Professor Edward Szczerbicki

Embedded systems have been in use since the 1970s. For most of their history embedded systems were seen simply as small computers designed to accomplish one or a few dedicated functions; and they were usually working under limited resources i.e. limited computing power, limited memories, and limited energy sources. As such, embedded systems have not drawn much attention from researchers, especially from those in the artificial intelligence area. Thanks to the efforts of scientists over recent years, great progress has been made in both computer hardware and software, which enables us to have much more powerful computers in very small sizes and with many more functions. Consequently, new expectations and needs for embedded systems have increased considerably. Today, smart embedded systems are expected, which are supposed to have capability to learn from past task executions and evolve their performance based on learnt knowledge, and assist users to make good decisions more efficiently. Therefore, how to make embedded systems smart is becoming one of the researchers¿ new challenges. In this chapter, we introduce the Experience-Oriented Smart Embedded Systems (EOSES) that is proposed as a new technological scheme providing embedded systems with capabilities for experiential knowledge capturing, storage, reuse, evolving, and sharing. In this scheme, knowledge is represented as the Set of Experience Knowledge Structure (SOEKS or shortly SOE) and organized as Decisional DNA. The scheme is mainly based on conceptual principles from embedded systems and knowledge management. The objective behind this research is to offer large-scale support for intelligent, autonomous, and coordinated knowledge management on various embedded systems. Several conceptual elements of this research have been implemented in testing prototypes, and the experimental results show that the EOSES scheme can not only provide active knowledge management to different embedded systems, it can also enable various systems to learn from their daily operations in many different fields to acquire valuable knowledge, assist decision making, reduce human workers¿ workload, and improve the system¿s performance. As a result, the EOSES has great potential for meeting today¿s demands for embedded systems, and providing a universe knowledge management scheme for mass autonomous mechanisms.

This chapter presents the concept of smart virtual product development (SVPD) system capable of supporting industrial product development. It enhances the decision making process during various activities involved in product development i.e. product design, manufacturing, and inspection planning. This is achieved by using the explicit knowledge of past formal decision events, which are captured, stored, and recalled in the form of set of experiences (SOEs). The basic description and principles of approach are introduced first, and then the prototype version of the system is developed and tested. Working of the design knowledge management module and manufacturing capability analysis and process planning module of the system are demonstrated with the case study, which verifies the feasibility of the proposed approach. The presented system successfully supports smart product design and manufacturing, and it can play a vital role in Industry 4.0.

Knowledge-based support has become an indispensable part not only to the traditional manufacturing set-ups but also to the new fast-emerging Industry 4.0 scenario. In this regard, successful research has been performed and extensively reported to develop Decisional DNA based knowledge representation models of engineering object and engineering process called Virtual engineering object (VEO), Virtual engineering process (VEP) and Virtual engineering factory (VEF). These models are the virtual representation of manufacturing resources, and with the help of IoT, are capable of capturing the past experience and formal decisions. In this chapter, a complete virtual manufacturing environment is summarized. Furthermore, the scope of this work is explained in the Cyber-Physical Systems (CPS) based Industry 4.0 framework. Four case studies are presented to validate the practical implementation of the proposed concept. In the first case the idea of VEO-VEP-VEF is applied to design an intelligent factory framework to achieve contextual information through real-time visualization. In the second study, the smart tool performance analysis is presented in which data of key tool parameters like tool life, surface integrity, tool forces, and chip formation can be sensed in real-time; also predictions can be made according to the specific requirements. In the third case study, the technique of Decisional DNA (DDNA) is applied to FMS to develop a generic model to achieve effective scheduling and manufacturing flexibility. In the last study, the framework to manage the storage, analysis, and processing of data, information, and knowledge of a typical CIM is presented. The benefits of this approach are manifold as it creates manufacturing DNA of a factory, felicitates in effective decision making, increases the rate of production, reduces errors and production waste, and streamlines manufacturing sub-systems. Moreover, and can be instrumental in designing Industry 4.0.

This chapter presents a description of Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA), argumentation for a knowledge representation, composition, configuration and metrics. SOEKS is a combination of filtered and amalgamated information obtained from formal decision events. It facilitates effective explicit representation of decisional experience taken from different technologies. SOEKS comprises variables, functions, constraints and rules associated in a DNA shape, allowing the construction of enterprises¿ fingerprints called Decisional DNA. SOEKS possesses characteristics that potentialize it as a more precise knowledge representation in a world guided by sensitive dependence and uncertainty, that is, SOEKS is a suitable representation for decisional explicit knowledge that has been gifted with capabilities to manage uncertainty, preciseness and incompleteness. Furthermore, SOEKS extends into the so-called DDNA due to the characterization and aggrupation of SOEKS into different classes termed decisional chromosomes. Such decisional chromosomes simulate specialized genes that when placed together create the decisional experience of an enterprise, the Decisional DNA.

This article proposes a mask refinement method for chromosome instance segmentation. The proposed method exploits the knowledge representation capability of Neural Knowledge DNA (NK-DNA) to capture the semantics of the chromosome¿s shape, texture, and key points, and then it uses the captured knowledge to improve the accuracy and smoothness of the masks. We validate the method¿s effectiveness on our latest high-resolution chromosome image dataset. The experimental results show that our proposed method¿s mask average precision (MaskAP) is 3.66% higher than Mask R-CNN and outperforms advanced Cascade Mask R-CNN by 1.35%.

Karyotyping requires chromosome instances to be segmented and classified from the metaphase images. One of the difficulties in chromosome segmentation is that the chromosomes are randomly positioned in the image, and there is a great chance for chromosomes to be touched or overlap with others. It is always much easier for operators and automatic programs to tackle images without overlapping chromosomes than ones with largely overlapped chromosomes. In order to reduce the processing difficulty, adding a smart image selection procedure ahead of segmentation is practical and necessary. In this paper, we introduce the Smart Karyotyping Image Selection (SKIS) based on Commonsense Knowledge Reasoning. The initial experiment demonstrates that the proposed approach can select the expected images based on reasoning and benefit following karyotyping processes.

Chromosome straightening plays an important role in karyotype analysis. Common straightening methods usually adopt geometric algorithms, which tend to affect the chromosome banding patterns in the process of straightening, resulting in feature changes, loss of details, and poor generalization. To solve these problems, this paper proposes a novel straightening method based on disentanglement representation learning. Our method consists of two main components: the Disentanglement Representation Encoder (DRE) and the Straightening Generator (SG), where DRE discovers and disentangles the bent representation and the content representation in the latent space, while SG is used to generate the straightened chromosome images based on the disentangled representations. Leveraging the bent representation and the content representation disentangled by DRE, our method produces the straightened representation by reducing the bent representation while keeping the content representation unchanged, making straightening chromosome without changing its banding patterns possible. Evaluation results on both the Frechet Initiation Distance (FID) and the Downstream Classification Accuracy (DCA) metrics show that our method achieves good performance.

Chromosome instance segmentation plays a crucial role in chromosomal karyotype analysis. However, the overlapping of chromosome instances and their individual morphological differences make accurate chromosome instance segmentation a challenging task. Especially in handling overlapping chromosome instances, traditional segmentation methods tend to confuse instances with one another. To solve these problems, this paper proposes an innovative method named Adaptive2Former. It builds upon our novel devised Adaptive Query Decoder (AQD) module to enhance segmentation precision. The AQD effectively utilizes the (Formula presented.) token from the backbone network to dynamically generate adaptive query vectors instead of using fixed queries. This new design leverages the semantic information inside the input images, producing representations more conducive to subsequent segmentation module, thereby improving the model¿s segmentation performance. Experiments conducted on our dataset demonstrate that the proposed Adaptive2Former significantly enhances the performance of chromosome instance segmentation compared to Mask2Former and other existing models, achieving results of 97.65% mAP75 and 0.21 Dice Loss.

This research work utilizes the University of New South Wales Network Based 2015 (UNSW-NB15) dataset to investigate the dynamic nature of cyber threats, departing from the obsolete Knowledge Discovery and Data Mining competition 1999 (KDD Cup99) dataset. The data preparation pipeline consists of essential procedures aimed at ensuring the integrity and appropriateness of the data for analysis. The method begins by removing null values, thereafter, applying one-hot encoding to categorical features, min-max scaling for data normalization, and label encoding for efficient management of binary labels. The process of feature selection is conducted utilizing the Pearson coefficient correlation. An exhaustive evaluation is conducted on six machine learning models for the purpose of binary classification. The evaluation takes into account key performance measures like accuracy, precision, recall, and F1 score. The Random Forest model demonstrated exceptional performance, with a remarkable accuracy of 99% and a robust F1 score of 98%. Additionally, it exhibited a well-balanced precision and recall at 98%. The Support Vector Machine, Gradient Boosting, Logistic Regression, Decision Tree, and K-Nearest Neighbors models exhibit notable performance, achieving accuracy and F1 scores around at the 98% level. During our investigation into multi-class classification research, we thoroughly examined numerous machine learning models, all of which exhibited robust performance, with accuracy rates ranging from 97% to 98%. The aforementioned results highlight the efficacy of these models in accurately classifying data, regularly achieving high levels of precision, recall, and F1 scores for positive case predictions. This study offers a current viewpoint on the identification of cyber threats and emphasizes the appropriateness of several machine learning models in this rapidly changing field.

Skin diseases are a significant global health concern, impacting millions worldwide. Severe diseases like psoriasis and dermatitis can coexist with more benign skin issues like acne and eczema. Primary care physicians in tropical areas often treat patients with skin issues in locations where onchocerciasis and tinea imbricate are prominent, such infections might even take center stage. Usually, skin illnesses are disregarded medically and considered cosmetic, but they can have serious psychosocial effects, especially at an early age, and very few global studies have attempted to quantify the frequency of skin diseases. Nevertheless, the ability to make an accurate diagnosis at an early stage is crucial for successful treatment of complex diseases. However, Skin disease identification is a complex process. We introduce a state-of-the-art approach that uses Mask R-CNN in conjunction with an augmented dataset from the HAM10000 from the Harvard University Open Data Repository to achieve close to 80% accuracy in skin disease classification. We provide an in-depth analysis of our approach, covering data preprocessing, model architecture, training, and evaluation, along with detailed tables presenting training and testing results and associated hyperparameters.

Personnel behavior understanding under complex scenarios is a challenging task for computer vision. This paper proposes a novel Compact model, which we refer to as CGARPN that incorporates with Global Association relevance and Adaptive Routing Pose estimation Network. Our framework firstly introduces CGAN backbone to facilitate the feature representation by compressing the kernel parameter space compared with typical algorithms, effectively lowering the calculation capacity and consumption. The framework integrates the Global Association information between keypoints, and learns the correlation between high-dimensional feature parameters. ARPN introduced by our structure is established to sufficiently excavate the resembling properties of outcome concealed in the network, adaptively achieving remarkable performance by selecting compatible paths for optimization. Meanwhile, Parametric Content Similarity NMS (PCSNMS) is developed where detailed information on proposal boxes is associated. Comparative experiments (datasets on FLIC, MPII, etc.) with CNN-based counterparts have empirically demonstrated the effectiveness and competitiveness of the model in perspective of accuracy, memory consumption, and computation perplexity. Our model contributes to an efficient and feasible framework of human behavior apprehension.

In this paper, we propose a knowledge sharing oriented approach to enable a robot to reuse other robots' knowledge by adapting itself to the inverse dynamics model of the knowledge-sharing robot. The purpose of this work is to remove the heavy fine-tuning procedure required before using a new robot for a task via reusing other robots' knowledge. We use the Neural Knowledge DNA (NK-DNA) to help robots gain empirical knowledge and introduce a Knowledge Adaption Module (KAM) utilizing the deep neural networks (DNN) for knowledge reuse. The initial experiment shows that the target robot can adapt to the inverse dynamic model of the source robot via our KAM and reuse the knowledge shared by the source robot.

This paper proposes a novel approach that adds the interpretability to Neural Knowledge DNA (NK-DNA) via generating a decision tree. The NK-DNA is a promising knowledge representation approach for acquiring, storing, sharing, and reusing knowledge among machines and computing systems. We introduce the decision tree-based generative method for knowledge extraction and representation to make the NK-DNA more explainable. We examine our approach through an initial case study. The experiment results show that the proposed method can transform the implicit knowledge stored in the NK-DNA into explicitly represented decision trees bringing fair interpretability to neural network-based intelligent systems.

Organizations must adapt their resources to meet the challenges associated with changes in the work environment in order to remain competitive in the information era. Several research findings identify knowledge sharing as a means for an organization to improve its competitiveness. Knowledge sharing can be defined in a variety of ways, but it essentially refers to the exchange of knowledge from an information giver to an information receiver. This is a purposeful activity that adds value to the client organization, particularly in IT system that employs Agile methodology. For the scope of this paper, we are going to consider only Agile knowledge transfer in IT projects that occurs in two angles: business knowledge transfers from client to consultant; and IT technical knowledge transfers from consultant to client. However, when interdisciplinary teams are involved in Agile IT projects, the knowledge transfer mentioned before remains inefficient once the knowledge loss persists throughout the project life cycle. The conversion of conceptual knowledge, which only exists in the brains and minds of individuals, into explicit knowledge is essential for organizations to gain and maintain competitive advantages over its competitor. This study proposes an alternative conceptual framework to address conceptual knowledge transfer in IT projects that use Agile methodology.

Deep learning suffers from the threat of adversarial attacks, and its defense methods have become a research hotspot. In all applications of deep learning, intelligent driving is an important and promising one, facing serious threat of adversarial attack in the meanwhile. To address the adversarial attack, this paper takes the traffic sign recognition as a typical object, for it is the core function of intelligent driving. Considering that the black box attack does not need to know the internal characteristics of the model, it can have more practical value. However, the existing black box attack algorithm has high visit time and low efficiency in attacking sample generation. In this regard, the SimBA algorithm with high efficiency is selected and improved according to the characteristics of traffic signs, named the L-SimBA algorithm. According to the graphic characteristics of traffic signs that are already known, L-SimBA algorithm limits the search subspace consciously and specifies the set of search directions, and that is the core idea of it. By this way, L-SimBA algorithm can generate adversarial samples faster. Experimental comparison shows that in the field of traffic sign recognition, L-SimBA algorithm is better than SimBA algorithm. On the premise of obtaining similar quality adversarial attack samples, the success rate of adversarial measures gets higher, and the number of model visits reduces considerably, thus the attack efficiency of the algorithm improves greatly.

Knowledge Management (KM) research outputs have been expanding exponentially in the past years, generating diversified topics, which lack integration and classification. It has been challenging for experts to classify KM because of its versatile open fields, and in our view, it contributes to the technocratic approach remaining behind the organizational approach. This paper highlights a way to classify KM publications through a pattern that will support technocratic developments representing knowledge in a more explicit form. This study uses a classification method that uses a template in a taxonomy shape, executing some procedures and allowing an accurate identification and organization of KM research outputs. The proposed taxonomy method is proven on a set of 150 different KM publications from the last 15years. This scheme is grouped into two main categories: Conceptual and Empirical which could enable academics and practitioners alike to better understand the current gaps that are prevalent in KM.

The fourth industrial revolution known as Industry 4.0 is reshaping and evolving the way industries produce products and individuals live and work therefore, gaining massive attraction from academia, business, and politics. The manufacturing industries are optimistic regarding the opportunities that Industry 4.0 may offer such as improved efficiency, productivity and customization. The present research contributes to the Industry 4.0 literature by identifying, modeling, analyzing, and prioritizing the challenges in implementing Industry 4.0 in manufacturing industries. In doing so, the article first introduces the interpretive structural modeling (ISM) to develop the hierarchical relationships among the challenges and analyzes their mutual interactions. Further, ¿Matrice d¿Impacts Croises Multiplication Appliquee aun Classement¿ (MICMAC) analysis is used to categorize the challenges into four categories, namely autonomous, driver, dependent, and linkage based on their driving power and dependence power. Moreover, fuzzy analytic hierarchy process (F-AHP) methodology is used to prioritize the challenges based on three criteria: driving power, dependence power, and change management. The hierarchical model developed through ISM methodology shows that ¿lack of vision and leadership from top management (C12), lack of skills training program and education (C2), and uncertainty of return on investment (C9)¿ are the major challenges in implementing Industry 4.0 in manufacturing industries. The findings of F-AHP analysis suggest that ¿lack of vision and leadership from top management (C12), lack of skilled workforce (C3), lack of skills training program and education (C2), and uncertainty of return on investment (C9)¿ are some of the major challenges of implementing Industry 4.0. Finally, the obtained results show how challenges affect other so that to uncover the root cause triggering the other challenges. The industrial practitioners and managers can then take advantage of these analyses to know which challenge acts as the main barrier in implementing Industry 4.0 and to be focused first in order to reach a solution.

Segmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on a smart, automated, and robust segmentation approach for brain tumor using a modified 3D U-Net architecture. The pre-operative multimodal 3D-MRI scans of High-Grade Glioma (HGG) and Low-Grade Glioma (LGG) are used as data. Our proposed approach solves the problem of memory and system resource constraints by robustly applying dense network training on image patches of 3D volumes. It improves the border region artifact detection by applying convolutions at an appropriate phase in the proposed neural network. Multi-class imbalance data are handled by using Categorical Cross Entropy (CCE) loss developed by combining the Weighted Cross Entropy (WCE) with Weighted Multi-class Dice Loss (WMDL) functions, which enables the network to perform smart segmentation of the smaller tumorous regions. The proposed approach is tested and evaluated for the challenge datasets of multimodal MRI volumes of tumor patients. Experiments are performed to compute the average dice scores on BraTS-2019 and BraTS-2020 datasets for the whole tumor region.

In this paper we propose a novel recommendation approach using past news click data and the Neural Knowledge DNA (NK-DNA). The Neural Knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for news recommendation tasks on the MIND benchmark dataset. By taking advantages of NK-DNA, deep learning, and the SOEKS technologies, our approach can learn from users¿ past behaviors to form reading preference of the user, and reuse learned knowledge for improving the recommendation performance.

In this paper we describe how our Smart Virtual Product Development (SVPD) system can be used to enhance product inspection planning. The SVPD system is comprised of three main modules, these being the design knowledge management (DKM) module, the manufacturing capability and process planning (MCAPP) module, and the product inspection planning (PIP) module. Experiential knowledge relating to formal decisional events is collected, stored and used by the system in the form of set of experiences (SOEs). Here we discuss the working mechanism of the PIP module and show how experiential knowledge relating to the inspection of products that have features and functions in common can be used to enhance product inspection planning during early stages of product development. Our discussion commences with an introduction to fundamental concepts and a general system overview. We then describe the development of our SVPD system¿s PIP module, and a case study we undertook for validation purposes. Results of the case study show that our system is capable of supporting product inspection planning in smart manufacturing, and thus has a vital role to play in Industry 4.0.

Together with the fast advancement of the Internet of Things (IoT), smart healthcare applications and systems are equipped with increasingly more wearable sensors and mobile devices. These sensors are used not only to collect data but also, and more importantly, to assist in daily activity tracking and analyzing of their users. Various human activity recognition (HAR) approaches are used to enhance such tracking. Most of the existing HAR methods depend on exploratory case-based shallow feature learning architectures, which struggle with correct activity recognition when put into real-life practice. To tackle this problem, we propose a novel approach that utilizes the convolutional neural networks (CNNs) and the attention mechanism for HAR. In the presented method, the activity recognition accuracy is improved by incorporating attention into multihead CNNs for better feature extraction and selection. Proof of concept experiments are conducted on a publicly available data set from wireless sensor data mining (WISDM) lab. The results demonstrate a higher accuracy of our proposed approach in comparison with the current methods.

This paper presents the idea of supporting product inspection planning process during the early stages of product life cycle for the experts working on product development. Aim of this research is to assist a collaborative product development process by using Smart Virtual Product Development (SVPD) system, which is based on Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA). The proposed system is developed to support three key aspects of industrial product development i.e. design, manufacturing, and product inspection. Therefore, it comprises of three main modules; design knowledge management (DKM), manufacturing capability and process planning (MCAPP), and product inspection planning (PIP). It collects, stores, and uses experiential knowledge from formal decisional events in the form of set of experience (SOE). This research enlightens the working mechanism of the PIP module, and shows how experiential knowledge related to product inspection can be used during the early stages of product development process. This experiential knowledge is extracted and stored from similar products having some common features and functions. First, the basic description and principles of the approach are introduced, then the prototype version of the system is developed and tested for product inspection planning (PIP) module for the case study, which verifies the feasibility of the proposed approach. The presented system successfully supports smart manufacturing and can play a vital role in Industry 4.0.

This paper presents the concept of Smart Cities from the perspective of those located by water, considering if there are more major differences in the way the concept is implemented in coastal cities, as opposed to those located anywhere else. It proves possible to point to such differences, in relation to the three key areas of mobility, the environment and living. Further consideration is given to specific legal and cross-cultural challenges ¿ like excessive tourism and issues of short-term rental ¿ as these appear from the Smart City perspective; and relevant mobility challenges are also addressed. The article further refers to aspects the Smart City and blue growth concepts have in common, as well as to areas in which coordination of the two will be necessary. Ultimately, conclusions are arrived at on the basis of research results for 10 large cities in Poland, the readiness of their city offices to implement the Smart City concept having been the subject of verification.

Product innovation always requires a foundation based on both knowledge and experience. The production and innovation process of products is very similar to the evolution process of humans. The genetic information of humans is stored in genes, chromosomes and DNA. Similarly, the information about the products can be stored in a system having virtual genes, chromosomes and decisional DNA (DDNA). The present paper proposes a semi-automatic system that facilitates product innovation process using a Smart Knowledge Management System comprising Set of Experience Knowledge Structure and DDNA. This system is called Smart Innovation Engineering System. Through this system, entrepreneurs and organizations will be able to perform the product innovation process technically and quickly, as it stores knowledge in the form of experiences of the past innovative decisions taken. This proposed system is dynamic in nature as it updates itself every time a decision is taken.

In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domains past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest neighbors), logistic regression, and AdaBoost in classification tasks, and the results show that our approach is very promising with regard to the enhancement of the accuracy of knowledge-based predictions required in complex decision-making problems.

Knowledge and experience are essential requirements for product innovation. The presented paper proposes a systematic approach for product innovation support using a Smart Knowledge Management System comprising a Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA). This proposed system is dynamic in nature because it updates itself every time a new decision related to innovation is made. Through this system, the product innovation process can be performed semiautomatically and efficiently because it stores knowledge of past experiences of innovative decisions.

In recent times, traditional manufacturing is upgrading and adopting Industry 4.0, which supports computerization of manufacturing by round-the-clock connection and communication of engineering objects. Consequently, Decisional DNA-based knowledge representation of manufacturing objects, processes, and system is achieved by virtual engineering objects (VEO), virtual engineering processes (VEP), and virtual engineering factories (VEF), respectively. In this study, assimilation of VEO-VEP-VEF concept in the Cyber-physical system-based Industry 4.0 is proposed. The planned concept is implemented on a case study. Also, Decisional DNA features such as similarity identification and phenotyping are explored for validation. It is concluded that this approach can support Industry 4.0 and can facilitate in real time critical, creative, and effective decision making.

The objective of this research is to provide a user-friendly and effective way of representing engineering processes for distributed manufacturing systems so that they can develop, accumulate and share knowledge. The basic definition and principle of the approach is introduced first and then the prototype version of the system is developed and demonstrated with case studies, which verify the feasibility of the proposed approach. This paper proposes a novel concept of virtual engineering process (VEP), which is experience-based knowledge representation of engineering processes. VEP is an extension of our previous work on virtual engineering object (VEO). VEP model includes complete process knowledge required to manufacture a component. This knowledge is captured from three distinctive aspects related to manufacturing. First, information about the manufacturing operations involved. Second, information about the resources/machines required to perform operations and third, information about process level decisions that are taken. It also aims to combine/share experience of engineering objects, manufacturing processes, and systems. It applies bio-inspired knowledge engineering approach called decisional DNA and set of experience-based knowledge representation.

In the real world, it is common to face optimization problems that have two or more objectives that must be optimized at the same time, that are typically explained in different units, and are in conflict with one another. This paper presents a hybrid structure that combines set of experience knowledge structures (SOEKS) and evolutionary algorithms, NSGA-II (Non-dominated Sorting Genetic Algorithm II), to solve multiple optimization problems. The proposed structure uses experience that is derived from a former decision event to improve the evolutionary algorithm's ability to find optimal solutions rapidly and efficiently. It is embedded in a smart experience-based data analysis system (SEDAS) introduced in the paper. Experimental illustrative results of SEDAS application to solve a travelling salesman problem show that our new proposed hybrid model can find optimal or close to true Pareto-optimal solutions in a fast and efficient way.

This paper proposes a service-oriented architecture for video analysis which separates object detection from event recognition. Our aim is to introduce new tools to be considered in the pathway towards Cognitive Vision as a support for classical Computer Vision techniques that have been broadly used by the scientific community. In the article, we particularly focus in solving some of the reported scalability issues found in current Computer Vision approaches by introducing an experience based approximation based on the Set of Experience Knowledge Structure (SOEKS). In our proposal, object detection takes place clientside, while event recognition takes place server-side. In order to implement our approach, we introduce a novel architecture that aims at recognizing events defined by a user using production rules (a part of the SOEKS model) and the detections made by the client using their own algorithms for visual recognition. In order to test our methodology, we present a case study, showing the scalability enhancements provided.

This paper presents a knowledge representation case study by constructing Decisional DNA of engineering objects. Decisional DNA, as a knowledge representation structure not only offers great possibilities on gathering explicit knowledge of formal decision events but also it is a powerful tool for decision-making process. The concept of Virtual engineering Object (VEO), which is a knowledge and experience representation of engineering artefacts, is also discussed. In this paper, we present several Sets of Experience of engineering objects used in manufacturing that were collected for the construction of a VEO-chromosome within the VEO-Decisional DNA. VEO is used to enhance manufacturing systems with predicting capabilities, facilitating decision-making in engineering processes knowledge handling.

Decision recommendations are a set of alternative options for clinical decisions (e.g. diagnosis, prognosis, treatment selection, follow-up and prevention) that are provided to decision makers by knowledge-based Clinical Decision Support Systems (k-CDSS) as aids. We propose to follow a reasoning over domain approach for the generation of decision recommendations, by gathering and inferring conclusions from production rules. In order to rationalize our approach we present a specification that will sustain the logic models supported in the Knowledge Bases we use for persistence. We introduce first the underlying knowledge model and then the necessary extensions that will convey towards the solution of the reported needs. The starting point of our approach is the work of Toro et al. [13] on Reflexive Ontologies (RO). We also propose an extension of RO, by including the handling and reasoning that production rules provide. Our approach speeds-up the recommendation generation process.

Clinical Decision Support Systems (CDSS) are active knowledge resources that use patient data to generate case specific advice. The fast pace of change of clinical knowledge imposes to CDSS the continuous update of the domain knowledge and decision criteria. Traditional approaches require costly tedious manual maintenance of the CDSS knowledge bases and repositories. Often, such an effort cannot be assumed by medical teams, hence maintenance is often faulty. In this paper, we propose a (semi-)automatic update process of the underlying knowledge bases and decision criteria of CDSS, following a learning paradigm based on previous experiences, such as the continuous learning that clinicians carry out in real life. In this process clinical decisional events are acquired and formalized inside the system by the use of the SOEKS and Decisional DNA experiential knowledge representation techniques. We propose three algorithms processing clinical experience to: (a) provide a weighting of the different decision criteria, (b) obtain their fine-tuning, and (c) achieve the formalization of new decision criteria. Finally, we present an implementation instance of a CDSS for the domain of breast cancer diagnosis and treatment. © 2014 Elsevier B.V.

This article reviews research work on set of experience knowledge structure (SOEKS)-decisional DNA (DDNA) done in the past, ongoing, and planned for the future. Firstly, the concept of the knowledge representation technique of SOEKS-DDNA is discussed, and then an attempt is made to organize the past research related with it in chronological order. This work focuses on the review on SOEKS-DDNA, its application in different domains, the various implementation platforms, as well as its benefits and its limitations. The second part of this article provides an idea of the SOEKS-DDNA-related research endeavors currently carried out by us and the last part is a sneak peek into our planned future work. © 2014 Copyright Taylor & Francis Group, LLC.

This article presents our continuing efforts to develop a model of the Internet-based mortgage market in Poland. It sums up modeling research done over the last 4 years, also showing the stages and the process of building and verifying the proposed model consisting of three submodels. The submodels are described for three market situations; that is, a stable market, financial crisis, and economic boom. The proposed model variables are analyzed statistically and the submodels are verified. The article presents the most current stage of model development and concludes with suggestions for further research in this area leading to the ultimate application of the proposed model in a real-life prognosis process. © 2013 Taylor & Francis Group, LLC.

Ontology processing is arguably a time-consuming process with high associated computational costs. Query actions constitute a crucial part of the reasoning process and are a primary source of time consumption. Reflexive ontologies (ROs) is a novel approach intended to reduce time consumption problems while providing a fast reaction from ontology-based applications. In this article we present the implementation of a knowledge-based clinical decision support system (CDSS) for the diagnosis of Alzheimer's disease, which was the benchmark used to evaluate the impact of RO in the overall performance of the system. The implementation details and the definition of the implementation methodology are exposed in this article, along with the results of the evaluation. Some novel techniques that aim to optimize the performance of ROs are also presented with highlights of the test application introduced in our previous work. © 2013 Taylor & Francis Group, LLC.

In this article, we present a concept and case study of a novel approach that generates a television (TV) user's profile utilizing principles of fuzzy logic. A user profile refers to the user's basic information, such as gender, age, and profession. The generated profile has the potential to significantly improve Digital TV (DTV), making the service smarter and more user friendly. We apply the proposed approach to our previous work that introduced decisional DNA TV, which enables TV broadcasters to suggest program choices based upon the user's past viewing habits. Decisional DNA is a domain-independent, flexible, and standard experiential knowledge repository solution that allows for knowledge to be acquired, reused, evolved, and shared in an easy and portable way. The presented conceptual approach demonstrates how fuzzy logic methods can be deployed within DNA TV through an experimental implementation that generates a user profile by capturing viewing habits. © 2013 Taylor & Francis Group, LLC.

The special edition of Cybernetics and Systems contains selected and reviewed papers that expand significantly on topics covered by some conferences on knowledge engineering and smart knowledge-based systems design and development. The selection enhances efforts toward intelligent systemic approaches researched in this area of new, innovative, and significant developments that can be of great interest to cybernetics and systems science professionals. The authors of the paper titled 'Impact of Reflexive Ontologies in Semantic Clinical Decision Support Systems' introduce reflex ontologies (ROs) as a novel approach intended to reduce time consumption problems while providing as a result a fast reaction from ontology-based applications. The presented real-life application is a case study for a knowledge-based clinical decision support system for the diagnosis of Alzheimer's disease.

The aim of the latest issue of the Cybernetics and Systems journal is to provide guidelines to develop tools for smart processing of knowledge and information. It gives ideas and case studies to explore and the complexities and challenges of modern knowledge management issues. It also encourages the reader to become aware of the multifaceted interdisciplinary character of such issues. The preview of this issue is that the reader will leave it with a heightened ability to think about developing, evaluating implementing, and supporting intelligent knowledge- and information-based management systems in real-life environments in different ways. This Guest Edition is based on some significant contributions provided by one of the most dynamic and innovative conference series in the area, held in Spain in 2012. A paper entitled 'A Hybrid Method for Fuzzy Ontology Integration', introduces a novel concept of combining heuristics and consensus-based conflict resolution for fuzzy ontology integration.

This article presents and discusses comprehensive development stages of an integrated, general model of the evolution of support organization enhancing information technology (IT) systems of a corporation. Both advantages and disadvantages of the proposed model are analyzed and future research directions communicated. This article signals one of the current efforts toward addressing the challenges of a very dynamic transformation of IT support in a real-life environment. © 2012 Taylor & Francis.

The paper introduces some challenges of the fast growing mortgage market in Poland, being also the next step of research presented in previous publications, showing the complete process of building and verifying three submodels for the internet mortgage market. The sub-models are described for three market situations, i.e. stable market, crisis, and boom, then the variables within the models are analyzed statistically (e.g. correlation level) and finally the models are verified. The paper presents the process of verification of submodel nr 3 (fast growing market) as an example of the verification process that was applied. The paper concludes with directions for further research in this area leading to the ultimate application of the proposed model in a real life prognosis process. © 2012 The authors and IOS Press. All rights reserved.

Business process modelling and simulation can be a way to improve efficiency in any formal business process support system. In this paper we discuss the underlying concepts and possible approaches that combines formal knowledge representation through past experiences stored in Set of Experience Knowledge structure with one of the popular simulation platforms iGrafx 2011. © 2012 The authors and IOS Press. All rights reserved.

Reinventing the wheel and making mistakes that have already been made by others are the obvious dangers when we embark on a new project. We can avoid these traps by smart use of past experience, which includes past mistakes, related to the area of our activities. The above creates two obvious challenges: first, experience capture and storage; and second, the ability to formalize it and use as a decision support tool. This article tries to address the two challenges by proposing an approach to smart experience management and illustrating this approach with a case involving the information technology (IT) workflow platform. Copyright © 2011 Taylor &Francis Group, LLC.

This paper presents the structure of initial fuzzy model representing the Polish Internet Mortgage Market. It starts with an introduction describing the market complexities and challenges, and description of previously created rule based model. Then the steps of the process of proposed model fuzzification are presented. Next, there is presented Graphic User Interface developed for the model created. The final part of the paper consists of conclusions and directions for future research.

Knowledge-based systems, knowledge technologies, and knowledge management are the areas that have been gaining significant attention and importance in the recent process of the knowledge-based economy creation. The above relates not only to the national economy as a whole (macroeconomic level) but also to particular economy sectors and individual organizations. This article focuses on the role of knowledge management tools, technologies, and approaches in the process of dynamic development of Polish nongovernmental organization (NGO) sector. First, the current state of this role is examined and then a systemic model solution is proposed with an example of implementation supporting the enhancement of NGO operations and performance. The article concludes with the outline of further research in this area.

This article is a brief communication of a concept for building an experience-related knowledge database on top of a workflow system. The presented solution has two important characteristics. First, it is based on minimal effort approach and thus is truly cost-efficient. The second advantage of the proposed approach is low risk related to introduction of new workflow features. The novel ideas of the approach are illustrated using well-known, open-source software and an ordinary relational database. The presented solution is universal and can be easily tailored to be possible to use with other real-life cases including commercially boxed software.

Information is seen as one of the main resources that systems analysts try to use in an optimal way. In this short article, we show how this resource can be used in integration issues. We introduce the problem of information-based integration, propose a solution, and discuss briefly future trends in this area.

Knowledge management, which covers knowledge acquisition, representation, storage, and usage, is one one of the most important smart use of information to enter into knowledge based society. The ability of the society to manage the existing knowledge base has become the benchmark by which the forward movement and expansion of knowledge horizons can be possible. Acquisition of the knowledge from efficient transformation of information, can mean the difference between success and failure for any company in the competitive environment of the global economy and knowledge society. The ability of the transformation of the information into knowledge, and then to use it in the decision making process, contributes in a substantial way to intelligent enterprises, known as the ability of a company to act appropriately in uncertain environments.

Systems become increasingly complex. Their decomposition into smaller units is the usual way to overcome the problem of complexity. This has historically led to the development of atomized structures consisting of a limited number of autonomous subsystems that decide about their own information input and output requirements, i.e., they can be characterized by what is called an information closure. Autonomous subsystems still can be interrelated and embedded in larger systems, as autonomy and independence are not equivalent concepts. These ideas are gaining a very strong interest in both academia and industry, and the atomized approach to information flow modeling and evaluation is an idea whose time has certainly come. This presentation discusses some modeling and evaluation issues, and challenges existing in the exciting area of knowledge capture for information flow-management support for autonomous subsystems.

Supplier selection process is one of the significant stages in supply chain management for industrial manufactured products. It plays an integral role in the success of any manufacturing organization and is an important part starting right from selecting raw material to dispatch of finished products. This paper contributes to enhance the supplier selection process by proposing a multi-criteria decision making framework for industrial manufactured products. The proposed framework is based on smart knowledge management technique called Set of experience knowledge structure (SOEKS) and Decisional DNA, which makes the proposed approach dynamic in nature as it updates itself every time a decision is taken.

Cognitive Vision Systems have gained significant interest from academia and industry during the past few decade, and one of the main reasons behind this is the potential of such technologies to revolutionize human life as they intend to work under complex visual scenes, adapting to a comprehensive range of unforeseen changes, and exhibiting prospective behavior. The combination of these properties aims to mimic the human capabilities and create more intelligent and efficient environments. Nevertheless, preserving the environment such as humans do still remains a challenge in cognitive systems applications due to the complexity of such process. Experts believe the starting point towards real cognitive vision systems is to establish a representation which could integrate image/video modularization and virtualization, together with information from other sources (wearable sensors, machine signals, context, etc.) and capture its knowledge. In this paper we show through a case study how Decisional DNA (DDNA), a multi-domain knowledge structure that has the Set of Experience Knowledge Structure (SOEKS) as its basis can be utilized as a comprehensive embedded knowledge representation in a Cognitive Vision System for Hazard Control (CVP-HC). The proposed application aims to ensure that workers remain safe and compliant with Health and Safety policy for use of Personal Protective Equipment (PPE) and serves as a showcase to demonstrate the representation of visual and non-visual content together as an experiential knowledge in one single structure.

In this paper, we propose a novel approach, the Experience-Oriented Smart Things that allows experiential knowledge discovery, storage, involving, and sharing for Internet of Things. The main features, architecture, and initial experiments of this approach are introduced. Rather than take all the data produced by Internet of Things, this approach focuses on acquiring only interesting data for its knowledge discovery process. By catching decision events, this approach gathers its own daily operation experience, which is the interesting data, and uses such experience for knowledge discovery. An initial experiment was made at the end of this paper, by applying this approach to a sensors-equipped bicycle, the bicycle is able to learn user¿s physical features and recognize its user out of other riders. Customized version of Decisional DNA is used in this approach as the knowledge representation technique. Decisional DNA is a domain-independent, and flexible, and standard experiential knowledge repository solution that allows knowledge to be acquired, reused, evolved and shared easily. The presented conceptual approach demonstrates how knowledge can be discovered through its domain¿s experiences and stored as Decisional DNA.

The concept of Decisional DNA is decade old. This article introduces the initial idea of Set of Experience Knowledge Structure, its advancement into Decisional DNA, and its potential for real life applications in divers domains. The most current and future research steps into Industry 4.0 are also presented and discussed

This paper reviews the theories, parallels and variances between Virtual Engineering Object (VEO)/Virtual Engineering Process (VEP) and Cyber Physical System (CPS). VEO and VEP is an experience based knowledge representation of engineering objects and processes respectively. Cyber-physical systems (CPSs) are the next generation of engineered systems in which computing, communication, and control technologies are tightly integrated. The analysis of basic concepts and implementation method proves that VEO/VEP is a specialized form of CPS and it can play a vital role in the structure building of Industry 4.0. Integration of the two models may result in intelligent machines and advanced analytics.

In real life organizations, the holistic implementations of knowledge based principles from top strategic level to day to day operations are usually missing. The purpose of this paper is to propose an approach that could bridge this gap. Our approach is illustrated with a case study for a company where we integrate Strategic Management with Business Process Management and introduce a decision support and knowledge management capabilities to process, store, share and exploit the knowledge gathered in routine decisions. © 2011 Springer-Verlag.

The paper introduces some challenges of the fast growing mortgage market in Poland. One of these challenges is the need for a model development that could be used for various predictions related to this market. At the current stage of the model development process our main goal is to propose and introduce sub-models the role of which would be to describe three different economic environments: stable, fast growing, and recession. After proposing the above three sub-models the paper concludes with directions of further research in this area. © 2011 Springer-Verlag.

The aim of this paper is to present the conceptual structure of basic fuzzy model representing the Polish Internet mortgage market. The paper starts with an introduction describing the market complexities and challenges, and description of previously created rule based model. Then the steps of the process of proposed model fuzzyfication are presented. Final part of the paper consists of conclusions and directions for future research. © 2010 Springer-Verlag.