A5103129777- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Metaheuristic Optimization Algorithms Research
- Fault Detection and Control Systems
- Advanced Clustering Algorithms Research
- Anomaly Detection Techniques and Applications
- Statistical and Computational Modeling
- Air Quality Monitoring and Forecasting
- Homotopy and Cohomology in Algebraic Topology
- Data Management and Algorithms
- Spectroscopy and Chemometric Analyses
- Synthesis and Biological Evaluation
- Advanced Multi-Objective Optimization Algorithms
- Synthesis and pharmacology of benzodiazepine derivatives
- Phenothiazines and Benzothiazines Synthesis and Activities
- Algebraic Geometry and Number Theory
- Data Stream Mining Techniques
- Evolutionary Algorithms and Applications
- Time Series Analysis and Forecasting
- Algebraic structures and combinatorial models
- Quinazolinone synthesis and applications
- Receptor Mechanisms and Signaling
- Machine Learning and Data Classification
- Control Systems and Identification
- Mechanical and Thermal Properties Analysis
AGH University of Krakow
2014-2024
Jagiellonian University
2022-2024
Systems Research Institute
2014-2023
Polish Academy of Sciences
2014-2023
University of Wrocław
2023
Instytut Nauk Geologicznych
2022
Keio University
2016
Cracow University of Technology
2004-2014
Institute of Organic Chemistry
2002-2013
Task of clustering, that is data division into homogeneous groups represents one the elementary problems contemporary mining. Cluster analysis can be approached through variety methods based on statistical inference or heuristic techniques. Recently algorithms employing novel meta-heuristics are special interest — as they effectively tackle problem under consideration which known to NP-hard. The paper studies application nature-inspired Flower Pollination Algorithm for clustering with...
In order to target behavioral and psychological symptoms of dementia (BPSD), we used molecular modeling-assisted design obtain novel multifunctional arylsulfonamide derivatives that potently antagonize 5-HT(6/7/2A) D2 receptors, without interacting with M1 receptors hERG channels. vitro studies confirmed their antagonism 5-HT(7/2A) weak interactions key antitargets (M1R hERG) associated side effects. Marked 5-HT6 receptor affinities were also observed, notably for...
In this paper, we propose the use of local sensitivity analysis (LSA) for structure simplification probabilistic neural network (PNN). Three algorithms are introduced. The first algorithm applies LSA to PNN input layer reduction by selecting significant features patterns. second utilizes remove redundant pattern neurons network. third combines proposed two and constitutes solution how they can work together. with a product kernel estimator is used, where each multiplicand computes...
In recent times, several new metaheuristic algorithms based on natural phenomena have been made available to researchers. One of these is that the Krill Herd Algorithm (KHA) procedure. It contains many interesting mechanisms. The purpose this article compare KHA optimization algorithm used for learning an artificial neural network (ANN), with other heuristic methods and more conventional procedures. proposed ANN training method has verified classification task. For benchmark examples drawn...
This study investigates the potential of hybrid metaheuristic algorithms to enhance training Probabilistic Neural Networks (PNNs) by leveraging complementary strengths multiple optimisation strategies. Traditional learning methods, such as gradient-based approaches, often struggle optimise high-dimensional and uncertain environments, while single-method metaheuristics may fail exploit solution space fully. To address these challenges, we propose constrained Hybrid Metaheuristic (cHM)...
Dividing a dataset into disjoint groups of homogeneous structure, known as data clustering, constitutes an important problem analysis.It can be solved with broad range methods employing statistical approaches or heuristic procedures.The latter often include mechanisms from nature they are to serve useful components effective optimizers.The paper investigates the possibility using novel nature-inspired technique -Grasshopper Optimization Algorithm (GOA) -to generate accurate clusterings.As...
Automated classification systems have allowed for the rapid development of exploratory data analysis. Such increase independence human intervention in obtaining analysis results, especially when inaccurate information is under consideration. The aim this paper to present a novel approach, neural networking, use classifying interval information. As presented, methodology generalization probabilistic network processing. simple structure algorithm makes it applicable research purposes....
The rapid growth of performance in the field neural networks has also increased their sizes. Pruning methods are getting more and attention order to overcome problem non-impactful parameters overgrowth neurons. In this article, application Global Sensitivity Analysis (GSA) demonstrates impact input variables on model’s output variables. GSA gives ability mark out least meaningful arguments build reduction algorithms these. Using several popular datasets, study shows how different levels...
This article focuses on a statistical analysis of the corona virus disease 2019 (COVID-19) data that appeared until November 31, 2020 in Poland. The studied database, expressed terms both population and air pollution (particulate) indicators, is provided mainly by Airly company, Central Statistical Office (GUS) Rogalski project. particular measured factors, which underwent standardization, were assessed for mutual dependency means Pearson correlation coefficient analysed linear regression....
Abstract The aim of this paper is to present a Complete Gradient Clustering Algorithm, its applicational aspects and properties, as well illustrate them with specific practical problems from the subject bioinformatics (the categorization grains for seed production), management design marketing support strategy mobile phone operator) engineering synthesis fuzzy controller). main property Algorithm that it does not require strict assumptions regarding desired number clusters, which allows...
Abstract In classical feedforward neural networks such as multilayer perceptron, radial basis function network, or counter‐propagation the neurons in input layer correspond to features of training patterns. The number these may be large, and their meaningfulness can various. Therefore, selection appropriate should regarded. aim this paper is present a complete step‐by‐step algorithm for determining significance particular probabilistic network (PNN). It based on sensitivity analysis...
Abstract A series of new long‐chain arylpiperazine (LCAP) derivatives with flexible and partly constrained alkyl linker were synthesized investigated in vitro as potential serotonin 5‐HT 1A 7 receptor ligands. The compounds prepared by a two‐step procedure using naphthalimide 2 H‐ 1,3‐benzoxazine‐2,4(3 H )‐dione imides, 1‐(2‐methoxyphenyl)piperazine ( o ‐OMe‐PhP) 1,2,3,4‐tetrahydroisoquinoline (THIQ) amine pharmacophores. Modifications the spacer structure included introduction penta‐...
Probabilistic neural network (PNN) has a sizable structure since it requires all training records in the activation of its hidden layer. This fact makes suffer from problem curse dimensionality. Therefore, an hypotheses can be easily formulated that order to manage large data classification tasks, is recommended minimise inner design. In this paper, we directly address issue: method for PNN's architecture reduction elaborated. It organised as follows. First, k-means clustering conducted and...
Particle swarm optimization constitutes currently one of the most important nature-inspired metaheuristics, used successfully for both combinatorial and continuous problems.Its popularity has stimulated emergence various variants swarm-inspired techniques, based in part on concept pairwise communication numerous members solving problem hand.This paper overviews some examples such namely Fully Informed Swarm Optimization (FIPSO), Firefly Algorithm (FA) Glowworm (GSO).It underlines...