Differences

This shows you the differences between two versions of the page.

--- aira:start [2025/03/18 12:50] – [Schedule Spring 2025] mzk
+++ aira:start [2025/04/17 08:34] (current) – [Schedule Spring 2025] mzk
@@ Line 15: / Line 15: @@
 ===== Schedule Spring 2025 =====
-  * **[PHD TRACK] 2025.03.13**: Maciej Szelążek,  PhD Candidate @ Jagiellonian University, [[#section20250313|Semantic Data Mining methods for decision support in smart manufacturing.]]
+  * **[PHD TRACK] 2025.04.24**: Natalia Wojak-Strzelecka,  PhD Candidate @ Jagiellonian University, [[#section20250424|Enhancing concept drift detection, explanation and adaptation to changes in industrial data streams.]]
-    * Meeting link: [[offline mode]]
+    * Meeting link: [[https://teams.microsoft.com/l/meetup-join/19%3aJF1L0935A7eV6s8R9brG5MMYONrqy4XmxPSYLeRMCGM1%40thread.tacv2/1744878780977?context=%7b%22Tid%22%3a%22eb0e26eb-bfbe-47d2-9e90-ebd2426dbceb%22%2c%22Oid%22%3a%22a39bd3b1-7b43-47ab-b5ec-29d9ab0ccbb2%22%7d|MS Teams]]
     * Recording:  TDA
     * Presentation slides:  TDA
+  * **[PHD TRACK] 2025.04.03**: Dmytro Polishchuk,  PhD Candidate @ Jagiellonian University, [[#section20250403|Automated GitHub Repository Quality Evaluation: A Metrics-Based Approach.]]
+    * Meeting link: [[https://teams.microsoft.com/l/meetup-join/19%3aJF1L0935A7eV6s8R9brG5MMYONrqy4XmxPSYLeRMCGM1%40thread.tacv2/1743415239609?context=%7b%22Tid%22%3a%22eb0e26eb-bfbe-47d2-9e90-ebd2426dbceb%22%2c%22Oid%22%3a%22a39bd3b1-7b43-47ab-b5ec-29d9ab0ccbb2%22%7d|MS Teams]]
+    * Recording:  [[https://ujchmura.sharepoint.com/:v:/t/Section_495645_1/EWqf_EYlyY9PiBDp4s6kJDsBQo_W7RnsB9aP1WagKm0MRw?e=ROAopX|View]]
+    * Presentation slides:  {{:aira:slides-dmytro-polishchuk-2025-04-03.pdf|Download}}
+  * **[PHD TRACK] 2025.03.27**: Jakub Jakubowski,  PhD Candidate @ AGH University, [[#section20250327|Dry run thesis defense IN POLISH - Explainable Predictive Maintenance in Steel Rolling.]]
+    * Meeting link: [[|The talk will be held stationary in room C-2-10]]
+    * Recording:  - (Dry run thesis defense)
+    * Presentation slides: {{:aira:slides-jakub-jakubowski-20250327.pdf|Download}}
+  * **[PHD TRACK] 2025.03.13**: Maciej Szelążek,  PhD Candidate @ Jagiellonian University, [[#section20250313|Semantic Data Mining methods for decision support in smart manufacturing.]]
+    * Meeting link: [[|offline mode]]
+    * Recording:  - (Dry run thesis defense)
+    * Presentation slides: {{:aira:slides-maciej-szelążek-20250313.pdf|Download}}
   * **[RESEARCH TRACK] 2025.03.06**: Renata Włoch,  Professor @ University of Warsaw, [[#section20250306|Does fear of automation motivate workers to reskill?]]
@@ Line 394: / Line 408: @@
 ===== Presentation details =====
+==== 2025-04-24 ====
+<WRAP column 15%>
+{{ :aira:natalia-wojak-strzelecka-foto.jpg?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Natalia Wojak-Strzelecka,  PhD Candidate @ Jagiellonian University
+**Title**: Automated GitHub Repository Quality Evaluation: A Metrics-Based Approach.
+**Abstract**:
+In this seminar, we will explore three complementary approaches to handling evolving data in industrial environments. We'll discuss methods for detecting and adapting to domain shifts in data streams, distinguishing between real system failures and normal process changes, and using explainable AI to better understand and interpret concept drift. The presented work combines domain adaptation, drift detection, and XAI to improve the robustness and transparency of machine learning models in real-time settings like manufacturing and healthcare.
+**Biogram**:
+Natalia has received Bachelor's (2020) and Master's (2022) degrees in Mathematics from Silesia Univerity of Technology, Faculty of Applied Mathematics. Her career path is deeply rooted in the industry, she started as a data scientist working on vibration signals for predictive maintenance applications and continuing as a modelling specialist at ArcelorMittal, where she develops and implements models for production optimization and image processing. Currently, as a PhD candidate, she is working on advanced domain adaptation techniques for industrial data stream applications and explainable anomaly detection.
+</WRAP>
+<WRAP clear></WRAP>
+==== 2025-04-03 ====
+<WRAP column 15%>
+{{ :aira:dmytro-polishchuk-foto.png?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Dmytro Polishchuk,  PhD Candidate @ Jagiellonian University
+**Title**: Automated GitHub Repository Quality Evaluation: A Metrics-Based Approach.
+**Abstract**:
+This research aims to develop an automated system for evaluating the quality of GitHub repositories using a pre-established quality model. The system will assess repositories based on a variety of quality metrics, such as the commit history and its associated metadata (e.g., size, date, description), code coverage, pull request review time, issue resolution time, number of open issues, code churn, and code complexity. Additional metrics may also be considered, potentially including those defined by standards like ISO/IEC 25010:2011.
+**Biogram**:
+Software engineer with a background in the telecom domain, specializing in network management systems and Software Defined Networking (SDN). Experienced in performance engineering, including byte code instrumentation, and has worked across various technologies, including IoT. Previously contributed to major companies like Ericsson, Cisco Systems, and Playtech.
+</WRAP>
+<WRAP clear></WRAP>
+==== 2025-03-27 ====
+<WRAP column 15%>
+{{ :aira:jakub-jakubowski-foto.jpg?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Jakub Jakubowski,  PhD Candidate @ AGH University
+**Title**: Dry run thesis defense IN POLISH - Explainable Predictive Maintenance in Steel Rolling.
+**Abstract**:
+In recent years, there has been a growing interest in Industry 4.0, which seeks to integrate digital technologies into manufacturing processes. One key area that stands to benefit from these advancements is maintenance of the equipment. Artificial Intelligence (AI) can play a crucial role in developing Predictive Maintenance (PdM) solutions, which aim to reduce downtime, lower maintenance costs, and enhance safety in manufacturing environments. These technologies are particularly valuable in steel manufacturing, a resource-intensive and economically critical industry. However, a significant challenge in deploying AI-based PdM solutions in production is the lack of transparency, as many AI methods function as "black boxes." Without a clear understanding of the AI’s decision-making process, operators and engineers may struggle to take appropriate corrective actions. The research conducted by the presenter focused on the development and implementation of Explainable Artificial Intelligence (XAI) techniques in the steel rolling process, a critical step in steel production. This presentation summarizes the PhD thesis, which addresses the discussed problems.
+**Biogram**:
+Jakub Jakubowski earned his Bachelor's degree in Energy Engineering from AGH University of Science and Technology in 2016, followed by a Master's degree in 2017 from the Faculty of Fuels and Energy. Since 2018, he has been working at ArcelorMittal, the world's largest steel producer, as a modeling specialist and data scientist. His responsibilities include developing and implementing mathematical models to optimize manufacturing processes. Additionally, he assists engineers in analyzing large-scale industrial data and developing business intelligence tools. In 2020, he completed postgraduate studies in Data Science at AGH UST's Faculty of Computer Science, Electronics, and Telecommunications. That same year, he became a PhD candidate at AGH UST, participating in the Implementation Doctorate Programme, which integrates academic research with industry work. His PhD thesis has been completed and is currently under review. His primary research interest is the application of AI techniques in industrial settings, particularly in predictive maintenance solutions.
+</WRAP>
+<WRAP clear></WRAP>
+==== 2025-03-13 ====
+<WRAP column 15%>
+{{ :aira:maciej-szelazek.jpg?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Maciej Szelążek,  PhD Candidate @ Jagiellonian University
+**Title**: Semantic Data Mining methods for decision support in smart manufacturing.
+**Abstract**:
+This thesis focuses on integrating Machine Learning (ML) and Explainable Artificial Intelligence (XAI) techniques in a suitable way for their effective use in the decision–making process in the industrial Quality Management (QM) field. Continuous improvement in product and process quality is essential for manufacturers to stay competitive, and ML is increasingly being used for tasks like production planning or advanced control of production line devices. However, the complexity of ML models often makes their results difficult for non–expert users to interpret, limiting their practical applications. To overcome this challenge, we introduces Semantic Data Mining (SDM) concept that refers, in this thesis, to utilisation of ML models along with explainability methods in industrial quality control tasks. We considered SDM approach to detect patterns and extracting inferences from data that are both meaningful and interpretable by end users, providing easy to understand and act upon insights. This ensures that ML–generated results can be effectively used in decision–making processes.
+The thesis explores three main research challenges: integrating XAI insights into QM systems, developing visualization methods that fuse ML outputs with existing quality control tools, and applying SDM to enhance decision–making in industrial contexts. By proposing a new SDM component for QM, the research aims to improve the usability and impact of ML models in smart manufacturing. The study also focuses on ensuring that these new approaches can be seamlessly integrated with current industry standards and practices, making them applicable in a wide range of industrial settings. Through the development of these methods, the research contributes to the advancement of smart manufacturing, enabling more accurate and actionable quality control decisions. Presented thesis consists o fa series of publications that explore various aspects of the SDM approach for industrial quality control. Collectively, they offer a comprehensive analysis of the QM field and advance both the theoretical understanding and practical aspects of incorporating ML models to facilitate decision–making for smart manufacturing.
+**Biogram**:
+Maciej Szelążek is a member of the GEIST research team led by Prof. Gregory J. Nalepa (Jagiellonian University). Conducting research in the areas of machine learning, modeling, statistics and Semantic Data Mining (SDM) methods. International research collaboration in projects related to predictive maintenance, quality optimization, and state-of-the-art methods for unsupervised data evaluation using explainable AI (XAI).
+He worked as a data analyst in the Statistical Process Control (SPC) Office of Arcelor Mittal Poland.
+He participated in the creation and development of an analytical system, as well as multidimensional big data analysis related to bottleneck finding, logistics, cost optimization and process variability reduction.
+In the role of Data Scientist at Comarch Sp. z o.o., he carried out a project related to predicting customer behavior to increase the effectiveness of marketing campaigns. Responsibilities included the design, execution and implementation in a production environment of a procedure based on a machine learning model.
+</WRAP>
+<WRAP clear></WRAP>
 ==== 2025-03-06 ====