Search

This research focuses on the development of a novel artificial multiple intelligence system (AMIS), which is more flexible and effective than existing techniques for determining vegetable crop land allocation. Eight intelligence boxes (IBs) have been newly designed to serve as AMIS improvement tools presented in this study. Furthermore, a novel formula has been developed to efficiently select the appropriate IB for various types of problems. The developed method will be incorporated into a vegetable land allocation decision support system. The decision-making of the planning about land allocation for crops, including what to grow and what is in demand during specific periods, was performed while considering important factors such as production yield, crop planting and harvesting time, vegetable price fluctuations, and plant incompatibility, leading to a sustainable production system and achieving the highest prices and annual income. Moreover, the developed vegetable crop land allocation models yield the similarity of the average profit per area, so farmers could plan their crops accordingly. To solve the problem, a mathematical model was proposed to solve a small-sized problem, while a novel metaheuristic called the Artificial Multiple Intelligence System (AMIS) was applied to solve larger-sized problems. The computational results revealed that AMIS outperformed all other traditional methods used for comparison in this research. The solution of AMIS was higher in quality than traditional methods such as Differential Evolution (DE), Multi-Agent Simulated Quenching (MASQ), and Genetic Algorithm (GA) by 21.78, 16.38, and 22.79%, respectively. [ABSTRACT FROM AUTHOR]

Multi-depot vehicle routing with precedence constraints and selective backhauling, along with practical challenges such as outsourcing, demand splitting, and flexible pickup and delivery formats, is a common issue in the animal feed industry. However, few studies address demand splitting and flexible pickup constraints. The industry struggles with inadequate management, leading to difficulties in efficiently utilizing limited vehicles for both raw material pickup and product delivery. This inefficiency results in higher transportation costs, including subcontractor vehicle expenses. This study proposes the Extended Adaptive Grey Wolf Optimizer to minimize total transportation costs by incorporating essential factors such as multi-depots, outsourcing services, optimization of split delivery and pickup operations, precedence constraints, and selective backhauling. The results show a remarkable 97.6% improvement toward optimality, representing a significant enhancement of 38.1% improvement over current practice. The findings emphasize the benefits to the industry of adopting proper route sequencing and utilizing subcontractor vehicles. [ABSTRACT FROM AUTHOR]

This paper presents the novel method variable neighbourhood strategy adaptive search (VaNSAS) for solving the special case of assembly line balancing problems type 2 (SALBP-2S), which considers a limitation of a multi-skill worker. The objective is to minimize the cycle time while considering the limited number of types of machine in a particular workstation. VaNSAS is composed of two steps, as follows: (1) generating a set of tracks and (2) performing the track touring process (TTP). During TTP the tracks select and use a black box with neighborhood strategy in order to improve the solution obtained from step (1). Three modified neighborhood strategies are designed to be used as the black boxes: (1) modified differential evolution algorithm (MDE), (2) large neighborhood search (LNS) and (3) shortest processing time-swap (SPT-SWAP). The proposed method has been tested with two datasets which are (1) 128 standard test instances of SALBP-2 and (2) 21 random datasets of SALBP-2S. The computational result of the first dataset show that VaNSAS outperforms the best known method (iterative beam search (IBS)) and all other standard methods. VaNSAS can find 98.4% optimal solution out of all test instances while IBS can find 95.3% optimal solution. MDE, LNS and SPT-SWAP can find optimal solutions at 85.9%, 83.6% and 82.8% respectively. In the second group of test instances, we found that VaNSAS can find 100% of the minimum solution among all methods while MDE, LNS and SPT-SWAP can find 76.19%, 61.90% and 52.38% of the minimum solution. [ABSTRACT FROM AUTHOR]

Smart cities need energy-efficient and low-emission transportation for people and goods. Most studies focus on sustainable urban-transportation systems for passengers. Freight transportation in cities has increased significantly during the COVID-19 pandemic, leading to greenhouse gases emissions and negative externalities, such as traffic congestion. The purpose of this paper is to identify through a systematic literature review which innovations (hardware and software) applied by logistics service providers (LSPs) in sustainable urban freight (SUF) are suitable to support the transition to energy-efficient smart cities. We propose to classify the existing innovations in last-mile delivery for SUF into categories: (1) urban freight consolidation and/or trans-shipment; (2) the Consumer as a Service Provider (CaaSP); (3) choice of transportation modes. We introduce the concept of CaaSP as an innovative solution in last-mile delivery (LMD), where customers take over some transport operations with the use of smart technologies, and thus reduce the energy demand. We consider the modes of transportation, such as: drones, autonomous delivery robots, autonomous vehicles, cargo bikes (including e-cargo bikes, e-tricycles), electric vehicles (mainly vans), and combined passenger-and-cargo transportation rapid-transit systems. From the analyzed dataset, we find that energy-efficiency in smart cities can be improved by the consolidation of parcels in micro-depots, parcel lockers, and mobile depots. We analyze smart technologies (the Internet of things, big data, artificial intelligence, and digital twins), which enable energy efficiency by reducing the energy demand (fuel) of SUF, due to better operational planning and infrastructure sharing by logistics service providers. We propose a new IEE matrix as an actionable tool for the classification of innovations applied by LSPs in SUF, according to the level of their interconnectivity and energy efficiency. Additionally, this paper contributes to the theory by exploring possible future research directions for SUF in energy-efficient smart cities. [ABSTRACT FROM AUTHOR]

This study focused on analyzing planning and scheduling services in the tourism industry. Because dealing with these issues necessitates consideration of several important factors and stakeholders in the tourism business, it is challenging to operate resources efficiently. The purpose of this research is to propose a novel approach that allows maximizing the profits of tourism-related service sectors while considering many real-life constraints, such as sequence-dependent travel time, tourist time windows, points of interest, and specific destination constraints. We test our mathematical model for solving first small-scale problems and then metaheuristics proposed for finding a solution for real-life size problems. Moreover, sensitivity analysis was used to analyze the case study's worthiness when the total cost and the revenue factor were changed. A real case study from Thailand's Khon Kaen and Kanchanaburi provinces were used to verify the proposed models. The results indicate that the proposed models can be applied to investment decisions and strategy development. Furthermore, the outputs of the proposed models (i.e., the mathematical and metaheuristics models) can be employed to enhance the sustainability of other supply chains. [ABSTRACT FROM AUTHOR]

This paper focuses on the dynamic workforce scheduling and routing problem for the maintenance work of harvesters in a sugarcane harvesting operation. Technician teams categorized as mechanical, hydraulic, and electrical teams are assumed to have different skills at different levels to perform services. The jobs are skill-constrained and have time windows. During a working day, a repair request from a sugarcane harvester may arrive, and as time passes, the harvester's position may shift to other sugarcane fields. We formulated this problem as a multi-visit and multi-period dynamic workforce scheduling and routing problem (MMDWSRP) and our study is the first to address the workforce scheduling and routing problem (WSRP). A mixed-integer programming formulation and a hybrid particle swarm and whale optimization algorithm (HPSWOA) were firstly developed to solve the problem, with the objective of minimizing the total cost, including technician labor cost, penalty for late service, overtime, travel, and subcontracting costs. The HPSWOA was developed for route planning and maintenance work for each mechanical harvester to be provided by technician teams. The proposed algorithm (HPSWOA) was validated against Lingo computational software using numerical experiments in respect of static problems. It was also tested against the current practice, the traditional whale optimization algorithm (WOA), and traditional particle swarm optimization (PSO) in respect of dynamic problems. The computational results show that the HPSWOA yielded a solution with significantly better quality. The HPSWO was also tested against the traditional genetic algorithm (GA), bat algorithm (BA), WOA, and PSO to solve the well-known CEC 2017 benchmark functions. The computational results show that the HPSWOA achieved more superior performance in most cases compared to the GA, BA, WOA, and PSO algorithms. [ABSTRACT FROM AUTHOR]

Outbound logistics is a crucial field of logistics management. This study considers a planning distribution for the poultry industry in Thailand. The goal of the study is to minimize the transportation cost for the multi-depot vehicle-routing problem (MDVRP). A novel enhanced differential evolution algorithm (RI-DE) is developed based on a new re-initialization mutation formula and a local search function. A mixed-integer programming formulation is presented in order to measure the performance of a heuristic with GA, PSO, and DE for small-sized instances. For large-sized instances, RI-DE is compared to the traditional DE algorithm for solving the MDVRP using published benchmark instances. The results demonstrate that RI-DE obtained a near-optimal solution of 99.03% and outperformed the traditional DE algorithm with a 2.53% relative improvement, not only in terms of solution performance, but also in terms of computational time. [ABSTRACT FROM AUTHOR]

This study presents a novel approach for chambermaid scheduling that integrates data and information flows through mobile applications and a technique called variable neighborhood strategy adaptive search (VaNSAS). VaNSAS employs two simple heuristics, moving network method (MNM) and simple neighborhood search routine (SNSR), along with a simplified differential evolution (SDE) to create schedules. The study demonstrates the effectiveness of the proposed approach, which outperforms traditional manual methods. The use of VaNSAS results in an average improvement of 184.39% in finding better solutions, a reduction in scheduling time by 175.78%, an enhancement in load balancing among chambermaids by 94.25%, and a productivity increase by 50%. The results contribute to improving overall efficiency in the hotel business by facilitating workforce management and demand uncertainties, reducing workload, enabling control of work duration, and enhancing customer satisfaction by allowing customers to better manage their daily schedules. The integration of data and information flows with VaNSAS for chambermaid scheduling has the potential to revolutionize the hospitality sector. In order to facilitate decision-making for the allocation and scheduling of chambermaids, an Internet of Things integrated chambermaid allocation and scheduling software is adopted, which provides a more efficient approach. [ABSTRACT FROM AUTHOR]

This research aims to develop decision making on how to provide employees with a transportation service that is fast, cost effective and timely. This work is different from previous research in that it integrates the bus stop determination, bus assignment and the bus route design sub-problems of an employee transportation service for a large-scale company. The objective of this article is to minimize total travelling costs and the total rental costs of the heterogeneous fleet capacitated vehicles. A mathematical model is applied to solve for small-size problems. Additionally, for large-size problems, five modified differential evolution (MDE) algorithms are developed to solve the three sub-problems simultaneously. New rules used in the mutation process of the MDE algorithms and an advanced design of the encoding and decoding method are presented in this article. The results demonstrate that the MDE is an efficient transportation management system for any organization. [ABSTRACT FROM AUTHOR]

This research focuses on the development of an artificial multiple intelligence system (AMIS) for solving multi-visit scheduling and routing of multi-heterogeneous resources. The proposed method has been developed as a decision-making tool for solving mechanical sugarcane harvest operations which have been replacing the manual harvesting system with the sugarcane field burning. The mechanical sugarcane harvesting system is a fresh one with a high potential reduction of CO2 emission. Two resources which are fuel service staff teams and technician teams were considered to support the mechanical harvester operations in order to improve the harvesters’ productivity and stability of its sugarcane supply by minimizing the downtime or waiting time of harvesters. Based on this approach, not only the sugar production is efficient, but also the harvesting which is the inbound activity is fuel-efficient. This problem was formulated as the allocation and scheduling of multi-Heterogeneous Resources with consideration of transportation for both resources and service operations. Sugarcane harvesters which get services from the workforce are geographically scattered in each time period. There are various technicians and fuel service staff with different skills giving services to the harvesters. The workforce allocation (WFAllcn) and the sequences and routing (WFSeqRoute) sub-problems were modeled as the integrating problem with the objective function to maximize the sugarcane harvested by all harvesters. To solve the problem, the Artificial Multiple Intelligence System (AMIS), which was developed with new intelligence box selection rules, is firstly developed. Using this approach, allocation and scheduling, and routing of technicians and fuel service staff in sugarcane mechanical harvest operations is very efficient. [ABSTRACT FROM AUTHOR]

This study aims to create a precise skin cancer classification system (SC-CS) able to distinguish various skin cancer types. Targeted categories include melanoma, vascular lesions, melanocytic nevus, cutaneous fibromas, benign keratosis, and different carcinomas and skin moles. The system employs image segmentation and convolutional neural network (CNN) algorithms within a double artificial multiple intelligence system (AMIS) ensemble model, optimizing results weighting for superior solution quality. Evaluation of the SC-CS involved assessing metrics like accuracy, precision, AUC, and F1-score, and gathering feedback from 31 volunteers, including dermatologists, medical professionals and other medical staff with expertise in skin cancer diagnosis. The system accurately classified varied skin cancer types using HAM10000 and malignant vs. benign datasets, chosen for their broad representation and research utility. With over 99.4% accuracy, it surpassed state-of-the-art models by 2.1% for larger and 15.7% for smaller sizes. The high system usability scale (SUS) score of 96.85% signals strong user satisfaction and recommendation potential. High data security ensured patient privacy, with no access to personal information. Uploaded data and images are promptly deleted after processing. The system aids dermatologists in accurate skin cancer diagnosis, integrating into workflows with resource requirements. Performance varies with image quality, dataset diversity, and population-specific variations. [ABSTRACT FROM AUTHOR]

Highlights • The scheduling of equipment under a sharing resource system is first studied. • The ALNS metaheuristics employing the idea of DE is developed to solve the problem. • The new destroy and repair methods have been developed as unique and effective. Abstract This paper presents the ALNS metaheuristics, employing the idea of DE to solve the mechanical harvester assignment and routing problem with time windows (HARPTW) to maximize the total area serviced by a mechanical harvester under a sharing infield resource system. The effective ALNS is designed to solve large-scale problems integrating the mechanical harvester assignment problem (HAP) and the mechanical harvester routing problem (HRP). The newly developed destroy and repair methods are unique and effective. Additionally, four new formulas have been developed to calculate the probability to accept the worse solution using linear and parabola functions instead of the exponential function that is used mostly in the literature. The numerical results show that the parabola function, which uses the information about the solution quality, outperforms all other proposed heuristics. This demonstrates that the proposed heuristics are very efficient and are not only useful for reducing the infield operations costs of small growers, but also for efficient management of the inbound logistics equipment and machinery of the sugarcane supply system. [ABSTRACT FROM AUTHOR]

This paper presents algorithms based on differential evolution (DE) to solve the generalized assignment problem (GAP) with the objective to minimize the assignment cost under the limitation of the agent capacity. Three local search techniques: shifting, exchange, and k -variable move algorithms are added to the DE algorithm in order to improve the solutions. Eight DE-based algorithms are presented, each of which uses DE with a different combination of local search techniques. The experiments are carried out using published standard instances from the literature. The best proposed algorithm using shifting and k -variable move as the local search (DE-SK) techniques was used to compare its performance with those of Bee algorithm (BEE) and Tabu search algorithm (TABU). The computational results revealed that the BEE and DE-SK are not significantly different while the DE-SK outperforms the TABU algorithm. However, even though the statistical test shows that DE-SK is not significantly different compared with the BEE algorithm, the DE-SK is able to obtain more optimal solutions (87.5%) compared to the BEE algorithm that can obtain only 12.5% optimal solutions. This is because the DE-SK is designed to enhance the search capability by improving the diversification using the DE's operators and the k -variable moves added to the DE can improve the intensification. Hence, the proposed algorithms, especially the DE-SK, can be used to solve various practical cases of GAP and other combinatorial optimization problems by enhancing the solution quality, while still maintaining fast computational time. [ABSTRACT FROM AUTHOR]

This article proposes the differential evolution algorithm (DE) and the modified differential evolution algorithm (DE-C) to solve a simple assembly line balancing problem type 1 (SALBP-1) and SALBP-1 when the maximum number of machine types in a workstation is considered (SALBP-1M). The proposed algorithms are tested and compared with existing effective heuristics using various sets of test instances found in the literature. The computational results show that the proposed heuristics is one of the best methods, compared with the other approaches. [ABSTRACT FROM AUTHOR]

This paper addresses a problem of the two-stage reentrant flexible flow shop (RFFS) with blocking constraint ( FFS|2-stage,rcrc,block|C max ). The objective is to find the optimal sequences in order to minimize the makespan. In this study, the hybridization of GA (HGA: hybrid genetic algorithm) with adaptive auto-tuning based on fuzzy logic controller and the hybridization of PSO (HPSO: hybrid particle swarm optimization) with Cauchy distribution were developed to solve the problem. The encoding and decoding routines that appropriate for blocking constraint and Relax-Blocking algorithm for improving chromosome and particle were suggested. Experimental results reveal that the HPSO and HGA algorithms give better solutions than the classical metaheuristics, GA and PSO, for all test problems respectively. Additionally, the relative improvement ( RI ) of the makespan solutions obtained by the proposed algorithms with respect to those of the current practice is performed in order to measure the quality of the makespan solutions generated by the proposed algorithms. The RI results show that the HGA and HPSO algorithms can improve the makespan solution by averages of 15.51% and 15.60%, respectively. We found that the performance of the HGA is not significantly competitive as compared to the HPSO but its computational times are significantly higher than those of the HPSO. [ABSTRACT FROM AUTHOR]

In this paper a decision support system to solve the problem of hen allocation to hen houses with the aim of minimizing the total cost is described. The total cost consists of farm utilization cost, hen transportation cost, and loss from mixing hens at different ages in the same hen houses. Clustering of hen houses using the traditional Growing Neural Gas (GNG) was first determined to allocate hens to the hen houses effectively. However, the traditional GNG often solves the clustering problem by considering distance only. Therefore the hybrid Growing Neural Gas (hGNG) considering both the distance from the centroids of the clusters to the hen houses and the weights of hen house sizes was proposed to solve the problem. In the second phase, allocating and determining routes to allocate hens to the hen houses using the nearest neighbor approach were carried out in order to minimize the total distance. The performance of the algorithm was measured using the relative improvement ( RI ), which compares the total costs of the hGNG and GNG algorithms and the current practice. The results obtained from this study show that the hGNG algorithm provides better total cost values than the firm’s current practice from 7.92% to 20.83%, and from 5.90% to 17.91% better than the traditional GNG algorithm. The results also demonstrate that the proposed method is useful not only for reducing the total cost, but also for efficient management of a poultry production system. Furthermore, the method used in this research should prove beneficial to other similar agro-food sectors in Thailand and around the world. [ABSTRACT FROM AUTHOR]

• Various types of workforces with multiple teams per each workforce type are considered. • Multi-visit for different types of workforces is included. • Hybrid differential evolution and particle swarm optimization for workforce scheduling and routing problem is proposed. This research proposed an optimization method (Hybrid Differential Evolution and Particle Swarm Optimization, HDEPSO) using a solution technique based on two well-known techniques, Differential Evolution (DE) and Particle Swarm Optimization (PSO), to tackle a multi-visit and multi-period workforce scheduling and routing problem (MMWSRP) in field service operation of a sugarcane mill company in Thailand. The HDEPSO can be used for planning of routes and maintenance work for each sugarcane harvester to be provided by service teams of mechanical, hydraulic, and electrical technicians. The members of the service teams will be determined according to their skills and skill levels and service routes for each individual service team so that the operation cost is minimized. At first, mixed integer programing was used to determine the best solution. This technique is, however, not suitable for large-size problems. A HDEPSO was therefore developed to solve the MMWSRP and then tested against the mixed integer programing for small-size problems and it was found that both methods were equally effective. However, for larger-size problems, shortcomings of the mixed-integer technique became obvious whereas the HDEPSO was much more advantageous. The HDEPSO was also tested against the DE and PSO. The computational results show that the objective value of the proposed method was decreased by 4.94% and 7.45% compared with the DE and the PSO, respectively. [ABSTRACT FROM AUTHOR]

Highlights: [•] This study addresses the problem of the sugarcane supply through loading station to the mill factory. [•] There exist different types of multi-facility services in each sugarcane loading station. [•] Designing a mathematical model for location–allocation problem with multi-facility services. [•] Proposing an efficient adaptive genetic algorithm to solve location–allocation problem with multi-facility services. [•] Outperforming well by the proposed adaptive genetic algorithm in large-sized problems. [Copyright &y& Elsevier]

This study provides circular economy principles in natural resource management (NRM) in Vietnam when merging financial sustainability. Prior studies have neglected NRM in terms of utilizing circular economy principles (CEP) with the support of financial sustainability (FS). The main goal is to improve CEP in NRM utilizing the FS. This study employs the novel hybrid method to explore the multi-hierarchical NRM structure, address the interrelationships among CE and NRM attributes, and identify the attributes for improvement with the support of FS. This study proposes 85 criteria across 13 aspects base on the natural resource-based view. The results reveal a valid set of 20 criteria spanning six aspects. The aspects comprise operational digitalization, Fintech application and environmental strategy. The practical criteria include digital ecosystem collaborations, automation and robotics operations, compliance with environmental standards and laws, blockchain adoption, and data security. The FS is indicated as the decisive perspective for improving the CEP in NRM. [Display omitted] [ABSTRACT FROM AUTHOR]

In this study, natural capital accounting (NCA) is enhanced by constructing a data-driven hierarchical model that can help improve policy decision-making. NCA enables the management and transparency of natural capital and ecological processes and services, resulting in better societal activities and well-being in Indonesia's regions; however, it does not account for environmentally related economic activities that may negatively influence natural capital, processes and services. In this study, a data-driven approach is used to address this issue. Valid attributes are identified, and a thorough NCA hierarchical model that incorporates synchronized accounting on ecology, environment-related economic activities and societal well-being is developed. This approach utilizes content and bibliographic analyses, the entropy weighted method (EWM) and the fuzzy Delphi method (FDM), which are used to validate the data-driven NCA measurements. Exploratory factor analysis (EFA) is utilized to cluster the measurements and assess their reliability. The fuzzy decision-making trial and evaluation laboratory (FDEMATEL) is used to construct the NCA hierarchical structure by considering the cause-and-effect interrelationships among attributes. The valid prioritized attributes are determined, and a hierarchical structure is built to support government decision-making processes. The findings suggest that water resource accounting, forestry production, raw material extraction, resource allocation management and resource consumption management are the criteria that fluctuate the most for practitioners and governments. [ABSTRACT FROM AUTHOR]

• Tractor scheduling and routing problem with tool allocation constraint is focused. • This research is based on real Thailand sugarcane agricultural case study. • The new neighborhood search strategies are added to the Hybrid PSO (HPSO). • Two new formulae for neighborhood search are used to increase the performance of proposed methods. This paper presents the Hybrid Particle Swarm Optimization and Neighborhood Strategy Search (HPSO-NS) to solve a tractor scheduling and routing problem with equipment allocation constraint in sugarcane field preparation, to help the growers catch the season and ensure advantageous production of sugar from sugarcane. This problem can be formulated as the flexible flow shop scheduling problem with machine eligibility, time windows, sequence dependent setup time (SDST), blocking, machine restriction and machine grouping (FFS | S smt , M j , Grouping, block, 6-stage, Tool, Tw | ∑ i N R i). A mixed-integer programming model was developed to solve small-scale problems. The HPSO-NS was developed for large-scale problems, and three neighborhood strategies were added to the PSO procedure and developed. Moreover, two new formulae which were used to select the neighborhood strategy in HPSO-NS are presented in this paper to increase the performance of the proposed method. The computational results show that the HPSO-NS outperforms the original PSO and the lower bound obtained from the optimization software, while using 97% less computational time. [ABSTRACT FROM AUTHOR]

• Develop method to find the best parameters to minimize the fuel used of the tractor. • The method combines response surface method and differential evolution algorithm. • The new recombination process in the differential evolution algorithm is presented. • The proposed method outperforms the use of traditional response surface methodology. This paper presents the green 2-echelon location routing problem (G2ELRP) which is a variant of the capacitated location-routing problem (CLRP) and the 2-echelon location routing problem (2ELRP), in that it deals with the collection problem for which routing decisions at both levels are required. The G2ELRP aims to minimize the total fuel consumption depending on the distance and the road conditions in both echelons. In the G2ELRP, that a customer can be served more than once is considered as a new constraint. Due to its complexity, the G2ELRP requires a complex problem formulation. A new variable neighborhood strategy adaptive search (VaNSAS) algorithm as a solution approach is introduced to solve the problem. The computational results indicate that the VaNSAS algorithm efficiently solves the case study problem and outperforms all other proposed heuristics. The G2ELRP model saved fuel cost by 3.71% over the traditional LRP. This demonstrates that the proposed VaNSAS is very efficient and not only useful for decreasing costs of rubber logistics, but also for application to other related agro-industries. [ABSTRACT FROM AUTHOR]

This study presents a new approach to find the optimal operating parameters of a tractor disc plough, to minimize the fuel used for the land preparation of sugarcane fields. The new approach is composed of three steps: (1) construct the regression model; (2) use modified differential evolution (MDE) to find the optimal parameters; and (3) verify the optimal parameters by performing a real experiment. The use of MDE obtained optimal parameters giving 12.37% and 16.96% lower fuel use than for the traditional method, when using the response optimizer and particle swarm optimization, respectively. [ABSTRACT FROM AUTHOR]

In practical semiconductor processes, the defect analysis for wafer map is a critical step for improving product quality and yield. These defect patterns can provide important process information so that the process engineers can identify the key cause of process anomalies. However, in supervised learning, the manual annotation for wafer maps is an extremely exhausting task, and it can also induce misjudgment when a long-term operation is implemented. Toward this end, this paper proposes a new auto-labeling system based on ensemble classification. The noted VGG16 model is used in ensemble learning as the building block to train the classifier via a limited number of labeled data. Through the model being trained, the auto-labeling procedure is executed to annotate abundant unlabeled data. Therefore, the classification performances between the models trained by supervised and semi-supervised learning can be compared. In addition, the gradient-weighted class activation mapping (Grad-CAM) is also adopted to analyze and verify the quality of auto-labeling by visual inspection. Based on the experimental results, the proposed auto-label system can return a satisfactory classification performance, and then, the manual labeling operation can be drastically reduced. The classification performance for wafer defect patterns can be further assured as the auto-labeled data are given with corresponding confidence scores of specific defect patterns being identified in this study. [ABSTRACT FROM AUTHOR]

This article aims to minimize cycle time for a simple assembly line balancing problem type 2 by presenting a variable neighborhood strategy adaptive search method (VaNSAS) in a case study of the garment industry considering the number and types of machines used in each workstation in a simple assembly line balancing problem type 2 (SALBP-2M). The variable neighborhood strategy adaptive search method (VaNSAS) is a new method that includes five main steps, which are (1) generate a set of tracks, (2) make all tracks operate in a specified black box, (3)operate the black box, (4) update the track, and (5) repeat the second to fourth steps until the termination condition is met. The proposed methods have been tested with two groups of test instances, which are datasets of (1) SALBP-2 and (2) SALBP-2M. The computational results show that the proposed methods outperform the best existing solution found by the LINGO modeling program. Therefore, the VaNSAS method provides a better solution and features a much lower computational time. [ABSTRACT FROM AUTHOR]

This research aimed to present a solution to the problem of production scheduling and assignment in broiler farms, which thus enabled the farms to achieve maximum profit. In the operation of farms, there are many factors that affect profits, such as the number of broilers being consistent with the demand of production plants, including profits from the sales and transportation costs. Therefore, we formulated a mathematical model and tested it while using three problem groups through the Lingo v.11 program. The results indicated that this mathematical model could find a suitable solution. However, finding the best solution had time constraints, which resulted in various other problems that prevented a search for an optimal solution due to time consumption exceeding 72 h. We developed an algorithm using the Adaptive Large Neighborhood Search (ALNS) method in order to find another possible solution using a shorter time period, which consisted of ALNS1, ALNS2, and ALNS3. These algorithms are based on a combination of the method of destruction solutions and methods accepting different solutions. We aimed to effectively solve the problems and ensure that they are appropriate for the case study, a broiler farm in Buriram. When comparing the algorithm effciency with the Lingo v.11 program, it was found that the ALNS1 algorithm was the most suitable for finding the optimal solution in the shortest time, which resulted in a 5.74% increase in operating profits. [ABSTRACT FROM AUTHOR]

This research addresses the critical challenge of disaster waste management, a growing concern exacerbated by the increasing frequency and intensity of natural disasters like flooding. Traditional waste systems often struggle with the volume and heterogeneity of disaster waste, highlighting the need for innovative solutions. In this study, we present a novel disaster waste classification model integrating advanced artificial intelligence (AI) and optimization techniques to streamline waste categorization in post-disaster environments. Our approach leverages a dual ensemble deep learning framework. The first ensemble combines various image-segmentation methods, while the second integrates outputs from diverse convolutional neural network architectures. A modified artificial multiple intelligence system serves as a decision fusion strategy, enhancing accuracy at both ensemble points. We rigorously evaluated our model using three datasets: the "TrashNet" dataset for benchmarking against existing methods, as well as two meticulously curated, real-world datasets collected from flood-affected areas in Thailand. The results demonstrate that our method outperforms existing algorithms like VGG19, YoloV5, and InceptionV3 in general solid waste classification, achieving an average improvement of 11.18%. Regarding disaster waste specifically, our model achieves 96.48% and 96.49% accuracy on the curated datasets, consistently outperforming ResNet-101, DenseNet-121, and InceptionV3 by an average of 3.47%. These findings demonstrate the potential of our AI-enhanced model to revolutionize disaster waste management practices. Thus, we advocate integrating such technologies into municipal waste management policies to enhance resilience and optimize disaster responses. Future research will explore scaling the model to diverse disaster types and incorporating real-time data for adaptable waste management strategies. • Advanced AI model for enhanced classification of disaster-related waste. • Exceptional accuracy in waste identification: 96.48% and 96.49%. • Versatile application in diverse disaster and urban scenarios. • Utilizes cutting-edge image segmentation and CNN for robust data processing. • Significantly mitigates environmental and health risks in disaster zones. [ABSTRACT FROM AUTHOR]

This study constructs a distributed generation (DG) multi-objective hierarchical optimal planning model. A solution method is proposed based on an improved beluga whale optimization algorithm (IBWO). Reasonable planning of the location and capacity of DG access to the distribution network plays an important role in minimizing actual power losses, reducing grid operating costs, and improving voltage distribution. The output power of DG has uncertainties and the demand response on the load side can also affect the DG planning; however, previous studies have ignored these two critical factors. This study aims to determine the optimal location and capacity of DG access to distribution network considering the demand response and the uncertainty of DG output power to improve the economic benefit, power quality and energy utilization efficiency. This study proposes an IBWO algorithm with better performance, aiming at the multi-objective, multi-constrained and nonlinear DG planning problem and a DG multi-objective hierarchical optimal planning model is established. The results show that proposed method can reduce the annual comprehensive cost, total voltage deviation and power loss of system by 11.66%, 40.55% and 38.61%. [ABSTRACT FROM AUTHOR]

An integrated energy system (IES) can effectively solve the energy crisis, realize multi-energy complementarity, and promote fine-grained energy development. Aiming at the low-carbon economy problem of IESs with combined heat and power (CHP), carbon capture systems (CCSs) and power-to-gas (P2G), the joint operation mode of CHP-CCS-P2G is proposed, and the output characteristics and carbon emissions of CHP units under this mode are analysed. On the supply side, a multi-objective optimization method based on compromise programming is proposed to solve the contradiction between economic and environmental objectives in the IES, and the energy operator balances economic and environmental performance to obtain the optimal configuration scheme and operation strategy. On the load side, a master-slave game energy trading strategy considering integrative demand response (IDR) is adopted to balance the interests of the energy operator and users centrally managed by the load aggregator to ensure the fairness of transactions between the two parties. The results show that the overall revenue of the energy operator decreases by 7.99 % after considering IDR. However, the carbon emissions decreased by 933.82 kg, the carbon trading revenue increased by 45.18 %, and the energy purchase cost of users decreased by 9.34 %. [ABSTRACT FROM AUTHOR]

An integrated energy system (IES) can effectively solve the energy crisis, realize multi-energy complementarity, and promote fine-grained energy development. Aiming at the low-carbon economy problem of IESs with combined heat and power (CHP), carbon capture systems (CCSs) and power-to-gas (P2G), the joint operation mode of CHP-CCS-P2G is proposed, and the output characteristics and carbon emissions of CHP units under this mode are analysed. On the supply side, a multi-objective optimization method based on compromise programming is proposed to solve the contradiction between economic and environmental objectives in the IES, and the energy operator balances economic and environmental performance to obtain the optimal configuration scheme and operation strategy. On the load side, a master-slave game energy trading strategy considering integrative demand response (IDR) is adopted to balance the interests of the energy operator and users centrally managed by the load aggregator to ensure the fairness of transactions between the two parties. The results show that the overall revenue of the energy operator decreases by 7.99 % after considering IDR. However, the carbon emissions decreased by 933.82 kg, the carbon trading revenue increased by 45.18 %, and the energy purchase cost of users decreased by 9.34 %. [ABSTRACT FROM AUTHOR]

This article aims to resolve a particular production planning and workforce assignment problem. Many production lines may have different production capacities while producing the same product. Each production line is composed of three production stages, and each stage requires different periods of times and numbers of workers. Moreover, the workers will have different skill levels which can affect the number of workers required for production line. The number of workers required in each farm also depends on the amount of pigs that it is producing. Production planning must fulfill all the demands and can only make use of the workers available. A production plan aims to generate maximal profit for the company. A mathematical model has been developed to solve the proposed problem, when the size of problem increases, the model is unable to resolve large issues within a reasonable timeframe. A metaheuristic method called adaptive large-scale neighborhood search (ALNS) has been developed to solve the case study. Eight destroy and four repair operators (including ant colony optimization based destroy and repair methods) have been presented. Moreover, three formulas which are used to make decisions for acceptance of the newly generated solution have been proposed. The present study tested 16 data sets, including the case study. From the computational results of the small size of test instances, ALNS should be able to find optimal solutions for all the random data sets in much less computational time compared to commercial optimization software. For medium and larger test instance sizes, the findings of the heuristics were 0.48% to 0.92% away from the upper bound and generated within 480–620 h, in comparison to the 1 h required for the proposed method. The Ant Colony Optimization-based destroy and repair method found solutions that were 0.98 to 1.03% better than the original ALNS. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing is a complicated flexible job-shop scheduling problem (FJSP) of combinatorial complexity. Because of the adoption of advanced process control and advanced equipment control, the processing time in advanced wafer fabs become uncertain. Existing approaches considering constant processing time may not be appropriate to address the present problem in a real setting. In practice, processing times can be represented as intervals with the most probable completion time somewhere near the middle of the interval. A fuzzy number that is a generalized interval can represent this processing time interval exactly and naturally. This paper developed a hybrid approach integrating a particle swarm optimization algorithm with a Cauchy distribution and genetic operators (HPSO+GA) for solving an FJSP by finding a job sequence that minimizes the makespan with uncertain processing time. In particular, the proposed hybridized HPSO+GA approach employs PSO for creating operation sequences and assigning the time and resources for each operation, and then uses genetic operators to update the particles for improving the solution. To estimate the validity of the proposed approaches, experiments were conducted to compare the proposed approach with conventional approaches. The results show the practical viability of this approach. This paper concludes with discussions of contributions and recommends directions for future research. [ABSTRACT FROM PUBLISHER]