Abstract: Increasingly, artificial intelligence (AI) is being used to assist complex decision-making such as financial investing. However, there are concerns regarding the black-box nature of AI algorithms. The field of explainable AI (XAI) has emerged to address these concerns. XAI techniques can reveal how an AI decision is formed and can be used to understand and appropriately trust an AI system. However, XAI techniques still may not be human-centred and may not support human decision-making adequately. In this work, we explored how domain knowledge, identified by expert decision makers, can be used to achieve a more human-centred approach to AI. We measured the effect of domain knowledge on trust in AI, reliance on AI, and task performance in an AI-assisted complex decision-making environment. In a peer-to-peer lending simulator, non-expert participants made financial investments using an AI assistant. The presence or absence of domain knowledge was manipulated. The results showed that participants who had access to domain knowledge relied less on the AI assistant when the AI assistant was incorrect and indicated less trust in AI assistant. However, overall investing performance was not affected. These results suggest that providing domain knowledge can influence how non-expert users use AI and could be a powerful tool to help these users develop appropriate levels of trust and reliance.

Abstract: Advancement and application of rule-based expert systems have been a key research area in explainable artificial intelligence (XAI) because the rule-base is one of the most common and natural explainable frameworks for knowledge representation. The present work aims to design a novel rule-based system, called Cumulative Belief Rule-Based System (CBRBS), by establishing efficient rule-base modeling and inference procedures, where the rule-base modeling procedure includes the generation of cumulative belief rules via numeric data transformation and extended belief rule integration, and the rule-base inference procedure includes the inference of cumulative belief rules via consistent rule activation and activated rule integration. All these procedures enable CBRBS to better achieve the balance of explainability, high-efficiency (or computing complexity), and accuracy to fit with different application scenarios, as well as overcome the limitations of classical rule-based systems. Extensive experiments based on the well-known pipeline leak detection problem and open-source classification problems are conducted to illustrate the feature and advantage of the CBRBS over other classical rule-based systems and some commonly used classifiers.

Abstract: Expert weight determination is a critical issue in the design concept evaluation process, especially for complex products. However, this phase is often ignored by most decision makers. For the evaluation of complex product design concepts, experts are selected by clusters with different backgrounds. This work proposes a novel integrated two-layer method to determine expert weight under these circumstances. In the first layer, a hybrid model integrated by the entropy weight model and the Multiplicative analytical hierarchy process method is presented. In the second layer, a minimized variance model is applied to reach a consensus. Then the final expert weight is determined by the results of both layers. A real-life example of cruise ship cabin design evaluation is implemented to demonstrate the proposed expert weight determination method. To analyze the feasibility of the proposed method, weight determination with and without using experts is compared. The result shows the expert weight determination method is an effective approach to improve the accuracy of design concept evaluation.

Abstract: The widespread adoption of algorithmic decision-making systems has brought about the necessity to interpret the reasoning behind these decisions. The majority of these systems are complex black box models, and auxiliary models are often used to approximate and then explain their behavior. However, recent research suggests that such explanations are not overly accessible to lay users with no specific expertise in machine learning and this can lead to an incorrect interpretation of the underlying model. In this article, we show that a predictive and interactive model based on causality is inherently interpretable, does not require any auxiliary model, and allows both expert and non-expert users to understand the model comprehensively. To demonstrate our method we developed Outcome Explorer, a causality guided interactive interface, and evaluated it by conducting think-aloud sessions with three expert users and a user study with 18 non-expert users. All three expert users found our tool to be comprehensive in supporting their explanation needs while the non-expert users were able to understand the inner workings of a model easily.

Abstract: Expert systems are effective for anomaly detection in building energy systems. However, it is usually inefficient to establish comprehensive rule bases manually for complex building energy systems. Association rule mining is available to accelerate the establishment of the rule bases due to its powerful capability of discovering rules from numerous data. This paper proposes a real-time abnormal operation pattern detection method towards building energy systems. It can benefit from both expert systems and association rule mining. Association rules are utilized to establish association rule bases of abnormal and normal operation patterns. The established rule bases are then utilized to develop an expert system for real-time detection of abnormal operation patterns. The proposed method is applied to an actual chiller plant for evaluating its performance. Results show that 15 types of known abnormal operation patterns and 11 types of unknown abnormal operation patterns are detected successfully by the proposed method.

Abstract: Previously Expert Systems (ES) dominated Artificial Intelligence (AI) applications and various ES were developed in multiple domains. However, due to knowledge acquisition bottlenecks, these systems fell out of use. With the rise in Machine Learning (ML) and Deep Learning (DL) approaches, another category of systems called Recommender Systems (RS) is now developed for various application domains. As ML/DL systems acted like black boxes, explainable AI (XAI) came into the picture to provide explanations for the recommendations or predictions made. In this paper, we review the architectural similarities and differences between these three approaches along with applications and future directions. It is important to study these to predict the future of RS and any possible resurgence of ES, developments in XAI and application domains.

Abstract: The diagnosis of diseases in their early stages can assist us in preventing life-threatening infections and caring for them better than in the last phase because prevention is better than cure. The death rate can be very high due to the unapproachability of diagnosed patients at an early point. Expert systems help us to defeat the problem mentioned above and enable us to automatically diagnose diseases in their early phases. Expert systems use a fuzzy, rule-based inference engine to provide forward-chain methods for diagnosing the patient. In this research, data have been gathered from different sources, such as a hospital, by performing the test on the patients’ age, gender, blood sugar, heart rate, and ECG to calculate the values. The proposed expert system for medical diagnosis can be used to find minimum disease levels and demonstrate the predominant method for curing different medical diseases, such as heart diseases. In the next step, the diagnostic test at the hospital with the novel expert system, the crisp, fuzzy value is generated for input into the expert system. After taking the crisp input, the expert system starts working on fuzzification and compares it with the knowledge base processed by the inference engine. After the fuzzification, the next step starts with the expert system in the defuzzification process converting the fuzzy sets’ value into a crisp value that is efficient for human readability. Later, the expert physician system’s diagnosis calculates the value by using fuzzy sets, and gives an output to determine the patient’s heart disease. In one case, the diagnosis step was accomplished, and the expert system provided the yield with the heart disease risk level as “low”, “high”, or “risky”. After the expert system’s responsibilities have been completed, the physician decides on the treatment and recommends a proper dose of medicine according to the level the expert system provided after the diagnosis step. The findings indicate that this research achieves better performance in finding appropriate heart disease risk levels, while also fulfilling heart disease patient treatment due to the physicians shortfalls.

Abstract: The development of technology and information systems that are growing rapidly as it is today, requires everyone to continue to develop knowledge so as not to be out of date. The use of technology today can be used in all fields, such as education, security, health, and so on. Expert systems in the health sector are designed and made to imitate an expert who can facilitate the work of an expert in making decisions to solve problems. In a case study conducted at the Dadi Family Hospital, Purwokerto, data were obtained from patients with a diagnosis of rhinitis, the majority of whom did not know information about the symptoms and diseases. Rhinitis is an inflammatory disease or inflammation of the nasal mucosa that is triggered by certain allergens. The increasing number of ENT diseases, especially rhinitis, is not accompanied by the number of experts. In this case, it is necessary to conduct an analysis to speed up the diagnosis process by medical personnel. Based on the case study, an information system is needed that can be used by its users as a source of information as well as a more practical consultation media. In designing this system using PHP and MySQL with research datasets obtained from hospital medical records. For the development of the system using the waterfall method with the forward chaining method as a method of searching or drawing conclusions based on existing data or facts leading to conclusions. Then in testing the system using the black box as a feature functionality test, as well as testing the System Usability Scale (SUS) as a system feasibility test, and testing the accuracy of the expert system using the confusion matrix. For the results of the accuracy of this expert system obtained by 93%

Abstract: The ubiquitous presence of sensors (e.g., in smartphones) in our everyday life allows a constant real-time collection of data. This data has been successfully used in diagnosis and prediction of health outcomes and has the potential to improve health care. However, with data security and accountability as core requirements of medical applications, it remains a major challenge to integrate smart sensing information into the health care systems. One promising application is the integration into expert systems, in which smart sensing information is used to assist medical experts in their decisions. The present chapter aims to introduce expert systems, outline conceptual examples of such a smart sensing enhanced expert system, and summarize the evidence for smart sensing enhanced expert systems in health care. Lastly, the chapter will be concluded by discussing challenges in the field including ethical, privacy and security, and clinical issues followed by an outlook about future directions and developments.

Abstract: Diseases in plants are very disturbing and hinder to obtain maximum yields, corn plants are plants that are very easy to attack by diseases or pests, so expertise is needed in dealing with corn plant diseases. Problems arise when farmers do not have the ability and expertise to detect early corn plant diseases as experienced by farmers in the mura tami district. This study aims to design an expert system application as a form of solution for farmers so that they can detect plant diseases as early as possible. The expert system was developed using the forward chaining method which is a forward trace method. System development using the PHP programming language and mysql database. The results of this study conclude that the forward chaining method is suitable to be implemented in an expert system. The test results using the black box method stated that 100% of the system's functionality could work well, while testing using the user acceptance test (UAT) method stated that 84% of respondents strongly agreed that the application was implemented.

Abstract: The introduction of collaborative robots (cobots) into the workplace has presented both opportunities and chal-lenges for those seeking to utilize their functionality. Prior research has shown that despite the capabilities afforded by cobots, there is a disconnect between those capabilities and the applications that they currently are deployed in, partially due to a lack of effective cobot-focused instruction in the field. Experts who work successfully within this collaborative domain could offer insight into the considerations and process they use to more effectively capture this cobot capability. Using an analysis of expert insights in the collaborative interaction design space, we developed a set of Expert Frames based on these insights and integrated these Expert Frames into a new training and programming system that can be used to teach novice operators to think, program, and troubleshoot in ways that experts do. We present our system and case studies that demonstrate how Expert Frames provide novice users with the ability to analyze and learn from complex cobot application scenarios.

Abstract: Today, the science of artificial intelligence has become one of the most important sciences in creating intelligent computer programs that simulate the human mind. The goal of artificial intelligence in the medical field is to assist doctors and health care workers in diagnosing diseases and clinical treatment, reducing the rate of medical error, and saving lives of citizens. The main and widely used technologies are expert systems, machine learning and big data. In the article, a brief overview of the three mentioned techniques will be provided to make it easier for readers to understand these techniques and their importance.

Abstract: Computers have become a huge requirement to support human performance. Computers also often experience Hardware damage such as processors, VGA, motherboards, memory, mouse, keyboards, hard disks, optical drives, monitors. Until now, many computer users still do not have sufficient knowledge of the initial diagnosis of computer Hardware damage which causes a lot of computer users to pay a lot of money to find out and repair the damage that occurs to Computer Hardware. In this Expert System application research development, the authors use a combination of two inference methods, namely the Forward Chaining method and the Certainty Factor Method. The programming tools used in the development of this Expert System application is using the Sublime Text 3 application while the database uses MySQL with PHP as the programming language. The purpose of this Expert System application is made to assist computer users in making an initial diagnosis of a damaged computer Hardware along with the causes and solutions to overcome the damage.

Abstract: BACKGROUND Temporomandibular disorders (TMDs) are disabling conditions with a negative impact on the quality of life. Their diagnosis is a complex and multi-factorial process that should be conducted by experienced professionals, and most TMDs remain often undetected. Increasing the awareness of un-experienced dentists and supporting the early TMD recognition may help reduce this gap. Artificial intelligence (AI) allowing both to process natural language and to manage large knowledge bases, could support the diagnostic process. OBJECTIVE In this work, we present the experience of an AI-based system for supporting non-expert dentists in early TMD recognition. METHODS The system was based on commercially available AI services. The prototype development involved a preliminary domain analysis and relevant literature identification, the implementation of the core cognitive computing services, of the web interface, and preliminary testing. Performance evaluation included a retrospective review of 7 available clinical cases, together with the involvement of expert professionals for usability testing. RESULTS The system comprises one module providing possible diagnoses according to a list of symptoms, and a second one represented by a question&answer tool, based on natural language. We found that, even when using commercial services, the training guided by experts is a key factor and that, despite the generally positive feedback, the application's best target is untrained professionals. CONCLUSION We provided a preliminary proof of concept of the feasibility of implementing an AI-based system aimed to support non-specialists in the early identification of TMDs, possibly allowing a faster and more frequent referral to second-level medical centers. Our results showed that AI is a useful tool to improve TMD detection by facilitating a primary diagnosis.

Abstract: Conspectus Passing knowledge from human to human is a natural process that has continued since the beginning of humankind. Over the past few decades, we have witnessed that knowledge is no longer passed only between humans but also from humans to machines. The latter form of knowledge transfer represents a cornerstone in artificial intelligence (AI) and lays the foundation for knowledge engineering (KE). In order to pass knowledge to machines, humans need to structure, formalize, and make knowledge machine-readable. Subsequently, humans also need to develop software that emulates their decision-making process. In order to engineer chemical knowledge, chemists are often required to challenge their understanding of chemistry and thinking processes, which may help improve the structure of chemical knowledge. Knowledge engineering in chemistry dates from the development of expert systems that emulated the thinking process of analytical and organic chemists. Since then, many different expert systems employing rather limited knowledge bases have been developed, solving problems in retrosynthesis, analytical chemistry, chemical risk assessment, etc. However, toward the end of the 20th century, the AI winters slowed down the development of expert systems for chemistry. At the same time, the increasing complexity of chemical research, alongside the limitations of the available computing tools, made it difficult for many chemistry expert systems to keep pace. In the past two decades, the semantic web, the popularization of object-oriented programming, and the increase in computational power have revitalized knowledge engineering. Knowledge formalization through ontologies has become commonplace, triggering the subsequent development of knowledge graphs and cognitive software agents. These tools enable the possibility of interoperability, enabling the representation of more complex systems, inference capabilities, and the synthesis of new knowledge. This Account introduces the history, the core principles of KE, and its applications within the broad realm of chemical research and engineering. In this regard, we first discuss how chemical knowledge is formalized and how a chemist’s cognition can be emulated with the help of reasoning algorithms. Following this, we discuss various applications of knowledge graph and agent technology used to solve problems in chemistry related to molecular engineering, chemical mechanisms, multiscale modeling, automation of calculations and experiments, and chemist–machine interactions. These developments are discussed in the context of a universal and dynamic knowledge ecosystem, referred to as The World Avatar (TWA).

Abstract: The features of the triangle of mutual influence of the basic diagnostic principles are analyzed depending on the known strategies of maintenance and repair, suggesting that these features be taken into account in diagnostic expert systems. Two options for the interaction of the diagnostic support of an object with its maintenance system are studied, specifically: the first is the influence of the set of possible defects in the diagnostic object and the existing maintenance system with a fixed maintenance strategy on the formation of system representations of this object; the second is the influence of the set of possible defects in the diagnostic object and the formed diagnostic model (system representations of the object) on the features of the designed maintenance system. It is proposed to modify the global algorithm for the functioning of the diagnostic expert system, taking into account various aspects of the relationship between the degradation representation of the diagnostic object and the existing maintenance strategies. The functional capabilities of two information platforms for organizing maintenance systems (Galaxy EAM and 1C:RCM Reliability Management) are assessed in relation to the triangle of mutual influence of basic diagnostic principles. The main conclusion is that the methodology for constructing diagnostic expert systems must necessarily be considered in the context of the triangle of mutual influence of basic diagnostic principles, otherwise it largely loses its pragmatic value.

Abstract: Around the world, private and public organizations use software called legal expert systems to compute taxes. This software must comply with the laws they are designed to implement. As such, a bug or an error in a program that leads to tax miscalculations can have heavy legal and democratic consequences. However, increasing evidence suggests that some legal expert systems may not comply with the law. Moreover, traditional software development processes mean that legal expert systems are difficult to adapt to the continuous flow of new legislation. To prevent further software decay and to reconcile these systems with the growing demand for algorithmic transparency, we argue that there is a need for a new development process for legal expert systems. This new system must be built to comply with the law, in particular the GDPR. It must also respect democratic transparency. For these reasons, we present a solution built by lawyers and computer scientists: Catala, a new programming language coupled with a pair programming development process.

Abstract: This paper introduces an Expert System acting as an intelligent agent to interrogate past aircraft occurrence data to support the aircraft occurrence investigators. This Expert System can potentially identify similar occurrences that provide indicators of contributing factors that may otherwise have been missed. This intelligence comes from the Expert System’s ability to learn from past occurrence data using the combined Fuzzy Logic System (FLS) inference technique and AcciMaps to emulate the aircraft occurrence investigators’ evidence analytical reason model. The learned expert knowledge is presented graphically and interactively to the user (investigator) using the AcciMaps. The paper includes an overview of the Australian Transport Safety Bureau (ATSB) investigation evidence analysis workflow, popular mainstream inference techniques used in Expert Systems, evaluation of the proposed Fuzzy Logic System (FLS) inference technique and AcciMap, including an example study. The FLS inference technique has met the Expert System requirements to support aviation occurrence investigations.

Abstract: The pandemic COVID-19 disease has had a dramatic impact on almost all countries around the world so that many hospitals have been overwhelmed with COVID-19 cases. As medical resources are limited, deciding on the proper allocation of these resources is a very crucial issue. Besides, uncertainty is a major factor that can affect decisions, especially in medical fields. To cope with these issues, we use fuzzy logic (FL) as one of the most suitable methods in modeling systems with high uncertainty and complexity. We intend to make use of the advantages of FL in decisions on cases that need to treat in ICU. In this study, an interval type-2 fuzzy expert system is proposed for the prediction of ICU admission in COVID-19 patients. For this prediction task, we also developed an adaptive neuro-fuzzy inference system (ANFIS). Finally, the results of these fuzzy systems are compared to some well-known classification methods such as Naive Bayes (NB), Case-Based Reasoning (CBR), Decision Tree (DT), and K Nearest Neighbor (KNN). The results show that the type-2 fuzzy expert system and ANFIS models perform competitively in terms of accuracy and F-measure compared to the other diagnosis systems.

Abstract: The constant increase in the amount and complexity of information obtained from IT data network elements, for its correct monitoring and management, is a reality. The same happens to data networks in electrical systems that provide effective supervision and control of substations and hydroelectric plants. Contributing to this fact is the growing number of installations and new environments monitored by such data networks and the constant evolution of the technologies involved. This situation potentially leads to incomplete and/or contradictory data, issues that must be addressed in order to maintain a good level of monitoring and, consequently, management of these systems. In this paper, a prototype of an expert system is developed to monitor the equipment status of data networks in electrical systems. This expert system is capable of dealing with inconsistencies without trivialising the inferences. This work was developed in the context of the remote control of hydroelectric plants and substations at a Regional Operation Centre (ROC). The expert system is developed with algorithms defined upon a combination of Fuzzy logic and Paraconsistent Annotated Logic with Annotation of Two Values (PAL2v) in order to analyse uncertain signals and generate the operating conditions (faulty, normal, unstable or inconsistent/indeterminate) of the equipment that are identified as important for the remote control of hydroelectric plants and substations. A prototype of this expert system was installed on a virtualised server with CLP500 software (from the EFACEC manufacturer) that was applied to investigate scenarios consisting of a Regional (Brazilian) Operation Centre, with a Generic Substation and a Generic Hydroelectric Plant, representing a remote control environment.

Abstract: • Designing an expert system to identify the operating regimes of a gas turbine . • Designing rules using a small number of sensors and parameters. • Designing rules with a low order of complexity for optimal hardware implementation. • Ability to use the algorithm for both offline and online scenarios. • High flexibility in implementing the expert rules on a variety of turbines . Operating regime detection plays a pivotal role not only in modeling and control, but also in performance monitoring of gas turbines. In this paper, an expert system is designed and implemented to discriminate the operating regimes of an industrial gas turbine. The proposed expert system identifies start-up regimes (successful/unsuccessful ignition, flame, starts, purge, and manual cooling), stand-still regimes (steady-state and the type of load), and turn-off regimes (normal/emergency shutdown, barring, and off), along with the type of active controller (three types) of the gas turbine. A comprehensive set of expert rules is extracted from the control system’s logic, the knowledge of technicians, and several examples of operating regimes in different environmental conditions. The rules of the expert system are designed so that the minimum number of input sensors and parameters are required to detect the operating regimes. The devised expert system works both online and offline. A concise implementation of the rules is achieved by reducing memory and processing resources on the hardware. To this end, the rules are designed to have the minimum order of complexity, while the processing and memory are confined to the detected beginning and end of each operating regime. The proposed expert system is implemented on an embedded hardware, and its performance is evaluated by using real gas turbine data. Evaluation data is gathered from a different turbine with a different manufacturer. Obtained results show a promising discrimination performance with a hint at the generalization capability of the proposed expert system across different turbines.

Abstract: In this work, we present an algorithmic framework that supports a decision process in which an end user is assisted by a domain expert to solve a problem. In addition, the communication between the end user and the domain expert is characterized by a limited number of questions and answers. The framework we have developed helps the domain expert to pinpoint a small number of questions to the end user to increase the likelihood of their insights being correct. The proposed framework is based on the domain expert’s knowledge and includes an interaction with both the domain expert and the end user. The domain expert’s knowledge is represented by a knowledge graph, and the end user’s information related to the problem is entered into the graph as evidence. This triggers the inference algorithm in the graph, which suggests to the domain expert the next question for the end user. The paper presents a detailed proposed framework in a medical diagnostic domain; however, it can be adapted to additional domains with a similar setup. The software framework we have developed makes the decision-making process accessible in an interactive and explainable manner, which includes the use of semantic technology and is, therefore, innovative.