This page has only limited features, please log in for full access.
Mining ubiquitous sensing data is important but also challenging, due to many factors, such as heterogeneous large-scale data that is often at various levels of abstraction. This also relates particularly to the important aspects of the explainability and interpretability of the applied models and their results, and thus ultimately to the outcome of the data mining process. With this, in general, the inclusion of domain knowledge leading towards semantic data mining approaches is an emerging and important research direction. This article aims to survey relevant works in these areas, focusing on semantic data mining approaches and methods, but also on selected applications of ubiquitous sensing in some of the most prominent current application areas. Here, we consider in particular: (1) environmental sensing; (2) ubiquitous sensing in industrial applications of artificial intelligence; and (3) social sensing relating to human interactions and the respective individual and collective behaviors. We discuss these in detail and conclude with a summary of this emerging field of research. In addition, we provide an outlook on future directions for semantic data mining in ubiquitous sensing contexts.
Grzegorz Nalepa; Szymon Bobek; Krzysztof Kutt; Martin Atzmueller. Semantic Data Mining in Ubiquitous Sensing: A Survey. Sensors 2021, 21, 4322 .
AMA StyleGrzegorz Nalepa, Szymon Bobek, Krzysztof Kutt, Martin Atzmueller. Semantic Data Mining in Ubiquitous Sensing: A Survey. Sensors. 2021; 21 (13):4322.
Chicago/Turabian StyleGrzegorz Nalepa; Szymon Bobek; Krzysztof Kutt; Martin Atzmueller. 2021. "Semantic Data Mining in Ubiquitous Sensing: A Survey." Sensors 21, no. 13: 4322.
Explainable Artificial Intelligence (XAI) methods form a large portfolio of different frameworks and algorithms. Although the main goal of all of explanation methods is to provide an insight into the decision process of AI system, their underlying mechanisms may differ. This may result in very different explanations for the same tasks. In this work, we present an approach that aims at combining several XAI algorithms into one ensemble explanation mechanism via quantitative, automated evaluation framework. We focus on model-agnostic explainers to provide most robustness and we demonstrate our approach on image classification task.
Szymon Bobek; Paweł Bałaga; Grzegorz J. Nalepa. Towards Model-Agnostic Ensemble Explanations. Transactions on Petri Nets and Other Models of Concurrency XV 2021, 39 -51.
AMA StyleSzymon Bobek, Paweł Bałaga, Grzegorz J. Nalepa. Towards Model-Agnostic Ensemble Explanations. Transactions on Petri Nets and Other Models of Concurrency XV. 2021; ():39-51.
Chicago/Turabian StyleSzymon Bobek; Paweł Bałaga; Grzegorz J. Nalepa. 2021. "Towards Model-Agnostic Ensemble Explanations." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 39-51.
We introduce J.A.N.E. – a proof-of-concept voice-based travel assistant. It is an attempt to show how to handle increasingly complex user queries against the web while balancing between an intuitive user interface and a proper knowledge quality level. As the use case, the search for travel directions based on user preferences regarding cuisine, art and activities was chosen. The system integrates knowledge from several sources, including Wikidata, LinkedGeoData and OpenWeatherMap. The voice interaction with the user is built on the Amazon Alexa platform. A system architecture description is supplemented by the discussion about the motivation and requirements for such complex assistants.
Krzysztof Kutt; Sebastian Skoczeń; Grzegorz J. Nalepa. A Voice-Based Travel Recommendation System Using Linked Open Data. Algorithms and Data Structures 2021, 370 -377.
AMA StyleKrzysztof Kutt, Sebastian Skoczeń, Grzegorz J. Nalepa. A Voice-Based Travel Recommendation System Using Linked Open Data. Algorithms and Data Structures. 2021; ():370-377.
Chicago/Turabian StyleKrzysztof Kutt; Sebastian Skoczeń; Grzegorz J. Nalepa. 2021. "A Voice-Based Travel Recommendation System Using Linked Open Data." Algorithms and Data Structures , no. : 370-377.
With advances of artificial intelligence (AI), there is a growing need for provisioning of transparency and accountability to AI systems. These properties can be achieved with eXplainable AI (XAI) methods, extensively developed over the last few years with relation for machine learning (ML) models. However, the practical usage of XAI is limited nowadays in most of the cases to the feature engineering phase of the data mining (DM) process. We argue that explainability as a property of a system should be used along with other quality metrics such as accuracy, precision, recall in order to deliver better AI models. In this paper we present a method that allows for weighted ML model stacking and demonstrates its practical use in an illustrative example.
Szymon Bobek; Maciej Mozolewski; Grzegorz J. Nalepa. Explanation-Driven Model Stacking. Transactions on Petri Nets and Other Models of Concurrency XV 2021, 361 -371.
AMA StyleSzymon Bobek, Maciej Mozolewski, Grzegorz J. Nalepa. Explanation-Driven Model Stacking. Transactions on Petri Nets and Other Models of Concurrency XV. 2021; ():361-371.
Chicago/Turabian StyleSzymon Bobek; Maciej Mozolewski; Grzegorz J. Nalepa. 2021. "Explanation-Driven Model Stacking." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 361-371.
Cluster discovery from highly-dimensional data is a challenging task, that has been studied for years in the fields of data mining and machine learning. Most of them focus on automation of the process, resulting in the clusters that once discovered have to be carefully analyzed to assign semantics for numerical labels. However, it is often the case that such an explicit, symbolic knowledge about possible clusters is available prior to clustering and can be used to enhance the learning process. More importantly, we demonstrate how a machine learning model can be used to refine the expert knowledge and extend it with an aid of explainable AI algorithms. We present our framework on an artificial, reproducible dataset.
Szymon Bobek; Grzegorz J. Nalepa. Augmenting Automatic Clustering with Expert Knowledge and Explanations. Transactions on Petri Nets and Other Models of Concurrency XV 2021, 631 -638.
AMA StyleSzymon Bobek, Grzegorz J. Nalepa. Augmenting Automatic Clustering with Expert Knowledge and Explanations. Transactions on Petri Nets and Other Models of Concurrency XV. 2021; ():631-638.
Chicago/Turabian StyleSzymon Bobek; Grzegorz J. Nalepa. 2021. "Augmenting Automatic Clustering with Expert Knowledge and Explanations." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 631-638.
Learning from uncertain or incomplete data is one of the major challenges in building artificial intelligence systems. However, the research in this area is more focused on the impact of uncertainty on the algorithms performance or robustness, rather than on human understanding of the model and the explainability of the system. In this paper we present our work in the field of knowledge discovery from uncertain data and show its potential usage for the purpose of improving system interpretability by generating Local Uncertain Explanations (LUX) for machine learning models. We present a method that allows to propagate uncertainty of data into the explanation model, providing more insight into the certainty of the decision making process and certainty of explanations of these decisions. We demonstrate the method on synthetic, reproducible dataset and compare it to the most popular explanation frameworks.
Szymon Bobek; Grzegorz J. Nalepa. Introducing Uncertainty into Explainable AI Methods. Transactions on Petri Nets and Other Models of Concurrency XV 2021, 444 -457.
AMA StyleSzymon Bobek, Grzegorz J. Nalepa. Introducing Uncertainty into Explainable AI Methods. Transactions on Petri Nets and Other Models of Concurrency XV. 2021; ():444-457.
Chicago/Turabian StyleSzymon Bobek; Grzegorz J. Nalepa. 2021. "Introducing Uncertainty into Explainable AI Methods." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 444-457.
In this article, we propose using personality assessment as a way to adapt affective intelligent systems. This psychologically-grounded mechanism will divide users into groups that differ in their reactions to affective stimuli for which the behaviour of the system can be adjusted. In order to verify the hypotheses, we conducted an experiment on 206 people, which consisted of two proof-of-concept demonstrations: a “classical” stimuli presentation part, and affective games that provide a rich and controllable environment for complex emotional stimuli. Several significant links between personality traits and the psychophysiological signals (electrocardiogram (ECG), galvanic skin response (GSR)), which were gathered while using the BITalino (r)evolution kit platform, as well as between personality traits and reactions to complex stimulus environment, are promising results that indicate the potential of the proposed adaptation mechanism.
Krzysztof Kutt; Dominika Drążyk; Szymon Bobek; Grzegorz J. Nalepa. Personality-Based Affective Adaptation Methods for Intelligent Systems. Sensors 2020, 21, 163 .
AMA StyleKrzysztof Kutt, Dominika Drążyk, Szymon Bobek, Grzegorz J. Nalepa. Personality-Based Affective Adaptation Methods for Intelligent Systems. Sensors. 2020; 21 (1):163.
Chicago/Turabian StyleKrzysztof Kutt; Dominika Drążyk; Szymon Bobek; Grzegorz J. Nalepa. 2020. "Personality-Based Affective Adaptation Methods for Intelligent Systems." Sensors 21, no. 1: 163.
Conformance checking is a process mining technique that compares a process model with an event log of the same process to check whether the current execution stored in the log conforms to the model and vice versa. This paper deals with the conformance checking of a longwall shearer process. The approach uses place-transition Petri nets with inhibitor arcs for modeling purposes. We use event log files collected from a few coal mines located in Poland by Famur S.A., one of the global suppliers of coal mining machines. One of the main advantages of the approach is the possibility for both offline and online analysis of the log data. The paper presents a detailed description of the longwall process, an original formal model we developed, selected elements of the approach’s implementation and the results of experiments.
Marcin Szpyrka; Edyta Brzychczy; Aneta Napieraj; Jacek Korski; Grzegorz J. Nalepa. Conformance Checking of a Longwall Shearer Operation Based on Low-Level Events. Energies 2020, 13, 6630 .
AMA StyleMarcin Szpyrka, Edyta Brzychczy, Aneta Napieraj, Jacek Korski, Grzegorz J. Nalepa. Conformance Checking of a Longwall Shearer Operation Based on Low-Level Events. Energies. 2020; 13 (24):6630.
Chicago/Turabian StyleMarcin Szpyrka; Edyta Brzychczy; Aneta Napieraj; Jacek Korski; Grzegorz J. Nalepa. 2020. "Conformance Checking of a Longwall Shearer Operation Based on Low-Level Events." Energies 13, no. 24: 6630.
Development of models for emotion detection is often based on the use of machine learning. However, it poses practical challenges, due to the limited understanding of modeling of emotions, as well as the problems regarding measurements of bodily signals. In this paper we report on our recent work on improving such models, by the use of explainable AI methods. We are using the BIRAFFE data set we created previously during our own experiment in affective computing.
Szymon Bobek; Magdalena M. Tragarz; Maciej Szelążek; Grzegorz J. Nalepa. Explaining Machine Learning Models of Emotion Using the BIRAFFE Dataset. Transactions on Petri Nets and Other Models of Concurrency XV 2020, 290 -300.
AMA StyleSzymon Bobek, Magdalena M. Tragarz, Maciej Szelążek, Grzegorz J. Nalepa. Explaining Machine Learning Models of Emotion Using the BIRAFFE Dataset. Transactions on Petri Nets and Other Models of Concurrency XV. 2020; ():290-300.
Chicago/Turabian StyleSzymon Bobek; Magdalena M. Tragarz; Maciej Szelążek; Grzegorz J. Nalepa. 2020. "Explaining Machine Learning Models of Emotion Using the BIRAFFE Dataset." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 290-300.
In this paper, we consider the use of wearable sensors for providing affect-based adaptation in Ambient Intelligence (AmI) systems. We begin with discussion of selected issues regarding the applications of affective computing techniques. We describe our experiments for affect change detection with a range of wearable devices, such as wristbands and the BITalino platform, and discuss an original software solution, which we developed for this purpose. Furthermore, as a test-bed application for our work, we selected computer games. We discuss the state-of-the-art in affect-based adaptation in games, described in terms of the so-called affective loop. We present our original proposal of a conceptual design framework for games, called the affective game design patterns. As a proof-of-concept realization of this approach, we discuss some original game prototypes, which we have developed, involving emotion-based control and adaptation. Finally, we comment on a software framework, that we have previously developed, for context-aware systems which uses human emotional contexts. This framework provides means for implementing adaptive systems using mobile devices with wearable sensors.
Grzegorz J. Nalepa; Krzysztof Kutt; Barbara Giżycka; Paweł Jemioło; Szymon Bobek. Analysis and Use of the Emotional Context with Wearable Devices for Games and Intelligent Assistants. Sensors 2019, 19, 2509 .
AMA StyleGrzegorz J. Nalepa, Krzysztof Kutt, Barbara Giżycka, Paweł Jemioło, Szymon Bobek. Analysis and Use of the Emotional Context with Wearable Devices for Games and Intelligent Assistants. Sensors. 2019; 19 (11):2509.
Chicago/Turabian StyleGrzegorz J. Nalepa; Krzysztof Kutt; Barbara Giżycka; Paweł Jemioło; Szymon Bobek. 2019. "Analysis and Use of the Emotional Context with Wearable Devices for Games and Intelligent Assistants." Sensors 19, no. 11: 2509.
Grzegorz J. Nalepa; José Palma; María Trinidad Herrero. Affective computing in ambient intelligence systems. Future Generation Computer Systems 2018, 92, 454 -457.
AMA StyleGrzegorz J. Nalepa, José Palma, María Trinidad Herrero. Affective computing in ambient intelligence systems. Future Generation Computer Systems. 2018; 92 ():454-457.
Chicago/Turabian StyleGrzegorz J. Nalepa; José Palma; María Trinidad Herrero. 2018. "Affective computing in ambient intelligence systems." Future Generation Computer Systems 92, no. : 454-457.
Over the last decades, number of embedded and portable computer systems for monitoring of activities of miners and underground environmental conditions that have been developed has increased. However, their potential in terms of computing power and analytic capabilities is still underestimated. In this paper we elaborate on the recent examples of the use of wearable devices in mining industry. We identify challenges for high level monitoring of mining personnel with the use of mobile and wearable devices. To address some of them, we propose solutions based on our recent works, including context-aware data acquisition framework, physiological data acquisition from wearables, methods for incomplete and imprecise data handling, intelligent data processing and reasoning module, hybrid localization using semantic maps, and adaptive power management. We provide a basic use case to demonstrate the usefulness of this approach.
Grzegorz J. Nalepa; Edyta Brzychczy; Szymon Bobek. On the Opportunities for Using Mobile Devices for Activity Monitoring and Understanding in Mining Applications. Privacy Enhancing Technologies 2018, 75 -83.
AMA StyleGrzegorz J. Nalepa, Edyta Brzychczy, Szymon Bobek. On the Opportunities for Using Mobile Devices for Activity Monitoring and Understanding in Mining Applications. Privacy Enhancing Technologies. 2018; ():75-83.
Chicago/Turabian StyleGrzegorz J. Nalepa; Edyta Brzychczy; Szymon Bobek. 2018. "On the Opportunities for Using Mobile Devices for Activity Monitoring and Understanding in Mining Applications." Privacy Enhancing Technologies , no. : 75-83.
In this chapter we present extensions to the XTT model aimed at handling uncertain knowledge. The primary motivation for this research were studies in the area of the context-aware systems. We implemented such systems on mobile platforms, including smartphones or tablets. Such an environment poses a number of challenges addressed by our work. In this chapter we present the classification of most common uncertainty sources present in mobile context-aware systems. We provide a short survey of methods that aim at modeling and handling these uncertainties. We present the approach developed for XTT to cover uncertainties caused by the imprecise data based on modified certainty factors algebra. Furthermore, we discuss its probabilistic extensions. Then the time-parametrised operators for handling noisy batches of data are provided. Finally, we give an insight into a probabilistic interpretation of rule-based models for handling uncertainties caused by the missing data.
Grzegorz J. Nalepa. Handling Uncertainty in Rules. Springer Texts in Business and Economics 2017, 155 -178.
AMA StyleGrzegorz J. Nalepa. Handling Uncertainty in Rules. Springer Texts in Business and Economics. 2017; ():155-178.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Handling Uncertainty in Rules." Springer Texts in Business and Economics , no. : 155-178.
In this chapter we introduce the Semantic Knowledge Engineering approach. It is a development approach for Knowledge-based Systems that uses rule-based knowledge representation. The core of the approach is the formalized rule representation method XTT. The motivation for the approach, along with its distinctive features are given. Then the SKE design process for rule-based systems is presented. SKE was developed to support a heterogeneous architecture of rule-based applications. The approach is well supported by a number of discussed software tools for knowledge base design, generation of the executable rule format, and execution of the rule-based system. Furthermore, tools for rule analysis are discussed.
Grzegorz J. Nalepa. Semantic Knowledge Engineering Approach. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 211 -244.
AMA StyleGrzegorz J. Nalepa. Semantic Knowledge Engineering Approach. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():211-244.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Semantic Knowledge Engineering Approach." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 211-244.
The Semantic Knowledge Engineering approach was proposed to address some of the limitations of knowledge engineering with classic expert systems shells. In this chapter we demonstrate how the formalized model for rule interoperability can be used to provide translation of rule base between Drools and CLIPS, using XTT. We will use the model to formalize the main aspects of both rule languages. First the semantically equivalent features of rule languages in production systems are discussed. Next, the main features of CLIPS and Drools are analyzed. Modularization of the rule base is also considered.
Grzegorz J. Nalepa. Rule Interoperability with Expert System Shells. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 245 -274.
AMA StyleGrzegorz J. Nalepa. Rule Interoperability with Expert System Shells. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():245-274.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Rule Interoperability with Expert System Shells." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 245-274.
Software engineering seeks novel methods and approaches for dealing with growing challenges, such as the quality control of software. Testing is an important area in the software lifecycle. In this chapter we present a practical rule-based method for supporting the unit testing process. First our approach to the use of rules in software unit testing is presented. Then we focus on decision table based testing. A practical tool implementing the method was developed, discussed, and evaluated.
Grzegorz J. Nalepa. Using Rules to Support Software Testing. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 299 -312.
AMA StyleGrzegorz J. Nalepa. Using Rules to Support Software Testing. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():299-312.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Using Rules to Support Software Testing." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 299-312.
In this chapter a formalized model for describing the integration of business processes with business rules is discussed. The solution uses the existing representation methods for processes and rules, specifically the Business Process Model and Notation (BPMN) for process models, and the XTT method for rules. The proposed model deals with the integration of processes with rules in order to provide a coherent formal description, and to support the practical design. Furthermore, in such an approach, BP can be used as a high level inference control for the XTT knowledge base. The chapter provides a formal description of a BPMN process model. This formalized process model is then integrated with rules, and this integration is specified as the General Business Logic Model. In order to apply this model to a specific rule solution, the Specific Business Logic Model is presented. As an evaluation, a case study described using the proposed model is presented.
Grzegorz J. Nalepa. Formalized Integration of Rules and Processes. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 109 -131.
AMA StyleGrzegorz J. Nalepa. Formalized Integration of Rules and Processes. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():109-131.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Formalized Integration of Rules and Processes." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 109-131.
This chapter discusses the practical application of the SKE approach in the context of Semantic Web technologies. In this chapter we present an original solution to a heterogeneous integration of forward chaining rules with Description logic. The Description And Attributive Logic formalism provides the integration of the ALSV(FD)-based rule solution with Description Logics. Furthermore, the Pellet-HeaRT framework enables practical runtime integration of an ontology reasoner a rule engine.
Grzegorz J. Nalepa. Rule-Based Systems and Semantic Web. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 339 -354.
AMA StyleGrzegorz J. Nalepa. Rule-Based Systems and Semantic Web. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():339-354.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Rule-Based Systems and Semantic Web." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 339-354.
Building systems that acquire, process and reason with context data is a major challenge, especially on mobile platforms. Constant updates of knowledge models are one of the primary requirements for the mobile context-aware systems. In this chapter we discuss selected practical results of the KnowMe project. We demonstrate the use of the formal model for uncertainty handling. We distinguish three phases that every context-aware system should pass during the development and later while operating on the mobile device. We discuss the knowledge modeling aspects and the use of the KnowMe toolset.
Grzegorz J. Nalepa. Rules in Mobile Context-Aware Systems. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 403 -430.
AMA StyleGrzegorz J. Nalepa. Rules in Mobile Context-Aware Systems. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():403-430.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Rules in Mobile Context-Aware Systems." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 403-430.
When it comes to practical software design, UML is the standard for modeling software applications. However, the design of complex business management systems requires much more than just UML for design. In the case of process modeling, UML is far too expressive to be understood by the average business user. Thus, BPMN was introduced. Although there is an important difference in abstraction levels of rules and processes, they can be complementary. A formal model for the integration was previously provided by us. In it, the BPMN component defines the high level behavior of the system while the low level logic is defined by rules in XTT. In this chapter we continue that discussion on a practical level. We discuss challenges that need to be addressed to provide full integration, not just on the design but also the runtime level. We demonstrate how the SKE design process can be applied to this goal. Then we discuss selected metrics for the evaluation of process complexity.
Grzegorz J. Nalepa. Integrating Business Process Models with Rules. A Journey Towards Bio-inspired Techniques in Software Engineering 2017, 130, 313 -337.
AMA StyleGrzegorz J. Nalepa. Integrating Business Process Models with Rules. A Journey Towards Bio-inspired Techniques in Software Engineering. 2017; 130 ():313-337.
Chicago/Turabian StyleGrzegorz J. Nalepa. 2017. "Integrating Business Process Models with Rules." A Journey Towards Bio-inspired Techniques in Software Engineering 130, no. : 313-337.