Industrial Decision Research Articles

Remanufacturing production planning and control: Conceptual framework for requirement definition

Abstract In the era of environmental degradation and resource scarcity, the concept of circular economy (CE) has emerged as a pivotal strategy to transform the contemporary industrial landscape. As an integral component of the 10R framework, remanufacturing is emerging as a production strategy that revitalizes end-of-life (EOL) products to a like-new condition, fostering a more sustainable production and consumption. Despite its immense environmental and economic benefits, the implementation of remanufacturing practices is confronted with a multitude of challenges, including sourcing of EOL products, managing component variability, and arbitrary failure rates that result in major process inefficiencies. This paper embarks on the definition of functional and non-functional requirements for remanufacturing production planning and control (RPPC) to establish a systematic approach to address the existing challenges and uncertainties that arise in remanufacturing systems. Based on the synthesis of a comprehensive literature study, eight functional requirements and a total of 48 associated key performance measures are derived and contextualized in a coherent conceptual framework. This establishes a consensus to mitigate the impacts caused by uncertainty in remanufacturing. The feasibility of the conceptual framework is validated in an industrial case study with an OEM remanufacturer of electric power steering products. The findings of this research paper advance the field of RPPC and offer guidance to industrial decision-makers to evaluate and optimize their remanufacturing production systems.

Prioritization of Preventive Measures: A Multi-Criteria Approach to Risk Mitigation in Road Infrastructure Projects

Risk management in construction projects is a critical process aimed at identifying, evaluating, and mitigating potential risks that could impact project performance. Preventive measures play a central role in this process, serving as proactive strategies to minimize the likelihood and impact of risks on project outcomes. This study involved 37 experts from multidisciplinary fields related to road infrastructure, ensuring a diverse and comprehensive perspective on risk evaluation and prevention. The DELPHI method was employed to systematically define key risks and their corresponding preventive measures, providing a structured foundation for further analysis. The experts evaluated 302 preventive measures across 56 risks using 4 predefined criteria: implementation costs, time required for implementation, implementation complexity, and probability of success. A multi-criteria decision making (MCDM) approach was then applied to analyze these evaluations, enabling the prioritization of preventive measures and the allocation of resources toward the most effective strategies. Additionally, fuzzy logic was employed to analyze and validate the results, providing a complementary approach to the MCDM methodology. The results of this research provide a robust framework for risk management, offering practical guidance for decision makers in the construction industry. By integrating expert judgment, systematic evaluation, and advanced analytical methods, this study delivers actionable insights and establishes a reliable methodology for enhancing the effectiveness of risk mitigation in road infrastructure projects.

MultiProduct Optimization of Cedrelinga cateniformis (Ducke) Ducke in Different Plantation Systems in the Peruvian Amazon

This study addressed multi-product optimization in Cedrelinga cateniformis plantations in the Peruvian Amazon, aiming to maximize volumetric yields of logs and sawn lumber. Data from seven plantations of different ages and types, established on degraded land, were analyzed by using ten stem profile models to predict taper and optimize wood use. In addition, the structure of each plantation was evaluated using diameter distributions and height–diameter ratios; log and sawn timber production was optimized using SigmaE 2.0 software. The Garay model proved most effective, providing high predictive accuracy (adjusted R2 values up to 0.963) and biological realism. Marked differences in volumetric yield were observed between plantations: older and more widely spaced plantations produced higher timber volumes. Logs of optimal length (1.83–3.05 m) and larger dimension wood (e.g., 25.40 × 5.08 cm) were identified as key contributors to maximizing volumetric yields. The highest yields were observed in mature plantations, in which the total log volume reached 508.1 m3ha−1 and the sawn lumber volume 333.6 m3ha−1. The findings demonstrate the power of data-driven decision-making in the timber industry. By combining precise modeling and optimization techniques, we developed a framework that enables sawmill operators to maximize log and lumber yields. The insights gained from this research can be used to improve operational efficiency and reduce waste, ultimately leading to increased profitability. These practices promote support for smallholders and the forestry industry while contributing to the long-term development of the Peruvian Amazon.

Enhancing intelligent marketing systems: a multi-layer hypernetwork approach integrating evidence theory for influential node identification

PurposeThis study proposes an intelligent marketing system model based on a combination of multi-layer hypernetworks and evidence theory, aiming to address the shortcomings of traditional marketing models in accurately identifying key nodes. We propose a new method to improve the accuracy and response speed of intelligent marketing systems by combining evidence theory with multi-layer hypernetworks. We conducted an experiment using a certain car brand (SUV) as an example, which has a wide customer base in both domestic and international markets and has branches in multiple countries. By analyzing its sales data and user behavior, we evaluated the potential reduction in advertising costs and improvement in user satisfaction that may result from adopting this model.Design/methodology/approachThe proposed model begins with the development of a user interest model, which is subsequently converted into a user label model based on user behavior and a rating matrix. A multi-layer aggregation hypernetwork is then constructed to define the network’s topology. An identification framework is established using evidence theory, and the Dempster–Shafer (D-S) evidence combination method is applied to integrate local, positional and global network indicators. Simulation experiments are conducted to evaluate the model’s performance.FindingsThis study proposes an intelligent marketing system model that integrates multi-layer hypernetworks with Dempster–Shafer evidence theory to address the limitations of traditional marketing models in identifying influential nodes. The proposed model is tested in the automotive industry, specifically using sales and user behavior data from a well-known SUV brand operating globally. This industry provides a complex and competitive environment ideal for validating the model’s ability to improve marketing precision. The results demonstrate that the model significantly enhances the accuracy of key node identification, reduces advertising costs by 10–15% and improves customer satisfaction scores to over 90%. Furthermore, preliminary experiments in the retail and e-commerce sectors highlight the model’s adaptability and potential for broader application. By combining local, positional and global indicators, the model effectively optimizes marketing strategies, providing a novel framework for intelligent decision-making in diverse industries. This study selected a well-known SUV car brand as the experimental subject. This brand mainly sells SUV models and has a wide customer base worldwide. Its products are known for their high performance and reliability. The brand has millions of customers, and its main markets include North America, Europe and Asia. It has branches in multiple countries and has significant international influence. According to publicly available data, the brand’s annual revenue reaches billions of dollars.Originality/valueThe main contribution of the research is the proposal of a novel intelligent marketing optimization framework based on multi-layer hypernetworks and evidence theory, which can effectively solve the problems of data silos and information asymmetry faced in traditional marketing systems.

Smart Decision-Making in Industry 4.0: Bayesian Meta-Learning and Machine Learning Approaches for Multimodal Tasks

Smart Decision-Making in Industry 4.0: Bayesian Meta-Learning and Machine Learning Approaches for Multimodal Tasks

An Intelligent Model to combat Soybean Plant Disease based on Random Forest and Support Vector Machine Algorithms

Given that plant disease is the primary factor contributing to damage in most plants, decision makers in the agriculture industry are highly interested in enhancing prediction strategies to detect illness in plants at an early stage. This is crucial for ensuring timely and effective plant care. Classifying healthy soybean plants is a dependable and efficient use of noninvasive techniques like machine learning (ML). In this work, we used ML to enhance a smart forecasting model for the prediction of soybean diseases. We utilized two feature selection techniques, namely gain ratio and correlation, two supervised ML algorithms (support vector machine and Random forest) and the cross-validation technique was used for assessing the proposed system, such as accuracy, F-measure, specificity, executing time, and sensitivity. The suggested technique can readily differentiate between soybean plants that are infected and those that are healthy. The suggested approach has undergone testing using a comprehensive collection of soybean characteristics, as well as a subset of attributes. The findings show that performance metrics are impacted when soybean traits are reduced.

The Impact of Multi-Dimensional Incentives on the Performance of Rail Transit PPP Projects

This study investigates how different types of incentives impact the performance of rail transit PPPs, focusing on their construction and operational phases. By surveying 121 practitioners working in the Chinese rail transit industry, we propose a new classification of incentives (i.e., control-oriented, neutrality-oriented, and recognition-oriented incentives) based on psychological theories to broaden the categorization of “positive” (rewards) and “negative” (punishment) incentives. We further explore how these multi-dimensional incentives influence project performance by surveying another 256 industry professionals. Our findings reveal that (1) in addition to punishments, performance-based payment/bonus, credit ratings, and reputation mechanisms are newly recognized as control-oriented incentives, which can restrain the autonomy of the private sector; (2) control-oriented incentives positively influence project performance in the construction phase where clear, measurable goals are available, but their impact diminishes in the operational phase; (3) recognition-oriented incentives enhance project performance in both construction and operational phases (especially the latter), fostering long-term sustainability; and (4) neutrality-oriented incentives focus on risk allocation and collaboration between public and private sectors, showing a modestly positive effect in the operational phase. As such, the study provides decision-makers in the rail transit industry with valuable insights to enhance project performance effectively when implementing incentive policies.

The Impact of ESG Performance on Investors' Decision-Making in the Real Estate Industry: Based on Green Building Certification and Facility Management

With the global climate problem escalating, the real estate investor's environmental awareness is gradually rising, and financial returns are no longer the only consideration for investors, who are increasingly interested in the real estate industry's performance on the environmental level. This paper focuses on the impact of real estate practices in green building certification and facility management on investors' economic returns and environmental considerations. The study shows that improved environmental, social and governance (ESG) performance not only increases property values and rent levels, but also improves tenant satisfaction and lease renewal rates, which in turn enhances the competitiveness of the real estate market, and thus ESG performance improvement has a positive effect on investors. However, the existing leadership in energy and environmental design (LEED) certification for green building certification still has some limitations in terms of actual energy efficiency assessment and LEED's assessment criteria, which need to be further optimized. In addition, the introduction of edge computing in this paper is superficial and weakly referential to the practice of real estate industry, but it can be used as a general direction to enhance ESG performance.

Modeling brand experience and brand equity association in the banking industry: mediating role of brand identification, attachment and engagement

Purpose This study aims to assess the relationship between brand experience and brand equity in the private banking industry, focusing on the potential mediating effects of brand identification, attachment and engagement. Design/methodology/approach Data was conveniently gathered from 293 customers with bank accounts in different private banks using a structured questionnaire. The collected data was analyzed using PLS-SEM. Findings The study found that brand identification, attachment, engagement and experience significantly influence brand equity. Furthermore, all three mediators mediate the correlation between brand experience and brand equity. Practical implications This study’s findings provide valuable insights for management and decision-makers in the private banking industry. They can use these insights to enhance their banks’ brand equity through exceptional brand experiences. This research also significantly contributes to the current body of knowledge on the importance of brand experience in developing brand equity and achieving business success in the banking sector. Originality/value This study makes a unique contribution to the existing body of knowledge by introducing the mediating roles of brand identification, attachment and engagement in the association between brand experience and brand equity. This enriches the current understanding of brand management strategies in the banking sector.

Industrial Engineering and Management Applications: Evaluation of Data Integration Tools for Smart Manufacturing

This study comprehensively evaluates leading data integration tools for smart manufacturing environments using a hybrid Analytic Hierarchy Process (AHP) and VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) methodology. As Industry 4.0 drives increased automation and data exchange in manufacturing processes, selecting appropriate data integration tools has become critical yet complex. We assessed seven prominent data integration tools across 24 criteria grouped into six main categories: functionality, vendor-related factors, user experience, cost, reliability, and flexibility. Our data collection was informed by expert interviews, vendor documentation analysis, user reviews, and benchmark testing. The AHP analysis revealed functionality and data integration features as the most crucial criteria (weight: 0.2493), followed by user-related factors (0.1814). The VIKOR method then ranked the tools, with Oracle Data Integrator emerging as the top performer (Q=0.0000), followed by Informatica PowerCenter (Q=0.22391). Our findings highlight the importance of cloud-native solutions and user experience in industrial data integration. This research contributes a robust framework for evaluating data integration tools in imaginative manufacturing contexts and offers insights to guide decision-making in Industry 4.0 initiatives.

Modelling resilience dynamics for smart manufacturing systems: quantification and empirical analysis

ABSTRACT Smart manufacturing contributes to a better management of uncertainties and risks in today’s business environment, leading to a more resilient system. Despite its significance, the quantification of resilience in manufacturing environments is not well developed and is considered a pressing research gap. This study introduces a novel approach for assessing resilience through the development of a mathematical model for smart manufacturing systems. The sensitivity and applicability of the proposed model are investigated through simulation-based experimentation. The results demonstrate the level of resilience with the adaptability of smart manufacturing technologies. Interestingly, the trigger point derived from the simulation results is an indicator of the threshold limit for effective implementation of smart manufacturing technologies for the desired system resilience. The research provides a tool for decision-makers in industry that are considering investing in smart manufacturing solutions to increase their operational resilience. Decision-makers can design the deployment of smart manufacturing systems based on an informative trade-off to maintain the required resilience capabilities and achieve a competitive edge in the market.

Predicting Used Car Prices Using Machine Learning: A Comparative Analysis of Regression and Ensemble Models

The globe is expanding daily, and with it are everyone's expectations. Purchasing an automobile is one of the demands out of all of them. However, not everyone can afford a new car, so they will purchase a used one. However, newcomers are often unaware of the market value of their ideal vehicle for an old car. That's why we require a platform that assists new users in estimating car prices. We propose that platform in this work, which is built with machine learning technology. Let's attempt to create a statistical model that can forecast the cost of a used car using supervised machine learning techniques including linear regression, KNN, Random Forest, XG boost, and decision trees. We will be assisted in this endeavor by prior customer data and a certain set of characteristics. In order to choose the best model, we will also compare the forecast accuracy of different models.For buyers, this system helps assess whether the asking price of a car is fair based on market trends. Sellers can use the predictions to set competitive prices for their vehicles, ensuring better market positioning. This predictive capability ultimately enhances transparency, allowing for more informed and confident decision-making in the automotive industry. With continuous advancements in machine learning, the accuracy and efficiency of car price predictions will continue to improve, offering even greater market insights.

Erosion wear performance of titania filled ramie-epoxy composites: A data driven optimization study using supervised machine learning approach

This paper reports on a data driven machine learning (ML) approach to analyze and predict the erosion behavior of titanium oxide (titania) filled ramie-epoxy composites. ML models are extensively used in recent years to mimic human decisions in various industries. After fabrication and well-designed erosion trials following design of experiments, the experimental data is critically analyzed to examine the effect of each input factor (erodent temperature, striking angle, striking velocity and filler content) on the output that is erosion wear rate. It is found that the erosion wear rate increases with increase in striking velocity and striking angle and decreases with increase in filler content. The experimental data is further used to feed five different ML models. The performance and adequacy of ML models are compared using five different performance metrics. It is noticed that although all the machine learning techniques effectively predicted the erosion rate, the Gradient boosting machine (GBM) model exhibited superior performance with an R2 value of 0.9486. The feature importance plot confirms that the, filler content, striking velocity and the striking angle played a major role in predicting the erosion rate of the hybrid composites.

Data Visualization: From Raw Data to Actionable Insight

Information age data is the backbone of industry decision-making. Raw data, however, lacks accessibility without effective visualization techniques to make it accessible and actionable. Data visualization takes complicated data sets and converts them into intuitive, visual formats, and using this, businesses can discover trends, correlations, and insights that guide informed decisions. This paper explores the process from raw data to actionable insights through data visualization, in terms of significance, core techniques, tools, and applications across multiple sectors. It further mentions best practices and challenges to ensure that the visual representation is accurate and meaningful.

Rethinking AI with Transformative Philosophy

Abstract This paper introduces the Transformative Philosophy (T:Phil) program, an initiative designed to embed ethical and socio-political literacy into the technological development process. T:Phil, developed within the Digitalized Lifeworld research cluster and in partnership with leading international technology reflection experts, provides a comprehensive framework for integrating philosophical insights with technical expertise. Aimed at decision-makers in the tech industry, T:Phil delivers tailored content through modular series such as Re:Thinking Technology, which challenge participants to reconsider their approaches to AI, digital infrastructures, and our language of technology. The paper highlights two key modules of the T:Phil program: The first, AI in an Atlas-View, promotes a holistic understanding of AI by examining its technical, human, and environmental aspects. This module encourages participants to view AI as a complex socio-technical ensemble rather than merely a technical innovation. The second module, AI as a Metaphor, explores the metaphorical language used to describe AI, fostering critical awareness of how these metaphors shape our perceptions and influence the ethical considerations of AI deployment. Through innovative delivery methods, including hybrid keynote- discussion events, short series, and intensive Thinkathons, T:Phil engages technical professionals in reflective practices that enhance their understanding of technology’s - especially AI’s - broader implications. The program aims to help cultivate a new cadre of ethically and philosophically informed tech experts capable of designing AI systems that promote equitable and just outcomes. This paper briefly introduces the T:Phil program and provides examples of its application, demonstrating its potential to transform the way we integrate ethical reflection into technology development.

Precast versus In Situ Concrete: Developing an Initial Feasibility Study for Early Decision-Making in the Australian Construction Industry

Precast versus In Situ Concrete: Developing an Initial Feasibility Study for Early Decision-Making in the Australian Construction Industry

ESTIMASI HASIL PRODUKSI TBS DI PTPN IV REGIONAL 4 DENGAN METODE INTERPOLASI POLINOM

The study aimed to provide an accurate prediction model to enhance decision-making and operational efficiency in the palm oil industry. The data in this research included the cultivated land area and Fresh Fruit Bunch (FFB) production records for the year 2023. Newton Polynomial Interpolation is a mathematical technique to estimate unknown values between data. In this research, it was applied to derive production estimates across varying land sizes. The result demonstrated a consistent relationship between land area and production output, as illustrated through linear scatter plots. Production estimates for land areas ranging from 20 hectares to 850 hectares yielded 385,996.381 kg and 21,159,940.984 kg FFB. This research concludes that as the land area increases, FFB production shows a propotional upward trend, supporting the utility of Newton’s interpolation method in agricultural forecasting. The findings contribute significantly to the company’s planning processes and reinforce the importance of integrating mathematical models in optimizing resource utilization and achieving production targets.

The benefits of social insurance system prediction using a hybrid fuzzy time series method.

Decision-making in many industries relies heavily on accurate forecasts, including the insurance sector. The Social Insurance System (SIS) in Egypt, operating under a fully funded paradigm, depends on reliable predictions to ensure effective financial planning. This research introduces a hybrid predictive model that combines fuzzy time series (FTS) Markov chains with the tree partition method (TPM) and difference transformation to forecast total pension benefits within Egypt's SIS. A key feature of the proposed model is its ability to optimize the partitioning process, resulting in the creation of nine intervals that reduce computational complexity while maintaining forecasting accuracy. These intervals were consistently applied across all fuzzy time series models for comparison. The model's performance is evaluated using established metrics such as MAPE, Thiels' U statistic, and RMSE. Additionally, prediction interval coverage probability (PICP) and mean prediction interval length (MPIL) are used to assess the quality of prediction intervals, with a 95% prediction interval serving as the baseline. The proposed model achieved a PICP of approximately 95%, indicating well-calibrated prediction intervals, although the MPIL of 424.5 reflects a wider uncertainty range. Despite this, the model balances coverage accuracy and interval precision effectively. The results demonstrate that the proposed model significantly outperforms traditional models like linear regression, ARIMA, and exponential smoothing and conventional FTS models like Song, Chen, Yu, and Cheng by achieving the lowest MAPE with the value of 11.8% for training and 10.65% for testing. This superior performance highlights the model's reliability and potential applicability to further forecasting tasks in the field of insurance and beyond.

A Diagnostic Approach to Improving the Energy Efficiency of Production Processes—2E-DAmIcS Methodology

This article presents the issue of energy waste in manufacturing processes, focusing on reducing unnecessary energy consumption and CO2 emissions. A significant challenge in modern production is identifying and minimizing energy waste, which not only increases operational costs but also contributes to environmental degradation. An improvement methodology referred to as 2E-DAmIcS is proposed. A distinguishing feature of the methodology is a risk map of energy waste in the production process. Application of the methodology is demonstrated using the example of a lead–acid battery production process. It is shown that even small but well-diagnosed changes to the process make it possible to significantly reduce energy consumption. The proposed methodology offers practical tools for managers and decision-makers in various industries to systematically identify and minimize energy waste. It highlights the importance of cross-disciplinary collaboration among specialists in technology, energy consumption, and statistical analysis to optimize energy use. By applying this approach, companies can achieve both financial savings and environmental benefits, contributing to more sustainable production practices.

Differences in Generation Y male and female customers’ perceived mobile banking trust, information, and system quality

Trust is key to mobile banking adoption, shaping customer confidence in the service. Trusting behaviors and expectations vary between genders and across generational cohorts, influenced by factors like system and information quality. As such, the purpose of this study was to determine whether South African Generation Y male and female banking customers differ in their mobile banking trust, system, and information quality. In accordance with a descriptive research design, self-administered surveys were voluntarily distributed to 334 South African mobile banking participants. Using structural equation modeling, the study found that, among the male participants, the system quality of mobile banking predicts their mobile banking trust (β = 0.72, p < .001) and perceived information quality of the system (β = 0.94, p < .001). However, their mobile banking trust had an insignificant influence on their perceived information quality (β = –0.04, p > .001). For female Generation Y banking customers, mobile banking system quality was a significant predictor of both trust (β = 0.53, p < .001) and information quality (β = 0.69, p < .001). In addition, the path between trust and information quality was statistically significant (β = 0.17, p < .05). Determining the role of trust and its relationship between information and system quality of mobile banking among males and females is essential for understanding customer behavior, enhancing user experience, mitigating perceived risk, and guiding strategic decision-making in the mobile banking industry.