Abstract: Deep learning has made significant contribution to the recent progress in artificial intelligence. In comparison to traditional machine learning methods such as decision trees and support vector machines, deep learning methods have achieved substantial improvement in various prediction tasks. However, deep neural networks (DNNs) are comparably weak in explaining their inference processes and final results, and they are typically treated as a black-box by both developers and users. Some people even consider DNNs (deep neural networks) in the current stage rather as alchemy, than as real science. In many real-world applications such as business decision, process optimization, medical diagnosis and investment recommendation, explainability and transparency of our AI systems become particularly essential for their users, for the people who are affected by AI decisions, and furthermore, for the researchers and developers who create the AI solutions. In recent years, the explainability and explainable AI have received increasing attention by both research community and industry. This paper first introduces the history of Explainable AI, starting from expert systems and traditional machine learning approaches to the latest progress in the context of modern deep learning, and then describes the major research areas and the state-of-art approaches in recent years. The paper ends with a discussion on the challenges and future directions.

Abstract: Normative expert systems have not become commonplace because they have been difficult to build and use. Over the past decade, however, researchers have developed the influence diagram, a graphical representation of a decision maker's beliefs, alternatives, and preferences that serves as the knowledge base of a normative expert system. Most people who have seen the representation find it intuitive and easy to use. Consequently, the influence diagram has overcome significantly the barriers to constructing normative expert systems. Nevertheless, building influence diagrams is not practical for extremely large and complex domains. In this book, I address the difficulties associated with the construction of the probabilistic portion of an influence diagram, called a knowledge map, belief network, or Bayesian network. I introduce two representations that facilitate the generation of large knowledge maps. In particular, I introduce the similarity network, a tool for building the network structure of a knowledge map, and the partition, a tool for assessing the probabilities associated with a knowledge map. I then use these representations to build Pathfinder, a large normative expert system for the diagnosis of lymph-node diseases (the domain contains over 60 diseases and over 100 disease findings). In an early version of the system, I encoded the knowledge of the expert using an erroneous assumption that all disease findings were independent, given each disease. When the expert and I attempted to build a more accurate knowledge map for the domain that would capture the dependencies among the disease findings, we failed. Using a similarity network, however, we built the knowledge-map structure for the entire domain in approximately 40 hours. Furthermore, the partition representation reduced the number of probability assessments required by the expert from 75,000 to 14,000.

Abstract: The application of Artificial Intelligence (AI) has been evident in the agricultural sector recently. The sector faces numerous challenges in order to maximize its yield including improper soil treatment, disease and pest infestation, big data requirements, low output, and knowledge gap between farmers and technology. The main concept of AI in agriculture is its flexibility, high performance, accuracy, and cost-effectiveness. This paper presents a review of the applications of AI in soil management, crop management, weed management and disease management. A special focus is laid on the strength and limitations of the application and the way in utilizing expert systems for higher productivity.

Abstract: This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and issues are expressed in this Report. The Report encapsulates the history of computer science efforts to create systems that explain and instruct (intelligent tutoring systems and expert systems). The Report expresses the explainability issues and challenges in modern AI, and presents capsule views of the leading psychological theories of explanation. Certain articles stand out by virtue of their particular relevance to XAI, and their methods, results, and key points are highlighted. It is recommended that AI/XAI researchers be encouraged to include in their research reports fuller details on their empirical or experimental methods, in the fashion of experimental psychology research reports: details on Participants, Instructions, Procedures, Tasks, Dependent Variables (operational definitions of the measures and metrics), Independent Variables (conditions), and Control Conditions.

Abstract: Intellectualization is an important direction of drying development and artificial intelligence (AI) technologies have been widely used to solve problems of nonlinear function approximation, pattern detection, data interpretation, optimization, simulation, diagnosis, control, data sorting, clustering, and noise reduction in different food drying technologies due to the advantages of self-learning ability, adaptive ability, strong fault tolerance and high degree robustness to map the nonlinear structures of arbitrarily complex and dynamic phenomena. This article presents a comprehensive review on intelligent drying technologies and their applications. The paper starts with the introduction of basic theoretical knowledge of ANN, fuzzy logic and expert system. Then, we summarize the AI application of modeling, predicting, and optimization of heat and mass transfer, thermodynamic performance parameters, and quality indicators as well as physiochemical properties of dried products in artificial biomimetic technology (electronic nose, computer vision) and different conventional drying technologies. Furthermore, opportunities and limitations of AI technique in drying are also outlined to provide more ideas for researchers in this area.

Abstract: In this paper, an effort has been made for intense review on Knowledge-Based Expert System (KB-ES) applications in manufacturing planning. Uniqueness of the present review work is addressed in term...

Abstract: Background: The rise of biomedical expert heuristic knowledge-based approaches for computational modeling and problem solving, for scientific inquiry and medical decision-making, and for consultation in the 1970’s led to a major change in the paradigm that affected all of artificial intelligence (AI) research. Since then, AI has evolved, surviving several “winters”, as it has oscillated between relying on expensive and hard-to-validate knowledge-based approaches, and the alternative of using machine learning methods for inferring classification rules from labelled datasets. In the past couple of decades, we are seeing a gradual but progressive intertwining of the two. Objectives: To give an overview of early directions in AI in medicine and threads of some subsequent developments motivated by the very different goals of scientific inquiry for biomedical research, and for computational modeling of clinical reasoning and more general healthcare problem solving from the perspective of today’s “AI-Deep Learning Boom”. To show how, from the beginning, AI was central to Biomedical and Health Informatics (BMHI), as a field investigating how to understand intelligent thinking in dealing professionally with the practice for healthcare, developing mathematical models, technology, and software tools to aid human experts in biomedicine, despite many previous bouts of “exuberant optimism” about the methodologies deployed. Methods: An overview and commentary on some of the early research and publications in AI in biomedicine, emphasizing the different approaches to the modeling of problems involved in clinical practice in contrast to those of biomedical science. A concluding reflection of a few current challenges and pitfalls of AI in some biomedical applications. Conclusion: While biomedical knowledge-based systems played a critical role in influencing AI in its early days, 50 years later they have taken a back seat behind “Deep Learning” which promises to discover knowledge structures for inference and prediction, both in science and for clinical decision-support. Early work on AI for medical consultation turned out to be more useful for explanation and teaching than for clinical practice, as had been originally intended. Today, despite the many reported successes of deep learning, fundamental scientific challenges arise in drawing on models of brain science, cognition, and language, if AI is to augment and complement rather than replace human judgment and expertise in biomedicine while also incorporating these advances for translational medicine. Understanding clinical phenotypes and how they relate to precision and personalization of care requires not only scientific inquiry, but also humanistic models of treatment that respond to patient and practitioner narrative exchanges, since it is the stories and insights of human experts which encourage what Norbert Weiner termed the ethical “human use of human beings”, so central to adherence to the Hippocratic Oath

Abstract: In the last two decades, the text summarization task has gained much importance because of the large amount of online data, and its potential to extract useful information and knowledge in a way that could be easily handled by humans and used for a myriad of purposes, including expert systems for text assessment. This paper presents an automatic process for text assessment that relies on fuzzy rules on a variety of extracted features to find the most important information in the assessed texts. The automatically produced summaries of these texts are compared with reference summaries created by domain experts. Differently from other proposals in the literature, our method summarizes text by investigating correlated features to reduce dimensionality, and consequently the number of fuzzy rules used for text summarization. Thus, the proposed approach for text summarization with a relatively small number of fuzzy rules can benefit development and use of future expert systems able to automatically assess writing. The proposed summarization method has been trained and tested in experiments using a dataset of Brazilian Portuguese texts provided by students in response to tasks assigned to them in a Virtual Learning Environment (VLE). The proposed approach was compared with other methods including a naive baseline, Score, Model and Sentence, using ROUGE measures. The results show that the proposal provides better f-measure (with 95% CI) than aforementioned methods.

Abstract: Deep learning has been applied in physical-layer communications systems in recent years and has demonstrated fascinating results that were comparable or even better than human expert systems. In this paper, a novel convolutional neural networks (CNNs)-based autoencoder communication system is proposed, which can work intelligently with arbitrary block length, can support different throughput and can operate under AWGN and Rayleigh fading channels as well as deviations from AWGN environments. The proposed generalized communication system is comprised of carefully designed convolutional neural layers and, hence, inherits CNN’s breakthrough characteristics, such as generalization, feature learning, classification, and fast training convergence. On the other hand, the end-to-end architecture jointly performs the tasks of encoding/decoding and modulation/demodulation. Finally, we provide the numerous simulation results of the learned system in order to illustrate its generalization capability under various system conditions.

Abstract: Conversational artificial intelligence (AI) is changing the way mental health care is delivered. By gathering diagnostic information, facilitating treatment, and reviewing clinician behavior, conversational AI is poised to impact traditional approaches to delivering psychotherapy. While this transition is not disconnected from existing professional services, specific formulations of clinician-AI collaboration and migration paths between forms remain vague. In this viewpoint, we introduce four approaches to AI-human integration in mental health service delivery. To inform future research and policy, these four approaches are addressed through four dimensions of impact: access to care, quality, clinician-patient relationship, and patient self-disclosure and sharing. Although many research questions are yet to be investigated, we view safety, trust, and oversight as crucial first steps. If conversational AI isn’t safe it should not be used, and if it isn’t trusted, it won’t be. In order to assess safety, trust, interfaces, procedures, and system level workflows, oversight and collaboration is needed between AI systems, patients, clinicians, and administrators.

Abstract: The use of machine learning (ML) in healthcare has enormous potential for improving disease detection, clinical decision support, and workflow efficiencies. In this commentary, we review published and potential applications for the use of ML for monitoring within the hospital environment. We present use cases as well as several questions regarding the application of ML to the analysis of the vast amount of complex data that clinicians must interpret in the realm of continuous physiological monitoring. ML, especially employed in bidirectional conjunction with electronic health record data, has the potential to extract much more useful information out of this currently under-analyzed data source from a population level. As a data driven entity, ML is dependent on copious, high quality input data so that error can be introduced by low quality data sources. At present, while ML is being studied in hybrid formulations along with static expert systems for monitoring applications, it is not yet actively incorporated in the formal artificial learning sense of an algorithm constantly learning and updating its rules without external intervention. Finally, innovations in monitoring, including those supported by ML, will pose regulatory and medico-legal challenges, as well as questions regarding precisely how to incorporate these features into clinical care and medical education. Rigorous evaluation of ML techniques compared to traditional methods or other AI methods will be required to validate the algorithms developed with consideration of database limitations and potential learning errors. Demonstration of value on processes and outcomes will be necessary to support the use of ML as a feature in monitoring system development: Future research is needed to evaluate all AI based programs before clinical implementation in non-research settings.

Abstract: The advancement of science and technology has facilitated adaptation of human intelligence into its computerized platform for logical analysis of any event. This porting of human intelligence to machine is known as Artificial Intelligence (AI). AI enhances human life since inception with the help of these intelligent machines, human potentials will be augmented in multiple spheres. An enormous improvement in this area of AI has been noticed in the past two decades that has given rise to expert systems. AI has huge impact on different fields of business, engineering, law, medicine, science, weather forecasting, etc. to enhance the quality and efficiency in our day to day life to solve complex problems. For the past few decades, AI has been playing an emerging role in the legal field and will definitely have an effect on the legal practices over the next few years. AI has the potential to analyses legal information based on semantics and make legal predictions from the legal data set, and hence it helps the judiciary system in automation thereby increasing the efficiency within affordable budget. For better understanding of the concept, in this paper authors have performed relevant survey on this field.

Abstract: Preventing cost overruns of such infrastructure projects as power plants is a global project management problem. The existing risk assessment methods/models have limitations to address the complicated nature of these projects, incorporate the probabilistic causal relationships of the risks and probabilistic data for risk assessment, by taking into account the domain experts’ judgments, subjectivity, and uncertainty involved in their judgments in the decision making process. A knowledge-based expert system is presented to address this issue, using a fuzzy canonical model (FCM) that integrates the fuzzy group decision-making approach (FGDMA) and the Canonical model (i.e. a modified Bayesian belief network model). The FCM overcomes: (a) the subjectivity and uncertainty involved in domain experts’ judgment, (b) significantly reduces the time and effort needed for the domain experts in eliciting conditional probabilities of the risks involved in complex risk networks, and (c) reduces the model development tasks, which also reduces the computational load on the model. This approach advances the applications of fuzzy-Bayesian models for cost overrun risks assessment in a complex and uncertain project environment by addressing the major constraints associated with such models. A case study demonstrates and tests the application of the model for cost overrun risk assessment in the construction and commissioning phase of a power plant project, confirming its ability to pinpoint the most critical risks involved in this case, the complexity of the lifting and rigging heavy equipment, inadequate work inspection and testing plan, inadequate site/soil investigation, unavailability of the resources in the local market, and the contractor's poor planning and scheduling.

Abstract: Advancements and new techniques in information technologies are making it possible to manage, analyze and present large-scale environmental modeling results and spatial data acquired from various sources. However, it is a major challenge to make this data accessible because of its unstructured, incomplete and varied nature. Extracting information and making accurate inferences from various data sources rapidly is critical for natural disaster preparedness and response. Critical information about disasters needs to be provided in a structured and easily accessible way in a context-specific manner. This paper introduces a group of information-centric ontologies that encompass the flood domain and describes how they can be benefited to access, analyze, and visualize flood-related data with natural language queries. The presented methodology enables the easy integration of domain knowledge into expert systems and voice-enabled intelligent applications that can be accessed through web-based information platforms, instant messaging apps, automated workflow systems, home automation devices, and augmented and virtual reality platforms. A case study is described to demonstrate the usage of presented ontologies in such intelligent systems.

Abstract: This paper presents an application of a recently well performing evolutionary algorithm for continuous numerical optimization, Success-History Based Adaptive Differential Evolution Algorithm (SHADE) including Linear population size reduction (L-SHADE), to an expert system for underwater glider path planning (UGPP). The proposed algorithm is compared to other similar algorithms and also to results from literature. The motivation of this work is to provide an alternative to the current glider mission control systems, that are based mostly on multidisciplinary human-expert teams from robotic and oceanographic areas. Initially configured as a decision-support expert system, the natural evolution of the tool is targeting higher autonomy levels. To assess the performance of the applied optimizers, the test functions for UGPP are utilized as defined in literature, which simulate real-life oceanic mission scenarios. Based on these test functions, in this paper, the performance of the proposed application of L-SHADE to UGPP is aggregated using statistical analyis. The depicted fitness convergence graphs, final obtained fitness plots, trajectories drawn, and per-scenario analysis show that the new proposed algorithm yields stable and competitive output trajectories. Over the set of benchmark missions, the newly obtained results with a configured L-SHADE outperforms existing literature results in UGPP and ranks best over the compared algorithms. Moreover, some additional previously applied algorithms have been reconfigured to yield improved performance. Thereby, this new application of evolutionary algorithms to UGPP contributes significantly to the capacity of the decision-makers, when they use the improved UGPP expert system yielding better trajectories.

Abstract: In highly complex industries, capturing and employing expert systems is significantly important to an organization's success considering the advantages of knowledge-based systems. The two most important issues within the expert system applications in risk and reliability analysis are the acquisition of domain experts' professional knowledge and the reasoning and representation of the knowledge that might be expressed. The first issue can be correctly handled by employing a heterogeneous group of experts during the expert knowledge acquisition processes. The members of an expert panel regularly represent different experiences and knowledge. Subsequently, this diversity produces various sorts of information which may be known or unknown, accurate or inaccurate, and complete or incomplete based on its cross-functional and multidisciplinary nature. The second issue, as a promising tool for knowledge reasoning, still suffers from lack of deficiencies such as weight and certainty factor, and are insufficient to accurately represent complex rule-based expert systems. The outputs in current expert system applications in probabilistic risk assessment could not accurately represent the increasingly complex knowledge-based systems. The reason is the lack of certainty and self-assurance of experts when they are expressing their opinions. In this paper, a novel methodology is presented based on the concept of Z-numbers to overcome this issue. A case study in a high-tech process industry is provided in detail to demonstrate the application and feasibility of the proposed methodology.

Abstract: Many expert systems have been developed for self-adaptive PID controllers of mobile robots. However, the high computational requirements of the expert systems layers, developed for the tuning of the PID controllers, still require previous expert knowledge and high efficiency in algorithmic and software execution for real-time applications. To address these problems, in this paper we propose an expert agent-based system, based on a reinforcement learning agent, for self-adapting multiple low-level PID controllers in mobile robots. For the formulation of the artificial expert agent, we develop an incremental model-free algorithm version of the double Q -Learning algorithm for fast on-line adaptation of multiple low-level PID controllers. Fast learning and high on-line adaptability of the artificial expert agent is achieved by means of a proposed incremental active-learning exploration-exploitation procedure, for a non-uniform state space exploration, along with an experience replay mechanism for multiple value functions updates in the double Q -learning algorithm. A comprehensive comparative simulation study and experiments in a real mobile robot demonstrate the high performance of the proposed algorithm for a real-time simultaneous tuning of multiple adaptive low-level PID controllers of mobile robots in real world conditions.

Abstract: Artificial intelligence ( AI ) is once again a topic of huge interest for computer scientists around the world. Whilst advances in the capability of machines are being made all around the world at an incredible rate, there is also increasing focus on the need for computerised systems to be able to explain their decisions, at least to some degree. It is also clear that data and knowledge in the real world are characterised by uncertainty. Fuzzy systems can provide decision support, which both handle uncertainty and have explicit representations of uncertain knowledge and inference processes. However, it is not yet clear how any decision support systems, including those featuring fuzzy methods, should be evaluated as to whether their use is permitted. This paper presents a conceptual framework of indistinguishability as the key component of the evaluation of computerised decision support systems. Case studies are presented in which it has been clearly demonstrated that human expert performance is less than perfect, together with techniques that may enable fuzzy systems to emulate human-level performance including variability. In conclusion, this paper argues for the need for “ fuzzy AI ” in two senses: ( i ) the need for fuzzy methodologies ( in the technical sense of Zadeh ʼ s fuzzy sets and systems ) as knowledge-based systems to represent and reason with uncertainty; and ( ii ) the need for fuzziness ( in the non-technical sense ) with an acceptance of imperfect performance in evaluating AI systems.

Abstract: The data management, interpretation and comparison of sets of DNA profiles can be complex, time-consuming and error-prone when performed manually. This, combined with the growing numbers of genetic markers in forensic identification systems calls for expert systems that can automatically compare genotyping results within (large) sets of DNA profiles and assist in profile interpretation. To that aim, we developed a user-friendly software program or DNA eXpert System that is denoted DNAxs. This software includes features to view, infer and match autosomal short tandem repeat profiles with connectivity to up and downstream software programs. Furthermore, DNAxs has imbedded the 'DNAStatistX' module, a statistical library that contains a probabilistic algorithm to calculate likelihood ratios (LRs). This algorithm is largely based on the source code of the quantitative probabilistic genotyping system EuroForMix [1]. The statistical library, DNAStatistX, supports parallel computing which can be delegated to a computer cluster and enables automated queuing of requested LR calculations. DNAStatistX is written in Java and is accessible separately or via DNAxs. Using true and non-contributors to DNA profiles with up to four contributors, the DNAStatistX accuracy and precision were assessed by comparing the DNAStatistX results to those of EuroForMix. Results were the same up to rare differences that could be attributed to the different optimizers used in both software programs. Implementation of dye specific detection thresholds resulted in larger likelihood values and thus a better explanation of the data used in this study. Furthermore, processing time, robustness of DNAStatistX results and the circumstances under which model validations failed were examined. Finally, guidelines for application of the software are shared as an example. The DNAxs software is future-proof as it applies a modular approach by which novel functionalities can be incorporated.

Abstract: Expert systems are computer-based systems that mimic the logical processes of human experts or organizations to give advice in a specific domain of knowledge. Fuzzy expert systems use fuzzy logic to handle uncertainties generated by imprecise, incomplete and/or vague information. The purpose of this paper is to present a comprehensive review of the methods and applications in fuzzy expert systems.,The authors have carefully reviewed 281 journal publications and 149 conference proceedings published over the past 37 years since 1982. The authors grouped the journal publications and conference proceedings separately accordingly to the methods, application domains, tools and inference systems.,The authors have synthesized the findings and proposed useful suggestions for future research directions. The authors show that the most common use of fuzzy expert systems is in the medical field.,Fuzzy logic can be used to manage uncertainty in expert systems and solve problems that cannot be solved effectively with conventional methods. In this study, the authors present a comprehensive review of the methods and applications in fuzzy expert systems which could be useful for practicing managers developing expert systems under uncertainty.

Abstract: The aim of this paper is to analyze the current situation regarding artificial intelligence in audit and accounting, including the newest trends, opportunities and threats. Due to its innovative character, this field is constantly changing, with the biggest companies investing enormous amounts of capital to achieve wide use of artificial intelligence in audit and accounting. One of the main goals of the paper is to provide an analysis of audit tasks that benefit from artificial intelligence implementation, with an emphasis on risk assessment. Another goal is to outline artificial intelligence technologies used in audit and accounting. The most practical purpose of the paper is to evaluate the current applications and audit tools developed by Big4 companies, the four leading consulting companies in audit and accounting. The results of the paper include overview of seven essential audit tasks proving the significance of using artificial intelligence in accounting and audit process. The research also confirmed that the technologies most commonly used are genetic algorithms and programming, fuzzy systems, neural networks and hybrid systems, the combination of the aforementioned technologies, with the synthesis of expert systems and neural networks proven to be the most successful. Finally, the practical result of this paper is a summary of the Big4 latest developed artificial intelligence tools and innovations, mainly for audit planning, benchmarking and documents analysis.

Abstract: Collaborative filtering is an emerging recommender system technique that aims guiding users based on other customers preferences with behavioral similarities. Such correspondences are located based on preference history of users. A relatively new extension of traditional collaborative filtering schemes takes into account not only how much a user likes an item, but also why she likes the item by collecting multi-criteria preferences focusing on distinctive features of the items. These multi-criteria collaborative filtering systems have the potential to improve recommender system accuracy since they reveal multiple views of users on products. However, due to providing more insightful recommendations, such systems might be subjected to malicious attacks more substantially than the traditional ones. Attackers attempt to insert fake profiles to bias outputs of these systems in favor of a particular product or disrepute the system itself. Since outputs of expert systems directly dependent on input signals; interventions to the inputs coherently cause failures on productions of such systems. In this study, we examine shilling attack strategies against multi-criteria preference collections, how to extend well-known attack scenarios against these systems, and propose an alternative attacking scheme. We analyze the robustness of baseline multi-criteria recommendation algorithms regarding various similarity aggregation procedures against proposed attacking schemes by the extensive experimental investigation. Empirical results on real-world data demonstrate that these systems are highly vulnerable to manipulations and proper attack detection practices are needed to ensure recommendation quality. According to our findings, manipulative attempts at such expert systems mislead decision-making process.

Abstract: Fuzzy Petri nets (FPNs) have been applied in many fields as a potential modeling tool for knowledge representation and reasoning. However, there exist many deficiencies in the conventional FPNs when applied in the real world. In this paper, we present a new type of FPN, called picture fuzzy Petri nets (PFPNs), to overcome the shortcomings and improve the effectiveness of the traditional FPNs. First, the proposed PFPN model adopts the picture fuzzy sets (PFSs), characterized by degrees of positive membership, neutral membership, and negative membership, to depict human expert knowledge. As a result, the uncertainty, due to vagueness, imprecision, partial information, etc., can be well-handled in knowledge representation. Second, a similarity degree-based expert weighting method is offered for consensus reaching processes in knowledge acquisition. The proposed PFPN model can manage the conflicts and inconsistencies among expert evaluations in knowledge parameters, thus, making the obtained knowledge rules more accurate. Finally, a realistic example of a gene regulatory network is provided to illustrate the feasibility and practicality of the proposed PFPN model.

Abstract: The death rate is caused by breast cancer in women is increasingly high and growing. A number of people are getting to lose this part of their body due to late diagnosis of this disease. This therefore requires the development of an efficient and accurate diagnosis approach that will aid providing the knowledge of the type of breast cancer type and severity in order to reduce the mortality rate through the disease. This need serves as the major motivation for this work. In this paper, we proposed a fuzzy expert system for diagnosis of and treatment recommendation of breast cancer problems which provide physicians and patients with information of the cancer type and treatment recommendation. The application was designed using JAVA programming language, MATLAB and SQLite database engine. This application permits update of new information as a means of knowledge. The evaluation showed that the inclusion of the fuzzy inference system improved the accuracy and precision of the system from 0.8 to 0.9. The system is user-friendly and has high level of acceptability from the validation conducted at the end of the research.

Abstract: There are only a few applications of infrared thermal imaging in aviation. In the area of turbojet engines, infrared imaging has been used to detect temperature field anomalies in order to identify structural defects in the materials of engine casings or other engine parts. In aviation applications, the evaluation of infrared images is usually performed manually by an expert. This paper deals with the design of an automatic intelligent system which evaluates the technical state and diagnoses a turbojet engine during its operation based on infrared thermal (IRT) images. A hybrid system interconnecting a self-organizing feature map and an expert system is designed for this purpose. A Kohonen neural network (the self-organizing feature map) is successfully applied to segment IRT images of a turbojet engine with high precision, and the expert system is then used to create diagnostic information from the segmented images. This paper represents a proof of concept of this hybrid system using data from a small iSTC-21v turbojet engine operating in laboratory conditions.