Decision System Research Articles

Value Plurality and Multifunctional Commensuration in Organisation: A Systems‐Theoretical Approach

ABSTRACTThis article aims to challenge the prevailing economic bias in studies of organised valuation and commensuration by exploring the broader plurality of values that organisations must manage. The article draws on social systems theory in the tradition of German sociologist Niklas Luhmann to conceptualise organisations as multifunctional systems of decisions that pertain to and commensurate a plurality values associated with a diverse set of value domains, also known as ‘function systems’. The utility of the proposed framework is demonstrated through cases related to carbon rationing and legal issues during the coronavirus crisis. A key finding is that commensuration is not limited to processes dominated by financial metrics, as political and educational metrics, among others, can also serve as primary drivers of commensuration processes, effectively guiding organisational decision‐making. The paper demonstrates how organisations can effectively commensurate diverse value systems without relying solely on financial metrics and concludes that future research in non‐/financial of valuation and commensuration will be crucial for developing more nuanced and multifaceted strategies and concepts, including multifunctional approaches to the formation, justification, and management of moral judgements and values.

ETHICAL CHALLENGES IN CONSTRUCTION PROCUREMENT ENSURING TRANSPARENCY IN SUBCONTRACTOR SELECTION

The construction industry faces persistent ethical challenges in procurement, including issues like favoritism, bribery, and hidden agreements, which compromise fairness, inflate costs, and erode trust. This article emphasizes the crucial importance of transparency in subcontractor selection, a key issue that needs urgent attention. It also highlights modern tools and methodologies that can address these challenges. E-tendering platforms, blockchain, and AI- powered decision-making systems provide structured and impartial frameworks for evaluating bids, ensuring accountability and fairness. By leveraging these innovative practices and overcoming barriers like resistance to change and confidentiality concerns, the construction sector can move toward a more ethical and efficient procurement system. The article also envisions a future where emerging technologies, such as smart contracts and IoT integration, create an equitable and transparent procurement ecosystem. Keywords— Construction Procurement, Ethical Challenges, Transparency, Subcontractor Selection, Blockchain Technology, AI in Construction, E-Tendering Platforms, Smart Contracts, Sustainability, Accountability in Procurement.

Methodology for Homogenous Market Area Determination HAD2 - Mission Accomplished

Abstract Property market delineation or determination of areas signifying property market consistency has been a subject of scientific investigation by a variety of researchers from different perspectives. Some explored it for the purposes of decision-making support systems, others for, for example, zoning or housing policy. The theory of property valuation also did not remain indifferent for spatial extraction of homogenous market areas. The following paper constitutes a several-year study within that area. Following the trace of thought formulated by John Maxwell that “every step back is a chance to look at your goals from a different perspective”, the study being based on, amongst others, the method of historic research and critical analysis, ultimately organizes and complements the author’s contribution to the scientific discussion, and in that scope is one of the substantial issues included in the concept of spatial management. It contributes to the current state of the art discussion by introducing the definition of property market tessellation, utilizing it for the purposes of original HAD2 methodology implementation.

Context-Based Human Influence and Causal Responsibility for Assisted Decision-Making.

The impact of the context in which automation is introduced to a decision-making system was analyzed theoretically and empirically. Previous work dealt with causality and responsibility in human-automation systems without considering the effects of how the automation's role is presented to users. An existing analytical model for predicting the human contribution to outcomes was adapted to accommodate the context of automation. An aided signal detection experiment with 400 participants was conducted to assess the correspondence of observed behavior to model predictions. The context in which the automation's role is presented affected users' tendency to follow its advice. When automation made decisions, and users only supervised it, they tended to contribute less to the outcome than in systems where the automation had an advisory capacity. The adapted theoretical model for human contribution was generally aligned with participants' behavior. The specific way automation is integrated into a system affects its use and the perceptions of user involvement, possibly altering overall system performance. The research can help design systems with automation-assisted decision-making and provide information on regulatory requirements and operational processes for such systems.

A Blockchain-based Landslide Mitigation Recommendation System for Decision-Making

Landslides are catastrophic natural disasters that could threaten the structural integrity of a building, imposing hazards to engineering and human life. This study proposes a TOPSIS landslide disaster mitigation recommendation system integrated with blockchain. New approaches to data provenance, transparency, and informed decision-making are explored in the context of geospatial blockchain. The decision-making process is carried out using the multicriteria evaluation method, which considers soil stability, rainfall, vegetation density, proximity to rivers, and slope. The results yielded promising precision, recall, accuracy, and F1 scores (91%, 93%, 95%, and 95%, respectively), suggesting that the model could make accurate and impartial prioritization predictions. Blockchain ensures data transparency, immutability, and security, and TOPSIS ranks mitigation strategies from worst to best to determine the better solution. The proposed approach is essential to predict regions that are prone to landslides and enables the appropriate management of relaxation measures. This application of blockchain technology can provide trust, reliability, and speed in decision-making while reducing landslides.

A fuzzy decision-making algorithm-based header height measurement system for combine harvester

A fuzzy decision-making algorithm-based header height measurement system for combine harvester

Premises for digital twins reporting on Atlantic salmon wellbeing.

Many species of fish, birds and mammals commonly live in human captivity; Atlantic salmon Salmo salar is one of them. The international legal status of the welfare of captive animals is slowly developing and still requires rigorous specification. For example, even though fish have complex cognition and elements of sentience, The United Nations' animal welfare principles still take a functional health-centred perspective overlooking the cognitive-affective component. Wellbeing problems remain a major source of slow growth and high mortality in intensive aquaculture of Atlantic salmon. The value system for decision making in vertebrates is based on expectations of emotional wellbeing for the options available and is linked with the individual's assessment of its future. We propose a new approach for monitoring and improving the welfare of salmon (or any other captive or wild vertebrate) based on modelling the salmon's wellbeing system by digital twins, which are simulation models that implement major bodily mechanisms of the organism. Indeed, predictions on boredom, stress and wellbeing can all be captured by a computational evolutionary model of the factors underlying behaviour. We explain how such an agent-based model of salmon digital twins can be constructed by modelling a salmon's subjective wellbeing experience along with prediction of its near future and allostasis (the bodily preparation for the expected near future). We attempt to identify the building blocks required in digital twin models to deliver early warnings about escalating issues that could eventually lead to negative effects on salmon health in aquaculture. These models would provide critical insights for optimizing production processes and could significantly reduce the reliance on animal experiments. Overall, reports of a population of digital twins could support the implementation of 3Rs - replacement, reduction, refinement - by offering actionable information to fish farmers as well as consumers, voters, politicians and regulators on relevant issues as well as guide experimental work on animal wellbeing across species.

Collaboration of Clustering and Classification Techniques for better Prediction of Severity of Heart Stroke using Deep Learning

Our research aims to present a comprehensive study of machine learning algorithms and deep learning advancements in medical field systems for decision making. Present study examines the idea of extracting most important risk factors from given medical data, which has major impact in the increase of severity condition of heart stroke. Three experimental prediction models are developed when k-means clustering is collaborated with classification which includes machine learning algorithms like Naïve Bayes, Decision Tree and a deep learning algorithm Artificial Neural Network. A detailed comparison analysis is done by evaluating performance metrics like sensitivity, specificity, accuracy, and AUC-ROC scores. Out of the three, k-means with Artificial Neural Network model outperformed with sensitivity 0.89, specificity 0.89, and accuracy of 0.90 in comparison with machine learning classifiers. The challenges of perfect balancing of sensitivity and specificity is achieved by AUC-ROC score of 0.96, which is the best possible result till now.

Integrating RS data with fuzzy decision systems for innovative crop water needs assessment

Integrating RS data with fuzzy decision systems for innovative crop water needs assessment

Scalable Feature Subset Selection With Fuzzy Rough Sets and Fuzzy Min–Max Neural Network in Hybrid Decision System

Scalable Feature Subset Selection With Fuzzy Rough Sets and Fuzzy Min–Max Neural Network in Hybrid Decision System

Diagnostics of lung cancer by fragmentated blood circulating cell-free DNA based on machine learning methods

IntroductionMinimally invasive diagnostics based on liquid biopsy makes it possible early detection of lung cancer (LC). The blood plasma circulating cell-free DNA (cfDNA) fragments reflect the genome and chromatin status and are considered as integral cancer biomarkers and the biological entities for ‘cancer-of-origin’ prediction. The aim of this work is to create a method for processing next-generation sequencing (NGS) data and an interpretable binary classification model (CM), which analyzed cfDNA fragmentation features for distinguishing healthy subjects and subjects with LC.Methods148 healthy subjects and 138 subjects with LC were included in the study. cfDNA fractions, isolated from blood plasma biospecimens, were used for DNA libraries preparations and NGS on the NovaSeq 6,000 Illumina system with a coverage of 100 million reads/sample. Twelve variables, describing the abundance and length distribution of cfDNA fragments within each genomic interval, and 40 variables based on the values of position-weight matrices, describing combinations of 5-bp-long terminal motifs of cfDNA fragments, were used to characterize genomic fragmentation. Classification models of the first phase of machine learning were based either on logistic regression with L1- and L2-regularization or were probabilistic CMs based on Gaussian processes. The second phase CM was based on kernel logistic regression.ResultsThe final CM can distinguish healthy subjects and subjects with LC with AUC values of 0.872–0.875. The performance of developed CM was evaluated using datum and testing sets for each LC stage category. Sensitivity values ranged from 66.7 to 85.7%, from 77.8 to 100%, and from 70 to 80% for LC stages I, II, and III, respectively. Specificity values ranged from 79.3 to 90.0%.DiscussionThus, the CM has a good diagnostic value and does not require clinical or other data on tumor-associated biomarkers. The current method for LC detection has some advantages for future clinical implementation as a decision-making support system due to the performance of the CM requires data exclusively from NGS-analysis of blood plasma cfDNA fragmentation; the accuracy of the CM does not depend on any additional clinical data; the CM is highly interpretable and traceable; CM has appropriate modular architecture.

Tacit knowledge-informed approximate dynamic programming for last-mile delivery operations in online-to-offline pharmacies

PurposeTacit knowledge in frontline operations is primarily reflected in the holders’ intuition about dynamic systems. Despite the implicit nature of tacit knowledge, the understanding of complex systems it encapsulates can be displayed through formalization methods. This study seeks to develop a methodology for formalizing tacit knowledge in a dynamic delivery system.Design/methodology/approachThis study employs a structured survey to gather experiential knowledge from dispatchers engaged in last-mile delivery operations. This knowledge is then formalized using a value function approximation approach, which transforms tacit insights into structured inputs for dynamic decision-making. We apply this methodology to optimize delivery operations in an online-to-offline pharmacy context.FindingsThe raw system feature data are not strongly correlated with the system’s development trends, making them ineffective for guiding dynamic decision-making. However, the system features obtained through preprocessing the raw data increase the predictiveness of dynamic decisions and improve the overall effectiveness of decision-making in delivery operations.Research limitations/implicationsThis research provides a foundational framework for studying sequential dynamic decision problems, highlighting the potential for improved decision quality and system optimization through the formalization and integration of tacit knowledge.Practical implicationsThis approach proposed in this study offers a method to preserve and formalize critical operational expertise. By embedding tacit knowledge into decision-making systems, organizations can enhance real-time responsiveness and reduce operational costs.Originality/valueThis study presents a novel approach to integrating tacit knowledge into dynamic decision-making frameworks, demonstrated in a real-world last-mile delivery context. Unlike previous research that focuses primarily on explicit data-driven methods, our approach leverages the implicit, experience-based insights of operational staff, leading to more informed and effective decision-making strategies.

An Autonomous Vehicle Behavior Decision Method Based on Deep Reinforcement Learning with Hybrid State Space and Driving Risk

Behavioral decision-making is an important part of the high-level intelligent driving system of intelligent vehicles, and efficient and safe behavioral decision-making plays an important role in the deployment of intelligent transportation system, which is a hot topic of current research. This paper proposes a deep reinforcement learning (DRL) method based on mixed-state space and driving risk for autonomous vehicle behavior decision-making, which enables autonomous vehicles to make behavioral decisions with minimal instantaneous risk through deep reinforcement learning training. Firstly, based on the various behaviors that may be taken by autonomous vehicles during high-speed driving, a calculation method for autonomous vehicle driving risk is proposed. Then, deep reinforcement learning methods are used to improve the safety and efficiency of behavioral decision-making from the interaction between the vehicle and the driving environment. Finally, the effectiveness of the proposed method is proved by training verification in different simulation scenarios, and the results show that the proposed method can enable autonomous vehicles to make safe and efficient behavior decisions in complex driving environments. Compared with advanced algorithms, the method proposed in this paper improves the driving distance of autonomous vehicle by 3.3%, the safety by 2.1%, and the calculation time by 43% in the experiment.

A Digital Twin Framework for Nuclear Power Equipment Maintenance: Design, Prototyping, and Preliminary Validation

Throughout the lifecycle of Nuclear Power Equipment (NPE), maintaining high-safety maintenance services is essential for optimal operation. Traditional time-based maintenance strategies are limited in NPE contexts due to stringent safety requirements and high costs of complex systems. Specifically, maintenance processes lack transparency, state monitoring relies heavily on manual inspections, and decisions depend passively on individual expertise. Digital Twin (DT) effectively breaks down "information silos," leverages data value, and enables proactive maintenance decision-making for NPE. However, DT application in the nuclear industry is still exploratory, with limited systematic and practical research, especially for critical equipment maintenance. This paper introduces a DT-based intelligent maintenance decision system featuring three key technologies: DT modeling, state monitoring with dynamic early warning, and systematic intelligent decision-making and verification. A DT-based prototype using a cooling water pump case study preliminarily validates the state monitoring model's accuracy. Results indicate that the proposed framework and methods are feasible and hold significant application potential.

Viable industrial supplier performance evaluation using fuzzy inference system: a case of the automotive industry

Purpose As the global focus on supply chain management has shifted toward the importance of digitalization, resilience and sustainability to ensure viability, this paradigm merits special consideration in the industrial supplier selection process in a VUCA (Volatile, Uncertain, Complex and Ambiguous) world. Additionally, the increasing geopolitical challenges further complicate the industrial supplier selection process, necessitating robust decision-making frameworks. Thus, this paper aims to present a decision-making system using a fuzzy inference system (FIS) for industrial supplier evaluation and selection, considering a new criterion: viability. Design/methodology/approach Fuzzy set theory, particularly a FIS, is used to address the subjectivity of decision-makers’ preferences. The suggested method’s validity is evaluated using a real automotive case study for industrial supplier selection situations. Findings Seventeen key criteria for viable industrial supplier selection were identified and used to evaluate and select the case study firm’s industrial supplier. The chosen supplier (B) demonstrated superior resilience, sustainability and digitalization capabilities, making it preferable to others. Specifically, supplier (B) exhibited exceptional adaptability to disruptions, a strong commitment to sustainable practices and advanced digital integration that enhances operational efficiency. Practical implications This study provides valuable insights for researchers and professionals by proposing a comprehensive industrial supplier selection system. Integrating diverse criteria is essential for viable performance in supply chains that enhances robustness and adaptability, supporting more strategic decision-making in supplier evaluation amid global and network-related challenges. Originality/value This novel paper introduces a new criterion, i.e. viability, in the industrial supplier selection process in the VUCA environment. In addition, it proposes a decision-making system for viable supplier performance evaluation. Furthermore, it validates the proposed FIS in an automotive case study.

Leveraging Artificial Intelligence and Machine Learning for Decision-Making in Business Management: A Comprehensive Analysis

This paper focuses on how AI and ML have changed decisions in retailing, healthcare, financing, and manufacturing careers. They demonstrate how AI is used in supply chain management to support the decision-making process by making forecasts, processing data, and optimizing operations, leading to higher efficiency, decreased costs, and increased customer satisfaction. Thus, the research incorporates quantitative and qualitative approaches, such as surveys and interviews with key stakeholders, and employs statistical and content analysis methods. Significant outcomes include a 20% enhancement of forecasting precision reduction while the operational cost decreases by 21 percent. Nonetheless, the research also discovers an essential issue that employs complex challenges that embrace high-cost implementation, resistance from the workforce, allowance of data privacy, and bias besides algorithms. Some are ethical concerns, and the importance of their regulation is noted. While adopting the decision theory and systems thinking perspectives, this research paper highlights the necessity of effectively and adequately implementing AI into an organization permanently to achieve more benefits. The following are realizable out-of-the-box solutions that the study suggests, including audiences for employees, data protection for compliance, and conscientization of fairness in AI algorithms. Future directions include situations where these applications are to be broadened to weigh on ethical issues and to encourage optimal technological fairness that will, in turn, ensure sustainable business improvement and innovation.

Intelligent Technologies for Joint Navigation and Functioning of Mobile Objects in Different Physical Environments

Scientific solutions for a group of heterogeneous unmanned vehicles functioning in different physical environments in a coordinated manner are presented. The following are proposed for this group: synthetic algorithms for complexing information from different measurement systems; neural network models of Earth geophysical fields for navigation; the method of joint functioning based on a frame model and an expert decision-making system.

Automated Decision-Making Systems for Behavioral Regulation: Understanding Perceptions and Behavioral Reactions

Automated decision-making systems for regulating human behaviors are increasingly deployed around the globe. This project investigates people's perceptions of and behavioral reactions to automated decision-making systems used for behavioral regulation; first, in experimentally replicated social scoring systems, and second, in survey-based studies on the Chinese Social Credit System (SCS). The objective of this project is to understand the overall legitimacy of these systems, the sources of harm stemming from these systems, and to identify future areas of research necessary to determine whether these systems can be ethically justified.

Implementation of Complex Proportional Assessment Method in Determining Prioritization of Beneficiary Groups Fish Seeds in Lhokseumawe City

The fisheries sector in Lhokseumawe City has an essential role in the regional economy, but the limited allocation of fish seed assistance requires an efficient and objective decision-making system (SPK). This research applies the Complex Proportional Assessment (COPRAS) method to prioritize groups of fish seed aid recipients. COPRAS was chosen because it can handle quantitative and qualitative criteria and produce a clear ranking of alternatives. The system evaluates criteria such as pond area, number of members, pond condition, and group age. The results showed that the Tani Mandiri group had the highest utility value = 1, while Tani Maju Berkah obtained the lowest value = 0.655. The COPRAS method effectively provided accurate and transparent recommendations in determining beneficiaries. Implementing this system is expected to help the Lhokseumawe City Marine, Fisheries, Agriculture, and Food Service Office allocate fairer and more targeted assistance, as well as increase the fisheries sector's productivity in the area. This research also contributes to developing technology-based decision-making systems to support government policies.

Graph Fairness via Authentic Counterfactuals: Tackling Structural and Causal Challenges

The extensive use of graph-based Machine Learning (ML) decision-making systems has raised numerous concerns about their potential discrimination, especially in domains with high societal impact. Various fair graph methods have thus been proposed, primarily relying on statistical fairness notions that emphasize sensitive attributes as a primary source of bias, leaving other sources of bias inadequately addressed. Existing works employ counterfactual fairness to tackle this issue from a causal perspective. However, these approaches suffer from two key limitations: they overlook hidden confounders that may affect node features and graph structure, leading to an oversimplification of causality and the inability to generate authentic counterfactual instances; they neglect graph structure bias, resulting in over-correlation of sensitive attributes with node representations. In response, this paper introduces the Authentic Graph Counterfactual Generator (AGCG), a novel framework designed to mitigate graph structure bias through a novel fair message-passing technique and to improve counterfactual sample generation by inferring hidden confounders. Comprising four key modules - subgraph selection, fair node aggregation, hidden confounder identification, and counterfactual instance generation - AGCG offers a holistic approach to advancing graph model fairness in multiple dimensions. Empirical studies conducted on both real and synthetic datasets demonstrate the effectiveness and utility of AGCG in promoting fair graph-based decision-making.