue 2, pp: (36-43), Summer-2024 Journal homepage: https://sanad.iau.ir/journal/josc |
|
The relationship between important achievements in soft computing technology with the transportation and logistics industry in Iran: A review
Ali Shahabi1, *
1. Department of Industrial Engineering, Central Tehran Branch, Islamic Azad University, Tehran.
Article Info |
| Abstract |
Article History: Received: 2024/08/24 Revised: 2024/09/25 Accepted: 2024/09/27
DOI: |
| The transportation and logistics industry in Iran plays a pivotal role in the nation's economic development, yet it faces significant challenges, including inefficiencies and high operational costs. This review explores the critical relationship between advancements in soft computing technologies-such as fuzzy logic, neural networks, and genetic algorithms and their transformative impact on this sector. The necessity of this study arises from the urgent need for innovative solutions to enhance decision-making processes, optimize resource allocation, and improve overall service delivery within the Iranian transportation and logistics framework. This review synthesizes existing literature and case studies to highlight the novelty of integrating soft computing techniques in addressing complex logistical challenges. By employing a systematic methodology that includes qualitative analysis of recent advancements and their practical applications, this study identifies key trends and successful implementations within the industry. The findings reveal that soft computing technologies significantly enhance predictive modeling, route optimization, and demand forecasting, leading to improved efficiency and reduced costs. This research underscores the importance of embracing these technologies to foster sustainable growth in Iran's transportation and logistics sector, ultimately contributing to the broader economic landscape. |
Keywords: Soft Computing; Transportation; Logistics; Digital Transformation; Communications. |
| |
*Corresponding Author’s Email Address: eng_shahabi@yahoo.com |
1. Introduction
The relationship between important achievements in soft computing technology and the transportation and logistics industry in Iran has become a crucial area of study, reflecting a significant evolution in operational efficiency and decision-making capabilities within this sector. Soft computing encompasses methodologies such as fuzzy logic, neural networks, and genetic algorithms, which have proven essential in optimizing logistics processes and enhancing intelligent industrial control systems. This integration has catalyzed substantial advancements in the transportation industry, facilitating digital transformation and improving service delivery across various logistical frameworks [1-3].
Historically, Iran's computing landscape has undergone profound changes over the last few decades, influenced by global technological trends and a growing emphasis on digitalization. The emergence of soft computing techniques has addressed challenges like information uncertainty and complex problem-solving in logistics operations, ultimately reshaping how transportation companies manage supply chains and respond to market demands [4, 5]. As these technologies gain traction, they have enabled improved data utilization, leading to better resource allocation and reduced operational costs [6].
Despite the benefits, the adoption of soft computing technologies is not without challenges. Issues such as data quality, interoperability among systems, and high initial implementation costs present significant hurdles that industry stakeholders must navigate [7, 8]. Moreover, research gaps persist regarding the operational-level integration of these technologies, which limits their full potential in optimizing logistics performance. As the industry moves forward, addressing these challenges will be pivotal in harnessing the capabilities of soft computing to foster a more efficient and sustainable transportation ecosystem in Iran [9, 10].
The ongoing digital transformation within the transportation and logistics industry heralds a promising future, as advancements in soft computing are expected to enhance operational practices and contribute to sustainable development. With an increasing focus on intelligent transportation systems and data analytics, the potential for innovation and growth within this sector is vast, positioning Iran as a key player in the evolution of logistics technology on a global scale [11-13].
Soft computing techniques have garnered significant attention in transportation and logistics due to their ability to address complex optimization problems and uncertainty [14, 15]. These methods, including fuzzy logic, neural networks, and evolutionary computing, offer flexibility and dynamism in supply chain management and tackle challenges in planning and decision-making [15, 16]. Applications of soft computing in maritime logistics, supply chain management, and industrial systems have shown promising results in improving efficiency and effectiveness [14, 17]. These techniques have been employed to enhance customer service levels, reduce operational costs, and maintain profit margins [17]. While soft computing has been widely applied in various aspects of logistics and transportation, some areas, such as customer relationship management and reverse logistics, remain underexplored, presenting opportunities for future research [17].
The present work provides an overview of the significant achievements in soft computing technologies and the necessity of utilizing them in the transportation and logistics industry in Iran. Conducting this research, being the first of its kind, will provide insights for decision-makers in the fields of transportation, logistics, and communications in Iran. The study includes a review of concepts, an examination of key soft computing methods used in the transportation and logistics industry, case studies conducted, the impact of soft computing technology on performance and cost improvement, a discussion of the challenges and limitations ahead, as well as an analysis and prediction of future trends.
2. Historical Context
The evolution of soft computing technologies has significantly impacted the transportation and logistics industry in Iran. Over the past several decades, key historical events and advancements in computing have shaped the industry’s landscape.
2.1. Development of Computing in Iran
Iran's journey into modern computing began with its ancient empires, notably the Achaemenid Empire, which is recognized as one of the earliest civilizations to employ basic forms of calculation and record-keeping [1]. This historical foundation laid the groundwork for more complex computing systems that would emerge later.
2.2. Key Historical Events
The last 60 years have seen transformative developments in the logistics and supply chain sectors, influenced by major technological advancements. A pivotal study by Herold et al. (2021) highlights specific field-configuring events that facilitated the emergence and adoption of digitalization in these industries [2]. These events not only advanced computing methodologies but also provided insights into the evolution of a digitalization logic that has redefined operational frameworks.
2.3. Soft Computing Techniques
Soft computing techniques, including fuzzy logic, neural networks, and genetic algorithms, have emerged as essential tools for enhancing intelligent industrial control systems within the transportation and logistics sectors [3, 4]. These methodologies address the challenges faced in modern industrial environments, such as information acquisition and system optimization, thereby playing a crucial role in the evolution of the logistics landscape in Iran.
2.4. Current Implications
The integration of soft computing solutions into supply chain management has proven beneficial in optimizing decision-making processes and improving efficiency [5]. As the logistics industry continues to evolve, the historical context of computing in Iran reveals a legacy of innovation that underpins current advancements in soft computing technology, ultimately contributing to the industry's growth and development.
3. Key Soft Computing Technologies
Soft computing encompasses a variety of methodologies designed to handle imprecise information and emulate complex human reasoning processes. In the context of the transportation and logistics industry in Iran, several key soft computing technologies have been pivotal in enhancing operational efficiency and decision-making capabilities.
Fuzzy logic is particularly useful in scenarios where information is uncertain or imprecise. It allows for the modeling of complex systems by incorporating linguistic variables and rules. Applications in the industry include fuzzy PI control for weigh belt feeders, which optimize material handling processes and improve accuracy in logistics operations [3]. The capability of fuzzy logic to deal with ambiguity makes it an ideal candidate for real-time decision-making in transportation systems [4].
3.2. Genetic Algorithms
Genetic algorithms (GAs) are optimization techniques inspired by natural selection that are particularly effective for solving complex problems with numerous variables. These algorithms have been applied to optimize logistics operations, including route planning and inventory management, significantly reducing costs and improving efficiency [3]. The integration of GAs with fuzzy systems has also shown promising results in enhancing decision-support mechanisms within logistics frameworks [4].
To provide a simple example, a genetic algorithm is used to optimally solve the following transportation problem in Figure 1. If there is a truck with a capacity of 50 cubic meters, which packages of various sizes can be placed in it to optimize the usable space?
|
Figure 1. Example of Genetic Algorithm applied to transportation problem |
3.3. Neural Computing
Neural computing employs artificial neural networks (ANNs) to learn from data and make predictions or decisions based on patterns. Recent advancements in neural computing have led to improved adaptive control systems in various applications, such as automated fault diagnosis and control in mechanical systems [3]. The adaptability of these systems enhances their utility in dynamic environments typical of transportation and logistics operations in Iran [4].
3.4. Hybrid Approaches
The combination of fuzzy logic, neural networks, and genetic algorithms forms hybrid approaches that leverage the strengths of each technique. For instance, fuzzy neural networks have been utilized to develop robust adaptive control systems for robot manipulators, showcasing their effectiveness in real-world applications such as automated warehousing and transportation systems [3]. This hybridization allows for the development of intelligent systems capable of tackling the multifaceted challenges faced in the transportation and logistics industry.
4. Case Studies
4.1. Digital Transformation in Railways
A significant trend in the railway sector is the integration of digitalization and intelligent technologies, which is pivotal for modernizing operations. This includes advancements in intelligent construction, equipment, and operational aspects. These initiatives are not merely about upgrading existing systems but are crucial for enhancing the safety, efficiency, and overall competitiveness of the railway networks globally [6].
4.2. Challenges and Responses
In recent years, railway systems have faced multiple challenges such as the need for modernization in engineering projects, effective management of intelligent digital railway equipment, and addressing the increasing demand for both passenger and freight transport. To tackle these issues, the shift toward intelligent digital transformation has become essential. This transformation not only aims to elevate the travel experience for passengers but also catalyzes collaborative development within the railway sector on a global scale [6, 7].
4.3. Practical Applications
One illustrative case is the use of a survey conducted in Singapore, which utilized a Fleet Management System platform to monitor the activity of heavy goods vehicles. The study indicated challenges such as unverified stop records and an imbalance in activity reporting. To address this, a predictive model was developed, employing gradient-boosting techniques to classify activity types based on collected data. This integration of technology significantly improved the quality and efficiency of data collection and insights into vehicle movement patterns [7].
4.4. Future Predictions
The future of railway digitization suggests a continued emphasis on intelligent technologies that can enhance various facets of operations, including passenger services and freight logistics. Industry stakeholders are focusing on harnessing these advancements to not only improve service quality but also to facilitate more sustainable and efficient railway systems globally [6].
By leveraging such digital transformations, the railway sector is expected to overcome existing challenges while simultaneously setting a foundation for future innovations.
5. Impact on Efficiency and Cost-Effectiveness
The integration of soft computing technologies in the transportation and logistics industry in Iran has significantly enhanced operational efficiency and cost-effectiveness. By leveraging advancements in digital connectivity and the Internet of Things (IoT), companies have improved data-driven decision-making processes, which are crucial for optimizing production rates according to fluctuating customer demand. This shift in operational strategy allows for real-time adjustments, ensuring that production aligns closely with market needs and reducing inventory holding costs [8, 9].
5.1. Enhanced Data Utilization
The transition towards data-driven planning is pivotal in the optimization of logistics operations. Traditional supply chains often suffer from inefficiencies due to linear information flow, leading to the "bullwhip" effect, where minor fluctuations in demand can create substantial inventory variances further upstream [10]. However, with the application of soft computing methods, stakeholders can access real-time data, facilitating quicker responses to changes and minimizing disruptions across the supply chain. This results in improved service levels and better resource allocation, ultimately driving down operational costs [9-11].
5.2. Cost Considerations
Despite the advantages, the adoption of IoT and other advanced technologies presents challenges, particularly concerning high upfront costs. Manufacturing firms in Iran, similar to their global counterparts, face significant investments for implementing these solutions, which include expenses for systems integration, workforce training, and security measures. Nevertheless, the long-term benefits, such as improved efficiency and reduced operational costs, often outweigh these initial hurdles [8]. For instance, advancements in Radio Frequency Identification tracking have led to greater accuracy in inventory management, thus diminishing instances of stock-outs and excess inventory, which can be financially burdensome [9].
5.3. Strategic Decision-Making
As companies adopt these technologies, they also enhance their strategic decision-making capabilities. The improved visibility across various processes allows businesses to make informed decisions about resource allocation and operational adjustments, fostering a more agile and responsive supply chain environment [10]. By utilizing optimization algorithms that can process vast amounts of data, transportation and logistics firms are better equipped to handle dynamic market conditions, ultimately leading to more cost-effective operations [11].
The strategic decision-making process is shown in the Figure 2.
|
Figure 2. The strategic decision-making process |
6. Challenges and Limitations
The integration of Intelligent Transportation Systems (ITS) in the transportation and logistics industry has introduced several significant challenges and limitations that impact the effectiveness of soft computing technologies in this sector. While ITS data has improved modeling accuracy concerning mobility's spatial and temporal characteristics, the application of optimization techniques remains hindered by various factors, including data quality, operational policies, and computational demands.
6.1. Data Quality Considerations
A primary challenge in leveraging ITS data is ensuring data quality. Many studies have indicated that the integrity and reliability of the data used in modeling can greatly influence the outcomes of research and implementation. Inadequate data quality can stem from privacy concerns and restrictive data-sharing policies adopted by certain transportation operators, limiting the availability of comprehensive datasets for analysis [11, 12]. Moreover, although simulation is frequently used to verify control strategies, such environments often overlook the technical challenges associated with real-time implementations, which can skew results and hinder practical applications [11].
6.2. Operator Data-Sharing Policies
The variation in operators' data-sharing policies poses another barrier. While some entities have adopted a more open approach, fostering ITS-related research, many others maintain restrictive practices that further complicate access to crucial data. This lack of data availability not only stifles research opportunities but also complicates the design and operational planning of public transportation systems, as identified by various studies [11].
6.3. Computational Burden
The computational burden associated with processing and analyzing ITS data is significant. The integration of optimization techniques with large datasets requires considerable computational resources and advanced algorithms, which may not be readily available to all researchers or agencies. This limitation can impede the timely and effective deployment of ITS applications in transportation and logistics, preventing optimal decision-making and strategic planning [11].
6.4. Interoperability Issues
Interoperability among different systems and agencies remains a critical concern. The lack of common standards and specifications for data inputs can lead to inefficiencies and hinder collaboration among various stakeholders in the transportation sector. A cohesive approach to establishing interoperability standards could enhance research and practical applications in ITS, yet achieving this remains a complex task due to existing disparities in technological adoption and infrastructure capabilities [ 11].
6.5. Overall Research Gaps
Lastly, there is a notable gap in the literature addressing design-related and operational-level problems in the context of ITS. While tactical and real-time issues have been explored extensively, the strategic level planning that incorporates broader research insights is still underrepresented [11, 12]. Addressing these research gaps is essential for developing more robust decision-support tools and improving the overall effectiveness of ITS in the transportation and logistics industry.
7. Future Trends
The future of the transportation and logistics industry in Iran is poised for significant transformation, largely driven by advancements in soft computing technologies. As digitalization continues to reshape various sectors, a deeper understanding of how these technologies can be leveraged may provide insights into emerging opportunities and challenges in logistics management [2].
7.1. Digitalization and Sustainability
One of the key trends is the integration of soft computing methods to enhance sustainability in inventory management. Recent studies highlight the growing interest in applying IoT technologies to achieve sustainable practices within the green supply chain. This trend indicates a shift towards more eco-friendly approaches in logistics, driven by the necessity of reducing carbon footprints and improving operational efficiency [9, 13].
7.2. Intelligent Transportation Systems
Moreover, the railway sector in Iran, similar to global trends, is expected to adopt intelligent digital transformation strategies to improve efficiency and safety. This includes optimizing maintenance through AI applications and robotics, which can facilitate a significant reduction in operational costs and increase service reliability. As the industry moves towards more automated systems, the role of human operators may evolve, leading to a workforce that closely collaborates with advanced technologies [6, 18]. Figure 3 shows the components of Intelligent Transportation Systems.
|
Figure 3. Components of Intelligent Transportation Systems |
7.3. Data Utilization and Analytics
The logistics sector is also set to benefit from enhanced data analytics capabilities, fueled by the massive volumes of data generated daily. Transportation companies will increasingly harness big data and machine learning algorithms to optimize routing, manage fleets, and improve overall service delivery. Effective integration of these technologies is crucial for achieving high performance and return on investment, particularly as the complexity of logistics operations continues to grow [19, 20].
7.4. Research and Development Focus
Future research is expected to concentrate on bridging existing gaps in soft computing applications within the logistics field. Areas such as the coordination of product flows, green logistics strategies, and the development of adaptive supply chain systems are likely to gain prominence. By focusing on these aspects, companies can enhance their responsiveness to market demands and environmental considerations [3-5].
8. Conclusion
The exploration of the relationship between advancements in soft computing technology and the transportation and logistics industry in Iran reveals a transformative potential that can significantly enhance operational efficiency and cost-effectiveness. As outlined in the historical context, the evolution of computing in Iran has set the stage for the adoption of innovative methodologies such as fuzzy logic, genetic algorithms, and neural computing. These techniques have proven instrumental in addressing complex logistical challenges, optimizing resource allocation, and improving decision-making processes.
The case studies presented illustrate successful implementations of soft computing technologies, particularly in the context of digital transformation within the railway sector. These examples underscore the capacity of these technologies to not only streamline operations but also to respond dynamically to the evolving demands of the industry. However, while the implications are promising, challenges such as data quality, interoperability, and computational burdens remain critical hurdles that must be addressed to fully realize the benefits of these advancements.
Looking ahead, the integration of intelligent transportation systems and enhanced data utilization will be paramount for driving future innovations in the sector. By embracing digitalization and fostering a culture of data-sharing among operators, the Iranian transportation and logistics industry can position itself for sustainable growth.
In conclusion, this research highlights a clear pathway for leveraging soft computing technologies to overcome existing limitations and seize opportunities for improvement. Continued investment in these areas will not only bolster the efficiency and effectiveness of transportation and logistics operations in Iran but will also contribute to the broader economic landscape, paving the way for a more resilient and competitive industry.
It is suggested that for the continuation of this work, a transportation problem be analyzed in detail using soft computing techniques, and the impact of these methods on performance, execution time, cost optimization, and so on be examined.
References
[1] Heidari, A., Jafari Navimipour, N. and Unal, M., 2022. The history of computing in Iran (Persia)-since the Achaemenid Empire. Technologies, 10(4), p. 94. https://doi.org/10.3390/technologies10040094
[2] Herold, D.M., Ćwiklicki, M., Pilch, K. and Mikl, J., 2021. The emergence and adoption of digitalization in the logistics and supply chain industry: an institutional perspective. Journal of Enterprise Information Management, 34(6), pp.1917-1938. https://doi.org/10.1108/JEIM-09-2020-0382
[3] Wu, Z., Liao, H., Lu, K. and Zavadskas, E.K., 2021. Soft computing techniques and their applications in intelligent industrial control systems: A survey. International Journal of Computers Communications & Control, 16(1), p. 4142. https://etalpykla.vilniustech.lt/handle/123456789/151666
[4] Kharola, S., Ram, M., Mangla, S.K. and Kazancoglu, Y., 2023. Advances in soft computing applications, 1st Edition, New York. River Publishers. https://api.taylorfrancis.com/content/books/mono/download?identifierName=doi&identifierValue=10.1201/9781003425885&type=googlepdf
[5] Jauha, S.K. and Pant, M., 2013. Recent trends in supply chain management: A soft computing approach. In Proceedings of Seventh International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA 2012), 2, pp. 465-478. https://doi.org/10.1007/978-81-322-1041-2_40
[6] Li, P., Xue, R., Shao, S., Zhu, Y. and Liu, Y., 2023. Current state and predicted technological trends in global railway intelligent digital transformation. Railway Sciences, 2(4), pp.397-412. https://doi.org/10.1108/RS-10-2023-0036
[7] Oladimeji, D., Gupta, K., Kose, N.A., Gundogan, K., Ge, L. and Liang, F., 2023. Smart transportation: an overview of technologies and applications. Sensors, 23(8), p.3880. https://doi.org/10.3390/s23083880
[8] Kalsoom, T., Ahmed, S., Rafi-ul-Shan, P.M., Azmat, M., Akhtar, P., Pervez, Z., Imran, M.A. and Ur-Rehman, M., 2021. Impact of IOT on Manufacturing Industry 4.0: A new triangular systematic review. Sustainability, 13(22), p.12506. https://doi.org/10.3390/su132212506
[9] Mashayekhy, Y., Babaei, A., Yuan, X.M. and Xue, A., 2022. Impact of Internet of Things (IoT) on inventory management: A literature survey. Logistics, 6(2), p.33. https://doi.org/10.3390/logistics6020033
[10] Hatami, A., Sasanpour, F., Asadzadeh, H. and van Bodegom, P.M., 2023. Scenario analyses to reach smart sustainability in Tehran. Journal of Urban Management, 12(4), pp. 385-397. https://doi.org/10.1016/j.jum.2023.09.002
[11] Iliopoulou, C. and Kepaptsoglou, K., 2019. Combining ITS and optimization in public transportation planning: state of the art and future research paths. European Transport Research Review, 11, p. 27. https://doi.org/10.1186/s12544-019-0365-5
[12] Najafi, M., Keymanesh, M., Moshrefi, R. and Zefreh, M.M., 2019. Impact of Economic Inputs on Production of Transportation Services in Iran. International Journal of Transportation Engineering, 7(1), pp.77-89. https://doi.org/10.22119/ijte.2018.101785.1371
[13] Sumbal, M.S., Ahmed, W., Shahzeb, H. and Chan, F., 2023. Sustainable Technology Strategies for Transportation and Logistics Challenges: An Implementation Feasibility Study. Sustainability, 15(21), p.15224. https://doi.org/10.3390/su152115224
[14] Expósito-Izquierdo, C., Melián-Batista, B. and Moreno-Vega, J.M., 2018. A review of soft computing techniques in maritime logistics and its related fields. Soft Computing Based Optimization and Decision Models: To Commemorate the 65th Birthday of Professor José Luis" Curro" Verdegay, pp. 1-23. https://doi.org/10.1007/978-3-319-64286-4_1
[15] Brito, J., Castellanos-Nieves, D., Expósito, A. and Moreno, J.A., 2018. Soft computing methods in transport and logistics. Soft Computing Based Optimization and Decision Models: To Commemorate the 65th Birthday of Professor José Luis" Curro" Verdegay, pp. 45-61. https://doi.org/10.1007/978-3-319-64286-4_3
[16] Dote, Y. and Ovaska, S.J., 2001. Industrial applications of soft computing: a review. Proceedings of the IEEE, 89(9), pp. 1243-1265. https://doi.org/10.1109/5.949483
[17] Ko, M., Tiwari, A. and Mehnen, J., 2010. A review of soft computing applications in supply chain management. Applied Soft Computing, 10(3), pp. 661-674. https://doi.org/10.1016/j.asoc.2009.09.004
[18] Li, X., 2024. Optimization of logistics flow management through big data analytics for sustainable development and environmental cycles. Soft Computing, 28(3), pp.2701-2717. https://doi.org/10.1007/s00500-023-09591-x
[19] Yaiprasert, C. and Hidayanto, A.N., 2024. AI-powered ensemble machine learning to optimize cost strategies in logistics business. International Journal of Information Management Data Insights, 4(1), p. 100209. https://doi.org/10.1016/j.jjimei.2023.100209
[20] Torre‐Bastida, A.I., Del Ser, J., Laña, I., Ilardia, M., Bilbao, M.N. and Campos‐Cordobés, S., 2018. Big Data for transportation and mobility: recent advances, trends and challenges. IET Intelligent Transport Systems, 12(8), pp. 742-755. https://doi.org/10.1049/iet-its.2018.5188
Nomenclature | |
GAs | Genetic Algorithms |
ANNs | Artificial Neural Networks |
IoT | Internet of Things |
ITS | Intelligent Transportation Systems |