User Tools

Site Tools


research_group:start

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
research_group:start [2020/05/06 20:51]
mpiekarski [Anomaly detection with the use of pre-trained CNN architectures]
research_group:start [2021/11/04 18:01] (current)
abrodzicki
Line 6: Line 6:
  
 ==== Deep neural networks in early detection of melanomas ==== ==== Deep neural networks in early detection of melanomas ====
-FIXME 
  
 ====  Computer-aided dermatopathology ==== ====  Computer-aided dermatopathology ====
Line 47: Line 46:
 **Research goal:**\\ **Research goal:**\\
 To detect anomalies in multivariate diagnostic signals of the synchrotron control system by pre-trained CNN architectures. To detect anomalies in multivariate diagnostic signals of the synchrotron control system by pre-trained CNN architectures.
 +
 +[[https://​synchrotron.uj.edu.pl|SOLARIS]] National Synchrotron Radiation Centre is a research facility that provides high quality synchrotron light. To control such a complex system it is necessary to monitor signals from various devices and subsystems. Anomaly detection prevents from financial loss, unplanned downtimes and in extreme cases cause damage. As artificial intelligence techniques including machine learning and deep neural networks have become state-of-the-art solutions for anomaly detection tasks which are one of the most challenging in data analysis, our team conducts research on the use of them for anomaly detection in multivariate diagnostic signals.
  
 The research topics include: The research topics include:
Line 56: Line 57:
   * M. Piekarski   * M. Piekarski
   * J. Jaworek-Korjakowska   * J. Jaworek-Korjakowska
-==== Detection and analysis of patterns ​(@asia: muszę dopracować ) ==== +==== Detection and analysis of patterns ====
-FIXME+
  
-==== Cell detection ​- Andrzej... ​====+==== Cell detection ====
  
-FIXME+To improve speed and quality of testing new drugs against Clostridium difficile infection, we developed an algorithm for automatic bacteria cytotoxicity classification. It was based on two kinds of fluorescence images - DAPI and GFP. We experimented with many different methods from classical image processing and machine learning algorithms to convolutional neural networks. This research was was conducted in cooperation with Stanford University.
  
 +The research topics include:
 +  * fluorescence images
 +  * image processing
 +  * sharing information from different images
 +  * convolutional neural networks
  
 +Team members involved:
 +  * J. Jaworek-Korjakowska
 +  * A. Brodzicki
  
 +==== Bacteria response clustering ====
 +
 +Newly opened project, in cooperation with Stanford University. The main idea is to analyse bacteria reaction in response to different serums.
 +
 +The research topics include:
 +  * data clustering
 +  * bacteria response analysis
 +
 +Team members involved:
 +  * J. Jaworek-Korjakowska
 +  * A. Brodzicki
 +
 +==== Reconstructing images'​ missing areas with generative models ====
 +
 +The research topics include:
 +  * reconstruction
 +  * generative learning
 +  * GANs
 +  * autoencoders
 +
 +Team members involved:
 +  * J. Jaworek-Korjakowska
 +  * D. Kucharski
 +
 +==== Vehicle interior image segmentation ====
 +
 +The research topics include:
 +  * dataset preparation
 +  * image classification
 +  * image segmentation
 +
 +Team members involved:
 +  * J. Jaworek-Korjakowska
 +  * A. Kostuch
  
 ---- ----
research_group/start.1588791095.txt.gz · Last modified: 2020/08/25 15:49 (external edit)