<?xml version="1.0" encoding="UTF-8"?>
<xml><records><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Jakub Szyguła</style></author><author><style face="normal" font="default" size="100%">Tadeusz Czachórski</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The self-similar markovian sources</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2020</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Applied Sciences</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/app10113727</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">10</style></volume><issue><style face="normal" font="default" size="100%">11</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Dariusz Marek</style></author><author><style face="normal" font="default" size="100%">Jakub Szyguła</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Long-Range Dependent Traffic Classification with Convolutional Neural Networks Based on Hurst Exponent Analysis</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style face="normal" font="default" size="100%">2020</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">Entropy</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.3390/e22101159</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">22</style></volume><issue><style face="normal" font="default" size="100%">10</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Miltiadis Siavvas</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Erol Gelenbe</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The Random Neural Network as a Bonding Model for Software Vulnerability Prediction</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2021</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Modelling, Analysis, and Simulation of Computer and Telecommunication Systems</style></secondary-title><tertiary-title><style face="normal" font="default" size="100%">Computer Communication Networks and Telecommunications, LNCS</style></tertiary-title><urls><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-030-68110-4_7</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1007/978-3-030-68110-4_7</style></electronic-resource-num><pages><style face="normal" font="default" size="100%">102-116</style></pages><volume><style face="normal" font="default" size="100%">12527</style></volume><publisher><style face="normal" font="default" size="100%">Springer International Publishing</style></publisher><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Erol Gelenbe</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Random Neural Network for Lightweight Attack Detection in the IoT</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2021</style></year></dates><secondary-title><style face="normal" font="default" size="100%">MASCOTS 2020: Modelling, Analysis, and Simulation of Computer and Telecommunication Systems</style></secondary-title><tertiary-title><style face="normal" font="default" size="100%">Computer Communication Networks and Telecommunications, LNCS</style></tertiary-title><urls><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-030-68110-4_5</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1007/978-3-030-68110-4_5</style></electronic-resource-num><pages><style face="normal" font="default" size="100%">79-91</style></pages><volume><style face="normal" font="default" size="100%">12527</style></volume><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Cyber-attack detection has become a basic component of all information processing systems, and once an attack is detected it may be possible to block or mitigate its effects. This paper addresses the use of a learning recurrent Random Neural Network (RNN) to build a lightweight detector for certain types of Botnet attacks on IoT systems. Its low computational cost based on a small 12-neuron recurrent architecture makes it particularly attractive for edge devices. The RNN can be trained off-line using a fast simplified gradient descent algorithm, and we show that it can lead to high detection rates of the order of 96%, with false alarm rates of a few percent.&lt;/p&gt;&#13;
</style></abstract><publisher><style face="normal" font="default" size="100%">Springer International Publishing</style></publisher><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Paweł Boryszko</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Miltiadis Siavvas</style></author><author><style face="normal" font="default" size="100%">Erol Gelenbe</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Efficient Feature Selection for Static Analysis Vulnerability Prediction</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2021</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Sensors</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.mdpi.com/1424-8220/21/4/1133</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/s21041133</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">21 (4)</style></volume><issue><style face="normal" font="default" size="100%">Special Issue: Security and Privacy in Software Based Critical Contexts</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Łukasz Sobczak</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">LIDAR Point Cloud generation for SLAM algorithm evaluation</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2021</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Sensors</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.mdpi.com/1424-8220/21/10/3313</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/s21103313</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">21 (10)</style></volume><issue><style face="normal" font="default" size="100%">Special Issue: Advance in Sensors and Sensing Systems for Driving and Transportation: Part B</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jakub Szyguła</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Dariusz Marek</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Szymon Mendla</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Supervised learning of Neural Networks for Active Queue Management in  the Internet</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2021</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Sensors</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.mdpi.com/1424-8220/21/15/4979</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/s21154979</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">21(15)</style></volume><issue><style face="normal" font="default" size="100%">Special Issue "Mathematical Modelling and Analysis in Sensors Networks"</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Charalampos Marantos</style></author><author><style face="normal" font="default" size="100%">Miltiadis Siavvas</style></author><author><style face="normal" font="default" size="100%">Dimitrios Tsoukalas</style></author><author><style face="normal" font="default" size="100%">Christos Lamprakos</style></author><author><style face="normal" font="default" size="100%">Lazaros Papadopoulos</style></author><author><style face="normal" font="default" size="100%">Paweł Boryszko</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Apostolos Ampatzoglou</style></author><author><style face="normal" font="default" size="100%">Alexander Chatzigeorgiou</style></author><author><style face="normal" font="default" size="100%">Erol Gelenbe</style></author><author><style face="normal" font="default" size="100%">Dionysios Kehagias</style></author><author><style face="normal" font="default" size="100%">Dimitrios Soudris</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">SDK4ED: One-click platform for Energy-aware, Maintainable and Dependable Applications</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year><pub-dates><date><style face="normal" font="default" size="100%">03/2022</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">25th Design, Automation and Test in Europe Conference</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.23919/DATE54114.2022.9774586</style></electronic-resource-num><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;Developing&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;modern&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;secure&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;and&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;low-energy&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;applica&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;tions in a short time imposes new challenges and creates the need &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;designing&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;new&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;&#160;&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;software&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;tools&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;to&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;assist&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;developers&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;in&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;all&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;phases &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;application&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;development.&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;The&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;design&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;such&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;tools&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;cannot &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;be&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;considered&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;a&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;trivial&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;task,&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;as&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;they&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;should&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;be&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;able&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;to&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;provide&lt;/span&gt; &lt;span style="font-family:sans-serif; font-size:14.944px"&gt;optimization&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;multiple&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;quality&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;requirements.&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;In&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;this&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;paper,&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;we &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;introduce&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;the&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;SDK4ED&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;platform,&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;which&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;incorporates&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;advanced&lt;/span&gt; &lt;span style="font-family:sans-serif; font-size:14.944px"&gt;methods and tools for measuring and optimizing maintainability, &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;dependability&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;and&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;energy.&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;The&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;presented&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;solution&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;offers&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;a&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;com&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;plete&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;tool-flow&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;for&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;providing&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;indicators&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;and&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;optimization&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;meth&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;ods&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;with&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;emphasis&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;on&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;embedded&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;software.&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;Effective&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;forecasting&lt;/span&gt; &lt;span style="font-family:sans-serif; font-size:14.944px"&gt;models&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;and&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;decision-making&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;solutions&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;are&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;also&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;implemented&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;to &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;improve&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;the&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;quality&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;the&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;software,&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;respecting&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;the&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;constraints&lt;/span&gt; &lt;span style="font-family:sans-serif; font-size:14.944px"&gt;imposed&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;on&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;maintenance&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;standards,&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;energy&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;consumption&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;limits &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;and&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;security&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;vulnerabilities.&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;The&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;use&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;of&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;the&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;SDK4ED&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;platform&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;is&lt;/span&gt; &lt;span style="font-family:sans-serif; font-size:14.944px"&gt;demonstrated&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;in&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;a&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;healthcare&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;embedded&lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt; &lt;/span&gt;&lt;span style="font-family:sans-serif; font-size:14.944px"&gt;application.&lt;/span&gt;&lt;/p&gt;&#13;
</style></abstract><pub-location><style face="normal" font="default" size="100%">Belgium</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Sławomir Nowak</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Jakub Duda</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Cost-Effective Filtering of Unreliable Proximity Detection Results Based on BLE RSSI and IMU Readings Using Smartphones</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Scientific Reports</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.nature.com/articles/s41598-022-06201-y</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">10.1038/s41598-022-06201-y</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">12</style></volume><issue><style face="normal" font="default" size="100%">1</style></issue><section><style face="normal" font="default" size="100%">2440</style></section><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Dariusz Marek</style></author><author><style face="normal" font="default" size="100%">Jakub Szyguła</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Marta Szczygieł</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Adaptive Hurst-Sensitive Active Queue Management</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Entropy</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.mdpi.com/1099-4300/24/3/418</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/e24030418</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">24</style></volume><issue><style face="normal" font="default" size="100%">3</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">NAM: What Does a Neural Network See?</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">International Joint Conference on Neural Networks (IJCNN 2022), IEEE WCCI 2022</style></secondary-title><urls><style face="normal" font="default" size="100%">https://ieeexplore.ieee.org/abstract/document/9892442</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1109/IJCNN55064.2022.9892442</style></electronic-resource-num><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Padova, 18-23 July, 2022</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Dariusz Marek</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Jakub Szyguła</style></author><author><style face="normal" font="default" size="100%">Tadeusz Czachórski</style></author><author><style face="normal" font="default" size="100%">Jerzy Klamka</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Approximation Models for the Evaluation of TCP/AQM Networks</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Bulletin of the Polish Academy of Sciences, Technical Sciences (BPASTS)</style></secondary-title><urls><style face="normal" font="default" size="100%">https://journals.pan.pl/dlibra/publication/141986/edition/123961/content</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.24425/bpasts.2022.141986</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">70</style></volume><issue><style face="normal" font="default" size="100%">4</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Software Vulnerabilities in TensorFlow-Based Deep Learning Applications</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year><pub-dates><date><style face="normal" font="default" size="100%">10/2022</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%"/></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S0167404822003406?via%3Dihub</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.cose.2022.102948</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">124</style></volume><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Łukasz Sobczak</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Finding the best hardware configuration for 2D SLAM in indoor environments via simulation based on Google Cartographer</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Scientific Reports</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.nature.com/articles/s41598-022-22938-y</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1038/s41598-022-22938-y</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">12</style></volume><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Łukasz Sobczak</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Building a real-time testing platform for unmanned ground vehicles with UDP Bridge</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Sensors</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.mdpi.com/1424-8220/22/21/8493</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.3390/s22218493</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">22</style></volume><issue><style face="normal" font="default" size="100%">21</style></issue><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Łukasz Sobczak</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Adam Domański</style></author><author><style face="normal" font="default" size="100%">Rafał Cupek</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Real-time testing of vision-based systems for AGVs with ArUco markers</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2022</style></year></dates><secondary-title><style face="normal" font="default" size="100%">IEEE International Conference on Big Data</style></secondary-title><urls><style face="normal" font="default" size="100%">https://ieeexplore.ieee.org/document/10020817</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/BigData55660.2022.10020817</style></electronic-resource-num><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Osaka, 17-20 December, 2022</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Global Entropy Pooling Layer for Convolutional Neural Networks</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Neurocomputing</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S0925231223007385</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.neucom.2023.126615</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">555</style></volume><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Recycling of Generic ImageNet-trained Models for Smart-city Applications</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year></dates><secondary-title><style face="normal" font="default" size="100%">The 10th IEEE International Conference on Data Science and Advanced Analytics (DSAA)</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/DSAA60987.2023.10302563</style></electronic-resource-num><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Thessaloniki, Greece</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Nur Kelesoglu</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">HierAct: a Hierarchical Model for Human Activity Recognition in Game-Like Educational Applications</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year><pub-dates><date><style face="normal" font="default" size="100%">01/2024</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">2023 IEEE International Conference on Big Data</style></secondary-title><urls><style face="normal" font="default" size="100%">https://ieeexplore.ieee.org/document/10386919</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/BigData59044.2023.10386919</style></electronic-resource-num><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Constantly evolving landscape of modern education makes the integration of technology crucial to enable more interactive and immersive learning experiences. One of the key problems in this domain is Human Activity Recognition (HAR), which uses standard smartphone sensors to understand and recognize user movements. While HAR exhibits high potential in this area, its persistent challenge is to differentiating between similar activities, whose occurrences can often lead to misclassification and reduced quality of applications. To tackle this problem, we employ specialized classifiers and use them in a hierarchical manner instead of using monolith multi-class models. We propose HierAct - a Hierarchical model that solves the multi-class human activity recognition problem. We also release a new HAR dataset - EduAct - (https://github.com/iitis/HierAct-Dataset) focused on activities that could be used to create game-like educational applications.Our results show that the performance of the proposed model is substantially better than other state-of-the-art machine learning models. Our work shows the potential of hierarchical classifiers in HAR applications for education, by offering educators and students a more accurate, reliable, and engaging interactive experience.&lt;/p&gt;&#13;
</style></abstract><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Sorrento, Italy </style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Marzena Halama</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Robust category recognition based on deep templates for educational mobile applications</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year><pub-dates><date><style face="normal" font="default" size="100%">01/2024</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">2023 IEEE International Conference on Big Data</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/BigData59044.2023.10386544</style></electronic-resource-num><publisher><style face="normal" font="default" size="100%">IEEE International Conference on Big Data</style></publisher><pub-location><style face="normal" font="default" size="100%">Sorrento, Italy</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">NetSat: Network Saturation Adversarial Attack</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year></dates><secondary-title><style face="normal" font="default" size="100%">IEEE International Conference on Big Data (IEEE BigData 2023)</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/BigData59044.2023.10386834</style></electronic-resource-num><pub-location><style face="normal" font="default" size="100%">Sorrento, Italy</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Łukasz Sobczak</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Marzena Halama</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Visual examination of relations between known classes for deep neural network classifiers.</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2023</style></year><pub-dates><date><style face="normal" font="default" size="100%">01/2024</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">2023 IEEE International Conference on Big Data</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/BigData59044.2023.10386987</style></electronic-resource-num><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Sorrento, Italy</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Miltiadis Siavvas</style></author><author><style face="normal" font="default" size="100%">Dimitrios Tsoukalas</style></author><author><style face="normal" font="default" size="100%">Charalambos Marantos</style></author><author><style face="normal" font="default" size="100%">Lazaros Papadopoulos</style></author><author><style face="normal" font="default" size="100%">Christos Lamprakos</style></author><author><style face="normal" font="default" size="100%">Oliviu Matei</style></author><author><style face="normal" font="default" size="100%">Christos Strydis</style></author><author><style face="normal" font="default" size="100%">Muhammad Siddiqi</style></author><author><style face="normal" font="default" size="100%">Philippe Chrobocinski</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Paris Avgeriou</style></author><author><style face="normal" font="default" size="100%">Apostolos Ampatzoglou</style></author><author><style face="normal" font="default" size="100%">Dimitrios Soudris</style></author><author><style face="normal" font="default" size="100%">Alexander Chatzigeorgiou</style></author><author><style face="normal" font="default" size="100%">Erol Gelenbe</style></author><author><style face="normal" font="default" size="100%">Dionysios Kehagias</style></author><author><style face="normal" font="default" size="100%">Dimitrios Tzovaras</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">SDK4ED: a platform for building energy efficient, dependable, and maintainable embedded software</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Automated Software Engineering</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">10.1007/s10515-024-00450-z</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Gustavo Machado-Guillen</style></author><author><style face="normal" font="default" size="100%">Jorge Cruz-Duarte</style></author><author><style face="normal" font="default" size="100%">Santiago Conant-Pablos</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Harnessing Machine Learning for Reliable Weather Forecasting: Meteorological Impact on Sustainable Energy in Monterrey</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year></dates><secondary-title><style face="normal" font="default" size="100%">IEEE Congress on Evolutionary Computation</style></secondary-title><urls><style face="normal" font="default" size="100%">https://ieeexplore.ieee.org/document/10611993</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">10.1109/CEC60901.2024.10611993</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Sebastian Pokuciński</style></author><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Dariusz Mrozek</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Finding the Perfect Cut: Selection of the Best Cutting Point in Equirectangular Panoramas for Object Detection</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year></dates><secondary-title><style face="normal" font="default" size="100%"/></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S1877050924024724</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.procs.2024.09.432</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Extracting coarse-grained classifiers from large Convolutional Neural Networks</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year><pub-dates><date><style face="normal" font="default" size="100%">12/2024</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">Engineering Applications of Artificial Intelligence</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S0952197624015355</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.engappai.2024.109377</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">138</style></volume><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Jerzy Klamka</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Evaluating Convolutional Neural Networks via measuring similarity of their first-layer filters and Gabor filters</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year></dates><secondary-title><style face="normal" font="default" size="100%">32nd International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1109/MASCOTS64422.2024.10786556</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Similarity-driven adversarial testing of neural networks</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2024</style></year><pub-dates><date><style face="normal" font="default" size="100%">12/2024</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">Knowledge-Based Systems</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S0950705124012553</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.knosys.2024.112621</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">305</style></volume><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">What is the doggest dog? Examination of typicality perception in ImageNet-trained networks</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2025</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Neural Networks</style></secondary-title><electronic-resource-num><style face="normal" font="default" size="100%">https://doi.org/10.1016/j.neunet.2025.107425</style></electronic-resource-num><volume><style face="normal" font="default" size="100%">188</style></volume><section><style face="normal" font="default" size="100%">107425</style></section><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Michał Romaszewski</style></author><author><style face="normal" font="default" size="100%">Mateusz Żarski</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities</style></title></titles><keywords/><dates/><secondary-title><style face="normal" font="default" size="100%">arXiv preprint</style></secondary-title><urls><style face="normal" font="default" size="100%">arXiv:2504.09956</style></urls><electronic-resource-num><style face="normal" font="default" size="100%"> https://doi.org/10.48550/arXiv.2504.09956</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Mateusz Żarski</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Beyond Accuracy: Uncovering the Role of Similarity Perception and its Alignment with Semantics in Supervised Learning</style></title></titles><keywords/><dates/><secondary-title><style face="normal" font="default" size="100%">arXiv preprint</style></secondary-title><urls><style face="normal" font="default" size="100%">https://arxiv.org/abs/2505.21338</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">https://arxiv.org/abs/2505.21338</style></electronic-resource-num><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Similarity manifests in various forms, including semantic similarity that is particularly important, serving as an approximation of human object categorization based on e.g. shared functionalities and evolutionary traits. It also offers practical advantages in computational modeling via lexical structures such as WordNet with constant and interpretable similarity. As in the domain of deep vision, there is still not enough focus on the phenomena regarding the similarity perception emergence. We introduce Deep Similarity Inspector (DSI) -- a systematic framework to inspect how deep vision networks develop their similarity perception and its alignment with semantic similarity. Our experiments show that both Convolutional Neural Networks' (CNNs) and Vision Transformers' (ViTs) develop a rich similarity perception during training with 3 phases (initial similarity surge, refinement, stabilization), with clear differences between CNNs and ViTs. Besides the gradual mistakes elimination, the mistakes refinement phenomenon can be observed.&lt;/p&gt;&#13;
</style></abstract><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>13</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">How CNNs and ViTs perceive similarities between categories</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2025</style></year></dates><secondary-title><style face="normal" font="default" size="100%">European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)</style></secondary-title><urls><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-032-06078-5_2</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">10.1007/978-3-032-06078-5_2</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Sebastian Pokuciński</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">SPHEREA: Synthetic dataset generation for equirectangular panoramas of home environments</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2025</style></year><pub-dates><date><style face="normal" font="default" size="100%">2025</style></date></pub-dates></dates><secondary-title><style face="normal" font="default" size="100%">Knowledge-Based Systems</style></secondary-title><urls><style face="normal" font="default" size="100%">https://www.sciencedirect.com/science/article/pii/S0950705125017897?via%3Dihub</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">doi.org/10.1016/j.knosys.2025.114751</style></electronic-resource-num><language><style face="normal" font="default" size="100%">eng</style></language></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Jorge Cruz-Duarte</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Target Selection for Adversarial Evaluation of Vision Models Using Language Models</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">IEEE International Joint Conference on Neural Networks</style></secondary-title></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Jorge Cruz-Duarte</style></author><author><style face="normal" font="default" size="100%">Mateusz Korpyś</style></author><author><style face="normal" font="default" size="100%">Andrzej Kołodziej</style></author><author><style face="normal" font="default" size="100%">Anna Gancarczyk</style></author><author><style face="normal" font="default" size="100%">El-Ghazali Talbi</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Feature- and Similarity-Based Explainability of Experimental Materials Data via Black-Box Hyperparameter Optimization</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Parallel Problem Solving from Nature</style></secondary-title><urls><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-032-36226-1_11</style></urls><electronic-resource-num><style face="normal" font="default" size="100%">doi.org/10.1007/978-3-032-36226-1_11</style></electronic-resource-num></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Mateusz Żarski</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Inspecting Training Dynamics of Similarity Development in Supervised Vision Networks </style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases</style></secondary-title></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Sebastian Pokuciński</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases</style></secondary-title></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Obinna Nwadiuto</style></author><author><style face="normal" font="default" size="100%">Zlatka Stoeva</style></author><author><style face="normal" font="default" size="100%">Joanna Domańska</style></author><author><style face="normal" font="default" size="100%">Fideline Tchuenbou-Magaia</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Lightweight Time-Series Representation for Battery State of Health Estimation from Graphene Sensor Data</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases</style></secondary-title></record><record><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Katarzyna Filus</style></author><author><style face="normal" font="default" size="100%">Kamil Faber</style></author><author><style face="normal" font="default" size="100%">Roberto Corizzo</style></author><author><style face="normal" font="default" size="100%">Christopher Kanan</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning</style></title></titles><keywords/><dates><year><style face="normal" font="default" size="100%">2026</style></year></dates><secondary-title><style face="normal" font="default" size="100%">Neural Information Processing Systems (NeurIPS)</style></secondary-title></record></records></xml>
