applsci-logo

Journal Browser

Journal Browser

Data Science and Machine Learning in Logistics and Transport

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Transportation and Future Mobility".

Deadline for manuscript submissions: 10 January 2025 | Viewed by 11064

Special Issue Editors


E-Mail Website
Guest Editor
Department of Industrial Engineering and Management, University of Porto, Porto, Portugal
Interests: data science; interaction design; service design; intelligent transport systems; logistics; sustainable mobility
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Faculdade de Engenharia, Universidade do Porto, 4099-002 Porto, Portugal
Interests: artificial intelligence; data mining; machine learning; pattern recognition; simulation; intelligent transport systems
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Faculdade de Engenharia, Universidade do Porto, Porto, Portugal
Interests: urban transport; optimization; intelligent transport systems; human computer interaction; decision support systems

Special Issue Information

Dear Colleagues,

In recent years, there have been important societal, environmental and economic developments that have posed challenges to the logistics and transport sectors. In terms of logistics, there has been a generalized increase in demand and for faster deliveries, posing challenges to the management of deliveries in urban centers and to the capacity and resilience of supply chains. On the other hand, the transport sector is undergoing important transformations, ranging from changing citizens' mobility habits, increasing offer of multimodal solutions and the emergence of connected and autonomous vehicles.

All of this has been accompanied by a growing digitalization and sensorization of transport and cities that generate large amounts of data on a daily basis. This has led to a paradigm shift where logistics and transport management is increasingly relying on strong data analytics to respond to strategic, tactical and operational planning challenges. For this, data science and machine learning play key roles in extracting meaningful insights, understanding patterns and predicting future trends.

This Special Issue welcomes articles in the areas of data science and machine learning, conveying new advances and developments in theory, modeling, simulation, prediction, testing, case studies, as well as large-scale deployment, with a focus on cutting-edge applications in logistics and transport.

Topics of interest for this Special Issue include, but are not limited to:

  • Behaviours and mobility patterns recognition and classification;
  • Connected and automated multimodal mobility;
  • Innovation in the use of data and machine learning in logistics and transport;
  • Intelligent transport systems;
  • New business models;
  • Innovative hubs;
  • Digitalization in logistics and transport;
  • E-commerce, ticketing and payment systems;
  • Intelligent logistics, transport services and sustainable cities;
  • Automation in urban logistics and transport;
  • Intelligent, inclusive and cooperative logistics and transport;
  • Environmental impacts of intelligent logistics and transport;
  • Safety and security in intelligent logistics and transport;
  • Intelligent logistics and transport planning and policy for recovery and resilience;
  • Simulation in logistics and transport;
  • Solutions of data science and machine learning in logistics and transport.

Dr. Marta Campos Ferreira
Prof. Dr. João Manuel R. S. Tavares
Dr. Teresa Galvão Dias
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • big data
  • data data mining
  • data analytics
  • artificial intelligence
  • deep learning
  • pattern recognition
  • classification
  • simulation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (9 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 392 KiB  
Article
A Machine Learning Approach for Predicting and Mitigating Pallet Collapse during Transport: The Case of the Glass Industry
by Francisco Carvalho, João Manuel R. S. Tavares and Marta Campos Ferreira
Appl. Sci. 2024, 14(18), 8256; https://doi.org/10.3390/app14188256 - 13 Sep 2024
Viewed by 666
Abstract
This study explores the prediction and mitigation of pallet collapse during transportation within the glass packaging industry, employing a machine learning approach to reduce cargo loss and enhance logistics efficiency. Using the CRoss-Industry Standard Process for Data Mining (CRISP-DM) framework, data were systematically [...] Read more.
This study explores the prediction and mitigation of pallet collapse during transportation within the glass packaging industry, employing a machine learning approach to reduce cargo loss and enhance logistics efficiency. Using the CRoss-Industry Standard Process for Data Mining (CRISP-DM) framework, data were systematically collected from a leading glass manufacturer and analysed. A comparative analysis between the Decision Tree and Random Forest machine learning algorithms, evaluated using performance metrics such as F1-score, revealed that the latter is more effective at predicting pallet collapse. This study is pioneering in identifying new critical predictive variables, particularly geometry-related and temperature-related features, which significantly influence the stability of pallets. Based on these findings, several strategies to prevent pallet collapse are proposed, including optimizing pallet stacking patterns, enhancing packaging materials, implementing temperature control measures, and developing more robust handling protocols. These insights demonstrate the utility of machine learning in generating actionable recommendations to optimize supply chain operations and offer a foundation for further academic and practical advancements in cargo handling within the glass industry. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

21 pages, 7061 KiB  
Article
Logistics Transportation Vehicle Supply Forecasting Based on Improved Informer Modeling
by Dudu Guo, Peifan Jiang, Yin Qin, Xue Zhang and Jinquan Zhang
Appl. Sci. 2024, 14(18), 8162; https://doi.org/10.3390/app14188162 - 11 Sep 2024
Viewed by 437
Abstract
This study focuses on the problem of the supply prediction of logistics transportation vehicles in road transportation. Aiming at the problem that the supply data of logistics transportation has the characteristics of long sequential data, numerous influencing factors, and a significant spatiotemporal evolution [...] Read more.
This study focuses on the problem of the supply prediction of logistics transportation vehicles in road transportation. Aiming at the problem that the supply data of logistics transportation has the characteristics of long sequential data, numerous influencing factors, and a significant spatiotemporal evolution law, which leads to the lack of accuracy of supply predictions, this paper proposes a supply prediction method for logistics transportation based on an improved Informer model. Firstly, multidimensional feature engineering is applied to historical supply data to enhance the interpretability of labeled data. Secondly, a spatiotemporal convolutional network is designed to extract the spatiotemporal features of the supply volume. Lastly, a long short-term memory (LSTM) model is introduced to capture the supply volume’s long- and short-term dependencies, and the predicted value is derived through a multilayer perceptron. The experimental results show that mean square error (MSE) is reduced by 73.8%, 79.36%, 82.24%, 78.58%, 77.02%, 53.96%, and 40.38%, and mean absolute error (MAE) is reduced by 52%, 59.5%, 60.36%, 57.52%, 53.9%, 31.21%, and 36.58%, respectively, when compared to the auto-regressive integrated moving average (ARIMA), support vector regression (SVR), LSTM, gated recurrent units (GRUs), a back propagation neural network (BPNN), and Informer and InformerStack single models; compared with the ARIMA + BPNN, ARIMA + GRU and ARIMA + LSTM integrated models, the MSE is reduced by 74.88%, 71.56%, and 74.07%, respectively, and the MAE is reduced by 51.31%, 50%, and 52.02%; it effectively reduces the supply prediction error and improves the prediction accuracy. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

15 pages, 1550 KiB  
Article
Secure and Privacy-Protected Bioinformation Implementation in Air Passenger Transport Based on DLT
by Yuhan Chen, Mingmei Lyu, Ho Yin Kan, Mei Pou Chan, Wei Ke and Giovanni Pau
Appl. Sci. 2024, 14(15), 6426; https://doi.org/10.3390/app14156426 - 23 Jul 2024
Viewed by 735
Abstract
Aviation information systems are a key component in ensuring efficient and smooth air transport operations. In this regard, the transfer of passenger information between parties is of paramount importance. With the continuous improvement of biometrics technology, this kind of individual identification that can [...] Read more.
Aviation information systems are a key component in ensuring efficient and smooth air transport operations. In this regard, the transfer of passenger information between parties is of paramount importance. With the continuous improvement of biometrics technology, this kind of individual identification that can provide accurate and unforgeable identification is widely used in various fields. This research presents the significance and effective application scenarios of facial recognition in biometrics in air transport operations. Due to the characteristics of aviation information systems, Distributed Ledger Technology (DLT) is used in this study for secure and private transmission of facial recognition information. Distributed systems can give a transparent and secure platform to multiple parties to access sensitive passenger data. This study uses the Corda framework as the DLT that supports CorDapp development. Based on the above techniques, this study proposes two feasible application scenarios. One is a baggage match detection system to prevent misplaced baggage, and the other is an iAPIS system that transmits passenger information in real-time communication between airlines and border control agencies. This article details how to apply the research in these two scenarios, as well as the benefits and implications of the applications. Finally, this article presents an outlook for future development and feasible directions for improvement. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

16 pages, 6644 KiB  
Article
Proposal of a Transport Planning Model for the Removal of Quarry Stone Using a Simulation
by Janka Saderova, Lubomir Ambrisko, Daniela Marasova and Patricia Muchova
Appl. Sci. 2024, 14(12), 5130; https://doi.org/10.3390/app14125130 - 12 Jun 2024
Viewed by 814
Abstract
This article describes a transport planning model which applies a simulation to support decision-making in quarry operations. The analysis of the transport system was used as input for creating the model and the subsequent research. There are five loading points in the quarry [...] Read more.
This article describes a transport planning model which applies a simulation to support decision-making in quarry operations. The analysis of the transport system was used as input for creating the model and the subsequent research. There are five loading points in the quarry from which, according to the plan, the quarry stone is transported to the crusher, where it proceeds for further processing. The required daily capacity of the downstream technological line is 3800 t/day. Based on the analysis, it was found that it was impossible to fulfill this requirement from the two loading points which were the furthest from the unloading point. For this reason, two simulation models of the transport system were created. The first simulation model is a transport system (loading, removal and dumping of quarry stone) from one loading point. Simulation experiments were performed on this model for all loading points. The findings from the analysis confirmed the results of the simulation experiments. Subsequently, a model of the combined quarry stone removal from two loading points was proposed. The model was designed for two variants of dividing the work shift into two work sections. In the model, which had a tabular form, the combinations of loading points and values of the minimum number of unloaded cars for stone removal were suitable to ensure its necessary daily capacity. The last part of this research was expanding the original model with an additional loading point. Several experiments were performed on this model. The aim of these experiments was to verify the combinations of loading points presented in the proposed model and the combinations of unsatisfactory loading points. Based on the research results, the transport planning model and simulation models are suitable additional tools for the decision-making process in removing quarry stone. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

21 pages, 5638 KiB  
Article
Investigating the Nonlinear Effect of Built Environment Factors on Metro Station-Level Ridership under Optimal Pedestrian Catchment Areas via the Machine Learning Method
by Zhenbao Wang, Shihao Li, Yongjin Li, Dong Liu, Shuyue Liu and Ning Chen
Appl. Sci. 2023, 13(22), 12210; https://doi.org/10.3390/app132212210 - 10 Nov 2023
Cited by 1 | Viewed by 1488
Abstract
Exploring the built environment factor’s impact on metro ridership can help develop metro station area planning strategies. This is in order to compensate for the shortcomings of previous studies, which mostly used all uniform pedestrian catchment areas (PCA) around metro stations. Beijing was [...] Read more.
Exploring the built environment factor’s impact on metro ridership can help develop metro station area planning strategies. This is in order to compensate for the shortcomings of previous studies, which mostly used all uniform pedestrian catchment areas (PCA) around metro stations. Beijing was divided into two zones and 12 built environment explanatory variables were selected as independent variables based on the “7D” dimension of the built environment. The boarding ridership during the morning peak hours was used as the dependent variable. Nineteen PCA radii from 200 to 2000 m were assumed. The optimal PCA of metro stations for each zone was determined by using the eXtreme Gradient Boosting (XGBoost) model with the objective of minimizing the Mean Absolute Percentage Error (MAPE). The nonlinear impact of the built environment factor of each zone on metro ridership is analyzed under the optimal PCA of metro stations. The study results show that (1) the optimal PCAs of metro stations inside the 4th Ring Road and outside the 4th Ring Road are the circular buffer zones with a radius of 800 m and 1300 m, respectively. (2) There is a nonlinear influence of the built environment factor on metro ridership, with strong threshold effects and spatial heterogeneity. The PCA results can be used for the built environment’s zoning of metro stations. The XGBoost model and the nonlinear impact results provide significant implications for the practice of station-level ridership forecasting and integrating TOD development and built environment renewal. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

11 pages, 6091 KiB  
Article
Optimizing Ambulance Allocation in Dynamic Urban Environments: A Historic Data-Driven Approach
by Seongho Kang and Taesu Cheong
Appl. Sci. 2023, 13(21), 11671; https://doi.org/10.3390/app132111671 - 25 Oct 2023
Viewed by 1603
Abstract
In this study, we present a methodology to solve the multi-period ambulance relocation problem based on historical data. We present a methodology to convert historical data in latitude–longitude coordinates into cell-based network data. Then, we propose a mixed-integer programming model that utilizes the [...] Read more.
In this study, we present a methodology to solve the multi-period ambulance relocation problem based on historical data. We present a methodology to convert historical data in latitude–longitude coordinates into cell-based network data. Then, we propose a mixed-integer programming model that utilizes the converted data for the concomitant problem. Patient incidence is highly uncertain. Rather than simply covering historical demand, we propose a methodology that allows ambulances to reach as many locations as possible at any given time within a limited amount of time, the golden time. We experimented with real data from Seoul, South Korea, and show that the proposed mathematical model can derive an efficient ambulance operation policy with fewer ambulances. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

21 pages, 3719 KiB  
Article
Investigating Highway–Rail Grade Crossing Inventory Data Quality’s Role in Crash Model Estimation and Crash Prediction
by Muhammad Umer Farooq and Aemal J. Khattak
Appl. Sci. 2023, 13(20), 11537; https://doi.org/10.3390/app132011537 - 21 Oct 2023
Cited by 3 | Viewed by 1541
Abstract
The highway–rail grade crossings (HRGCs) crash frequency models used in the US are based on the Federal Railroad Administration’s (FRA) database for highway–rail crossing inventory. Inaccuracies or missing values within this database directly impact the estimated parameters of the crash models and subsequent [...] Read more.
The highway–rail grade crossings (HRGCs) crash frequency models used in the US are based on the Federal Railroad Administration’s (FRA) database for highway–rail crossing inventory. Inaccuracies or missing values within this database directly impact the estimated parameters of the crash models and subsequent crash predictions. Utilizing a set of 560 HRGCs in Nebraska, this research demonstrates variations in crash predictions estimated by the FRA’s 2020 Accident Prediction (AP) model under two scenarios: firstly, employing the unchanged, original FRA HRGCs inventory dataset as the input, and secondly, utilizing a field-validated inventory dataset for the same 560 HRGCs as input to the FRA’s 2020 Accident Prediction (AP) model. The findings indicated a significant statistical disparity in the predictions made with the two input datasets. Furthermore, two new Zero-inflated Negative Binomial (ZINB) models were estimated by employing 5-year reported HRGCs crashes and the two inventory datasets for the 560 HRGCs. These models facilitated the comparison of model parameter estimates and estimated marginal values. The results indicated that errors and missing values in the original FRA HRGCs inventory dataset resulted in crash predictions that statistically differed from those made using the more accurate and complete (validated in the field) HRGCs inventory dataset. Furthermore, the crash prediction model estimated upon the corrected inventory data demonstrated enhanced prediction performance, as measured by the statistical fitness criteria. The findings emphasize the importance of collecting complete and accurate inventory data when developing HRGCs crash frequency models. This will enhance models’ precision, improve their predictive capabilities to aid in better resource allocation, and ultimately reduce HRGCs crashes. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

16 pages, 34558 KiB  
Article
Using Connected Vehicle Data to Evaluate National Trip Trends
by Jairaj Desai, Jijo K. Mathew, Justin Anthony Mahlberg, Howell Li and Darcy M. Bullock
Appl. Sci. 2023, 13(18), 10228; https://doi.org/10.3390/app131810228 - 12 Sep 2023
Cited by 1 | Viewed by 1264
Abstract
The National Household Travel Survey (NHTS), conducted by the Federal Highway Administration, has historically been used for documenting personal mobility trends. Current techniques using surveys to collect this data are labor-intensive and difficult to scale. Emerging connected vehicle (CV) data can provide an [...] Read more.
The National Household Travel Survey (NHTS), conducted by the Federal Highway Administration, has historically been used for documenting personal mobility trends. Current techniques using surveys to collect this data are labor-intensive and difficult to scale. Emerging connected vehicle (CV) data can provide an alternative data source to potentially provide a more scalable method to measure the temporal and spatial usage of passenger vehicles in near real-time. With an impending shift in the automobile industry towards alternative fuel vehicles (AFV), agile monitoring of trip trends is important to help guide state and national investments in AFV infrastructure. This study presents methodologies and visualizations summarizing observed trip characteristics using a sample of more than 500 billion CV records and nearly 1 billion CV trips for December 2022 in the United States. The analysis found very close agreement between trip lengths for internal combustion engine vehicles (ICEV) for CVs and those reported by the 2017 NHTS. Mean trip lengths and trip durations from CVs and NHTS for ICEVs are within 7.8% and 6.6% of each other. The 85th percentile comparison was similarly close, within 0.7% and 8.3%. A comparison of trip trends among states for ICEVs and AFVs as well as US census places and temporal trends for a selection of states, including Indiana, Texas, Wyoming, and California, is provided. The paper concludes that CV data is an important source to monitor trip characteristics across ICEVs and AFVs in near real-time, which will be particularly important to track during the anticipated change to AFVs. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

18 pages, 630 KiB  
Article
Experimental Study on the Risk Preference Characteristics of Members in Supply Chain Emergencies
by Yulei Gu, Wenqiang Chen and Haiping Liu
Appl. Sci. 2023, 13(14), 8188; https://doi.org/10.3390/app13148188 - 14 Jul 2023
Viewed by 1127
Abstract
Since risk preference affects the behavior of decision makers, the study of its characteristics and impact on decision-making contributes to good planning for emergency coordination. The consistency of a member’s risk preferences in the conventional risk field and emergencies of a supply chain [...] Read more.
Since risk preference affects the behavior of decision makers, the study of its characteristics and impact on decision-making contributes to good planning for emergency coordination. The consistency of a member’s risk preferences in the conventional risk field and emergencies of a supply chain was analyzed by applying the prospect theory and adapting the domain-specific risk-taking (DOSPERT) scale. The influence of time pressure on the risk preferences and decision-making behaviors of members was studied in the emergency field and its sub-emergencies of a supply chain. The conclusions were drawn based on the empirical study. First, the risk preference could be measured in terms of conventional risk and emergencies. Second, the members tended to be risk averse with no time pressure, and the degree of risk aversion was weakened with time pressure, which had the greatest effect in the natural disaster event. Third, even though the change in risk preference had a consistency regarding the four types of sub-events of supply chain emergencies, it was inconsistent regarding the conventional risks and emergencies. With the evolution trend of risk preference demonstrated and the relationship between preference and time pressure revealed, this study may provide a decision-making reference for the formulation of a supply chain emergency coordination scheme. Full article
(This article belongs to the Special Issue Data Science and Machine Learning in Logistics and Transport)
Show Figures

Figure 1

Back to TopTop