Risk Decision Research Articles

The power of digital twins and concurrency

Supply chains are complex ecosystems, so quickly assessing the short and long-term impacts of events in such an ecosystem is a formidable challenge. We all know that the faster these assessments can be made, the better chance we have of responding and making decisions that will mitigate risk and supply disruptions. For instance, the case study about P&G rapidly adjusting its plans to respond to hurricanes1 is a classic example of why it is critical to make fast assessments amid disruption. While we intuitively understand the value of rapid decision making, it is difficult to quantify and provide a return on investment (ROI) analysis supporting investments in digital twins and concurrent planning. Why? Disruptions typically affect a limited number of sectors and enterprises, their durations vary, geographical impact varies and other events could be happening at the same time. All of this makes it difficult to assess a before, during and after. And then along came COVID-19. The pandemic’s impact was global, across all sectors and almost all enterprises, with a duration of well over a year, with a clear start and relatively clear end. This paper discusses the power of digital twins combined with concurrent supply chain orchestration in risk assessment and decision making as well as the impact on key financial results.

Digitale Informationsmaterialen über Demenz – Eine explorative inhaltsanalytische Betrachtung

ZusammenfassungHintergrundEine Demenzdiagnose bedeutet eine hohe Belastung für die Betroffenen und ihre Angehörigen. Häufig müssen schwierige Entscheidungen getroffen werden. Idealerweise treffen Menschen mit einer neuen Demenzdiagnose informierte Entscheidungen gemeinsam mit Angehörigen. Im Vorfeld einer informierten Entscheidung sind digitale Informationsmaterialien eine wichtige niederschwellige Quelle. Sie sollten möglichst umfassend über Demenz aufklären, sowohl zur Primärprävention (Risikofaktoren für Demenzentstehung) als auch zu späteren Behandlungsmöglichkeiten. Auch über vorsorgliche Maßnahmen, die spätere Entscheidungen erleichtern können (bspw. Patient*innenverfügung, Vorsorgevollmacht), sollte informiert werden. Einen umfassenden Überblick über die diversen Onlineangebote zu Demenzerkrankungen gibt es bisher nicht.MethodeDaher untersucht diese Studie im deutschen Sprachraum mittels einer innovativen systematischen Suchstrategie, welche demenzbezogenen Informationsangebote es digital für welche Zielgruppen gibt und wie diese Materialien inhaltlich hinsichtlich Risikofaktoren und Behandlungsmaßnahmen sowie Entscheidungsunterstützungen aufbereitet sind. Dieser methodische Ansatz ist neu und wird daher ausführlich vorgestellt und diskutiert.ErgebnisseDie Ergebnisse zeigen, dass die meisten Materialien für Menschen mit Demenz sowie deren Angehörige aufbereitet sind. Häufig werden Behandlungsmaßnahmen thematisiert, ohne die Risikofaktoren zu erklären, auf die diese Maßnahmen abzielen. Auf präventive Maßnahmen zur Entscheidungsunterstützung wird kaum eingegangen.DiskussionDie unausgewogene Darstellung kann dazu führen, dass einzelne Maßnahmen (für Laien) schwer nachvollziehbar sind oder Risikofaktoren falsch eingeordnet werden. Wichtige Implikationen werden abgeleitet.

Advancing maintenance, monitoring, and control techniques for the optimization of power electronic systems

This paper explores the innovative methodologies and technologies in predictive maintenance, real-time monitoring, fault detection, and advanced control strategies for power electronic devices. Initially, we delve into data acquisition and preprocessing techniques crucial for ensuring the quality and reliability of data used in predictive models. These models, leveraging machine learning and time-series analysis, predict the remaining useful life of devices, guiding proactive maintenance strategies. Furthermore, we discuss the significance of risk assessment and decision support systems in prioritizing maintenance tasks and allocating resources efficiently. The narrative then shifts to real-time monitoring and fault detection, emphasizing the role of sensor integration, data fusion, anomaly detection, and diagnostics in maintaining system integrity. Condition-based maintenance strategies, underscored by real-time data analytics, are presented as a means to optimize maintenance activities and enhance operational performance. The paper concludes with a detailed examination of advanced control strategies, including model predictive control, reinforcement learning, and distributed control and optimization techniques, highlighting their potential to improve system efficiency, reliability, and adaptability. Through comprehensive research and analysis, this work aims to provide valuable insights into the development of sophisticated maintenance and control mechanisms for power electronic systems, ultimately contributing to their longevity and operational efficacy.

Ex ante litigation risk and firm restatement decisions: Evidence from district courts

This study examines whether ex ante securities litigation risk prompts firms to make more or less voluntary restatements. The litigation risk is captured by a new measure based on the dismissal rate of the district court where the firm is headquartered. We find that misreporting firms headquartered in lenient (high dismissal rate) court jurisdictions are more likely to make voluntary restatements. Using the U.S. Supreme Court’s Tellabs decision as an exogenous shock that reduces the leniency of some district courts, we find robust evidence that higher litigation risk decreases managers’ incentives to admit their misreporting. Our finding sheds new light on the litigation risk-voluntary disclosure paradox by pointing to a positive aspect of court leniency in motivating self-policing behavior such as restatement.

Bayesian decision based fusion algorithm for remote sensing images

Remote sensing image fusion is dedicated to obtain a high-resolution multispectral (HRMS) image without spatial or spectral distortion compared to the single source image. In this paper, a novel fusion algorithm based on Bayesian estimation for remote sensing images is proposed from the new perspective of risk decisions. In this study, an observation model based on Bayesian estimation for remote sensing image fusion is constructed. Three categories of probabilities including prior, conditional and posterior probabilities are calculated after an intensity-hue-saturation (IHS) transformation is applied to the original low-resolution MS image. To obtain the desired HRMS image, with the corrected posterior probability, a fusion rule based on Bayesian decisions is designed to estimate which pixels to select from the panchromatic (PAN) image and the intensity component of the MS image. The selected pixels constitute a new component that will participate in an IHS inverse transformation to yield the fused image. Extensive experiments were performed on the Pleiades, WorldView-3, and IKONOS datasets, and the results demonstrate the effectiveness of the proposed method.

Coastal emergency managers’ risk perception and decision making for the Tonga distant tsunami

On January 15, 2022, the Hunga-Tonga-Hunga-Ha'apai (Tonga) volcano erupted and triggered a tsunami forecasted to reach North America. This event provided a unique opportunity to investigate risk perception and communication among coastal emergency managers and emergency program coordinators (EMs). In response, this research explores 1) how risk can be communicated most effectively and 2) how risk perceptions associated with “distant” tsunami alerts and warnings affect EMs' willingness to issue emergency alerts. A purposive sample of coastal EMs (n = 21) in the U.S. Pacific Northwest participated in semi-structured interviews. Participants represented Tribal, county, state, and federal agencies in Washington, Oregon, and California. Interview transcripts were deductively coded and thematically analyzed. Participants perceived low risk from the Tonga tsunami but took precautionary measures and alerted the public. Participants described how their actions were driven by community characteristics and the anticipated reactions to messaging among residents. Many reported the need to balance notifying the public and avoiding the negative impacts of their messaging (e.g., “crying wolf,” panic, curiosity). The unique nature of the event led to identification of unanticipated facilitators and barriers to decision-making among participants. These findings can inform distant tsunami risk communication and preparedness for coastal communities.

Contamination of herbs and spices: A 23‐year EU RASFF notifications analysis

AbstractFrom 2000 to 2022, all and serious notifications of the EU Rapid Alert System for Food and Feed (RASFF) on herbs and spices were examined to identify the most notified products, their associated hazards and origin countries, as well as the consequent notification classification and actions taken. The data reveals that 3741 notifications were transmitted for herbs and spices during the last 23 years, accounting for 5.3% of the RASFF total notifications of all product categories (70630). Border rejection and serious risk decisions represented 37.9% and 39.5% of the total herbs and spices notifications, respectively. In the last 5 years, serious notifications ranged from 76.6% to 87.2% of all herbs and spices notifications. India was the most notified origin country (23.6%), followed by Brazil (8.7%), Thailand (7.2%), Turkey (5.8%), and China (4.6%). The top 10 notified herbs and spices were chili, black pepper, curry, paprika, nutmeg, spice mix, basil, mint, ginger, and cumin, while the top 10 hazards were Salmonella, aflatoxin, Sudan 1, Sudan 4, ethylene oxide (EtO), ochratoxin A, chlorpyrifos, Escherichia coli, pyrrolizidine alkaloids, and color E 160b. Approximately 96.3% of black pepper, 71% of chili, and almost all nutmeg serious notifications were related to Salmonella, aflatoxins, and mycotoxins, respectively. Strict measures to minimize the risk associated with such contaminants in herbs and spices must be implemented.

Phylogenomics-driven host test list selection for weed biological control

A concern in weed biological control research is the potential for candidate biocontrol agents to impact not only the target weed but also native or economically important flora. The degree of evolutionary relatedness between the target weed species and a non-target species is a key predictor of the susceptibility of the non-target to the biocontrol agent. To manage this risk, biocontrol practitioners need to understand the phylogenetic position of the host weed relative to non-target plant species. However, comprehensively sampled phylogenetic trees are often unavailable, with incomplete information scattered across multiple publications. Further, older published phylogenies based on Sanger sequence data often lack branch resolution and support, which increases uncertainty in biocontrol decision making. Decreasing sequencing cost and technological advances have led to phylogenomic approaches being more widely used to understand evolutionary relationships between species. For example, target capture sequencing methods using bait kits such as Angiosperms353 enable cost-effective and timely phylogenomic-level analysis of flowering plant groups at different scales. Here, we introduce a workflow to embed a comprehensive understanding of evolutionary relationships into the efficient development of host test lists in weed biological control. We demonstrate the effectiveness of the workflow through a case study on the major crop weed flaxleaf fleabane (Erigeron bonariensis). Phylogenomic analysis was conducted on 280 species of the tribe Astereae (family Asteraceae) occurring in Australia and New Zealand, clarifying relationships between the target species and related clades of native and non-native Astereae. We consider the phylogenetic tree in the context of a previously proposed host test list and discuss taxonomic implications, highlighting avenues of future molecular-based work to uncover the origin of Australian fleabanes. This study provides a workflow and demonstrates the practical application of target sequence capture for phylogenomic inference to support risk analysis and decision making in classical weed biological control.

The prognostic value of preoperative systemic inflammatory response index in predicting outcomes of acute type A aortic dissection patients underwent surgical treatment.

The systemic inflammatory response index (SIRI) is a novel inflammatory-immune biological marker that has prognostic value in various cardiovascular diseases. This study aims to investigate the relationship between SIRI and short-term and long-term prognosis in patients with acute type A aortic dissection (AAAD) underwent surgical treatment. We conducted a retrospective analysis of patients with AAAD who underwent emergency surgical treatment at our center. Through multifactorial logistics regression analysis and cox proportional hazards regression analysis, we identified SIRI as an independent risk factor for major adverse events (MAEs) and long-term aorta-related adverse events (ARAEs) post-surgery. The optimal cutoff value of preoperative SIRI was determined using receiver operating characteristic (ROC) curve analysis, and patients were divided into low SIRI group and high SIRI group. The prognostic outcomes at different time points post-surgery for the two groups of patients were analyzed using Kaplan-Meier survival analysis, and the significance was determined by log-rank test. A total of 691 AAAD patients were included in this study. Among them, 50 patients (7.2%) died within 30 days post-surgery, and 175 patients (25.3%) experienced MAEs. A total of 641 patients were followed up, with an average follow-up time of 33.5 ± 17.5 months, during which 113 patients (17.6%) experienced ARAEs. The results of multifactorial logistics regression analysis and cox proportional hazards regression analysis showed that SIRI was an independent risk factor for postoperative MAEs (OR=3.148, 95%CI[1.650-6.006], p<0.001) and ARAEs (HR=2.248, 95%CI[1.050-4.809], p<0.037). Kaplan-Meier analysis demonstrated that the MAEs-free survival in the high SIRI group was significantly lower than that in the low SIRI group, and a similar trend was observed in the ARAEs-free survival during follow-up (log-rank test, p<0.001). Preoperative SIRI is significantly associated with the short-term and long-term prognosis of AAAD patients underwent emergency open surgery, demonstrating its valuable prognostic value. Therefore, preoperative SIRI is a reliable biological marker that can serve as a valuable tool for preoperative risk stratification and decision management.

The impact of stress on the risk decision-making process.

The effect of stress on risk-taking or risk-averse behavior in decision-making has been inconclusive in previous research, with few studies revealing the underlying neural mechanisms. This study employed event-related potentials technique and combined a social cold pressor assessment test with a mental arithmetic task to induce stress responses, aiming to investigate the influence of exogenous stress on the risk decision-making process. Stress induction results indicated that, in addition to raising heart rate and blood pressure, stress responses were accompanied by enhanced negative emotions, diminished positive emotions, and alterations in neural activity. The outcomes of risk decision-making showed that stress did not significantly affect risk preference or time of choice but did reduce the feedback-related negativity/reward positivity, with a particularly significant effect observed for large outcomes. Stress also altered the amplitude of the P3 component, with stress decreasing the P3 value for winning outcomes relative to losing outcomes. The study suggests that understanding how stress affects risk preference should consider the emotional valence induced by stress. Contrary to the reward sensitivity hypothesis, stress weakened reward sensitivity. Stress led to changes in the allocation of cognitive resources for outcome evaluation: compared to negative outcomes, stress reduced cognitive resources for positive outcomes, which might be related to the enhanced negative emotions induced by stress. The study highlights the importance of focusing on the subjective emotional experience induced by stress in future research on stress and risk decision-making.

The impact of information presentation on self-other risk decision-making.

To explore the impact of social distance and information presentation types on self-other risk preferences in monetary tasks. Risk preferences were examined in decision-making tasks and experiential information tasks within different frameworks when participants made decisions for themselves and others. Experiment 1 employed experiential decision tasks and revealed individual differences in decision-making for oneself and others. In gain situations, participants exhibited more risk aversion when deciding for others compared to themselves. Experiment 2 presented both types of information simultaneously to investigate whether risk decisions for oneself and others are influenced by information types. Results indicated that experiential information led participants to make more conservative choices for others, while descriptive information eliminated this effect. This study discovered the influence of social distance on self-other risk decisions and the role of information presentation types in self and other risk decision-making. Future research could further explore self-other decision-making from the perspectives of decision-makers' traits and culture.

Diurnal biological effects of correlated colour temperature and its exposure timing on alertness, cognition, and mood in an enclosed environment

Artificial lighting, which profits from the non-visual effects of light, is a potentially promising solution to support residents’ psychophysiological health and performance at specific times of the day in enclosed environments. However, few studies have investigated the non-visual effects of daytime correlated colour temperature (CCT) and its exposure timing on human alertness, cognition, and mood. However, the neural mechanisms underlying these effects are largely unknown. The current study evaluated the effects of daytime CCT and its exposure timing on markers of subjective experience, cognitive performance, and cerebral activity in a simulated enclosed environment. Forty-two participants participated a single-blind laboratory study with a 4 within (CCT: 4000 K vs. 6500 K vs. 8500 K vs. 12,000 K) × 2 between (exposure timing: morning vs. afternoon) mixed design. The results showed time of the day dependent benefits of the daytime CCT on subjective experience, vigilant attention, response inhibition, working memory, emotional perception, and risk decisions. The results of the electroencephalogram (EEG) revealed that lower-frequency EEG bands, including theta, alpha, and alpha-theta, were quite sensitive to daytime CCT intervention, which provides a valuable reference for trying to establish the underlying mechanisms that support the performance-enhancement effects of exposure to CCT in the daytime. However, the results revealed no consistent intervention pattern across these measurements. Therefore, future studies should consider personalised optimisation of daytime CCT for different cognitive demands.

Machine Learning-Based Resilience Modeling and Assessment of High Consequence Systems Under Uncertainty

Abstract This study proposes a theoretical model and assessment method for the resilience of High Consequence System (HCS), addressing the risk assessment and decision-making needs in critical system engineering activities. By analyzing various resilience theories in different domains and considering the characteristics of risk decision-making for HCS, a comprehensive theoretical model for the resilience of HCS is developed. This model considers the operational capability under normal environment (consisting of reliability and maintainability) and the safety capability under abnormal environment (consisting of resistance and emergence response ability). A case study is conducted on a spent fuel transportation packaging system, where the sealing performance after sealing ring aging is regarded as the reliability of the system and calculated using reliability methods, and impact resistance after impact is regard as resistance the impact safety of the packaging system is assessed using finite element analysis and surrogate modelling methods. The surrogate model fits the deformation output results of finite elements. Maintainability and emergency response ability are also essential elements of the resilience model for HCS facing exceptional events. The resilience variation of the spent fuel transportation packaging system is computed under the uncertainty of yielding stress of buffer material. The resilience of the packaging system is evaluated for different buffer thicknesses. The system's resilience decreases with higher uncertainty in the yielding stress of the buffer material, while it increases with thicker buffer materials. The improvement of emergency rescue ability will also lead to the improvement of system resilience.

Decoding Adolescent Decision Making: Neurocognitive Processes, Risk Perception, and the Influence of Peers

Investigating the neurocognitive mechanisms behind implicit risk assessment and decision making in adolescents is crucial for understanding the intricate array of behaviors typical of this developmental phase [...]

Optimizing Financial Risk Models in Digital Transformation-Deep Learning for Enterprise Management Decision Systems

The digital transformation of enterprises has amplified the complexity of financial risks, underscoring the significance of optimizing financial risk warning models to ensure sustainable development. This study integrates several deep learning techniques, including Back Propagation Neural Network (BPNN), Bi-Long Short-Term Memory (Bi-LSTM), and transfer learning, to enhance the risk warning system and improve the accuracy and efficiency of financial risk prediction models. The results demonstrate that the proposed algorithm surpasses the baseline models in various metrics. For instance, on the Altman's Z-Score dataset, there is an improvement of 1.4% in accuracy, a reduction of over 48.8% in FLOP, and an enhancement of 43.5% in MAPE. These outcomes underscore the significant advancements in risk identification, decision support, and proactive risk management facilitated by the proposed model. As a result, enterprises can derive benefits from more precise and reliable financial risk warning tools, and effectively address the challenges brought about by digital transformation.

Enterprise Credit Risk Decision: Application Based on Improved AHP

The credit risk of Shouguang vegetable enterprises in China is the biggest obstacle to corporate loans. Building a credit risk assessment model for Shouguang vegetable enterprises and accurately rating the risk of loan enterprises is the key to successful loans. This article aims to construct an AHP evaluation model for the credit risk of Shouguang vegetable enterprises. The data is sourced from managers, bank credit personnel, university researchers, and enterprise related customers who are familiar with the enterprise, while considering four risk levels: impact degree(I), occurrence probability(P), risk manageability(M), and government support(S). This article uses AHP and risk index scores to evaluate the credit risk of Shouguang vegetable enterprises. This model calculates the risk index score based on survey data from 41 corporate credit risk professionals, constructs a pairwise comparison judgment matrix, and conducts consistency testing. It calculates the risk level membership vectors of impact degree, occurrence probability, risk manageability, and government support level at four risk levels, and then calculates the comprehensive evaluation membership vector of credit risk for Shouguang vegetable enterprise. The calculation results show that the comprehensive credit risk assessment level of Shouguang vegetable enterprise belongs to the general risk level, with a membership value of 0.5836. The results still show that the credit rating of Shouguang vegetable enterprises in the four risk levels of impact degree, occurrence probability, risk manageability, and government support are all average risk levels, but there are differences in membership values. The maximum membership value under the impact degree level is 0.6163, and the minimum membership value under the risk manageability level is 0.5572. This study provides a feasible and practical model for enterprise credit risk assessment and conducts a detailed evaluation of the credit risk of Shouguang vegetable enterprise, providing valuable reference for enterprise managers, bank credit personnel, and related researchers.

The effect of tone, signature, and visual elements in compliance management systems disclosures on financial analysts’ decisions

Numerous corporate scandals, in conjunction with managerial misbehavior, demonstrate both the need for effective compliance management systems (CMS) and the relevance of compliance reporting. Disclosure elements are a major differentiator when reporting on CMS. This study investigates whether the tone, top managers’ signatures, and visual elements affect financial analysts’ perceptions and decisions. We use several theories from cognitive psychology which suggest that positive tone, the presence of signatures, and the combination of textual and visual elements can induce more favorable perceptions of compliance disclosure. In a 2 × 2 × 2 between-subjects experiment with 148 financial analysts from Germany, we manipulate tone (positive vs. negative), top managers’ signatures (present vs. absent), and visual elements (present vs. absent) to measure analyst perceptions of reliability, understandability, and usability, as well as credit risk, purchase, and recommendation decisions. We then sum up these dependent variables to create two new variables, perceptions, and decisions. Our results suggest that negatively toned compliance disclosure positively affects financial analyst perceptions, unless it is combined with a visual, as well as their decisions, unless it is combined with both a signature and a visual element. Additionally, signatures and a visual element have an overall positive effect on analyst perceptions. The study’s results confirm the relevance of disclosure elements in compliance reporting, which should be of interest to preparers, users, auditors, and regulators of compliance disclosure.

The non-visual effects of correlated color temperature on the alertness, cognition, and mood of fatigued individuals during the afternoon

Railway dispatchers are prone to mental fatigue due to prolonged periods of intense concentration. As the main or even the only light source in the enclosed control centers, artificial lighting has non-visual effects on human alertness, cognition, and mood. To investigate whether external environmental cues could counteract performance decline induced by endogenous cardiac exhaustion, the current study modulated four correlated color temperature (CCT) levels and developed one visual task and six cognitive tasks representing basic and advanced cognitive functions, including sustained attention, response inhibition, working memory, risk decision-making, executive control, and emotion perception. A within-subjects design was employed to collect subjective and behavioral responses under both normal and fatigued mental antecedent states. Electroencephalogram (EEG) with alpha and theta bands as well as four fatigue-related algorithms including θ/β, α/β, (θ+α)/β, and (θ+α)/(α+β) were analyzed to explore the underlying neural mechanisms behind these responses. The results indicated a complex interactive pattern of CCT and mental antecedent state on alertness, cognition, and mood. Higher CCT had a supportive effect on subjective alertness and positive mood, independent of mental antecedent state. However, it exhibited a slight performance-impairing effect on sustained attention tasks. Conversely, higher CCT demonstrated a significant enhancement in advanced cognitive functions for fatigued individuals. EEG data revealed alpha oscillations increased, but theta activity and (θ + α)/β suppressed at 12,000 K, suggesting higher CCT partially alleviated the decline in alertness and cognition induced by mental fatigue. To develop an appropriate photobiological lighting scheme for fatigue intervention, larger and longer-term studies are needed in the future to measure a range of confounding factors and individual differences.

Research on the Optimal Strategy of Investment Portfolio Based on Markowitz Model

Nowadays, investment is becoming increasingly common. Under the globalization of the economy, investors are given more investment opportunities and choices. Investors need to select excellent assets and allocate the selected asset portfolio on weight during the investment process. The mean-variance model proposed by Markowitz plays an important guiding role in investment and risk management. This model can effectively evaluate investors portfolio risk and return decisions and significantly impact their decision-making choices. This study uses the data of the annual average return and variance from 11 risky assets and 1 risk-free asset in about 20 years to construct an investment portfolio in a fixed group based on the Markowitz Model. The study calculates the changes in the allocation of the maximum Sharpe ratio and the minimum variance portfolios under three different constraints and one condition with the addition of risk-free assets, respectively, and then analyzes changes in the outcome of data. The capital allocation lines are introduced to analyze the outcome of an investment portfolio with risk-free assets. Compared with the changes from three constraints, reasons are explained why these changes happen under three constraints. Then, the above limitations are taken as a premise, and the study proposes recommendations for the optimal investment portfolio selection for different investors according to the investment cycle, the preference of investors based on the situation of different investors, and market constraints. The study guides investors future investment decisions.

Weighted probability kernel multi-granularity three-way decision integrating GRA and its application in medical diagnosis

Three-way decision, an outstanding method to handle decision-making uncertainties, relies on essentially the loss functions derived from the Bayesian risk decision process. Actually, there are plentiful loss functions that depend on the subjective judgment of decision-makers under different decision scenarios, lacking uniform and objective measurement frameworks. This study pays attention to the real clinical diagnosis, and constructs a weighted probability kernel multi-granularity three-way decision method (WKMG-TWD) integrating gray relation analysis (GRA) over a multi-source heterogeneous decision information system (MHDIS). The method establishes a standardized data-driven calculation framework of loss functions. Foremost, the multi-kernel probabilistic similarity is defined and granularity's weights with knowledge consistency are explored. Subsequently, a weighted probability kernel multi-granularity rough set (WKMGRS) is constructed in this paper. Secondly, to introduce the three-way decision, this study proposes the cost-sensitive individual loss functions considering the correlation determined by GRA between decision objects and different decision classes. Ultimately, this study establishes and applies a three-way iterative classification model to hypertension diagnosis. The experimental results confirm the effectiveness and superiority of the model. The main contribution of this paper is twofold. One is to offer a uniform calculation framework for loss functions and granularity's weights. The other is to furnish invaluable guidance for solving complex medical decision-making problems.