Wyniki wyszukiwania - Biblioteka Nauki

1

Fine tuning of agent-based evolutionary computing

100%

Mizera M. , Nowotarski P. , Byrski A. , Kisiel-Dorohinicki M.

|

2019

|

tom Vol. 9, No. 2

81--97

EN

Evolutionary Multi-agent System introduced by late Krzysztof Cetnarowicz and developed further at the AGH University of Science and Technology became a reliable optimization system, both proven experimentally and theoretically. This paper follows a work of Byrski further testing and analyzing the efficacy of this metaheuristic based on popular, high-dimensional benchmark functions. The contents of this paper will be useful for anybody willing to apply this computing algorithm to continuous and not only optimization.

2

A new approach to detecting and preventing populations stagnation through dynamic changes in multi-population-based algorithms

100%

Łapa K. , Rutkowska D. , Byrski A. , Napoli C.

Journal of Artificial Intelligence and Soft Computing Research

|

2023

|

tom Vol. 13, No. 4

289--306

EN

In this paper, a new mechanism for detecting population stagnation based on the analysis of the local improvement of the evaluation function and the infinite impulse response filter is proposed. The purpose of this mechanism is to improve the population stagnation detection capability for various optimization scenarios, and thus to improve multi-population-based algorithms (MPBAs) performance. In addition, various other approaches have been proposed to eliminate stagnation, including approaches aimed at both improving performance and reducing the complexity of the algorithms. The developed methods were tested, among the others, for various migration topologies and various MPBAs, including the MNIA algorithm, which allows the use of many different base algorithms and thus eliminates the need to select the population-based algorithm for a given simulation problem. The simulations were performed for typical benchmark functions and control problems. The obtained results confirm the validity of the developed method.

3

A novel approach to type-reduction and design of interval type-2 fuzzy logic systems

88%

Starczewski J. T. , Przybyszewski K. , Byrski A. , Szmidt E. , Napoli C.

|

tom Vol. 12, No. 3

197--206

EN

Fuzzy logic systems, unlike black-box models, are known as transparent artificial intelligence systems that have explainable rules of reasoning. Type 2 fuzzy systems extend the field of application to tasks that require the introduction of uncertainty in the rules, e.g. for handling corrupted data. Most practical implementations use interval type-2 sets and process interval membership grades. The key role in the design of type-2 interval fuzzy logic systems is played by the type-2 inference defuzzification method. In type-2 systems this generally takes place in two steps: type-reduction first, then standard defuzzification. The only precise type-reduction method is the iterative method known as Karnik-Mendel (KM) algorithm with its enhancement modifications. The known non-iterative methods deliver only an approximation of the boundaries of a type-reduced set and, in special cases, they diminish the profits that result from the use of type-2 fuzzy logic systems. In this paper, we propose a novel type-reduction method based on a smooth approximation of maximum/minimum, and we call this method a smooth type-reduction. Replacing the iterative KM algorithm by the smooth type-reduction, we obtain a structure of an adaptive interval type-2 fuzzy logic which is non-iterative and as close to an approximation of the KM algorithm as we like.

4

Combined YOLOv5 and HRNet for high accuracy 2D keypoint and human pose estimation

75%

Nguyen H.-C. , Nguyen T.-H. , Nowak J. , Byrski A. , Siwocha A. , Le V.-H.

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

tom Vol. 12, No. 4

281--298

EN

Two-dimensional human pose estimation has been widely applied in real-world applications such as sports analysis, medical fall detection, human-robot interaction, with many positive results obtained utilizing Convolutional Neural Networks (CNNs). Li et al. at CVPR 2020 proposed a study in which they achieved high accuracy in estimating 2D keypoints estimation/2D human pose estimation. However, the study performed estimation only on the cropped human image data. In this research, we propose a method for automatically detecting and estimating human poses in photos using a combination of YOLOv5 + CC (Contextual Constraints) and HRNet. Our approach inherits the speed of the YOLOv5 for detecting humans and the efficiency of the HRNet for estimating 2D keypoints/2D human pose on the images. We also performed human marking on the images by bounding boxes of the Human 3.6M dataset (Protocol #1) for human detection evaluation. Our approach obtained high detection results in the image and the processing time is 55 FPS on the Human 3.6M dataset (Protocol #1). The mean error distance is 5.14 pixels on the full size of the image (1000×1002). In particular, the average results of 2D human pose estimation/2D keypoints estimation are 94.8% of PCK and 99.2% of PDJ@0.4 (head joint). The results are available.

5

Microscopic simulation of pedestrian traffic in urban environment under epidemic conditions

75%

Paciorek M. , Poklewski-Koziełł D. , Racoń-Leja K. , Byrski A. , Gyurkovich M. , Turek W.

|

tom Vol. 69, nr 4

art. no. e137725

EN

The ongoing period of the pandemic makes everybody focused on the matters related to fighting this immense problem posed to the societies worldwide. The governments deal with the threat by publishing regulations which should allow to mitigate the pandemic, walking on thin ice as the decision makers do not always know how to properly respond to the threat in order to save people. Computer-based simulations of e.g. parts of the city or rural area should provide significant help, however, there are some requirements to fulfill. The simulation should be verifiable, supported by the urban research and it should be possible to run it in appropriate scale. Thus in this paper we present an interdisciplinary work of urban researchers and computer scientists, proposing a scalable, HPC-grade model of simulation, which was tested in a real scenario and may be further used to extend our knowledge about epidemic spread and the results of its counteracting methods. The paper shows the relevant state of the art, discusses the micro-scale simulation model, sketches out the elements of its implementation and provides tangible results gathered for a part of the city of Krakow, Poland.