Iztok Fister

University of Maribor | UM · Faculty of Electrical Engineering and Computer Science (FERI)

Numerical association rule mining offers a very efficient way of mining association rules, where algorithms can operate directly with categorical and numerical attributes. These methods are suitable for mining different transaction databases, where data are entered sequentially. However, little attention has been paid to the time series numerical a...

Data squashing is a well-known preprocessing method in Machine Learning that enables construction of smaller datasets from the original ones and provides approximately the same results of data analysis as the original. The paper proposes a new data squashing method for Association Rule Mining based on the Cosine similarity and Euclidean distance si...

This work addresses the IFS-based image reconstruction problem for binary images. Given a binary image as the input, the goal is to obtain all the parameters of an iterated function system whose attractor approximates the input image accurately; the quality of this approximation is measured according to a similarity function between the original an...

The results of evolutionary algorithms depend on population diversity that normally decreases by increasing the selection pressure from generation to generation. Usually, this can lead the evolution process to get stuck in local optima. This study is focused on mechanisms to avoid this undesired phenomenon by introducing parallel self-adapted diffe...

Decisions made nowadays by Artificial Intelligence-powered systems are usually hard for users to understand. One of the most important issues faced by developers is on how to create more explainable Machine Learning models. In line with this, more explainable techniques need to be developed, where visual explanation also plays a more important role...

Companies nowadays eagerly compete in providing their customers with the best possible services, where the companies in the electrical energy market are no exception. As artificial intelligence and machine learning are considered the fundamental multi-purpose technologies and the innovation entity with the most significant potential for disruption,...

Image processing techniques are becoming standard technology in many medical specialities, such as dermatology, where they are a key tool for the early detection and diagnosis of melanoma and other skin cancers and tumors. A previous paper by the authors presented at SOCO 2020 conference introduced a new method for image segmentation of skin images...

Computational Intelligence methods for automatic generation of sport training plans in individual sport disciplines have achieved a mature phase. In order to confirm their added value, they have been deployed into practice. As a result, several methods have been developed for generating well formulated training plans on computers automatically that...

Searching for a set of rules, with which the knowledge hidden in data is extracted, can also be applied for multi-class classification. In line with this, a collection of nature-inspired algorithms are selected for determining the set of rules capable of classifying the samples into three or more classes. This set is encoded into representation of...

Using machine learning methods in the real-world is far from being easy, especially because of the number of methods on the one hand, and setting the optimal values of their parameters on the other. Therefore, a lot of so-called AutoML methods have emerged nowadays that also enable automatic construction of classification pipelines to users, who ar...

Association Rule Mining is a machine learning method for discovering the interesting relations between the attributes in a huge transaction database. Typically, algorithms for Association Rule Mining generate a huge number of association rules, from which it is hard to extract structured knowledge and present this automatically in a form that would...

Numerical Association Rule Mining is a popular variant of Association Rule Mining, where numerical attributes are handled without discretization. This means that the algorithms for dealing with this problem can operate directly, not only with categorical, but also with numerical attributes. Until recently, a big portion of these algorithms were bas...

The authors got the motivation for writing the paper based on an issue, with which developers of the newly developed nature-inspired algorithms are usually confronted today: How to select the test benchmark such that it highlights the quality of the developed algorithm most fairly? In line with this, the CEC Competitions on Real-Parameter Single-Ob...

Nowadays, only a few papers exist dealing with Association Rule Mining with numerical attributes. When we are confronted with solving this problem using nature-inspired algorithms, two issues emerge: How to shrink the values of the upper and lower bounds of attributes properly, and How to define the evaluation function properly? This paper proposes...

This work is an extension of a previous paper (presented at the Cyberworlds 2019 conference) introducing a new method for fractal compression of bitmap binary images. That work is now extended and enhanced through three new valuable features: (1) the bat algorithm is replaced by an improved version based on optimal forage strategy (OFS) and random...

This paper considers the problem of image segmentation for medical images, in particular, cutaneous lesions. Given a digital image of a skin lesion, our goal is to compute the border curve separating the lesion from the image background. This problem can be formulated as an optimization problem, where the border curve is computed through data fitti...

The results of evolutionary algorithms depends on population diversity that normally decreases by increasing the selection pressure from generation to generation. Usually, this can lead evolution process to get stuck in local optima. The study is focused on mechanisms to avoid this undesired phenomenon by introducing parallel differential evolution...

In recent years, some sport clubs have adopted web forums for online discussions about planning training sessions, races, club problems, sponsors and supporters, equipment and so on. Mostly, these forums are closed, because some discussions about critical information must be permitted only to registered club members. Indeed, various members are con...

Numerical Association Rule Mining is a popular variant of Association Rule Mining, where numerical attributes are handled without discretization. This means that the algorithms for dealing with this problem can operate directly, not only with categorical, but also with numerical attributes. Until recently, a big portion of these algorithms were bas...

The paper presents a novel software framework for Association Rule Mining named uARMSolver. The framework is written fully in C++ and runs on all platforms. It allows users to preprocess their data in a transaction database, to make discretization of data, to search for association rules and to guide a presentation/visualization of the best rules f...

Decisions made nowadays by Artificial Intelligence powered systems are usually hard for users to understand. One of the more important issues faced by developers is exposed as how to create more explainable Machine Learning models. In line with this, more explainable techniques need to be developed, where visual explanation also plays a more import...

Association Rule Mining belongs to one of the more prominent methods in Data Mining, where relations are looked for among features in a transaction database. Normally, algorithms for Association Rule Mining mine a lot of association rules, from which it is hard to extract knowledge. This paper proposes a new visualization method capable of extracti...

The term Swarm Robotics collectively refers to a population of robotic devices that efficiently undertakes diverse tasks in a collaborative way by virtue of computational intelligence techniques. This paradigm has given rise to a profitable stream of contributions in recent years, all sharing a clear consensus on the performance benefits derived fr...

Advising athletes how to improve their performance after a race is a very important aspect of sport training. It can also be called a post-hoc analysis, which often includes a deep analysis of an athlete's performance, behavior and body characteristics after a race. These analyses help trainers to adapt their training plan according to the athlete'...

Preference time in a triathlon denotes the time that is planned to be achieved by an athlete in a particular competition. Usually, the preference time is calculated some days, weeks, or even months before the competition. Mostly, trainers calculate the proposed preference time according to the current form, body performances of athletes, psychologi...

Stochastic nature-inspired population-based algorithms are very powerful tools for solving stationary and deterministic, NP-hard optimization problems. These algorithms have rarely been applied to real-world dynamic and uncertain optimization due to their complexity. In this paper, this kind of algorithms were ported onto real hardware (i.e., the v...

With the advent of big data, interest for new data mining methods has increased dramatically. The main drawback of traditional data mining methods is the lack of comprehensibility. In this paper, the firefly algorithm was employed for standalone binary classification, where each solution is represented by two classification rules that are easy unde...

A COVID-19 pandemic has already proven itself to be a global challenge. It proves how vulnerable humanity can be. It has also mobilized researchers from different sciences and different countries in the search for a way to fight this potentially fatal disease. In line with this, our study analyses the abstracts of papers related to COVID-19 and cor...

Nowadays, a big pool of different machine learning components (i.e., algorithms and tools) exists that are capable of predicting various decisions in different problem domains successfully. Unfortunately, a problem has emerged in this respect that we cannot estimate safely which component behaves well on a particular dataset without huge experiment...

Association Rule Mining is a data mining method for discovering the interesting relations between attributes in a huge transaction database. Typically, algorithms for association rule mining generate a huge number of association rules, from which it is hard to extract structured knowledge and automatically present this in a form that would be suita...

Nowadays, the majority of data on the Internet is held in an unstructured format, like websites and e-mails. The importance of analyzing these data has been growing day by day. Similar to data mining on structured data, text mining methods for handling unstructured data have also received increasing attention from the research community. The paper...

Knowledge discovery in databases is a comprehensive procedure which enables researchers to explore knowledge and information from raw sample data usefully. Some problems may arise during this procedure, for example the Curse of Dimensionality, where the reduction of database is desired to avoid feature redundancy or irrelevancy. In this paper, we p...

Border reconstruction is a key technology in medical image processing, where it is applied to identify and separate different tissues, organs, and tumors in diagnostic procedures. The classical approaches for this problem are based on either linear or polynomial functions to describe the border of the region of interest. However, little effort has...

Stochastic population-based nature-inspired metaheuristics have recently revealed that they are a very robust tool for planning sport training sessions in various sports, e.g. running, cycling, triathlon. Most of the existing solutions in literature are focused on planning training sessions for a particular training cycle. Until recently, no specia...

Novelty search ensures evaluation of solutions in stochastic population-based nature-inspired algorithms according to additional measure, where each solution is evaluated by a distance to its neighborhood beside the fitness function. Thus, the population diversity is preserved that is a prerequisite for the open-ended evolution in evolutionary robo...

Detecting communities of interconnected nodes is a frequently addressed problem in situation that be modeled as a graph. A common practical example is this arising from Social Networks. Anyway, detecting an optimal partition in a network is an extremely complex and highly time-consuming task. This way, the development and application of meta-heuris...

Bat algorithm belongs to a class of swarm intelligence algorithms. Comparing to the other stochastic nature-inspired population-based algorithms, this has always been considered as computationally inexpensive. Due to its simplicity and effectiveness, it is very popular in scientific community by solving various optimization problems. However, not e...

Nowadays, mobile wearable devices (e.g., Garmin, Polar) enable information needed for analyzing the performance achieved by athletes in training. On the other hand, new algorithms and methods in computational intelligence and data mining allow an intelligent mode of evaluating the progress of athletes in all phases of sports training. This Special...

Novelty search is a tool in evolutionary and swarm robotics for maintaining the diversity of population needed for continuous robotic operation. It enables nature-inspired algorithms to evaluate solutions on the basis of the distance to their k-nearest neighbors in the search space. Besides this, the fitness function represents an additional measur...

This paper capitalizes on the increasingly high relevance gained by data-intensive technologies in the development of intelligent transportation system, which calls for the progressive adoption of adaptive, self-learning methods for solving modeling, simulation, and optimization problems. In this regard, certain mechanisms and processes observed in...

Studying the lifestyle of various groups of athletes has been a very interesting research direction of many social sport scientists. Following the behavior of these athletes' groups might reveal how they work, yet function in the real-world. Triathlon is basically depicted as one of the hardest sports in the world (especially long-distance triathlo...

This paper proposes a novel filter-based multi-objective particle swarm optimization (PSO) algorithm for feature selection, based on information theory. The PSO is enhanced with clustering and crowding features, which enable the algorithm to maintain a diverse set of solutions throughout the optimization process. Two objectives based on mutual info...

Automatic planning of sport training sessions with Swarm Intelligence algorithms has been proposed recently in the scientific literature that influences the sports training process in practice dramatically. These algorithms are capable of generating sophisticated training plans based on an archive of the existing sports training sessions. In recent...

In the last chapter, the automatic generation of sports training plans using CI algorithms was presented, where it was expected that the their realization would be proceeded smoothly. However, realization of the proposed training plan can be disrupted when an athlete in training process ill or is injured. These unpredictable events can interrupt th...

Creating training plans is the more important task for real trainers, in which specific training sessions are prescribed to trainees according to intensity, duration, type, and repetition, for a specific training period. After realization of the plan, it is expected that the athlete in training would acquire the proper performance level needed for...

The process of sports training consists of four phases: planning, realization, control and evaluation. In the planning phase, trainers prescribe a training load that must be overcome by the athlete during the realization. The response of the athlete on the load represents physical stress. This can be measured indirectly by several physical measures...

Pervasive computing has emerged with the advent of mobile technology. The aim is to be able to obtain information everywhere, at any time, for any objective. Consequently, the concept of disappearing hardware has been developed, where computers are hidden from the users perceptions. This is made possible through the use of sensors that are capable...

This chapter deals with identifying the characteristics of athletes in training. According to the theory of the sports training, this identification is conducted after an evaluation phase, where goals set prior to the training cycle are compared with the achieved results. The purpose of this process is to discover those characteristics of the athle...

Movement is one of the more complex human functions requiring multiple biological systems in the body to operate in concert. There are five systems that enable the functioning of the organism: skeletal, muscular, nervous, respiratory, and cardiovascular. The first three create a so-called kinetic chain that is responsible for performing the functio...

This chapter presents an automatic construction of sports dietary plans based on the training plan generated by an artificial sports trainer. Differential evolution serves as the core algorithm for this purpose. The goal of this algorithm is to select the suitable foods from a food list dataset according to estimated macro-nutrient requirements. Th...

Nowadays, the use of sport trackers increases from day to day. Athletes from different sports disciplines use them in three ways: (1) to monitor their performance data during training, (2) to analyze data after training sessions, and (3) to use the results of the analysis to improve their performance. Many different tracking technologies have been...

The artificial sports trainer bases on CI algorithms for enriching knowledge from data in databases that are obtained from sports activity datasets. These datasets are generated by wearable mobile devices (e.g., sports watches and smart phones) during sports training sessions. Indeed, the artificial sports trainer serves as an intelligent system ca...

The chapter deals with knowledge discovery from data in sport. In the narrower sense, knowledge discovery from data refers to a data mining that also incorporates methods from other domains, like statistics, pattern recognition, machine learning, visualization, association rule mining and computational intelligence algorithms.

For many people, sport is one of the stress-relieving activities. People being involved with sport wish to achieve attractive shape, healthy lifestyle, lose weight, and so on. However, there are also people who deal with sport because of competition goals. In order to fulfill their competition goals, they need to train properly. Even for profession...

Association rule mining is a method for identification of dependence rules between features in a transaction database. In the past years, researchers applied the method using features consisting of categorical attributes. Rarely, numerical attributes were used in these studies. In this paper, we present a novel approach for mining association based...

Finding groups from a set of interconnected nodes is a recurrent paradigm in a variety of practical problems that can be modeled as a graph, as those emerging from Social Networks. However, finding an optimal partition of a graph is a computationally complex task, calling for the development of approximative heuristics. In this regard, the work pre...

This paper presents a swarm robotics approach for dual non-cooperative search, where two robotic swarms are deployed within a map with the goal to find their own target point, placed at an unknown location of the map. We consider the self-centered mode, in which each swarm tries to solve its own goals with no consideration to any other factor exter...

Nowadays, most of databases for classification or regression consists of numerous features that describe the domain of interest. Therefore, they may have a huge influence on the results of classification/regression. A lot of research has shown that some features can be eliminated before the classification/regression in order to obtain better result...

In this paper, a driving route planning system for multi-point routes is designed and developed. The routing problem has modeled as an Open-Path and Asymmetric Green Traveling Salesman Problem (OAG-TSP). The main objective of the proposed OAG-TSP is to find a route between a fixed origin and destination, visiting a group of intermediate points exac...

Analyzing sport data becomes, every year, more interesting for a wide spectrum of researchers in the sports domain. Recently, more and more data relating to sports have become available to researchers due to the huge progress of information technologies. New wearable devices enable athletes to track performance data that are saved into sport activi...

This paper addresses the problem of automatic fitting of feature points for border detection of skin lesions. This problem is an important task in segmentation of dermoscopy images for semi-automatic early diagnosis of melanoma and other skin lesions. Given a set of feature points selected by a dermatologist, we apply a powerful nature-inspired met...

In recent years, planning sport training sessions with computational intelligence have been studied by many authors. Most of the algorithms were used for proposing basic and advanced training plans for athletes. In a nutshell, most of the solutions focused on the individual sports disciplines, such as, for example, cycling and running. To the knowl...

In this paper, we analyze the interplay of two robotic swarms applied to solve a target point search in a non-cooperative mode. In particular, we consider the case of two identical robotic swarms deployed within the same environment to perform dynamic exploration seeking for two different unknown target points. It is assumed that the environment is...

Novelty search in evolutionary robotics measures a distance of potential novelty solutions to their k-nearest neighbors in the search space. This distance presents an additional objective to the fitness function, with which each individual in population is evaluated. In this study, the novelty search was applied within the differential evolution. T...

This paper proposes a new memetic approach to address the problem of obtaining the optimal set of individual Self-Similar Contractive Functions (SSCF) for the reconstruction of self-similar binary IFS fractal images, the so-called SSCF problem. This memetic approach is based on the hybridization of the modified cuckoo search method for global optim...

In recent years, some sport clubs have adopted web forums for online discussions about planning training sessions, races, club problems, sponsors and supporters, equipment and so on. Mostly, these forums are closed, because some discussions about critical information must be permitted only to registered club members. Indeed, various members are con...