Logical Rules Research Articles

Redescription mining-based business process deviance analysis

AbstractBusiness processes often deviate from their expected or desired behavior. Such deviations can be either positive or negative, depending on whether or not they lead to better process performance. Deviance mining addresses the problem of identifying such deviations and explaining why a process deviates. In this paper, we propose a novel approach to identify and explain the causes of deviant process executions based on the technique of redescription mining, which extracts knowledge in the form of logical rules. By analyzing, comparing, and filtering these rules, the reasons for the deviant behaviors of a business process are identified both in general and for particular process instances. Afterward, the results of this analysis are transformed into a concise and well-readable natural language text that can be used by business analysts and process owners to optimize processes in a reasoned manner. We evaluate our approach from different angles using four process models and provide some advice for further optimization.

A method for analyzing handwritten program flowchart based on detection transformer and logic rules

A method for analyzing handwritten program flowchart based on detection transformer and logic rules

Computational reaching of quantified consequences from imperfect initial data

Usually, it is not direct to translate theoretical results to practice. One of the challenges is the real computation of solutions to proposed problems, when infinite numbers (such as real numbers or the unit interval) are considered. The same is true when consequences (information) from a data set modeled by logical rules need to be obtained. In this framework, this information is obtained from the immediate consequences operator and ensuring its continuity is fundamental for making sure the computation of this information in a countable number of iterations. Recently, a versatile operator using generalized quantifiers has been introduced. This note will advance in the knowledge introducing necessary and sufficient conditions to ensure the continuity of this new flexible operator.

Interpretable neural network classification model using first-order logic rules

Over the past decade, the field of neural networks has made significant strides, particularly in deep learning. However, their limited interpretability has constrained their application in certain critical domains, drawing widespread criticism. Researchers have proposed various methods for explaining neural networks to address this challenge. This paper focuses on rule-based explanations for neural network classification problems. We propose IRCnet, a scalable classification model based on first-order logic rules. IRCnet consists of layers for learning conjunction and disjunction rules, utilizing binary logic activation functions to enhance interpretability. The model is initially trained using a continuous-weight version, which is later binarized to produce a discrete-weight version. During training, we innovatively employed gradient approximation method to handle the non-differentiable weight binarization function, thereby enabling the training of split matrices used for binarization. Finally, Conjunctive Normal Form (CNF) or Disjunctive Normal Form (DNF) rules are extracted from the model’s discrete-weight version. Experimental results indicate that our model achieves the highest or near-highest performance across various classification metrics in multiple structured datasets while demonstrating significant scalability. It effectively balances classification accuracy with the complexity of the generated rules.

Relational semantic-enhanced logic rule learning for knowledge graph completion

Relational semantic-enhanced logic rule learning for knowledge graph completion

Algorithm Improvement for Mobile Event Detection with Intelligent Tunnel Robots

Mobile inspections conducted by intelligent tunnel robots are instrumental in broadening the inspection reach, economizing on inspection expenditures, and augmenting the operational efficiency of inspections. Despite differences from fixed surveillance, mobile-captured traffic videos have complex backgrounds and device conditions that interfere with accurate traffic event identification, warranting more research. This paper proposes an improved algorithm based on YOLOv9 and DeepSORT for intelligent event detection in an edge computing mobile device using an intelligent tunnel robot. The enhancements comprise the integration of the Temporal Shift Module to boost temporal feature recognition and the establishment of logical rules for identifying diverse traffic incidents in mobile video imagery. Experimental results show that our fused algorithm achieves a 93.25% accuracy rate, an improvement of 1.75% over the baseline. The algorithm is also applicable to inspection vehicles, drones, and autonomous vehicles, effectively enhancing the detection of traffic events and improving traffic safety.

Establishment and application of autoverification system for HbA1c testing.

This study aimed to determine autoverification rules for routine glycated hemoglobin (HbA1c) analysis based on high-performance liquid chromatography (HPLC) principle. Laboratory information system (LIS) and Bio-Rad D-100 Advisor software (Bio-Rad, Hercules, USA) with graphics recognition function were carriers for the autoverification system. A total of 105,126 HbA1c results, including 98,249 HbA1c matching fast plasma glucose (FPG) results of real-world data from May 2019 to June 2020, were collected to determine autoverification rules including flags, delta checks, reporting limits, and logical rules. The validation database was composed of 48,045 HbA1c results and 41,083 matching FPG results. Autoverification passing rate and the reduction of turnaround time (TAT) were evaluated. Four autoverification systems (A, B, C, D) were established by two types of delta check rules, 28 flags, one reporting limits, and two kinds of logical rules. The autoverification passing rates were 80.6%, 78.8%, 83.7%, and 81.3%, and the average time saved in TAT were 117.5 min, 116.7 min, 121.1 min, and 121.7 min, respectively. Autoverification system C was the optimal one. Application of distribution of FPG corresponding to HbA1c groups had better performance as logical rules. Established HbA1c autoverifcation system shortened the auditing report time and improved work efficiency.

Mobility Prediction via Rule-Enhanced Knowledge Graph

With the rapid development of location acquisition technologies, massive mobile trajectories have been collected and made available to us, which support a fantastic way of understanding and modeling individuals’ mobility. However, existing data-driven methods either fail to capture the long-range dependency or suffer from a high computational cost. To overcome these issues, we propose a knowledge-driven framework for mobility prediction, which leverages knowledge graphs (KG) to formulate the mobility prediction task into the KG completion problem through integrating the structured “knowledge” from the mobility data. However, most related mobility prediction works only focus on the structured information encoded in existing triples, which ignores the rich semantic information of relation paths composed of multiple relation triples. In this article, we apply a dedicated module to extract the supplementary semantic structure of paths in KG, which contributes to the interpretability and accuracy of our model. Specifically, the extracted rules are applied to capture the dependencies between relational facts. Moreover, by incorporating user information in the entity-relation space with the corresponding hyperplane, our method could capture diverse user mobility patterns and model the personal characteristics of users to improve the accuracy of mobility prediction. Extensive evaluations illustrate that our proposed model beats state-of-the-art mobility prediction algorithms, which verifies the superiority of utilizing logical rules and user hyperplanes. Our implementation code is available at https://github.com/tsinghua-fib-lab/RulekG-MobiPre.git

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models

Large language models (LLMs) have revolutionized language processing, but face critical challenges with security, privacy, and generating hallucinations — coherent but factually inaccurate outputs. A major issue is fact-conflicting hallucination (FCH), where LLMs produce content contradicting ground truth facts. Addressing FCH is difficult due to two key challenges: 1) Automatically constructing and updating benchmark datasets is hard, as existing methods rely on manually curated static benchmarks that cannot cover the broad, evolving spectrum of FCH cases. 2) Validating the reasoning behind LLM outputs is inherently difficult, especially for complex logical relations. To tackle these challenges, we introduce a novel logic-programming-aided metamorphic testing technique for FCH detection. We develop an extensive and extensible framework that constructs a comprehensive factual knowledge base by crawling sources like Wikipedia, seamlessly integrated into Drowzee. Using logical reasoning rules, we transform and augment this knowledge into a large set of test cases with ground truth answers. We test LLMs on these cases through template-based prompts, requiring them to provide reasoned answers. To validate their reasoning, we propose two semantic-aware oracles that assess the similarity between the semantic structures of the LLM answers and ground truth. Our approach automatically generates useful test cases and identifies hallucinations across six LLMs within nine domains, with hallucination rates ranging from 24.7% to 59.8%. Key findings include LLMs struggling with temporal concepts, out-of-distribution knowledge, and lack of logical reasoning capabilities. The results show that logic-based test cases generated by Drowzee effectively trigger and detect hallucinations. To further mitigate the identified FCHs, we explored model editing techniques, which proved effective on a small scale (with edits to fewer than 1000 knowledge pieces). Our findings emphasize the need for continued community efforts to detect and mitigate model hallucinations.

Type-3 fuzzy neural networks for dynamic system control

This paper presents a Type-3 Fuzzy Neural Network (T3FNN) for dynamic system control. The structure of the T3FNN controller, which is based on the compositional rule of inference of interval type-3 fuzzy systems, is proposed. TSK-type fuzzy rules, employing three-dimensional membership functions (MFs) in the antecedent part and linear functions with coefficients represented as interval sets in the consequent part, are utilized to design T3FNN. Gaussian functions with uncertain centers are employed to describe the type-3 membership functions. By employing three-dimensional MFs, type-3 fuzzy logic rules can accurately model a high degree of uncertainty and effectively handle uncertain information. The design of the T3FNN was accomplished by integrating the type-3 fuzzy logic system (T3FLS) with neural networks. The learning of the T3FNN was conducted using the genetic algorithms and gradient descent algorithm. As a result, the type-3 rule base of the system was effectively developed. The learning algorithms are presented and the proposed T3FNN structure is employed for the development of dynamic system control. The simulations of the T3FNN system for the control of the nonlinear and time-varying dynamic systems were carried out. The results obtained from the simulations indicate the suitability of using the T3FNN in controlling dynamic systems.

Intelligent System for Tourist Guidance in Tumbes-Perú

An Intelligent System (IS) for Tourist Guidance was developed for the city of Tumbes, Peru. Considering the preferences of the tourist, the IS obtains the optimal route for the visit and provides a visit plan with schedules and times of stay in each place. It is an innovative hybrid system since it is complemented by two artificial intelligence techniques, a rule-based expert system and a genetic algorithm. The methodology for the implementation of the IS consisted of the collection of tourist, geographic, georeferenced information and photographs of 28 tourist places, grouped into Beaches, Nature, Adventure, Culture and Medicinal Sites, then the logical rules, the distance matrix and time of stay in each place were developed, and finally with the vehicle routing technique the genetic algorithm is implemented that allows obtaining the optimal route. The results indicate that the GA provides optimal solutions with an execution time of 5.6 seconds and zero errors. This contribution is very important for future work on tourist profiles and new tourist routes, since the intelligent system can be adapted for use in other cities.

Meta-collaboration-based semantic contrast for inductive knowledge representation learning

Inductive knowledge representation learning aims at effectively representing new entities in emerging knowledge graphs based on current ones, providing positive support for reasoning facts with newly emerging entities. It requires a scheme that can derive the instant knowledge to generate rational representations for new entities. Recently, some approaches have been developed for it by capturing logical rules between entities, mining structural information of KGs, or learning multiple structural patterns of entities. However, there are two main challenges that they have yet to overcome. The first is the structural bias-induced semantic ambiguity, where new entities are typically represented in a manner akin to those with analogous structures, during which the identical structures are emphasized while the differences are overlooked. We refer to this as the structural bias, which will lead to the generated representations of new entities being semantically ambiguous. The second is the potential sparsity of new entities. The presence of new entities with low frequencies brings about the insufficient representations for these new entities even training a model from scratch with substantial costs. To this end, we propose a Meta-Collaboration-based Semantic Contrast (MCSC) framework with the aim of addressing both issues above. Following the current meta-task formulation scheme, we first acquire the relation-specific knowledge to produce entity representations through modeling relations as feedback. Then, a multi-layer graph neural network module is developed to aggregate sufficient neighbor information to update entity representations. In the final, a collaborative semantic contrast module is designed on both support and query sets to respectively overcome the structural bias-induced semantic ambiguity and the potential sparsity of new entities challenges. Such a meta-collaboration-based semantic contrast procedure transcends current meta-learning paradigms in inductive knowledge representation learning that fail to learn semantically discriminative entity representations. Experimental results of the inductive link prediction task on 12 benchmark datasets demonstrate the superiority of MCSC over SOTA baselines.

Using AI explainable models and handwriting/drawing tasks for psychological well-being

This study addresses the increasing threat to Psychological Well-Being (PWB) posed by Depression, Anxiety, and Stress conditions. Machine learning methods have shown promising results for several psychological conditions. However, the lack of transparency in existing models impedes practical application. The study aims to develop explainable machine learning models for depression, anxiety and stress prediction, focusing on features extracted from tasks involving handwriting and drawing.Two hundred patients completed the Depression, Anxiety, and Stress Scale (DASS-21) and performed seven tasks related to handwriting and drawing. Extracted features, encompassing pressure, stroke pattern, time, space, and pen inclination, were used to train the explainable-by-design Entropy-based Logic Explained Network (e-LEN) model, employing first-order logic rules for explanation. Performance comparison was performed with XGBoost, enhanced by the SHAP explanation method.The trained models achieved notable accuracy in predicting depression (0.749 ±0.089), anxiety (0.721 ±0.088), and stress (0.761 ±0.086) through 10-fold cross-validation (repeated 20 times). The e-LEN model’s logic rules facilitated clinical validation, uncovering correlations with existing clinical literature. While performance remained consistent for depression and anxiety on an independent test dataset, a slight degradation was observed for stress prediction in the test task.

Vulnerability module in the multi-level ontology of risk assessment of Wireless Sensor Networks

This work presents the development of a vulnerability module within a multi-level ontology for risk assessment in wireless sensor networks (WSNs) used in industrial environments. WSNs consist of multiple sensor nodes with microcontrollers, sensors, communication devices, and power sources, playing a key role in monitoring, diagnostics, and managing industrial processes. Their main advantages include reduced costs due to the lack of cabling and ease of scaling by adding new nodes. However, WSNs face significant challenges, including limited power supply, vulnerability to electromagnetic interference, low bandwidth, and exposure to cyber-attacks. These issues make them less suitable for real-time systems where fast and reliable data transmission is critical. The vulnerability module developed in this study addresses these challenges by identifying weaknesses, analyzing potential threats, and assessing risks using logical rules. These rules assess various network components such as devices, communication protocols, and external factors like physical access and radio interference. The module continuously monitors the network, detects new vulnerabilities, and provides real-time feedback to the risk assessment module, suggesting measures to mitigate risks. This enhances the security and reliability of WSNs in industrial applications. In conclusion, the vulnerability module within the multi-level ontology provides a structured approach to identifying and mitigating risks in WSNs. Despite the inherent vulnerabilities of WSNs, advancements in security protocols and energy efficiency make them increasingly viable for industrial automation and optimization.

Recommender systems based on neuro-symbolic knowledge graph embeddings encoding first-order logic rules

Recommender systems based on neuro-symbolic knowledge graph embeddings encoding first-order logic rules

State Violence, Divine Abuse

Abstract It is tempting to attribute state violence to the imposition of a normative order, and it is tempting to construct an opposition between sanctifying that order and messianic interruptions of that order. This framework supposes that God, and the surrounding language of the sacred, follows the logic of rule, imposing a set of expectations on what is to be done enforced by threat of punishment. But what if we centre the story of Job in our account of the divine and with it an image of God as abuser rather than ruler, that is, God as only imposing the phantom of norms, norms that shift or evaporate as soon as they are imposed, never fulfilling a promise of reward or threat of punishment as expected? I explore this possibility through brief encounters with two texts on the racial violence of the state, one by Aimé Césaire and the other by the contemporary Black American writer Kiese Laymon.

Optimization and characterization of boric acid powder mixed electrical discharge machining of Ti-6Al-4V ELI

The powder mixed electrical discharge machining (PMEDM) process is used for enhancing machining efficiency and improving the surface characteristics of the workpiece compared to normal EDM. The present study evaluates the effect of boric acid powder mixed in deionized water in PMEDM of Ti-6Al-4V ELI (extra low interstitial). The PMEDM process is assessed by evaluating material removal rate (MRR) and surface roughness (SR) at varying powder concentration (PC), current and pulse duration ( Ton). Boric acid PMEDM exhibits advantageous for both MRR and SR, where MRR increases and SR decreases with an increase in PC. To simultaneously achieve higher MRR and lower SR, the grey-fuzzy logic method is employed. Initially, the raw input data is normalized into grey numbers and a single index is obtained through grey relational analysis. Subsequently, triangular membership functions are assigned to the inputs and output. Fuzzy logic rules are then formulated, and grey fuzzy relational grade (GFRG) is calculated for each condition. The optimum condition (GFRG = 0.787) is attained at 15 g/l PC, 9 A current and 106 µs Ton, resulting in a 63% improvement compared to the initial condition. At the optimum condition, MRR increased by 145% and SR decreased by 29% compared to the initial condition. The effect of boric acid in PMEDM can be visualized through the formation of smooth surfaces, exhibiting reduced SR, smaller and shallower craters, and fewer debris and globules. Additionally, the boric acid PMEDM experiments resulted in the formation of a hard TiB phase on Ti-6Al-4V, thus improving its wear resistance.

Enhanced classification performance using deep learning based segmentation for pulmonary embolism detection in CT angiography

PurposeTo develop a deep learning-based algorithm that automatically and accurately classifies patients as either having pulmonary emboli or not in CT pulmonary angiography (CTPA) examinations. Materials and methodsFor model development, 700 CTPA examinations from 652 patients performed at a single institution were used, of which 149 examinations contained 1497 PE traced by radiologists. The nnU-Net deep learning-based segmentation framework was trained using 5-fold cross-validation. To enhance classification, we applied logical rules based on PE volume and probability thresholds. External model evaluation was performed in 770 and 34 CTPAs from two independent datasets. ResultsA total of 1483 CTPA examinations were evaluated. In internal cross-validation and test set, the trained model correctly classified 123 of 128 examinations as positive for PE (sensitivity 96.1 %; 95 % C.I. 91–98 %; P < .05) and 521 of 551 as negative (specificity 94.6 %; 95 % C.I. 92–96 %; P < .05), achieving an area under the receiver operating characteristic (AUROC) of 96.4 % (95 % C.I. 79–99 %; P < .05). In the first external test dataset, the trained model correctly classified 31 of 32 examinations as positive (sensitivity 96.9 %; 95 % C.I. 84–99 %; P < .05) and 2 of 2 as negative (specificity 100 %; 95 % C.I. 34–100 %; P < .05), achieving an AUROC of 98.6 % (95 % C.I. 83–100 %; P < .05). In the second external test dataset, the trained model correctly classified 379 of 385 examinations as positive (sensitivity 98.4 %; 95 % C.I. 97–99 %; P < .05) and 346 of 385 as negative (specificity 89.9 %; 95 % C.I. 86–93 %; P < .05), achieving an AUROC of 98.5 % (95 % C.I. 83–100 %; P < .05). ConclusionOur automatic pipeline achieved beyond state-of-the-art diagnostic performance of PE in CTPA using nnU-Net for segmentation and volume- and probability-based post-processing for classification.

Dynamic Fault Tree Generation and Quantitative Analysis of System Reliability for Embedded Systems Based on SysML Models.

As embedded systems become increasingly complex, traditional reliability analysis methods based on text alone are no longer adequate for meeting the requirements of rapid and accurate quantitative analysis of system reliability. This article proposes a method for automatically generating and quantitatively analyzing dynamic fault trees based on an improved system model with consideration for temporal characteristics and redundancy. Firstly, an "anti-semantic" approach is employed to automatically explore the generation of fault modes and effects analysis (FMEA) from SysML models. The evaluation results are used to promptly modify the system design to meet requirements. Secondly, the Profile extension mechanism is used to expand the SysML block definition diagram, enabling it to describe fault semantics. This is combined with SysML activity diagrams to generate dynamic fault trees using traversal algorithms. Subsequently, parametric diagrams are employed to represent the operational rules of logic gates in the fault tree. The quantitative analysis of dynamic fault trees based on probabilistic models is conducted within the internal block diagram of SysML. Finally, through the design and simulation of the power battery management system, the failure probability of the top event was obtained to be 0.11981. This verifies that the design of the battery management system meets safety requirements and demonstrates the feasibility of the method.

Case-Based Deduction for Entailment Tree Generation

Maintaining logical consistency in structured explanations is critical for understanding and troubleshooting the reasoning behind a system’s decisions. However, existing methods for entailment tree generation often struggle with logical consistency, resulting in erroneous intermediate conclusions and reducing the overall accuracy of the explanations. To address this issue, we propose case-based deduction (CBD), a novel approach that retrieves cases with similar logical structures from a case base and uses them as demonstrations for logical deduction. This method guides the model toward logically sound conclusions without the need for manually constructing logical rule bases. By leveraging a prototypical network for case retrieval and reranking them using information entropy, CBD introduces diversity to improve in-context learning. Our experimental results on the EntailmentBank dataset show that CBD significantly improves entailment tree generation, achieving performance improvements of 1.7% in Task 1, 0.6% in Task 2, and 0.8% in Task 3 under the strictest Overall AllCorrect metric. These findings confirm that CBD enhances the logical consistency and overall accuracy of AI systems in structured explanation tasks.