Practical Decision Support Research Articles

Practical evaluation of intelligent algorithms in ESG management of manufacturing enterprises

ESG (Environmental, Social and Governance) management practice is an important part of promoting sustainable operation and development of manufacturing enterprises. Currently, traditional evaluation methods have limitations such as low efficiency and lack of objectivity. To improve the efficiency and accuracy of ESG evaluation and promote the optimization of ESG performance in manufacturing enterprises, this article combined data mining and analytic hierarchy process (AHP) to conduct effective research on ESG management practice evaluation in manufacturing enterprises. This article adopted the best priority search strategy to collect and process enterprise ESG data. By using AHP to construct hierarchical and segmented objectives for target problems, a performance evaluation index system for management practices was built based on the evaluation objectives and hierarchical priority order. Finally, based on the performance evaluation of ESG management practices, the K-nearest Neighbor algorithm was applied to analyze historical data of key indicators. According to the weights, various key indicators were re-integrated, achieving practical evaluation and decision support for enterprise ESG management. To verify the effectiveness of data mining and AHP, this article took Z enterprise as the research object and conducted empirical analysis on it. The results showed that in terms of evaluation accuracy, the method proposed in this article achieved the highest evaluation accuracy of 92.51%, 91.16%, and 91.75% in environmental, social, and governance dimension data use case evaluation, respectively. The conclusion indicated that data mining and AHP could improve the accuracy of ESG management practice evaluation in enterprises, provide reliable decision support for enterprise development, and help promote sustainable development of enterprises.

Firefighting Vehicle Dispatch and Route Planning Model Based on Priority Passage Rights

<div>Efficient fire rescue operations in urban environments are critical for saving lives and reducing property damage. By utilizing connected vehicle systems (CVS) for firefighting vehicles planning, we can reduce the response time to fires while lowering the operational costs of fire stations. This research presents an innovative nonlinear mixed-integer programming model to enhance fire rescue operations in urban settings. The model focuses on expediting the movement of firefighting vehicles within intricate traffic networks, effectively tackling the complexities associated with collaborative dispatch decisions and optimal path planning for multiple response units. This method is validated using a small-scale traffic network, providing foundational insights into parameter impacts. A case study in Sioux Falls shows its superiority over traditional “nearest dispatch” methods, optimizing both cost and response time significantly. Sensitivity analyses involving clearance speed, clearance time, minimum rescue force, and fire loss parameters contribute to the enhancement of urban fire rescue operations and the refinement of practical decision support systems.</div>

Artificial Intelligence Background Corporate Financial Management Transformation Study

This paper aims to explore the trends of corporate financial management transformation under the backdrop of Artificial Intelligence (AI). With the rapid development of AI technology, corporate financial management is facing unprecedented opportunities and challenges. Through an in-depth analysis of the basic concepts, key technologies, and application cases of AI technology in financial management, this paper reveals the revolutionary impact of AI technology on financial management. Combined with practical cases, this paper discusses the success factors and challenges faced in the AI-driven financial management transformation process, including issues such as data privacy protection and human resources training. Finally, this paper outlines the future development trends of AI in financial management, including more intelligent decision support systems, and the widespread application of blockchain technology in the financial sector. Through this research, it is hoped to provide practical guidance and decision support for enterprise leaders and decision-makers on how to effectively utilize AI technology to optimize financial management.

Development of an Energy Planning Model Using Temporal Production Simulation and Enhanced NSGA-III

This paper presents an innovative model of Energy Planning Model which allows navigating the complexities of modern energy systems. Our model utilizes a combination of Temporal Production Simulation and an Enhanced Non-Dominated Sorting Genetic Algorithm III to address the challenge associated with fluctuating energy demands and renewable sources integration. The model represents a significant advancement in energy planning due to its capacity to simulate energy production and consumption dynamics over time. The unique feature of the model is based on Temporal Production Simulation, meaning that the model is capable of accounting for hourly, daily, and seasonal fluctuations in energy supply and demand. Such temporal sensitivity is crucial for optimization in systems with high percentages of intermittent renewable sources, as existing planning solutions largely ignore such fluctuations. Another component of the model is the Enhanced NSGA-III algorithm that is uniquely tailored for the nature of multi-objective energy planning where one must balance their cost, environmental performance, and reliability. We have developed improvements to NSGAIII to enhance its efficiency when navigating the complex decision space associated with energy planning to reach faster convergence and to explore more optimal solutions. Methodologically, we use a combination of in-depth problem definition approach, advanced simulation, and algorithmic adjustments. We have validated our model against existing models and testing it in various scenarios to illustrate its superior ability to reach optimal energy plans based on efficiency, sustainability, and reliability under various conditions. Overall, through its unique incorporation of the Temporal Production Simulation and an improved optimization algorithm, the Energy Planning Model provides novel insights and practical decision support for policymakers and energy planners developed to reach the optimal sustainable solutions required for the high penetration of renewables.

Personalizing renal replacement therapy initiation in the intensive care unit: a reinforcement learning-based strategy with external validation on the AKIKI randomized controlled trials.

The timely initiation of renal replacement therapy (RRT) for acute kidney injury (AKI) requires sequential decision-making tailored to individuals' evolving characteristics. To learn and validate optimal strategies for RRT initiation, we used reinforcement learning on clinical data from routine care and randomized controlled trials. We used the MIMIC-III database for development and AKIKI trials for validation. Participants were adult ICU patients with severe AKI receiving mechanical ventilation or catecholamine infusion. We used a doubly robust estimator to learn when to start RRT after the occurrence of severe AKI for three days in a row. We developed a "crude strategy" maximizing the population-level hospital-free days at day 60 (HFD60) and a "stringent strategy" recommending RRT when there is significant evidence of benefit for an individual. For validation, we evaluated the causal effects of implementing our learned strategies versus following current best practices on HFD60. We included 3748 patients in the development set and 1068 in the validation set. Through external validation, the crude and stringent strategies yielded an average difference of 13.7 [95% CI -5.3 to 35.7] and 14.9 [95% CI -3.2 to 39.2] HFD60, respectively, compared to current best practices. The stringent strategy led to initiating RRT within 3 days in 14% of patients versus 38% under best practices. Implementing our strategies could improve the average number of days that ICU patients spend alive and outside the hospital while sparing RRT for many. We developed and validated a practical and interpretable dynamic decision support system for RRT initiation in the ICU.

Agrarian Synthesis and Precision Cultivation Optimization System

The ever-growing demand for food production calls for innovative solutions in agriculture. This research introduces a machine learning-based approach, specifically utilizing logistic regression, to predict optimal crops based on soil and weather conditions. The dataset encompasses crucial attributes including Nitrogen (N), Phosphorus (P), Potassium (K), temperature, humidity, pH, rainfall, with corresponding crop labels. The proposed methodology employs logistic regression, a powerful classification algorithm, to model the relationships between input features and crop types. Through careful feature engineering, the model is fine-tuned to enhance its predictive accuracy. Rigorous evaluation metrics validate the model's performance, ensuring its reliability in real-world applications. Results showcase the logistic regression model's efficacy in accurately predicting suitable crops for given soil and weather parameters. This predictive tool serves as a practical decision support system for farmers, aiding in crop selection and resource allocation. This research contributes to the synergy of machine learning and agriculture, showcasing logistic regression as a valuable tool for crop prediction and resource optimization. As technology continues to transform traditional farming, the integration of logistic regression in precision agriculture offers a practical and efficient approach to crop selection.

Machine learning tool for the prediction of electrode wear effect on the quality of resistance spot welds

The quality of resistance spot welding (RSW) joints is strongly affected by the condition of the electrodes. This work develops a machine learning-based tool to automatically assess the influence of electrode wear on the quality of RSW welds. Two different experimental campaigns were performed to evaluate the effect of electrode wear on the mechanical strength of spot welds. The resulting failure load of the joints has been used to define the weld quality classes of the machine learning tool, while data from electrode displacement and electrode force sensors, embedded in the welding machine, have been processed to identify the predictors of the tool. Some machine learning algorithms have been tested. The most performing algorithm, i.e., the neural network, achieved an accuracy of 90%. This work provides important theoretical and practical contributions. First, the decreasing thermal expansion of the weld nugget as the electrode degradation advances results in a strong correlation between the difference of the maximum displacement value and the last value recorded during the welding and the relative failure load. Then, this work offers a practical decision support tool for manufacturers. In fact, the automatic detection of low-quality welds allows to reduce or eliminate unnecessary redundant welds, which are performed to compensate for the uncertainty of electrode wear. This leads to savings in time, energy, and resources for manufacturers. Finally, general recommendations for the timing of redressing or replacing the electrode are provided in the manuscript based on the company willingness to accept some non-compliant welds or not.

Identification and validation of a novel anoikis-related signature for predicting prognosis and immune landscape in ovarian serous cystadenocarcinoma

BackgroundOvarian serous cystadenocarcinoma (OSC) is the most prevalent histological subtype of ovarian cancer (OV) and presents a serious threat to women's health. Anoikis is an essential component of metastasis, and tumor cells can get beyond it to become viable. The impact of anoikis on OSC, however, has only been the topic of a few studies. MethodsThe mRNA sequencing and clinical information of OSC came from The Cancer Genome Atlas Target Genotype-Tissue Expression (TCGA TARGET GTEx) dataset. Anoikis-related genes (ARGs) were collected by Harmonizome and GeneCards websites. Centered on these ARGs, we used unsupervised consensus clustering to explore potential tumor typing and filtered hub ARGs to create a model of predictive signature for OSC patients. Furthermore, we presented clinical specialists with a novel nomogram based on ARGs, revealing the underlying clinical relevance of this signature. Finally, we explored the immune microenvironment among various risk groups. ResultsWe identified 24 ARGs associated with the prognosis of OSC and classified OSC patients into three subtypes, and the subtype with the best prognosis was more enriched in immune-related pathways. Seven ARGs (ARHGEF7, NOTCH4, CASP2, SKP2, PAK4, LCK, CCDC80) were chosen to establish a risk model and a nomogram that can provide practical clinical decision support. Risk scores were found to be an independent and significant prognostic factor in OSC patients. The CIBERSORTx result revealed an inflammatory microenvironment is different for risk groups, and the proportion of immune infiltrates of Macrophages M1 is negatively correlated with risk score (rs = −0.21, P < 0.05). Ultimately, quantitative reverse transcription polymerase chain reaction (RT-PCR) was utilized to validate the expression of the seven pivotal ARGs. ConclusionIn this study, based on seven ARGs, a risk model and nomogram established can be used for risk stratification and prediction of survival outcomes in patients with OSC, providing a reliable reference for individualized therapy of OSC patients.

Evaluation of a new practical low-cost method for prioritising the remediation of fish passage barriers in resource-deficient settings

A key challenge in fishery restoration strategies is prioritising fish passage remediation efforts to achieve optimal ecological and socio-economic outcomes. Various methodologies have been developed for assessing and prioritising the mitigation of fish passage barriers, but they have been designed for developed countries where site data and/or other resources are often readily available. We evaluated a new practical, low-cost basin-scale approach — referred to as the Fish Barrier Prioritisation Support System (FBPSS) — for assessing and prioritising the remediation of fish passage barriers of all types (i.e. large dams, small irrigation structures and road crossings) in resource-deficient settings, like those typical of developing countries. The FBPSS applies a five-stage decision-support framework to prioritise barriers for remediation based on geospatial, biological and socio-economic criteria. The stages involve identifying all potential barriers within the target basin using satellite imagery; conducting GIS analysis to rank the barriers for further investigation; field-validating the highest ranked barriers to ground-truth the GIS analysis results; identifying the highest priority field-validated barriers affecting fisheries productivity; and further refining the list according to socio-economic considerations. We applied the FBPSS to the Bago catchment in Myanmar as a case study, and then validated its effectiveness by comparing the fragmentation impacts (as measured by the Dendritic Connectivity Index) of the FBPSS-prioritised large dams with those of all large dams. The FBPSS successfully identified 876 potential barriers in the Bago catchment, and then systematically assessed these barriers using its filters to produce a prioritised list of 23 barriers for cost-effectively achieving optimal fishery and community benefits. The validation analysis revealed that the high priority FBPSS-combined barriers were responsible for 97–100% of the fragmentation of the combined barriers (with all large dams included). Our findings suggest that the FBPSS could be used as a practical decision support tool, in conjunction with expert knowledge, for prioritising the mitigation of fish passage barriers in resource-deficient settings. Future research could compare the results of the FBPSS with those of an optimisation model to assess how the two approaches perform under different scenarios, and to identify key modelling features that could potentially be integrated into the FBPSS.

Enhancing community resilience in arid regions: A smart framework for flash flood risk assessment

This paper presents a novel framework for smart integrated risk management in arid regions. The framework combines flash flood modelling, statistical methods, artificial intelligence (AI), geographic evaluations, risk analysis, and decision-making modules to enhance community resilience. Flash flood is simulated by using Watershed Modelling System (WMS). Statistical methods are also used to trim outlier data from physical systems and climatic data. Furthermore, three AI methods, including Support Vector Machine (SVM), Artificial Neural Network (ANN), and Nearest Neighbours Classification (NNC), are used to predict and classify flash flood occurrences. Geographic Information System (GIS) is also utilised to assess potential risks in vulnerable regions, together with Failure Mode and Effects Analysis (FMEA) and Hazard and Operability Study (HAZOP) methods. The decision-making module employs the Classic Delphi technique to classify the appropriate solutions for flood risk control. The methodology is demonstrated by its application to the real case study of the Khosf region in Iran, which suffers from both drought and severe floods simultaneously, exacerbated by recent climate changes. The results show high Coefficient of determination (R2) scores for the three AI methods, with SVM at 0.88, ANN at 0.79, and NNC at 0.89. FMEA results indicate that over 50% of scenarios are at high flood risk, while HAZOP indicates 30% of scenarios with the same risk rate. Additionally, peak flows of over 24 m3/s are considered flood occurrences that can cause financial damage in all scenarios and risk techniques of the case study. Finally, our research findings indicate a practical decision support system that is compatible with sustainable development concepts and can enhance community resilience in arid regions.

A comparative assessment of building sustainability schemes in Norway

Various schemes are established to evaluate the sustainability of buildings during their life cycle. These schemes introduce a range of evaluation criteria and indicators and are periodically revised to align with current sustainability trends. This study reviews leading schemes in Norway, and compares their scope, similarities, limitations, and advantages. The review is carried out against a proposed office building in Oslo, Norway. The paper evaluates how the schemes comply with the EU taxonomy and Norwegian building regulations. The schemes are assessed through a literature review and interviews with programme operators. Common sustainability criteria are identified and reviewed. In addition, a comparison of how the schemes address the United Nations Sustainable Development Goals is conducted. The comparative assessment provides a valuable and practical reference and decision support for project owners in Norway to select the appropriate scheme for their construction project.

World Cup 2022 Knockout Stage Prediction Using Poisson Distribution Model

Football is one of the most popular sports in the world. The popularity makes every topic related to football interesting, for instance, the FIFA World Cup winner prediction. This topic is not only for casual discussion but could be a practical decision support for coaching staff to rate the team’s readiness. Most prediction methods use large match datasets. Since every national team has a different squad for every world cup and the FIFA World Cup is held every four years, the usage of a large match dataset is irrelevant. Therefore, there is a need for a prediction method based on the relevant data. We applied the Poisson distribution model for predicting the FIFA World Cup 2022 knockout stage match results. We calculate the probability of winning and losing based on their average goal scores and goal conceded and evaluate the difference by the actual result using de Finetti distance. The successful prediction is 8 out of 15 matches, with six inside the round of 16 games. Thus, the new data attributes need to reformulate Poisson’s lambda. Further studies need to add the 3-4 prior world cup matches data to increase the acceptance of prediction.

Asset Portfolio Risk Management Study-Empirical Analysis Based on VaR Model

This research paper is based on an empirical analysis of portfolio risk management using the value-at-risk (VaR) model. First, the theoretical foundations of portfolio management are introduced, including portfolio theory, asset pricing models, risk management theory and methods, and VaR models. Then the research methodology is described, including data sources and processing, VaR model construction, and risk metric calculation and interpretation. The empirical results section shows the risk analysis and source identification of asset portfolios, the estimation of VaR model parameters and confidence intervals, and the results of VaR calculations and risk measures at different confidence levels. Finally, the results are discussed and analyzed, including the interpretation and comparison of the risk measure results and the advantages and disadvantages of the VaR model. The paper also provides practical risk management recommendations and decision support for investors based on the results of the study. Limitations of the study and future research directions are also discussed. Overall, insights into portfolio risk management using VaR models are provided and a useful reference for researchers and investors interested in this area.

Supply Chains: Planning the Transportation of Animals among Facilities

Pig supply chains conform differently depending on country; however, the industrial production of pig meat has led to an increasing specialization of agents taking part in the supply chain production. Nowadays, pigs are rarely produced in one single farm, the existence of specialized farms devoted to breeding, rearing, and fattening pigs being more common since this organization provides sanitary advantages against disease outbreaks. Management strategies such as batch management in sow and fattening farms add complexity to the production management. Pigs have to be transferred from facility to facility as they are growing and sent to the abattoir as soon as they reach commercial weight. All these stages involve either independent farmers or farmers integrated in some pig supply chain management organization operating with production contracts or cooperation agreements. This study presented the challenge of using a stochastic model for planning the transportation of animals among facilities in pig supply chains over time. The model provides an optimal schedule of transfers between farms, occupancy rate, and trucks involved. The integrality of several variables was relaxed, and further analysis was performed in view of inspecting the model behavior for achieving practical decision support. We demonstrated that we can achieve good enough results in few minutes and, so, practical use is feasible.

Lead time and quality driven transport strategies for the wood supply chain

Fresh roundwood loses quality during storage at roadside primarily through blue stain and insect infestation leading to wood value loss. The potential of altitude zone-based risk forecasts to prioritize spruce sawlog piles at devaluation risk for unimodal and multimodal transport strategies was evaluated with a discrete event simulation model. This enabled tracking roundwood quality development through the supply chain as well as identifying and modelling the relationship between lead time and roundwood quality devaluation. Respective regression analyses showed that the procurement lead time is a significant predictor of the downgraded roundwood amount, explaining over 98% of the variance of downgraded wood. This knowledge was applied to provide practical decision support for procurement management. Presented transport strategies using roundwood quality forecasts significantly outperformed those currently being used by preventing, on average, 57% of the roundwood devaluation in a case study. Moreover, 73% of the devaluation could be avoided if up to 25% supplementary truck transport capacity was deployable in peak periods. If no additional self-loading trucks were available, still 67% of the devaluation could be prevented by using the bottleneck resource more efficiently through transferring 20% of the roundwood to rail wagons leading to a more sustainable and resilient wood procurement.

Valetudinarian Situation Categorize Using Drug Reviews

Human healthcare is one of society's most important issues. To ensure that patients receive the care they require as quickly as possible, it searches for the best diagnosis and thorough disease. For the health-related component of searching, other disciplines are required, such as statistics and computer science, because this recognition is frequently complex[3]. These disciplines must go beyond the traditional ones in order to follow innovative methodologies. Because there are so many new strategies, it is possible to give a general summary without focusing on certain details. In order to do this, we propose a thorough examination of machine learning-related disorders in humans. In order to find interesting trends, make unimportant forecasts, and aid in decision-making[1], this research focuses on existing approaches connected to machine learning growth applied to the diagnosis of human disorders in the medical industry. In order to produce suitable decision support, this study examines distinctive machine learning methods employed in healthcare applications[4], [5]. With the goal of developing a practical decision support system for medical applications, the research gap is to be filled up by this work. Key Words: Human disease, Machine learning, Neural Networks.

Towards Public Opinion Digital Twin: A Conceptual Prototype

This paper proposes a novel modeling concept, the “public opinion digital twin,” for public opinion analysis. The public opinion digital twin can be regarded as an experimental sandbox for social science. By digitalizing public data acquired from cyberspace into digital models, the modeling enables practical simulation, data analytics, scenario reflection, and decision support in a digital space with fine controllability, so that all possible evolutions of the research target can be analyzed. By simply inputting or filtering variables, any number of future scenarios are simulated, the effect models of each strategy for coping with public opinion are presented, and the optimized solution can be derived from continuous deep learning. If a robust digital twin is established and the required digital replicas are constantly updated, the system can perform risk assessments and trend predictions for social events. In this case, public opinion information can provide intelligent decision support for governments or enterprises and significantly facilitate social loss aversion, which will greatly advance the revolution in production, dissemination, and guidance.

Applying cognitive task analysis to health services research.

Designing practical decision support tools and other health care technology in health services research relies on a clear understanding of the cognitive processes that underlie the use of these tools. Unfortunately, methods to explore cognitive processes are rarely used in health services research. Thus, the objective of this manuscript is to introduce cognitive task analysis (CTA), a family of methods to study cognitive processes involved in completing a task, to a health services research audience. This methods article describes CTA procedures, proposes a framework for their use in health services research studies, and provides an example of its application in a pilot study. Observations and interviews of health care providers involved in discharge planning at six hospitals in the Veterans Health Administration. Qualitative study of discharge planning using CTA. Data were collected from structured observations and semi-structured interviews using the Critical Decision Method and analyzed using thematic analysis. We developed an adaptation of CTA that could be used in a clinical environment to describe clinical decision-making and other cognitive processes. The adapted CTA framework guides the user through four steps: (1) Planning, (2) Environmental Analysis, (3) Knowledge Elicitation, and (4) Analyses and Results. This adapted CTA framework provides an iterative and systematic approach to identifying and describing the knowledge, expertise, thought processes, procedures, actors, goals, and mental strategies that underlie completing a clinical task. A better understanding of the cognitive processes that underly clinical tasks is key to developing health care technology and decision-support tools that will have a meaningful impact on processes of care and patient outcomes. Our adapted framework offers a more rigorous and detailed method for identifying task-related cognitive processes in implementation studies and quality improvement. Our adaptation of this underutilized qualitative research method may be helpful to other researchers and inform future research in health services research.

Prediction of forest nutrient and moisture regimes from understory vegetation with random forest classification models

The proper choice of the tree species to be grown in a specific forest site requires a good knowledge of the tree species autecology and a comprehensive description of the local environmental conditions. In Belgium (Western Europe), ecological forest site are classified according to three major gradients: climate, soil nutrient (fertility) and soil moisture regimes. Understory indicator species are used by practitioners to determine nutrient and moisture regimes, but requires a significant expertise of forest ecosystems. The present work aims in a first instance at modelling the nutrient and moisture regimes based on species composition. Secondly, a practical decision support tool is developped and made available in order to predict forest nutrient and moisture regime starting from a floristic relevé. To do so, we collected floristic relevés representing understory vegetation diversity in Belgium and covering all the nutrient and moisture gradient. The combination of soil and topographic measurements with the indicator plants presence/absence support forest scientists in inferring a nutrient and moisture regime to each relevé. The resulting dataset was balanced along the different nutrient or moisture regimes and Random Forest classification models were trained in order to predict the forest site characteristic from indicator species presence (or absence). One model was fitted for the prediction of the nutrient regime, exclusively based on the floristic information. A second one was trained to classify the moisture regime. Accurate predictions confirms the appropriate use of indicator species for the Belgian forest site classification. The two models are intregrated in a web application dedicated to forest practionners. This website enables the automatic determination of nutrient and moisture regimes from the species list of a floristic relevé.

Exploring the Potential of Machine Learning for Modeling Growth Dynamics in an Uneven-Aged Forest at the Level of Diameter Classes: A Comparative Analysis of Two Modeling Approaches

Growth models of uneven-aged forests on the diameter class level can support silvicultural decision making. Machine learning brings added value to the modeling of dynamics at the stand or individual tree level based on data from permanent plots. The objective of this study is to explore the potential of machine learning for modeling growth dynamics in uneven-aged forests at the diameter class level based on inventory data from practice. Two main modeling approaches are conducted and compared: (i) fine-tuned linear models differentiated per diameter class, (ii) an artificial neural network (multilayer perceptron) trained on all diameter classes. The models are trained on the inventory data of the Canton of Neuchâtel (Switzerland), which are area-wide data without individual tree-level growth monitoring. Both approaches produce convincing results for predicting future diameter distributions. The linear models perform better at the individual diameter class level with test R2 typically between 50% and 70% for predicting increments in the numbers of stems at the diameter class level. From a methodological perspective, the multilayer perceptron implementation is much simpler than the fine-tuning of linear models. The linear models developed in this study achieve sufficient performance for practical decision support.