Uncertain Reasoning Research Articles

Enhancing AI interpretation and decision-making: Integrating cognitive computational models with deep learning for advanced uncertain reasoning systems

Advancements in uncertain reasoning systems within healthcare are crucial for navigating the complexities of patient data, requiring innovative methodologies that integrate AI interpretation capabilities and robust handling of inherent ambiguity. Healthcare systems face the challenge of handling uncertainty inherent in patient data, necessitating sophisticated decision-making tools like Uncertain Reasoning Systems (URS) for effective ambiguity navigation. Recognizing the complexity of healthcare scenarios, advancements in AI interpretation within URS are crucial beyond traditional methods. Conventional techniques like statistical approaches and rule-based systems often prove inadequate due to their rigid frameworks and limited ability to manage inherent ambiguity. This paper proposes an innovative methodology that integrates Min-Max normalization and robust missing data handling techniques with Hybrid Fuzzy Rule-Based Systems and Neural Networks, supplemented by Game Theory for model refinement. Through the integration of Game Theory, it can dynamically adjust its strategies to healthcare data uncertainties, thereby enhancing its resilience and efficacy. Implemented using Python tools, the proposed system achieves an exceptional 99.4 % accuracy, surpassing baseline methods such as FNN (88.1 %) and Naïve Bayes (90 %), highlighting its superior performance in healthcare decision-making. These findings represent significant strides in AI interpretation and decision-making within Uncertain Reasoning Systems, underscoring the practical relevance of the proposed approach.

Rationale for the Inclusion of β-Blockers Among Major Antihypertensive Drugs in the 2023 European Society of Hypertension Guidelines.

We address the reasons why, unlike other guidelines, in the 2023 guidelines of the European Society of Hypertension β-blockers (BBs) have been regarded as major drugs for the treatment of hypertension, at the same level as diuretics, calcium channel blockers, and blockers of the renin-angiotensin system. We argue that BBs, (1) reduce blood pressure (the main factor responsible for treatment-related protection) not less than other drugs, (2) reduce pooled cardiovascular outcomes and mortality in placebo-controlled trials, in which there has also been a sizeable reduction of all major cause-specific cardiovascular outcomes, (3) have been associated with a lower global cardiovascular protection in 2 but not in several other comparison trials, in which the protective effect of BBs versus the other major drugs has been similar or even greater, with a slightly smaller or no difference of global benefit in large trial meta-analyses and a similar protective effect when comparisons extend to BBs in combination versus other drug combinations. We mention the large number of cardiac and other comorbidities for which BBs are elective drugs, and we express criticism against the exclusion of BBs because of their lower protective effect against stroke in comparison trials, because, for still uncertain reasons, differences in protection against cause-specific events (stroke, heart failure, and coronary disease) have been reported for other major drugs. These partial data cannot replace global benefits as the main deciding factor for drug choice, also because in the general hypertensive population whether and which type of event might occur is unknown.

Multicenter prospective observational study to clarify the current status and clinical outcome in Japanese patients who have an indication for implantable cardioverter defibrillator (ICD) or wearable cardioverter defibrillator (WCD) (TRANSITION JAPAN‐ICD/WCD study): Rationale and design of a prospective, multicenter, observational, comparative study

AbstractBackgroundDespite the positive impact of implantable cardioverter defibrillators (ICDs) and wearable cardioverter defibrillators (WCDs) on prognosis, their implantation is often withheld especially in Japanese heart failure patients with reduced left ventricular ejection fraction (HFrEF) who have not experienced ventricular tachycardia (VT) or ventricular fibrillation (VF) for uncertain reasons. Recent advancements in heart failure (HF) medications have significantly improved the prognosis for HFrEF. Given this context, a critical reassessment of the treatment and prognosis of ICDs and WCDs is essential, as it has the potential to reshape awareness and treatment strategies for these patients.MethodsWe are initiating a prospective multicenter observational study for HFrEF patients eligible for ICD in primary and secondary prevention, and WCD, regardless of device use, including all consenting patients. Study subjects are to be enrolled from 31 participant hospitals located throughout Japan from April 1, 2023, to December 31, 2024, and each will be followed up for 1 year or more. The planned sample size is 651 cases. The primary endpoint is the rate of cardiac implantable electronic device implementation. Other endpoints include the incidence of VT/VF and sudden death, all‐cause mortality, and HF hospitalization, other events. We will collect clinical background information plus each patient's symptoms, Clinical Frailty Scale score, laboratory test results, echocardiographic and electrocardiographic parameters, and serial changes will also be secondary endpoints.ResultsNot applicable.ConclusionThis study offers invaluable insights into understanding the role of ICD/WCD in Japanese HF patients in the new era of HF medication.

A novel multi-criteria conflict evidence combination method and its application to pattern recognition

In recent years, the Dempster–Shafer Theory (DST) has been widely applied in areas such as target classification and multi-modal fusion due to its advantages in uncertain reasoning. However, in DST, when there exists highly conflicts between Sources of Evidence (SoEs), it often leads to counterintuitive fusion results, thereby affecting the performance of the final fused decision-making. To eliminate the potential impact of highly conflicts during the fusion process, this paper primarily focuses on modifying the SoEs themselves to achieve the discounting fusion. Currently, existing literature has proposed numerous discounting fusion methods to address highly conflict fusion. However, in these discounting strategies, the determination of discounting factors is typically based on a single criterion. Considering that a single indicator cannot comprehensively and accurately assess the reliability of each evidence source, this paper introduces a novel conflict evidence combination method based on a multi-criteria evaluation strategy. In this method, the Best and Worst Method (BWM) is initially used to prioritize the best SoE, determining the solution points for each criterion and subsequently selecting the ideal solution. Then, combining the selected criteria: distance, relative entropy, and divergence metrics, reliability calculation is performed based on the Stable Preference Order Theory for Ideal Solution (SPOTIS), which achieves a stable preference order strategy towards the ideal solutions. Finally, leveraging the discounting fusion method in DST, modification and fusion of the original highly conflict SoEs are achieved. Through extensive experiments, the effectiveness and practicality of the proposed method in this paper have been validated.

Early onset metastatic colorectal cancer in Australia

BackgroundColorectal cancer (CRC) incidence and mortality rates have been increasing among young patients (YP), for uncertain reasons. It is unclear whether YP have a distinct tumor biology or merit a different treatment approach to older patients (OP). MethodsWe reviewed prospectively collected data from consecutive patients with metastatic CRC (MCRC) enrolled in the multi-site Treatment of Recurrent and Advanced Colorectal Cancer (TRACC) Australian registry. Clinicopathological features, treatment and survival outcomes were compared between YP (<50 years) and OP (≥50 years). ResultsOf 3692 patients diagnosed August 2009 - March 2023, 14 % (513) were YP. YP were more likely than OP to be female (52% vs. 40 %, P < 0.0001), have ECOG performance status 0–1 (94% vs. 81 %, P < 0.0001), to have a left-sided primary (72% vs. 63 %, P = 0.0008) and to have fewer comorbidities (90% vs. 60 % Charleston score 0, P < 0.0001). There were no differences in the available molecular status, which was more complete in YP. YP were more likely to have de novo metastatic disease (71% vs. 57 %, P < 0.0001). YP were more likely to undergo curative hepatic resection (27% vs. 17 %, P < 0.0001), to receive any chemotherapy (93% vs. 78 % (P < 0.0001), and to receive 3+ lines of chemotherapy (30% vs. 24 % (P < 0.0034)). Median first-line progression free survival (10.2 versus 10.6 months) was similar for YP vs OP, but overall survival (32.1 versus 25.4 months, HR = 0.745, P < 0.0001) was longer in YP. ConclusionKnown prognostic variables mostly favored YP versus OP with newly diagnosed mCRC, who were also more heavily treated. Consistent with this, overall survival outcomes were improved. This data does not support that CRC in YP represent a distinct subset of mCRC patients, or that a modified treatment approach is warranted.

Belief f-divergence for EEG complexity evaluation

Evidence theory, as a useful uncertain reasoning method, is widely used in various fields. Nevertheless, how to quantify the divergence between the basic belief assignments in belief theory and how to apply it are still open issues. To measure the discrepancy between basic belief assignments, we first introduce belief f-divergence (BFD) in this paper. We also analyze and verify its related properties that are expected to significantly improve the performance of electroencephalogram (EEG) complexity evaluation. Then, we employ empirical mode decomposition to detrend EEG noise and reconstruct EEG signals with inherent components and develop a belief f-divergence-based complexity (BFDC) evaluation method with five different functions, including belief KL divergence, belief Hellinger divergence, belief χ2 divergence, belief triangular divergence, and belief total variation divergence, to evaluate the complexity of the EEG signals. Based on a benchmark lane-keeping EEG driving experiment, our proposed BFDC evaluation approach can identify the differences among keep–drift events more obviously and significantly reduce the root mean squared error up to the order of 102 compared to the existing complexity measurement of fuzzy entropy. We believe that our proposed BFDC evaluation method has the potential to be a new and robust approach to precisely evaluate the dynamic complexity of physiological signals.

Information Fusion-Based Fault Diagnosis Method Using Synthetic Indicator

Multisensor information fusion technology plays an essential role in fault diagnosis. Uncertain reasoning is the core of information fusion, and the DS evidence theory (DSE) has founded a general and popular framework for uncertainty reasoning. Under this framework, a novel information fusion method is developed in this article, to solve the problems of counterintuitive results, poor robustness, and “one-vote veto” when fusing highly conflicting evidence using DSE. We proposed a new synthetic indicator, which can effectively eliminate the conflicts between evidences. This synthetic indicator is composed of two indexes: measurement index of indirect conflicts and that of the evidence’s information itself. First, the divergence is used to measure the degree of conflict between bodies of evidence, and the Decision-Making Trial and Evaluation Laboratory (DEMATEL) model is employed to deal with indirect conflicts. Second, the Deng entropy is utilized to quantitatively measure the uncertainty of evidences, and the relative credibility preference of the evidence is expressed by the fuzzy preference relation. Finally, the initial body of evidence frame is weighted and revised by synthetic indicator before adopting the Dempster Shafer (DS) fusion rule. The superiority of the developed method is illustrated by numerical examples and application cases. The results show that fault diagnosis using the developed information fusion method can have a higher diagnostic accuracy.

Book Reviews

Jurgen Eichberger of University of Heidelberg reviews “Beyond Uncertainty: Reasoning with Unknown Possibilities” by Katie Steele and H. Orri Stefansson. The Econlit abstract of this book begins: “Examines cases of limited awareness and changes in awareness in the philosophy of decision-making and uncertain reasoning, presenting the argument that the unpredictability of awareness growth does not preclude anticipating awareness growth.”

Simplified antibiotic treatment for paediatric osteoarticular infections achieved good outcomes.

Early diagnosis of osteoarticular infections (OAI) in children and effective treatment prevents complications. The objective of this study was to evaluate effectiveness and safety of shortened intravenous antibiotic treatment of OAI. Incidence, diagnostics and pathogens of paediatric OAI were assessed. This retrospective study included all paediatric OAI admissions to The Children's Hospital Iceland in 2006-2020. The treatment was evaluated by dividing the study cohort into two groups. The simplified treatment group received intravenous antibiotics for less than 7 days. The longer intravenous group received intravenous antibiotics for a minimum of 7 days. In total, 205 cases of OAI were included: 106 osteomyelitis, 83 septic arthritis and 16 with both. Age standardised incidence was 17 per 100,000 children and decreased over the study period (p=0.004). A pathogen was identified in 37% (75/205) of cases of which 65% (49/75) were Staphylococcus aureus and 12% (9/75) Kingella kingae. Simplified treatment was not associated with increased risk of complications. This study supports claims that simplified treatment for OAI is safe and effective. Further simplification of treatment might be viable. For uncertain reasons the incidence of OAI was decreasing in Iceland, predominantly in young children.

Revisiting the phase transformations involving Cu6Sn5 intermetallic: resolving local domain structures induced by ordering

Cu6Sn5 is one of the most important intermetallics present in solder joints based on Cu and Sn. Due to still uncertain reasons for failure of these joints, detailed microstructural research can help to figure out the underlying mechanisms. For Cu- and as well for Sn-rich environments of the Cu6Sn5 the microstructural occurrence of the phase transformations are investigated. During the formation of stable η′ from the disordered high temperature η phase the formation of metastable modulated incommensurately ordered η′′ takes place. For the copper rich samples long-range ordering and twin-related domain formation within η′′ was observed. Although conventional Hough-based EBSD analysis was not able to identify the correct domain orientation, Kikuchi pattern matching using simulated patterns was able to resolve the correct microstructure. As ordered intermetallics tend to be brittle in nature, the current microstructure research provides a basis to investigate unresolved problems in the initiation of failure.

A logic-based tractable approximation of probability

Abstract We provide a logical framework in which a resource-bounded agent can be seen to perform approximations of probabilistic reasoning. Our main results read as follows. First, we identify the conditions under which propositional probability functions can be approximated by a hierarchy of depth-bounded belief functions. Second, we show that under rather palatable restrictions, our approximations of probability lead to uncertain reasoning which, under the usual assumptions in the field, qualifies as tractable.

Integrating Cognitive Principles From ACT-R Into Probabilistic Conditional Reasoning by Taking the Example of Maximum Entropy Reasoning

Many modern artificial intelligence (AI) systems like human-interacting smart devices or expert systems adapt to specific users' information processes but the underlying AI methods commonly lack a theory of mind. Thus, there is a need to better understand human thinking and to integrate the resulting cognitive models into AI methods. By taking the example of maximum entropy reasoning (MaxEnt), we integrate cognitive principles from the cognitive architecture ACT-R into uncertain reasoning based on probabilistic conditionals. Therewith, we combine two powerful and well-established methodologies from probabilistic reasoning (MaxEnt) and cognitive science (ACT-R) and establish a blueprint for cognitive probabilistic reasoning.

Uncertainty prediction of mining safety production situation

In order to explore the occurrence and development law of mining safety production accidents, analyze its future change trends, and aim at the ambiguity, non-stationarity, and randomness of mining safety production accidents, an uncertainty prediction model for mining safety production situation is proposed. Firstly, the time series effect evaluation function is introduced to determine the optimal time granularity, which is used as the window width of fuzzy information granulation (FIG), and the time series of mining safety production situation is mapped to Low, R, and Up three granular parameter sequences, according to the triangular fuzzy number; then, the mean value of the intrinsic mode function (IMF) is maintained in the normal dynamic filtering range. After the ensemble empirical mode decomposition (EEMD), the three non-stationary granulation parameter sequences of Low, R, and Up are decomposed into the intrinsic mode function components representing the detail information and the trend components representing the overall change, and then the sub-sequences are reconstructed according to the sample entropy to highlight the correlation among the sub-sequences; finally, the cloud model language rules of mining safety production situation prediction are created. Through time series discretization, cloud transformation, concept jump, time series set division, association rule mining, and uncertain reasoning, the reconstructed component sequence is modeled and predicted by uncertainty information extraction. The accuracy of the uncertainty prediction model was verified by 21 sets of test samples. The average relative errors of Low, R, and Up sequences were 9.472 %, 16.671 %, and 3.625 %, respectively. The research shows that the uncertainty prediction model of mining safety production situation overcomes the fuzziness, non-stationarity, and uncertainty of safety production accidents, and provides theoretical reference and practical guidance for mining safety management and decision-making.

Conflicting evidence combination based on Belief Mover’s Distance

The Dempster-Shafer evidence theory has been extensively used in various applications of information fusion owing to its capability in dealing with uncertain modeling and reasoning. However, when meeting highly conflicting evidence, the classical Dempster’s combination rule may give counter-intuitive results. To address this issue, we propose a new method in this work to fuse conflicting evidence. Firstly, a new evidence distance metric, named Belief Mover’s Distance, which is inspired by the Earth Mover’s Distance, is defined to measure the difference between two pieces of evidence. Subsequently, the credibility weight and distance weight of each piece of evidence are computed according to the Belief Mover’s Distance. Then, the final weight of each piece of evidence is generated by unifying these two weights. Finally, the classical Dempster’s rule is employed to fuse the weighted average evidence. Several examples and applications are presented to analyze the performance of the proposed method. Experimental results manifest that the proposed method is remarkably effective in comparison with other methods.

Robotic assisted artificial hip and knee arthroplasty is an inevitable trend in the future

Artificial joint arthroplasty, such as total hip and total knee arthroplasty, is one of the most successful procedures in orthopedics. The quality of life of these patients can be improved significantly through relieving pain, correcting the deformity and improving joint function. Although hip and knee arthroplasty currently are routine surgeries for patients with late stage joint diseases, post-operative complications like leg length discrepancy, dislocation or instability, limp and uncertain reason pain are still common. The position of the implants plays important roles in all these complications. Robotic assisted joint arthroplasty can not only provide 3D pre-operative visual planning, but also can assist to fulfill the pre-operation plan perfectly. But the current joint arthroplasty robots cannot carry out automatic personalized pre-operation planning, and also have the shortcomings of low efficiency and high cost etc. However, based on their current performance and with the help of artificial intelligence and better algorithm, we believe that joint arthroplasty will be more and more precisive, intelligent and minimally invasive, which is an inevitable trend in the development of joint surgery.

Assessment of Quality in Saudi Arabian Roadways

A new assessment model was developed in this work. The developed model introduced a new approach and reference for assessment factors control the quality in Saudi Arabian roads using the fuzzy logic system. Fuzzy logic system was chosen to be used in this research due to its suitability for uncertain and approximate reasoning that involves human intuitive thinking as well as, it requires a little data to achieve the aim of the proposed model. Furthermore, the fuzzy logic has the ability for combining many effects such as the probability of occurrence and the impact of factors on the quality of roadways construction. The methodology of this research included conducting a field survey with construction practitioners in the field of roadways projects across Saudi Arabia. The proposed model was then evaluated and applied using the collected data from the field survey. The study results proved that the proposed model can be successfully used in the assessment of factors affecting quality in roadways. The major factors that found to be significantly affecting the quality in construction of roadways projects were identified according to their importance as; 1) Change order control; 2) Fluctuation default of Subcontractor; 3) Third party delay 4) Contract dispute results from disagreement. The proposed model is considered as a general model that can be easily adapted and applied to other types of projects.

Prognosis of patients hospitalized with a diagnosis of COVID-19 pneumonia in a tertiary hospital in Turkey.

BACKGROUND: SARS-CoV2/COVID-19 emerged in China and caused a global pandemic in 2020. The mortality rate has been reported to be between 0% and 14.6% in all patients. In this study, we determined the clinical and laboratory parameters of COVID-19 related morbidity and mortality in our hospital.OBJECTIVES: Investigate the relationship between demographic, clinical, and laboratory parameters on COVID-19-related morbidity and mortality.DESIGN: Retrospective observational study.SETTINGS: Tertiary care hospital.PATIENTS AND METHODS: Patients diagnosed with COVID-19 pneumonia from March until the end of December were included in the study.MAIN OUTCOME MEASURES: The relationship between demographic, clinical, and laboratory parameters and the morbidity and mortality rates of patients diagnosed with COVID-19.SAMPLE SIZE: 124 patientsRESULTS: The mortality rate was 9.6% (12/124). Coronary artery disease (P<.0001) diabetes mellitus (P=.04) fever (>38.3°C) at presentation (P=.04) hypertension (P<.0001), and positive smoking history (P<.0001) were significantly associated with mortality. Patients who died were older, had a higher comorbid disease index, pneumonia severity index, fasting blood glucose, baseline serum creatinine, D-dimer, and had lower baseline haemoglobin, SaO2, percentage of lymphocyte counts and diastolic blood pressure. Patients admitted to the ICU were older, had a higher comorbidity disease index, pneumonia severity index, C-reactive protein, WBC, D-dimer, creatinine, number of antibiotics used, longer O2 support duration, lower hemoglobin, lymphocyte (%), and baseline SaO2 (%).CONCLUSIONS: Our results were consistent with much of the reported data. We suggest that the frequency, dosage, and duration of steroid treatment should be limited.LIMITATIONS: Low patient number, uncertain reason of mortality, no standard treatment regimen, limited treatment options, like ECMO.CONFLICT OF INTEREST: None.

Uncertain reasoning

Uncertain reasoning

Influences of TiO2 or Y2O3 doping on the homogeneity of polycrystalline Al2O3 produced by pulsed electric current sintering

ABSTRACT Influences of TiO2 or Y2O3 dopants on pressure-assisted sintering of polycrystalline Al2O3 were investigated to control the microstructure of sintered Al2O3 as well as to improve the homogeneity of transparent Al2O3 samples. The transparent polycrystalline Al2O3 samples with and without the dopants were fabricated by two-step pulsed electric current sintering (TS-PECS). By the grain boundary segregation by the dopants, both TiO2 and Y2O3 depressed the densification and grain growth processes during the sintering of polycrystalline Al2O3. The principle originalities of this work include the relationship between the homogeneities of microstructure and of optical transmittance of large-size polycrystalline Al2O3 and the consequent doping strategy for controlling of homogeneity of transparent polycrystalline Al2O3 prepared by two-step PECS. Doping of Y2O3 dramatically reduced the grain size of polycrystalline Al2O3 and improved its optical transparency. The homogeneity of the microstructure and the optical transparency of the large-sized polycrystalline Al2O3 with 0.1 mol% Y2O3 was improved. The addition of TiO2 also slightly retarded densification and reduced the grain size of the sintered Al2O3 samples. However, TiO2 dopant is not good for applications of transparent Al2O3 because it caused a dark color in transparent polycrystalline Al2O3 samples by uncertain reasons.

Modeling and Detection of Flooding-Based Denial of Service Attacks in Wireless Ad Hoc Networks Using Uncertain Reasoning

Wireless Ad Hoc Networks are self-organizing networks deployed without any centralized infrastructure. Flooding based Denial-of-Service (DoS) attacks were targeting the constrained resources of mobile nodes as well as the network. Route Request (RREQ) flooding attack is one of the prominent DoS attacks launched from the network layer in which the attacker sends a huge number of spoofed Route Request (RREQ) packets which not only overflows the target buffer but also creates network congestion. In this work, novel methods were suggested for defending RREQ flooding attack in Wireless Ad Hoc Network using two well-known frameworks in uncertain reasoning namely Bayesian Inference and Dempster-Shafer (D-S) evidence theory. The present work reports the modeling of RREQ traffic and developed an optimum algorithm for the detection of persistent RREQ flooding attack using Bayesian Inference. The algorithm was further refined for the detection of high rate and low rate pulsed RREQ flooding attack using D-S evidence theory. Based on the comprehensive evaluation using mathematical modeling and simulation, the proposed method successfully defended any type of flooding based DoS attack in Wireless Ad Hoc Network with lower communication and memory overhead.