Automated Reasoning Research Articles

Rule-Based Verification of Autonomous Unmanned Aerial Vehicles

Automation enhances the capabilities of unmanned aerial vehicles (UAVs) by enabling self-determined behavior, while reducing the need for extensive human involvement. Future concepts envision a single human operator commanding multiple autonomous UAVs with minimal supervision. Despite advances in automation, there remains a demand for a “human in command” to assume overall responsibility, driven by concerns about UAV safety and regulatory compliance. In response to these challenges, a method for runtime verification of UAVs using a knowledge-based system is introduced. This method empowers human operators to identify unsafe behavior without assuming full control of the UAV. Aspects of automated formalization, updating and processing of knowledge elements at runtime, coupled with an automatic reasoning process, are considered. The result is an ontology-based approach for runtime verification, addressing the growing complexity of UAVs and the need to ensure safety in the context of evolving aviation regulations.

Methods for building ontologies to ensure coordinated behavior of autonomous intellectual systems in agriculture

Ontologies are the main tool for representing domain knowledge. The need to use ontologies to ensure consistent behavior of autonomous intelligent systems in agriculture is determined by the need to create semantic interactiveness of agricultural systems and decision support systems, in which automatic knowledge inference occurs based on semantic processing of data from a sensor network. The purpose of the study is to develop methods for constructing ontologies to ensure consistent behavior of autonomous intelligent systems in agriculture. The paper presents the architecture of an intelligent control system for a heterogeneous human-machine team, consisting of an autonomous robot for active plant protection and an unmanned aerial vehicle (UAV) for monitoring the condition of the garden from the air. A multiagent architecture for constructing ontologies has been developed to ensure consistent behavior of a human-machine team. In particular, a multiagent architecture for constructing an ontology when a robot detects a new object is presented, as well as a scheme for exchanging knowledge between team members. The results obtained can be used in the development of decision support systems, in which automatic knowledge inference occurs based on semantic processing of data from a sensor network.

Machine Reasoning in FCAPS: Towards Enhanced Beyond 5G Network Management

Machine Reasoning in FCAPS: Towards Enhanced Beyond 5G Network Management

Credal Valuation Networks for Machine Reasoning Under Uncertainty

Contemporary undertakings provide limitless opportunities for widespread application of machine reasoning and artificial intelligence in situations characterised by uncertainty, hostility and sheer volume of data. The paper develops a valuation network as a graphical system for higher-level fusion and reasoning under uncertainty in support of the human operators. Valuations, which are mathematical representation of (uncertain) knowledge and collected data, are expressed as credal sets, defined as coherent interval probabilities in the framework of imprecise probability theory. The basic operations with such credal sets, combination and marginalisation, are defined to satisfy the axioms of a valuation algebra. A practical implementation of the credal valuation network is discussed and its utility demonstrated on a small scale example.

Ontological analysis in the problems of container applications threat modelling

Objectives. The main purpose of the work is the experimental verification of the method of automatic threat modelling based on the ontological approach using the example of multicomponent container applications presented in the form of data flow diagrams.Methods. Methods of ontological modelling and knowledge management are used in the work. The Web Ontology Language is used to represent knowledge; automatic reasoning based on description logics is used for threat modelling.Results. A machine-readable set (dataset) of 200 data flow diagrams is developed; each diagram is obtained from the configuration of a real container application and is presented as an ontology and a knowledge graph. An ontological two-level domain-specific threat model of container applications is formed. An experiment is conducted to compare the coverage by threats using the common approach and using domain-specific threats for created dataset. For 95 % of the diagrams, the domain-specific threat model showed the coverage similar or greater than the common approach.Conclusion. The results of the experiment prove the suitability and effectiveness of the ontological approach for automatic threat modelling. The created dataset can be used for various research in the field of automation of threat modelling.

Ontologies in digital twins: A systematic literature review

Digital Twins (DT) facilitate monitoring and reasoning processes in cyber–physical systems. They have progressively gained popularity over the past years because of intense research activity and industrial advancements. Cognitive Twins is a novel concept, recently coined to refer to the involvement of Semantic Web technology in DTs. Recent studies address the relevance of ontologies and knowledge graphs in the context of DTs, in terms of knowledge representation, interoperability and automatic reasoning. However, there is no comprehensive analysis of how semantic technologies, and specifically ontologies, are utilized within DTs. This Systematic Literature Review (SLR) is based on the analysis of 82 research articles, that either propose or benefit from ontologies with respect to DT. The paper uses different analysis perspectives, including a structural analysis based on a reference DT architecture, and an application-specific analysis to specifically address the different domains, such as Manufacturing and Infrastructure. The review also identifies open issues and possible research directions on the usage of ontologies and knowledge graphs in DTs.

Ontology-Based AI Design Patterns and Constraints in Cancer Registry Data Validation.

Data validation in cancer registration is a critical operation but is resource-intensive and has traditionally depended on proprietary software. Ontology-based AI is a novel approach utilising machine reasoning based on axioms formally described in description logic. This is a different approach from deep learning AI techniques but not exclusive of them. The advantage of the ontology approach lies in its ability to address a number of challenges concurrently. The disadvantages relate to computational costs, which increase with language expressivity and the size of data sets, and class containment restrictions imposed by description logics. Both these aspects would benefit from the availability of design patterns, which is the motivation behind this study. We modelled the European cancer registry data validation rules in description logic using a number of design patterns and showed the viability of the approach. Reasoning speeds are a limiting factor for large cancer registry data sets comprising many hundreds of thousands of records, but these can be offset to a certain extent by developing the ontology in a modular way. Data validation is also a highly parallelisable process. Important potential future work in this domain would be to identify and optimise reusable design patterns, paying particular attention to avoiding any unintended reasoning efficiency hotspots.

A complementary ratio based clause selection method for contradiction separation dynamic deduction

Automated reasoning is a key research area of Artificial Intelligence (AI) and has attracted much greater attention in recent years due to the demands of trustworthy AI, where binary resolution inference rule based first-order automated reasoning play a crucial role. Recently, a novel multi-clause dynamic standard contradiction separation (S-CS) inference rule and related automated deduction theory were proposed to overcome the limitations of binary resolution-based automated deduction. Now that strategies for dynamic clause selection are essential for S-CS based automated deduction, in the present work, a class of novel clause selection strategies, along with the corresponding novel complementary ratio based dynamic S-CS automated deduction algorithm (called CRA), are proposed. Furthermore, we are interested in determining whether CRA may be deployed on top of the current best first-order automated reasoning system designs to increase their performance. As a result, CRA is applied to the current leading systems, Vampire and E, resulting in two integrated automatic reasoning systems, CRA_Vampire and CRA_E. Experiment results demonstrate that CRA can improve E and Vampire in CASC 2020–2022 competitions. The new integrated automated reasoning systems can resolve 44 problems with rating of 1, meaning they are intractable by other existing first-order automated systems.

Multimodal Deep Learning for Robust Road Attribute Detection

Automatic inference of missing road attributes (e.g., road type and speed limit) for enriching digital maps has attracted significant research attention in recent years. A number of machine learning-based approaches have been proposed to detect road attributes from GPS traces, dash-cam videos, or satellite images. However, existing solutions mostly focus on a single modality without modeling the correlations among multiple data sources. To bridge this gap, we present a multimodal road attribute detection method, which improves the robustness by performing pixel-level fusion of crowdsourced GPS traces and satellite images. A GPS trace is usually given by a sequence of location, bearing, and speed. To align it with satellite imagery in the spatial domain, we render GPS traces into a sequence of multi-channel images that simultaneously capture the global distribution of the GPS points, the local distribution of vehicles’ moving directions and speeds, and their temporal changes over time, at each pixel. Unlike previous GPS-based road feature extraction methods, our proposed GPS rendering does not require map matching in the data preprocessing step. Moreover, our multimodal solution addresses single-modal challenges such as occlusions in satellite images and data sparsity in GPS traces by learning the pixel-wise correspondences among different data sources. On top of this, we observe that geographic objects and their attributes in the map are not isolated but correlated with each other. Thus, if a road is partially labeled, then the existing information can be of great help on inferring the missing attributes. To fully use the existing information, we extend our model and discuss the possibilities for further performance improvement when partially labeled map data is available. Extensive experiments have been conducted on two real-world datasets in Singapore and Jakarta. Compared with previous work, our method is able to improve the detection accuracy on road attributes by a large margin.

Toward Sustainable Model Services for Deep Learning: A Sub-Network-Based Solution Integrating Blockchain with IPFS and a Use Case in Intelligent Transportation

In the era of deep learning as a service, ensuring that model services are sustainable is a key challenge. To achieve sustainability, the model services, including but not limited to storage and inference, must maintain model security while preserving system efficiency, and be applicable to all deep models. To address these issues, we propose a sub-network-based model storage and inference solution that integrates blockchain and IPFS, which includes a highly distributed storage method, a tamper-proof checking method, a double-attribute-based permission management method, and an automatic inference method. We also design a smart contract to deploy these methods in the blockchain. The storage method divides a deep model into intra-sub-network and inter-sub-network information. Sub-network files are stored in the IPFS, while their records in the blockchain are designed as a chained structure based on their encrypted address. Connections between sub-networks are represented as attributes of their records. This method enhances model security and improves storage and computational efficiency of the blockchain. The tamper-proof checking method is designed based on the chained structure of sub-network records and includes on-chain checking and IPFS-based checking stages. It efficiently and dynamically monitors model correctness. The permission management method restricts user permission based on the user role and the expiration time, further reducing the risk of model attacks and controlling system efficiency. The automatic inference method is designed based on the idea of preceding sub-network encrypted address lookup. It can distribute trusted off-chain computing resources to perform sub-network inference and use the IPFS to store model inputs and sub-network outputs, further alleviating the on-chain storage burden and computational load. This solution is not restricted to model architectures and division methods, or sub-network recording orders, making it highly applicable. In experiments and analyses, we present a use case in intelligent transportation and analyze the security, applicability, and system efficiency of the proposed solution, particularly focusing on the on-chain efficiency. The experimental results indicate that the proposed solution can balance security and system efficiency by controlling the number of sub-networks, thus it is a step towards sustainable model services for deep learning.

Identifying equipment health status from maintenance records using Lexicon based Unsupervised Sentiment Analysis Adjusted for Negation (LUSAA-N)

During periodic inspection and repair of industrial equipment, technicians create maintenance records in the form of unstructured text to document valuable information regarding the equipment condition, operating environment, failed components, failure mechanism, etc. Inferring the equipment health status from these records can help in planning future maintenance actions to avoid expensive machine failures. However, automatic inference of the equipment health status is non-trivial due to various challenges inherent in analyzing unstructured text such as domain-specific vocabulary and negation words. Further, manual labeling of the records for supervised classification is arduous and impractical. Thus, in this paper, we present a model to automatically extract the equipment health status from maintenance records in a completely unsupervised manner. We show that using general English sentiment lexicons is highly inefficient for analyzing maintenance records, and thus propose a method that leverages sentiment lexicons curated for the maintenance domain and addresses the central issue of negation. We demonstrate the effectiveness of our proposed model over extant research using data from real-life maintenance records from oil rig equipment.

A model-based approach for converting CGMES power system models into operational networks

This paper presents a model-based approach for converting Common Grid Model Exchange Specification (CGMES) power system models into operational networks. The approach utilizes the Model-Driven Architecture (MDA), borrowed from software engineering, to create a Platform-Independent Model (PIM) saved in a graph database, neo4j. The PIM is then transformed into Platform-Specific Model (PSM) using cypher queries. Finally, from the PSM, a Pandapower network is generated that is used later for running power flow simulations. The Common Information Model (CIM) ontology classes, which form the metamodel behind CGMES, are loaded into the same database, connecting them to the grid instances, allowing for automatic validation and inference. The proposed approach has been successfully applied to large-scale real-world grids that include renewable energy sources.

Oocyte cryopreservation with in vitro maturation for fertility preservation in girls at risk for ovarian insufficiency.

To assess the feasibility and outcomes of oocyte cryopreservation with in vitro maturation (IVM) in post-pubertal girls undergoing fertility preservation (FP) for primary ovarian insufficiency (POI) risk. Ovarian stimulation was performed with an antagonist protocol or progesterone priming. Ultrasound monitoring was performed transabdominally. Oocytes were retrieved transvaginally under IV sedation. Immature oocytes were subjected to IVM for up to 36h. All MII oocytes were vitrified. The main outcome measure was the total number of mature oocytes cryopreserved. The secondary outcome was the increase in the mature oocyte yield after IVM. Indications for FP included mosaic Turner syndrome (mTS; n = 10), malignancy (n = 3), and POI risk (n = 2). The mean ± SD age, antral follicle count (AFC), and AMH levels were 14.2 ± 1.4years, 8 ± 5.2 and 1.3 ± 1.3ng/mL. In girls with mTS, the ovarian reserve was low for age (AFC 7.4 ± 4.7 and AMH 1.4 ± 1.6ng/mL). Oocyte cryopreservation was possible in all girls with a range of 1-27 mature oocytes obtained, even in those who were previously exposed to chemotherapy or with low ovarian reserve, and no surgical complications were encountered. After IVM, the median mature oocyte yield increased significantly from 7.5 to 10.5 (p = 0.001). Oocyte cryopreservation appears to be feasible and safe in girls as young as 12years of age at risk for POI The utility of IVM increases the yield of cryopreserved mature oocytes. Prior exposure to chemotherapy or low ovarian reserve should not be an automatic reason to exclude these girls from FP consideration.

Towards a Domain-Neutral Platform for Sustainable Digital Twin Development

In this paper, we propose an abstract domain-neutral architecture for a cognitive digital twin (CDT) and a software platform to develop such CDTs, including machine reasoning capabilities. Sustainable development refers here to an abstract model that enables a holistic view of limiting resources and has an ability to adapt to different application domains while reusing existing resources. The proposed solution allows for a unified abstract representation and the development of a wide range of diverse digital twins, as well as facilitating their interoperability. The abstract architecture consists of a four-layer structure (observation/actuation layer, data management layer, reasoning layer, and simulation layer) with an upper ontology to which the domain ontology of the specific CDT is mapped. The architecture relies on semantic web technologies, including ontology-based reasoning using OWL, and a loosely coupled, component-based service-oriented software architecture. The platform utilizes a microservice architecture that enables separate, loosely coupled services on each layer, message queues to provide asynchronous communication, and possesses cloud technologies to achieve scalability. The proposed approach was validated by implementing a software platform prototype and demonstrating its key features through two dissimilar scenarios. The first scenario demonstrates simple sustainable energy management through IoT systems inside smart buildings, while the second one demonstrates knowledge quality management based on knowledge space theory.

Mind meets machine: Unravelling GPT-4’s cognitive psychology

Cognitive psychology delves on understanding perception, attention, memory, language, problem-solving, decision-making, and reasoning. Large Language Models (LLMs) are emerging as potent tools increasingly capable of performing human-level tasks. The recent development in the form of Generative Pre-trained Transformer 4 (GPT-4) and its demonstrated success in tasks complex to humans exam and complex problems has led to an increased confidence in the LLMs to become perfect instruments of intelligence. Although GPT-4 report has shown performance on some cognitive psychology tasks, a comprehensive assessment of GPT-4, via the existing well-established datasets is required. In this study, we focus on the evaluation of GPT-4’s performance on a set of cognitive psychology datasets such as CommonsenseQA, SuperGLUE, MATH and HANS. In doing so, we understand how GPT-4 processes and integrates cognitive psychology with contextual information, providing insight into the underlying cognitive processes that enable its ability to generate the responses. We show that GPT-4 exhibits a high level of accuracy in cognitive psychology tasks relative to the prior state-of-the-art models. Our results strengthen the already available assessments and confidence on GPT-4’s cognitive psychology abilities. It has significant potential to revolutionise the field of Artificial Intelligence (AI), by enabling machines to bridge the gap between human and machine reasoning.

Hierarchical Bayesian pharmacometrics analysis of Baclofen for alcohol use disorder

Alcohol use disorder (AUD), also called alcohol dependence, is a major public health problem, affecting almost of the world’s population. Baclofen, as a selective receptor agonist, has emerged as a promising drug for the treatment of AUD. However, the inter-trial, inter-individual and residual variability in drug concentration over time in a population of patients with AUD is unknown. In this study, we use a hierarchical Bayesian workflow to estimate the parameters of a pharmacokinetic (PK) population model from Baclofen administration to patients with AUD. By monitoring various convergence diagnostics, the probabilistic methodology is first validated on synthetic longitudinal datasets and then applied to infer the PK model parameters based on the clinical data that were retrospectively collected from outpatients treated with oral Baclofen. We show that state-of-the-art advances in automatic Bayesian inference using self-tuning Hamiltonian Monte Carlo (HMC) algorithms provide accurate and decisive predictions on Baclofen plasma concentration at both individual and group levels. Importantly, leveraging the information in prior provides faster computation, better convergence diagnostics, and substantially higher out-of-sample prediction accuracy. Moreover, the root mean squared error as a measure of within-sample predictive accuracy can be misleading for model evaluation, whereas the fully Bayesian information criteria correctly select the true data generating parameters. This study points out the capability of non-parametric Bayesian estimation using adaptive HMC sampling methods for easy and reliable estimation in clinical settings to optimize dosing regimens and efficiently treat AUD.

A Sequential Addressing Subsampling Method for Massive Data Analysis Under Memory Constraint

The emergence of massive data in recent years brings challenges to automatic statistical inference. This is particularly true if the data are too numerous to be read into memory as a whole. Accordingly, new sampling techniques are needed to sample data from a hard drive. In this paper, we propose a sequential addressing subsampling (SAS) method that can sample data directly from the hard drive. The newly proposed SAS method is time saving in terms of addressing cost compared to that of the random addressing subsampling (RAS) method. Estimators (e.g., the sample mean) based on the SAS subsamples are constructed, and their properties are studied. We conduct a series of simulation studies to verify the finite sample performance of the proposed SAS estimators. The time cost is also compared between the SAS and RAS methods. An analysis of the airline data is presented for illustration purpose.

Dynamic Graph-Based Adaptive Learning for Online Industrial Soft Sensor With Mutable Spatial Coupling Relations

Accurate online soft sensor in complex industrial processes remains challenging because underlying spatial coupling relations among process variables have not been effectively mined and exploited. Recently, some deep learning-based studies construct static graphs to explicitly represent underlying spatial coupling relations among process variables, but they neglect the fact that spatial coupling relations have mutable characteristics, leading to the poor performance in online soft sensor. Therefore, we propose a novel deep learning model to address this issue to achieve accurate soft sensor. Specifically, a dynamic graph is proposed to realize adaptive learning and automatic inference for mutable spatial coupling relations, so that the proposed model is endowed with the ability to real-timely sense spatial coupling relations in online industrial soft sensor. Then, based on the dynamic graph, a new multi-hop attention graph convolutional network is proposed to systematically aggregate various crucial node feature representations during graph convolution processes to capture fine-grained spatial dependence features, thereby achieving effective modeling for variation patterns of process variables. Finally, a new multivariate incremental training algorithm is designed for deep learning models to further improve the prediction performance. Verification study on a coal mill rig demonstrates the feasibility and effectiveness of the proposed model.

Hybrid Fusion of High-Resolution and Ultra-Widefield OCTA Acquisitions for the Automatic Diagnosis of Diabetic Retinopathy.

Optical coherence tomography angiography (OCTA) can deliver enhanced diagnosis for diabetic retinopathy (DR). This study evaluated a deep learning (DL) algorithm for automatic DR severity assessment using high-resolution and ultra-widefield (UWF) OCTA. Diabetic patients were examined with 6×6 mm2 high-resolution OCTA and 15×15 mm2 UWF-OCTA using PLEX®Elite 9000. A novel DL algorithm was trained for automatic DR severity inference using both OCTA acquisitions. The algorithm employed a unique hybrid fusion framework, integrating structural and flow information from both acquisitions. It was trained on data from 875 eyes of 444 patients. Tested on 53 patients (97 eyes), the algorithm achieved a good area under the receiver operating characteristic curve (AUC) for detecting DR (0.8868), moderate non-proliferative DR (0.8276), severe non-proliferative DR (0.8376), and proliferative/treated DR (0.9070). These results significantly outperformed detection with the 6×6 mm2 (AUC = 0.8462, 0.7793, 0.7889, and 0.8104, respectively) or 15×15 mm2 (AUC = 0.8251, 0.7745, 0.7967, and 0.8786, respectively) acquisitions alone. Thus, combining high-resolution and UWF-OCTA acquisitions holds the potential for improved early and late-stage DR detection, offering a foundation for enhancing DR management and a clear path for future works involving expanded datasets and integrating additional imaging modalities.

Automatic mechanistic inference from large families of Boolean models generated by Monte Carlo tree search.

Many important processes in biology, such as signaling and gene regulation, can be described using logic models. These logic models are typically built to behaviorally emulate experimentally observed phenotypes, which are assumed to be steady states of a biological system. Most models are built by hand and therefore researchers are only able to consider one or perhaps a few potential mechanisms. We present a method to automatically synthesize Boolean logic models with a specified set of steady states. Our method, called MC-Boomer, is based on Monte Carlo Tree Search an efficient, parallel search method using reinforcement learning. Our approach enables users to constrain the model search space using prior knowledge or biochemical interaction databases, thus leading to generation of biologically plausible mechanistic hypotheses. Our approach can generate very large numbers of data-consistent models. To help develop mechanistic insight from these models, we developed analytical tools for multi-model inference and model selection. These tools reveal the key sets of interactions that govern the behavior of the models. We demonstrate that MC-Boomer works well at reconstructing randomly generated models. Then, using single time point measurements and reasonable biological constraints, our method generates hundreds of thousands of candidate models that match experimentally validated in-vivo behaviors of the Drosophila segment polarity network. Finally we outline how our multi-model analysis procedures elucidate potentially novel biological mechanisms and provide opportunities for model-driven experimental validation.