An Integrated Approach for Sustainable Supply Chain Management with Replenishment, Transportation, and Production Decisions

How to improve competitive edges to meet rapidly changing market environment and dynamic customer needs is critical for the survival and success of firms these days. A good supply chain and inventory management is a necessity in the intensive competitive market. This paper considers a dynamic-demand joint replenishment problem with multiple vehicle routing. The problem is first formulated as a mixed integer programming model with an objective to minimise total costs, which include ordering cost, purchase cost, production cost, transportation cost and holding cost, under a prerequisite that inventory shortage is prohibited in the system. A particle swarm optimisation model is proposed next to solve large-scale problems which are computationally difficult. A case study of a touch panel manufacturer is presented to examine the practicality of the models.

This paper aims to perform a hybrid study with a focus on empirical modeling (EM) and its applications in sustainable supply chain management (SSCM) concepts using bibliometric, network, thematic, and content analyses. The outcomes provide a viewpoint on literature categorization and several innovative insights and perspectives into contemporary research trends in this field. The review is undertaken using 2192 out of more than 24,000 research papers that are extracted and sifted from the Scopus and WoS databases. The results indicate an annual growth rate of 17.65% for the subject under consideration, which holds considerable significance and portends a promising outlook for the field. Seven clusters of papers are identified: (1) SSCM and design using versatile empirical approaches; (2) socially and environmentally responsible SCM and design; (3) new theories and impacts of SSCM integration; (4) data science, predictive analytics, and big data for SC sustainability; (5) closed loop SC roles in bringing sustainability; (6) SSCM during disasters with respect to humanitarian aspects; and (7) linkages between Industry 5.0, digital technologies, circular economy, and SSCM. In this review, fundamental ideas are established, research gaps are identified, and multiple future research subjects are proposed. In addition, important topics are presented for managers and practitioners to consider when adopting EM principles in SSCM. The results contribute to both theoretical and practical management elements and give a solid road map for future study in this sector. This study provides an overview of the evolution of EM and its applications in SSCM concepts; it also particularly elaborates on general pertinent research dimensions, SSCM, sustainability practices, and EM aspects.

Convolutional Neural Networks (CNNs) have become the de facto technique for image feature extraction in recent years. However, their design and construction remains a complicated task. As more developments are made in progressing the internal components of CNNs, the task of assembling them effectively from core components becomes even more arduous. To overcome these barriers, we propose the Swarm Optimized Block Architecture, combined with an enhanced adaptive particle swarm optimization (PSO) algorithm for deep CNN model evolution. The enhanced PSO model employs adaptive acceleration coefficients generated using several cosine annealing mechanisms to overcome stagnation. Specifically, we propose a combined training and structure optimization process for deep CNN model generation, where the proposed PSO model is utilized to explore a bespoke search space defined by a simplified block-based structure. The proposed PSO model not only devises deep networks specifically for image classification, but also builds and pre-trains models for transfer learning tasks. To significantly reduce the hardware and computational cost of the search, the devised CNN model is optimized and trained simultaneously, using a weight sharing mechanism and a final fine-tuning process. Our system compares favorably with related research for optimized deep network generation. It achieves an error rate of 4.78% on the CIFAR-10 image classification task, with 34 hours of combined optimization and training, and an error rate of 25.42% on the CIFAR-100 image data set in 36 hours. All experiments were performed on a single NVIDIA GTX 1080Ti consumer GPU.

Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models

System dynamics modeling for sustainable supply chain management: A literature review and systems thinking approach

Given a feasible solution to a Mixed Integer Programming (MIP) model, a natural question is whether that solution can be improved using local search techniques. Local search has been applied very successfully in a variety of other combinatorial optimization domains. Unfortunately, local search relies extensively on the notion of a solution neighborhood, and this neighborhood is almost always tailored to the structure of the particular problem being solved. A MIP model typically conveys little information about the underlying problem structure. This paper considers two new approaches to exploring interesting, domain-independent neighborhoods in MIP. The more effective of the two, which we call Relaxation Induced Neighborhood Search (RINS), constructs a promising neighborhood using information contained in the continuous relaxation of the MIP model. Neighborhood exploration is then formulated as a MIP model itself and solved recursively. The second, which we call guided dives, is a simple modification of the MIP tree traversal order. Loosely speaking, it guides the search towards nodes that are close neighbors of the best known feasible solution. Extensive computational experiments on very difficult MIP models show that both approaches outperform default CPLEX MIP and a previously described approach for exploring MIP neighborhoods (local branching) with respect to several different metrics. The metrics we consider are quality of the best integer solution produced within a time limit, ability to improve a given integer solution (of both good and poor quality), and time required to diversify the search in order to find a new solution.

In this paper we describe a procedure that automatically synthesizes a neighborhood from an ensemble of Mixed Integer Programming (MIP) and/or Constraint Programming (CP) models. We move on from a recent paper by Adamo et al. (2015) in which a neighborhood structure is automatically designed from a (single) MIP model through a three-step approach: (1) a semantic feature extraction from the MIP model; (2) the derivation of neighborhood design mechanisms based on these features; (3) an automatic configuration phase to find the “proper mix” of such mechanisms taking into account the instance distribution. Here, we extend the previous work in order to generate a suitable neighborhood from an ensemble of MIP and/or CP models of a given combinatorial optimization problem. Computational results show relevant improvements over the approach considering a single model.

Sustainable cold supply chain management under demand uncertainty and carbon tax regulation

This paper examines a new problem, which integrates the multi-level lot-sizing problem and the well-known facility location problem. A mixed integer programming model with the objective to minimize the system-wide costs, including facility operating cost, setup cost, production cost, transportation costs, inventory-holding cost and backlog cost, is established. For small-scale instances, the commercial solvers can be employed to solve the problem to optimality. For large-scale instances, we propose a two-phase relax-and-fix heuristic to conquer the NP-hardness. Experimental results show that the designed two-phase relax and fix algorithm performs well, especially in large cases.

Purpose —Sustainable supply chain management has become a continuing stream of research with increased interest especially from the year 2005 onwards. The purpose of this article is to conduct a literature review of academic publications on relevant tools, methods, and practices that can be instrumental in the creation of sustainable supply chains. Design / Methodology —A systematic and reproducible literature review was conducted in order to identify, evaluate, and interpret the existing body of knowledge on sustainable supply chain management. The review process comprised material collection, descriptive analysis, categorisation, and interpretation. Findings / Implications —A content analysis of approaches for sustainable supply chain management is presented. The review is structured along categories that relate directly to well‐established key issues in supply chain management. This process provides tangibility to the review insights as they are enfolded against familiar aspects of supply chains. The findings can guide scholars in the field and their understanding thereof. Originality / Value —With the rapid expansion of theoretical contributions and practical developments with regard to sustainable supply chain management, this article offers a needed reference point. It informs researchers of the state of knowledge, guides potential avenues for future research, and may influence practitioners in their selection of approaches that are applicable to their specific requirements.

This paper considers the precast production problem with identical parallel molds. To produce precast elements, multiple processes including mold preparing, concrete mixing, curing, stripping and finishing must be completed in a mold. Some processes require an additional resource shared among molds. All the processing times are constant except the curing time, which increases when using a more expensive concrete mixing formula. Given a demand and a production time frame, this paper proposes a heuristics to select concrete formulas and schedule jobs to minimise the total product cost. A mixed integer programming (MIP) model is formulated to solve for the optimal solutions. The results demonstrate that the proposed heuristics finds the same optimal solutions as obtained from the MIP model but with many orders of magnitude less than computational times. In the problems where the MIP model cannot find the optimal solutions due to the problem complexity, the proposed heuristics can find feasible solutions that are within 3% differences for 4-mold problems and 9.5% differences for 8-mold problems from the approximate lower bound solutions and only uses less than a few seconds of computational time.

This study was aimed at analyzing the implementation of the Sustainable Supply Chain Management (SSCM) approach as a branding strategy of tourism development of Hutan Bambu in Bekasi city. This study employed a descriptive research method using a qualitative approach. The data sources were primary and secondary data. The techniques of data collection were observation, interviews, and documentation. The interviews were conducted with six informants representing the manager, visitors, local communities, and food sellers in the Hutan Bambu area of Bekasi city. Furthermore, the data were analyzed by using the SSCM approach. The results of the study showed that the branding strategy for developing the Hutan Bambu tourism object can apply several ways. First, it considered SSCM concerns, especially sustainability, marketing-logistics empowerment, market-driven SCM, synchronous SCM, fast response logistics, and network-based resource management. Second, the tourism development was carried out by creating strong branding with the advantages of the Hutan Bambu tourism object, namely by marketing through social media to local and national communities. Third, the development can be done by holding attractive soft skills programs regularly by collaborating with training studios or certain institutions, so they can bring in visitors on a more regular and programmed basis. Fourth, this can also be done by modifying the management system, so the tourists can find alternative tourism objects in the city. Finally, the SSCM approach could be implemented in the development of the Hutan Bambu tourism object, Bekasi by strengthening branding and interesting soft-skills, as well as modifying the management system.

A cutting plane algorithm for the site layout planning problem with travel barriers

An iterative mixed integer programming method for classification accuracy maximizing discriminant analysis

A generic planning approach for sustainable supply chain management - How to integrate concepts and methods to address the issues of sustainability?