Transportation Algorithm Research Articles

A UAV perspective based lightweight target detection and tracking algorithm for intelligent transportation

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP and NGCTrack-based target detection and tracking algorithm to address these issues. Firstly, the performance of detecting small targets in occluded scenes is enhanced by adding a MODConv to the small-target detection head and increasing its size; In addition, excessive deletion of prediction boxes is prevented by utilizing LSKAttention mechanism to adaptively adjust the target sensing field at the downsampling stage and combining it with the Soft-NMS strategy. Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. At the target tracking stage, the so-called NGCTrack in our algorithm replaces IOU with GIOU and employs a modified NSA Kalman filter to adjust the state-space aspect ratio for width prediction. Finally, the camera adjustment mechanism was introduced to improve the precision and consistency of tracking. The experimental results show that, compared to YOLOv8, the YOLO-LMP model improves map50 and map50:95 metrics by 10.3 and 12.2%, respectively and the number of parameters is decreased by 47.7%. After combined it with the improved NGCTrack, the number of IDSW reduced by 73.6% compared to the ByteTrack method, while the MOTA and IDF1 increase by 5.2 and 9.8%, respectively.

Queuing‐based energy‐efficient processing algorithm for smart transportation through V2V communication

SummaryApplications of intelligent systems installed in vehicles require substantial computational processing for various tasks. These intensive computations result in high energy consumption and power demands within vehicles. Computational offloading based on Vehicle‐to‐Vehicle (V2V) communication in vehicular fog computing (VFC) has been proposed as a promising solution to enhance energy efficiency in transportation applications. In this paper, the primary objective is addressing this concern by identifying the optimal nearby vehicle that minimizes energy consumption for the offloading and execution of computational tasks. Therefore, a decision‐making and intelligent task offloading mechanism based on queueing theory is proposed. By modeling the problem environment based on queueing theory and modeling the behavior of distributed tasks with discrete‐time Markov chain, the proposed solution can predict the future behavior of vehicles in selecting the most energy‐efficient processing node. Therefore, this paper investigates three energy decision parameters based on queueing theory extracted from the Markov model to enhance the performance of the proposed algorithm. Experimental results demonstrate that the computational energy parameter achieves the most significant improvement. The proposed algorithm outperforms previous methods, improving energy‐efficient system performance by 6.25% and 2.67%, and reducing delivery failure rate by 6.52% and 2.72%. It also decreases overall transportation system processing energy consumption by 0.05% for 100–500 vehicle arrival rates, resulting in an average total processing energy consumption of 0.48%.

Embedded technique-based formation control of multiple wheeled mobile robots with application to cooperative transportation

The cooperative transportation problem for multiple wheeled mobile robots (WMRs) via formation control is investigated in this paper. A formation control algorithm based on an embedded technique is proposed for cooperative transportation of a shared object using n-WMRs. Instead of relying on the conventional design philosophy directly based on formation errors, the proposed algorithm is divided into two parts by considering the communication topology and WMRs’ dynamics “separately”. The first part involves a distributed signal generator that generates desired trajectories for the WMRs based on their initial positions, the formation vector, and the desired trajectory of the object. The second part consists of tracking controllers to enable the WMRs to track their desired trajectories. The proposed algorithm is distributed and differs from the existing cooperative transportation algorithms, as it eliminates the requirement for all WMRs to know the object’s position. Moreover, it exhibits remarkable compatibility and features a concise modular design. With the proposed algorithm, WMRs achieve formation in finite time. Theoretical proof supports the effectiveness of the proposed algorithm, which is further validated through several conducted experiments.

The content optimization of supplementary cementitious materials in coral sand-seawater cement mortar: A focus on mechanical properties and transportation costs

This study examines how supplementary cementitious materials (SCMs) such as fly ash (FA), blast furnace slag (BFS), and metakaolin (MK) affect the mechanical properties and transportation costs of coral sand-seawater cement mortar (CSSC). The Dinger-Funk equation was used to obtain the most densely packed design and preparation of coral sand and cementitious materials. The mechanical properties of CSSC were assessed utilizing the RMT testing apparatus. A thorough examination of the mechanical properties and transportation costs of CSSC was undertaken using the principle of value engineering and the effectiveness coefficient approach. Research results show that BFS10 has outstanding mechanical qualities in the binary cementitious system. Within the ternary cementitious system, the mechanical qualities typically exceed those of the binary system, with FA15BFS15 demonstrating the highest performance. The best appropriate mix ratio is FA15BFS15, as determined by a thorough examination and cost-benefit analysis. This ratio offers temporal sensitivity and maximized transit capacity. The SVR model is highly proficient in forecasting the compressive strength of CSSC, showcasing accurate prediction and data interpretation abilities. The research findings provide practical evidence for optimizing the proportion of CSSC in calcium sulfoaluminate cement, considering transportation expenses and algorithm prediction needs.

APPLICATION OF TRANSPORTATION MODEL TO SOLVE TANKERS’ – ROUTING PROBLEM

The problem of selecting minimum cost routes for tankers in distributing petroleum products and satisfying customers’ requirement without scarcity in Nigeria remains a huge challenge to major marketers in the oil industries. The cost of transporting petroleum products from sources to destinations matters a lot to oil marketers because of the direct impact it has on their profits. The means of distributing petroleum products from refineries to depots or filling stations are tankers’ routing and pipelines. In this research, we extended some existing tankers’-routing models in literature which use a discrete integer programming approach to determine efficient and effective distribution of petroleum products. Consequently, we developed a new transportation linear programming algorithm to determine minimum cost routes in the delivery of petroleum product from their supply centers (refinery) to demand centers (filling stations). The significance of the application we adopted in this research lies in the modified distribution approach to tackle the complexity involved when transportation problems are formulated as linear programming problem having several variables and constraints. In this research, we formulate a new version of transportation model of tankers’ routing with the aim of reducing the cost of petroleum products delivery. The proposed transportation linear programming model was applied to a numerical example alongside other existing transportation algorithms. It is observed that, the new algorithm produced approximately the same total cost obtained by using other existing algorithms

A Knowledge-Driven Cooperative Coevolutionary Algorithm for Integrated Distributed Production and Transportation Scheduling Problem

A Knowledge-Driven Cooperative Coevolutionary Algorithm for Integrated Distributed Production and Transportation Scheduling Problem

Source-Guided Target Feature Reconstruction for Cross-Domain Classification and Detection.

Existing cross-domain classification and detection methods usually apply a consistency constraint between the target sample and its self-augmentation for unsupervised learning without considering the essential source knowledge. In this paper, we propose a Source-guided Target Feature Reconstruction (STFR) module for cross-domain visual tasks, which applies source visual words to reconstruct the target features. Since the reconstructed target features contain the source knowledge, they can be treated as a bridge to connect the source and target domains. Therefore, using them for consistency learning can enhance the target representation and reduce the domain bias. Technically, source visual words are selected and updated according to the source feature distribution, and applied to reconstruct the given target feature via a weighted combination strategy. After that, consistency constraints are built between the reconstructed and original target features for domain alignment. Furthermore, STFR is connected with the optimal transportation algorithm theoretically, which explains the rationality of the proposed module. Extensive experiments on nine benchmarks and two cross-domain visual tasks prove the effectiveness of the proposed STFR module, e.g., 1) cross-domain image classification: obtaining average accuracy of 91.0%, 73.9%, and 87.4% on Office-31, Office-Home, and VisDA-2017, respectively; 2) cross-domain object detection: obtaining mAP of 44.50% on Cityscapes → Foggy Cityscapes, AP on car of 78.10% on Cityscapes → KITTI, MR -2 of 8.63%, 12.27%, 22.10%, and 40.58% on COCOPersons → Caltech, CityPersons → Caltech, COCOPersons → CityPersons, and Caltech → CityPersons, respectively.

AGV dispatching and bidirectional conflict-free routing problem in automated container terminal

Automated guided vehicles (AGVs) are automated devices that replace internal trucks in container terminals for horizontal container transportation. Compared to internal trucks, AGV has the special characteristic of bidirectional transportation. This characteristic makes AGV change the transport direction without turning around, significantly saving the transport space and time taken up by vehicle transport. However, few studies focus on the bidirectional transportation mode in the AGV scheduling problem to improve the overall efficiency of the automated container terminal (ACT). This study aims at the AGV dispatching and bidirectional conflict-free routing problem. A bi-level mixed integer programming model is proposed, which fully considers equipment coordination, bidirectional conflict-free routing, and import and export container tasks. The bi-level differential evolution algorithm based on the dynamic routing approach is developed to minimize the completion time of all tasks. A series of numerical experiments are conducted to validate the performance of the proposed bidirectional transportation mode and algorithm. The result shows that the efficiency of the bidirectional transportation mode of AGVs is more suitable in the actual ACT operation scenario, and the proposed algorithm can find a better solution within a reasonable amount of time.

A discrete-time distributed optimization algorithm for cooperative transportation of multi-robot system

Multi-robot cooperation is a typical application of multi-robot system, which has strong potential applications in many special occasions. However, few scholars have considered cooperative optimization transportation from the perspective of optimization. This paper investigates the cooperative transportation optimization problem for multiple mobile robots with kinematically redundant manipulators. First, a discrete-time distributed optimization algorithm with fixed step size is proposed to achieve linear convergence. Second, by introducing a rotation variable into the optimization problem, the joint angular velocity of manipulator and the velocity of moving platform change more smoothly. Third, a virtual leader-follower transport strategy is used in this paper to improve the stability of the multi-robot system. In the physical experiment, the trajectory of each end-effector matches the expected trajectory, and the center trajectory of the transport object almost coincides with the virtual leader trajectory with acceptable error. Moreover, the simulation and physical example are provided to demonstrate the effectiveness of the proposed algorithm.

Synthesis and optimization of energy integrated advanced distillation sequences

This paper explores the basis on which reliable screening of distillation sequences for energy-efficient separation of zeotropic multicomponent mixtures can be carried out. A case study for the separation of natural gas liquids is used to demonstrate the approach. To solve this generic problem, a screening algorithm has been developed using optimization of a superstructure for sequence synthesis using shortcut models, in conjunction with a transportation algorithm for the synthesis of the heat integration arrangement. Different approaches for the inclusion of heat integration are explored and compared. The best few designs from this screening are then evaluated using rigorous simulation. It has been found that separation problems of the type explored can be screened reliably using shortcut distillation models in conjunction with the synthesis of heat exchanger network designs. Non-integrated designs using thermally coupled complex columns show much better performance than the corresponding designs using simple columns. However, once heat integration is included the difference between designs using complex columns and simple columns narrows significantly.

To Use an Ant Colony Technique to Solve a Crispy Type Bi- and Tri-Objective Transportation Problem

Transportation problem (TP) aims to reduce the entire transportation cost of moving resources from various supply hubs to various demand hubs. However, in real-life situations, all organizations want to achieve numerous objectives while making transportation of goods. The degree of deterioration may vary depending on the mode, route, and time of transport. In some cases, the multiobjective could be used to reduce the use of a scarce resource, such as energy. As a result, the proposed approach was discovered to be an algorithm that improves bi- and triobjective TP techniques. This is an innovative way for solving the new bi- and triobjective transportation algorithm using a modified ant colony optimization (ACO) algorithm. According to the literature, various strategies have been developed in the past to tackle the multiobjective transportation problem (MOTP). The MOTP is solved using goal programming, fuzzy programming, interactive solution algorithms, and other techniques. These strategies are occasionally good or bad in achieving better results in a reasonable amount of time. The heuristic technique used in this work is the improved ACO algorithm, which is based on the ant colony algorithm and has been found to provide solutions with a reasonable degree of satisfaction for two and three objective TPs. When the findings are compared, the solution achieved using the proposed method has delivered the best performance and provides a case study to show the new strategy. Received: 19 September 2022 | Revised: 28 December 2022 | Accepted: 19 January 2023 Conflicts of Interest The author declares that he has no conflicts of interest to this work.

Transportation Algorithm: Awareness and Usage among Production, Operations and Logistics Managers in Rivers State, Nigeria

This study explored the level of awareness and use of transportation algorithms among Production, Operations and Logistics Managers in Rivers State, Nigeria. The study employed a survey-based quasi-experimental research design. Thirty manufacturing and logics enterprises in the Trans-Amadi Industrial Area of Rivers were surveyed using a structured questionnaire. Copies of the questionnaire were administered to 53 managers. A total of 41 valid responses were collected were used for data analysis. The research used means to gauge the degree of awareness and usage. According to the findings, very few managers have ever heard of transportation algorithms. Many managers are aware of transportation algorithms but have never used them. Furthermore, an average number of production and operations managers use transportation algorithms only occasionally, while the majority of them do not use transportation algorithms on a regular basis. This implies that while managers are cognizant of transportation algorithms, they are hesitant to use them. As a result, the research suggests that manufacturing, operations, and logistics companies raise consciousness about the benefits of transportation algorithms through education initiatives and the formation of communities of practise. Firms should also educate managers on the use of transportation algorithms and make it obligatory whenever they move products from origin to destination. This is, as to the best of the researcher’s knowledge, the first study on the degree of awareness and usage of Transportation Algorithms among Production, Operations, and Logistics Managers in Rivers State, Nigeria.

The solution to the Profit maximization transportation problem using new transportation algorithm

Any engineering system requires engineers to make numerous managerial and technological decisions during the design, building, and maintenance phases. All such decisions aim to either maximize the desired benefit or minimize the amount of effort needed. There is no solitary approach that can effectively address all optimization problems. As a result, number of optimization techniques have been created to address various optimization problems. Transportation problem (TP) formulation is the most significant programing applications in optimization which is attached to everyday life and used in industries under logistics. This study proposed a new algorithm to obtain a basic feasible solution (BFS) for the maximization TP. The approach outlined in this study yields an initial solution that is close to or optimal in most scenarios. A variety of numerical examples are used to demonstrate the new technique. The proposed technique is effective for analyzing balanced or unbalanced transportation problems with maximization objective function.

Towards Sim2Real Transfer of Autonomy Algorithms using AutoDRIVE Ecosystem

The engineering community currently encounters significant challenges in the development of intelligent transportation algorithms that can be transferred from simulation to reality with minimal effort. This can be achieved by robustifying the algorithms using domain adaptation methods and/or by adopting cutting-edge tools that help support this objective seamlessly. This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem. In this paper, we extensively explore the modeling and simulation aspects of the ecosystem and substantiate its efficacy by demonstrating the successful transition of two candidate autonomy algorithms from simulation to reality to help support our claims: (i) autonomous parking using probabilistic robotics approach; (ii) behavioral cloning using deep imitation learning. The outcomes of these case studies further strengthen the credibility of AutoDRIVE as an invaluable tool for advancing the state-of-the-art in autonomous driving technology.

Optimal locations and flow allocations for aggregation hubs in supply chain networks of perishable products

Establishment of aggregation hubs in a supply chain network (SCN) is typically a facility location-allocation (FLA) decision, which is known to be a NP-hard optimization problem. Considering the flow of heterogeneous perishable products, like fresh produce, with different spoilage rates, further increases the complexity of such a problem. This is due to the effect of transportation time and conditions, services provided in the hub, and hub proximity to supply sources, on the quality and quantity of products eventually reaching the demand destinations, and hence on the location-allocation decision. In this paper, this problem is formulated as a mixed integer linear programming (MILP) model that considers a number of problem characteristics simultaneously for the first time, to minimize the transportation, spoilage, processing, and capacity-based hub establishment costs. Due to its complexity, two hybrid algorithms that combine a meta-heuristic with a perishability-modified transportation algorithm, are proposed to solve the problem. The algorithms are based on binary particle swarm optimization (BPSO) and simulated annealing (SA). Taguchi analysis is used to tune the significant parameters of both algorithms considering different problem sizes. Computational analysis is further conducted to evaluate and compare the performances of the algorithms using randomly generated test instances and exact solutions obtained using CPLEX. Results show that while both algorithms are capable of obtaining optimum solutions for most instances, the hybrid BPSO slightly outperforms the hybrid SA in terms of consistency and solution time.

A decision aid algorithm for long-haul parcel transportation based on hierarchical network structure

With the explosion of e-commerce, optimising parcel transportation has become increasingly important. We study the long-haul stage of parcel transportation which takes place between sorting centres and delivery depots and is performed on a two-level hierarchical network. In our case study, we describe the application framework of this industrial problem faced by a French postal company: There are two vehicle types that must be balanced over the network on a daily basis, and there are two possible sorting points for each parcel, which allows a better consolidation of parcels. These industrial constraints are formalised in the Long-Haul Parcel Transportation Problem (LHPTP). We present a Mixed Integer Linear Program (MILP) and a hierarchical algorithm with aggregation of demands which uses the MILP as a subroutine. We perform numerical experiments on large-size datasets provided by a postal company, which consist of approximately 2500 demands on a network of 225 sites. These tests enable the tuning of certain parameters resulting in a tailored heuristic for the LHPTP. Our algorithm can serve as a decision aid tool for transportation managers to build daily transportation plans, modeled on solutions produced given daily demand forecasts and can also be used to improve the network design.

IoT-Based Waste Management System in Formal and Informal Public Areas in Mecca.

Urban areas worldwide are in the race to become smarter, and the Kingdom of Saudi Arabia (KSA) is no exception. Many of these have envisaged a chance to establish devoted municipal access networks to assist all kinds of city administration and preserve services needing data connectivity. Organizations unanimously concentrate on sustainability issues with key features of general trends, particularly the combination of the 3Rs (reduce waste, reuse and recycle resources). This paper demonstrates how the incorporation of the Internet of Things (IoT) with data access networks, geographic information systems and combinatorial optimization can contribute to enhancing cities’ administration systems. A waste-gathering approach based on supplying smart bins is introduced by using an IoT prototype embedded with sensors, which can read and convey bin volume data over the Internet. However, from another perspective, the population and residents’ attitudes directly affect the control of the waste management system. The conventional waste collection system does not cover all areas in the city. It works based on a planned scheme that is implemented by the authorized organization focused on specific popular and formal areas. The conventional system cannot observe a real-time update of the bin status to recognize whether the waste level condition is ‘full,’ ‘not full,’ or ‘empty.’ This paper uses IoT in the container and trucks that secure the overflow and separation of waste. Waste source locations and population density influence the volume of waste generation, especially waste food, as it has the highest amount of waste generation. The open public area and the small space location problems are solved by proposing different truck sizes based on the waste type. Each container is used for one type of waste, such as food, plastic and others, and uses the optimization algorithm to calculate and find the optimal route toward the full waste container. In this work, the situations in KSA are evaluated, and relevant aspects are explored. Issues relating to the sustainability of organic waste management are conceptually analyzed. A genetic-based optimization algorithm for waste collection transportation enhances the performance of waste-gathering truck management. The selected routes based on the volume status and free spaces of the smart bins are the most effective through those obtainable towards the urgent smart bin targets. The proposed system outperforms other systems by reducing the number of locations and smart bins that have to be visited by 46% for all waste types, whereas the conventional and existing systems have to visit all locations every day, resulting in high cost and consumption time.

A 2-Phase Method for Solving Transportation Problems with Prohibited Routes

The Transportation Problem (TP) is a mathematical optimization technique which regulates the flow of items along routes by adopting an optimum guiding principle to the total shipping cost. However, instances including road hazards, traffic regulations, road construction and unexpected floods sometimes arise in transportation to ban shipments via certain routes. In formulating the TPs, potential prohibited routes are assigned a large penalty cost, M, to prevent their presence in the model solution. The arbitrary usage of the big M as a remedy for this interdiction does not go well with a good solution. In this paper, a two-phase method is proposed to solve a TP with prohibited routes. The first phase is formulated as an All-Pairs Least Cost Problem (APLCP) which assigns respectively a non-discretionary penalty cost M*ij <= M to each of n prohibited routes present using the Floyd¢s method. At phase two, the new penalty values are substituted into the original problem respectively and the resulting model is solved using the transportation algorithm. The results show that, setting this modified penalty cost ( M*) logically presents a good solution. Therefore, the discretionary usage of the M <= ∞ is not a guarantee for good model solutions. The modified cost M*<= M so attained in the sample model, is relatively less than the Big M ( <= ∞) and gives a good solution which makes the method reliable.

Exploring Potential Applications of Quantum Computing in Transportation Modelling

The idea that quantum effects could be harnessed to allow faster computation was first proposed by Feynman. As of 2020 we appear to have achieved ‘quantum supremacy’, that is, a quantum computer that performs a given task faster than its classical counterpart. This paper examines some possibilities opened up by potential future application of quantum computing to transportation simulation and planning. To date, no such research was found to exist, therefore we begin with an introduction to quantum computing for the programmers of transport models. We discuss existing quantum computing research relevant to transportation, finding developments in network analysis, shortest path computation, multi-objective routing, optimization and calibration – of which the latter three appear to offer the greater promise in future research. Two examples are developed in greater detail, (1) an application of Grover’s quantum algorithm for extracting the mean, which has general applicability towards summarizing distributions which are expensive to compute classically, is applied to an assignment or betweenness model - quantum speedup is elusive in the general case but achievable when trading speed for accuracy for limited outputs; (2) quantum optimization is applied to an activity-based model, giving a theoretically quadratic speedup. Recent developments notwithstanding, implementation of quantum transportation algorithms will for the foreseeable future remain a challenge due to space overheads imposed by the requirement for reversible computation.

Real-Time Intelligent Automatic Transportation Safety Based on Big Data Management

The purposes are to analyze the safety and real-time performance of intelligent transportation under big data and solve urban transportation safety problems. The existing problems of complex traffic data collection and single factor analysis are analyzed. Guangzhou target road section and its historical traffic flow are taken as the data source, the big data analytics (BDA) platform is constructed after preprocessing, and then the deep belief network (DBN) is introduced to build the intelligent transportation model based on BDA. Finally, the model is simulated to analyze its performance. The results reveal that the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) of the proposed algorithm are 4.42%, 6.21%, and 8.03%, respectively compared to Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Neuro fuzzy c-means model (FCM), Deep Neural Network (DNN), and neural network (NN). The mean absolute error (MAE) and mean absolute percentage error (MAPE) are 4.42%, 6.21% and 8.03% respectively. The prediction accuracy is significantly better than that of other algorithms. The analysis of Accuracy, Precision, Recall and F1 suggests that the safety prediction accuracy of the proposed algorithm can reach up to 88.57%, which is at least 3.19% higher than that of other algorithms. Meantime, the proposed algorithm can effectively inhibit the spread of congestion, and achieve the effect of timely evacuation for traffic congestion. Regarding the data transmission performance, the delay is less than 40ms and the packet loss rate is less than 0.1, which is significantly better than other model algorithms in real-time performance. Hence, the constructed intelligent transportation algorithm based on BDA has high precision and excellent congestion evacuation performance, which can provide an experimental basis for constructing intelligent and safe transportation in the future.