Landslide prediction is a critical task for ensuring public safety and preventing economic loss in regions prone to such natural disasters. Traditional models for landslide prediction often lack accuracy and precision because of the intricate interactions between various factors that lead to landslide events. To tackle this issue, we introduce an innovative hybrid approach for landslide prediction that combines Time Series Analysis (TSA), Genetic Algorithm (GA), and Support Vector Machine (SVM). TSA decomposes landslide displacement data into trend, seasonal, and residual components, improving the clarity of the data. GA optimizes the hyperparameters of SVM, ensuring the most effective application of the SVM. Finally, the SVM is trained on detrended data, producing a model capable of accurately predicting future landslides. Our experimental outcomes manifest that the TSA-GA-SVM model we advanced performs far better than the individual TSA and SVM models when it comes to forecasting landslide displacement. The hybrid model achieved a mean absolute error of 0.15 m compared to 0.42 m for TSA and 0.38 m for SVM alone. Sensitivity analysis revealed that increasing GA population size improved model stability, while higher mutation rates led to more variable predictions. The model showed good generalization ability, performing well across different regions and under various geological and hydrological conditions. This research not only advances the state of the art in landslide prediction but also provides a practical tool for authorities to implement in their disaster prevention and management strategies.

As Industry 4.0 continues to transform the manufacturing domain, the focus is shifting towards mass personalization of products, enabling companies to efficiently produce customized goods that meet individual customers’ unique needs and preferences. This requires manufacturing enterprises to be flexible and adaptable with their scheduling processes and manufacturing setup. Flexibility and subsequent realization of personalization of products can be realized by utilizing the notion of a Line-less Assembly System (LAS), which replaces a fixed conveyor system with a system in which the products move between machines, with products being fitted on Autonomous Mobile Robots (AMRs) to transport the products from one machine to another as per their production routing. This necessitates scheduling products as per their production routing on available AMRs to reap the benefits of LAS, which is viewed as a Job Shop Scheduling Problem (JSSP) to maximize resource utilization while adhering to constraints. The novelty of this approach is that, in addition to scheduling products, it also considers the scheduling of AMRs. A mathematical formulation to solve the deterministic JSSP is presented in the current work. The formulation is solved for various inputs using a mathematical solver. In general, JSSPs are NP-hard problems. Subsequently, a meta-heuristic-based Genetic Algorithm (GA) has been constructed to solve the JSSP. The solutions obtained through both GA and mathematical solver are compared, and it was found that GA performs well in computation and optimization efficiencies.

With a decentral and global economy, distributed scheduling problems are getting a lot of attention. This paper addresses a distributed flexible job shop scheduling problem (DFJSP) with minimizing makespan, in which three subproblems, namely operations sequencing, factory selection and machine selection must be determined. To solve the DFJSP, a novel mixed-integer linear programming (MILP) model is first developed, which can solve the small-scaled instances to optimality. Since the NP-hard characteristic of DFJSP, a hybrid algorithm (GA-VNS-CP) of genetic algorithm (GA), variable neighborhood search (VNS) and constraint programming (CP). Specifically, the GA-VNS-CP is divided into two stages. The first stage uses the hybrid meta-heuristic algorithms of GA and VNS (GA-VNS), and the VNS is designed to improve the local search ability of GA. In GA-VNS, the encoding only considers the factory selection and the operations sequencing problems, and the machine selection problem is determined by the decoding rule. Because the solution space may be limited by the decoding rule, the second stage uses the CP to extend the solution and further improve the solution. Numerical experiments based on benchmark instances are conducted to evaluate the effectiveness of the MILP model, VNS, CP and GA-VNS-CP. The experimental results show effectiveness of the MILP model, VNS and CP. Moreover, the GA-VNS-CP algorithm has better performance than traditional algorithms and improves 6 current best solutions for benchmark instances

In this paper, an electric vehicle routing problem with time windows and under travel time uncertainty (U-EVRW) is addressed. The U-EVRW aims to find the optimal proactive routing plan of the electric vehicles under the travel time uncertainty during the route of the vehicles which is rarely studied in the literature. Furthermore, customer time windows, limited loading capacities and limited battery capacities constraints are also incorporated. A new mixed integer programming (MIP) model is formulated for the proposed U-EVRW. In addition to the commercial CPLEX Optimizer version 20.1.0, a modified Clustering Search based Genetic algorithm (MCSGA) is developed as a solution method. Numerical tests are conducted on the one hand to validate the effectiveness of the proposed MCSGA and on the other hand to analyze the impact of travel time uncertainty of the electric vehicle on the solutions quality.

This paper investigates a novel problem concerning material delivery in a matrix manufacturing workshop, specifically the multi-automated guided vehicle (AGV) dispatching problem with unloading setup time (MAGVDUST). The objective of the problem is to minimize transportation costs, including travel costs, time penalty costs, AGV costs, and unloading setup time costs. To solve the MAGVDUST, this paper builds a mixed-integer linear programming model and proposes an improved genetic algorithm (IGA). In the IGA, an improved nearest-neighbor-based heuristic is proposed to generate a high-quality initial solution. Several advanced technologies are developed to balance local exploitation and global exploration of the algorithm, including an optimal solution preservation strategy in the selection process, two well-designed crossovers in the crossover process, and a mutation based on Partially Mapped Crossover strategy in the mutation process. In conclusion, the proposed algorithm has been thoroughly evaluated on 110 instances from an actual electronic factory and has demonstrated its superior performance compared to state-of-the-art algorithms in the existing literature.

Vehicle Routing Problem (VRP) is important in the transportation and logistics industries. Vehicle Routing Problem with Time Window (VRPTW) is a kind of VRP with the additional time windows constraint in the model and is classified as an NP-hard problem. In this study, we proposed Stas crossover in Genetic Algorithm (GA) to solve VRPTW by developing the problem with K-mean clustering. The experiments use the standard Solomon’s benchmark problem instances for VRPTW. The results with K-mean clustering are shown to perform better for minimum distance and average distance than without K-mean clustering. In the case of location and dispersion characteristics of the customer, the paths with K-mean clustering are arranged into groups and are orderly, but the paths without K-mean clustering are disordered. After that, this paper shows the comparison of the crossover operator performance on instances of Solomon benchmark, and appropriate crossover operators are recommended for each type of problem. The results of the proposed algorithm are better than the best-known solutions from the previous studies for some instances. Moreover, our proposed research will serve as a guideline for a real-world case study.

Conveying the products to the customers under optimized circumstances is as crucial for the companies as the production itself. One optimization strategy to consider is transportation with the minimum quantity of vehicles and the selection of courses with the minimum distance between the locations. In other words, it is the examination of the solution to the Vehicle Routing Problem (VRP), particularly the Capacitated VRP (CVRP), which is a more realistic modelization approach. For businesses that perform distribution to customers frequently, such as management work with the coordination of daily distribution, finishing the distribution on time is of great importance. In big cities with complicated roads and many dropping points, this can be achieved by benefiting from the systematic modeling of the CVRP. In this study, the delivery network investigation for one production facility of the Istanbul People's Bread positioned on the Asian side of Istanbul, Türkiye that distributes three times a day will be the focus of interest. The corresponding Asymmetric CVRP (ACVRP) for the facility network and 215 bread-selling buffets with authentic driving distances will be solved with the Genetic Algorithm (GA), and an optimized transportation network will be presented.

The Multiple Traveling Salesman Problem (MTSP) was able to model and solve various theoretical and real-life applications. This problem is one of the many difficult issues that have no perfect solution yet. In this paper, on the one hand genetic algorithms with different combinations of operators and simulated annealing were used to solve the MTSP. On the other hand, the genetic algorithm with the combination of operators that gave the best solutions of the MTSP was hybridized with a Simulated Annealing algorithm. The simulation results showed that the hybrid algorithm significantly outperforms most of the comparable methods in obtaining the best-fitness solutions compared to the other methods in most of the test cases. In addition, by scaling the fitness function according to the amplitude of tours, it was obvious that the non-dominated front obtained by the hybrid algorithm was better than the non-dominated front obtained by the other algorithms.

The multiple travelling salesman problem (MTSP) extends the classical travelling salesman problem (TSP) by involving multiple salesman in the solution. MTSP has found widespread applications in various domains, such as transportation, robotics, and networking. Despite extensive research on MTSP and its variants, there has been limited attention given to the open close multiple travelling salesman problem (OCMTSP) and its variants in the literature. To the best of the author's knowledge, only one study has addressed OCMTSP, introducing an exact algorithm designed for optimal solutions. However, the efficiency of this existing algorithm diminishes for larger instances due to computational complexity. Therefore, there is a crucial need for a high-level metaheuristic to provide optimal/best solutions within a reasonable timeframe. Addressing this gap, this study proposes a first meta-heuristic called multi-chromosome-based Genetic Algorithm (GA) for solving OCMTSP. The effectiveness of the developed algorithm is demonstrated through a comparative study on distinct asymmetric benchmark instances sourced from the TSPLIB dataset. Additionally, results from comprehensive experiments conducted on 90 OCMTSP symmetric instances, generated from the renowned TSPLIB benchmark dataset, highlight the efficiency of the proposed GA in addressing the OCMTSP. Notably, the proposed multi-chromosome-based GA stands out as the top-performing approach in terms of overall performance. Further, solutions to symmetric TSPLIB benchmark instances are also reported, which will be used as a basis for future studies.

The vehicle routing problem is widespread in terms of optimization, which is known as being NP-Hard. In this study, the vehicle routing problem with capacity constraints is solved using cost- and time-efficient metaheuristic methods: an invasive weed optimization algorithm, genetic algorithm, savings algorithm, and hybridized variants. These algorithms are tested using known problem sets in the literature. Twenty-four instances evaluate the performance of algorithms from P and five instances from the CMT data set group. The invasive weed algorithm and its hybrid variant with savings and genetic algorithms are used to determine the best methodology regarding time and cost values. The proposed hybrid approach has found optimal P group problem instances with a 2% difference from the best-known solution on average. Similarly, the CMT group problem is solved with about a 10% difference from the best-known solution on average. That the proposed hybrid solutions have a standard deviation of less than 2% on average from BKS indicates that these approaches are consistent.