ul. Z. Janiszewskiego 7, 50-372 Wrocław
building C-16, room P 2.2
phone +48 71 320 7625

Office hours

Wednesday 14.00-15.00
Wednesday (even week) 17.00-19.00
Thursday 13.00-15.00

Research fields

• Machine learning; neural networks; deep neural networks; artificial intelligence; digital image processing; artificial intelligence in audio; objective evaluation of audio quality.

Recent papers

2017

• Bazan M., Janiczek T., Halawa K., Wykrzykowski A., Łabuda P., A new method to estimate dimensions of vehicle using a single camera. Archives of Transport System Telematics. 2017, vol. 10, nr 3, s. 3-7.

2016

• Halawa K., Method enabling the first hidden layer of multilayer perceptrons to make division of space with various hypercurves. W: Artificial intelligence and soft computing: 15th International Conference, ICAISC 2016, Zakopane, Poland, June 12-16, 2016: proceedings. Pt. 1 / Leszek Rutkowski [i in.] (eds.). [Cham]: Springer, cop. 2016. s. 104-113.
  (Lecture Notes in Computer Science. Lecture Notes in Artificial Intelligence, ISSN 0302-9743; vol. 9692)
• Halawa K., Bazan M., Ciskowski P., Janiczek T., Kozaczewski P., Rusiecki A., Road traffic predictions across major city intersections using multilayer perceptrons and data from multiple intersections located in various places. IET Intelligent Transport Systems. 2016, vol. 10, nr 7, s. 469-475.

2014

• Halawa K., A new multilayer perceptron initialisation method with selection of weights on the basis of the function variability. W: Artificial intelligence and soft computing: 13th International Conference, ICAISC 2014, Zakopane, Poland, June 1-5, 2014: proceedings. Pt. 1 / Leszek Rutkowski [i in.] (eds.). Cham [i in.]: Springer, cop. 2014. s. 47-58.
  (Lecture Notes in Computer Science. Lecture Notes in Artificial Intelligence, ISSN 0302-9743; vol. 8467)

2011

• Halawa K., A method to improve the performance of multilayer perceptron by utilizing various activation functions in the last hidden layer and the least squares method. Neural Processing Letters. 2011, vol. 34, nr 3, s. 293-303.

Papers in DONA database

Selected publications
1	Artykuł 2026 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Deep learning-based automatic segmentation and classification for cervical cancer detection using an improved U-Net and ensemble methods. Scientific Reports. 2026, s. 1-22. ISSN: 2045-2322 Zasoby:DOIURL
2	Referat konferencyjny 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Eyerus Zewdu Wubineh, Classification of brain tumor using MobileNet and CBAM-based deep learning approach from MRI images. W: 2025 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), Bahir Dar, Ethiopia, November 21-23, 2025 / eds. Esubalew Alemneh, Ethiopia Nigussie, Fisseha Mekuria. Danvers, MA : IEEE, cop. 2025. s. 72-77. ISBN: 979-8-3315-9184-7; 979-8-3315-9185-4 Zasoby:DOIURL
3	Artykuł 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa SE-DeepLabV3+: cervical cell segmentation and classification using a novel SE-based DeepLabV3+ and ensemble method. IEEE Access. 2025, vol. 13, s. 116430-116441. ISSN: 2169-3536 Zasoby:DOIURLSFX
4	Referat konferencyjny 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa ViT-SE_Res: a hybrid vision transformer and ResNet50V2 with squeeze-and-excitation block for cervical cell classification. W: Computational Science – ICCS 2025 Workshops : 25th International Conference, Singapore, Singapore, July 7-9, 2025 : Proceedings. Pt. 2 / eds. Maciej Paszynski, Amanda S. Barnard, Yongjie Jessica Zhang. Cham : Springer Nature Switzerland AG, cop. 2025. s. 11-23. ISBN: 978-3-031-97556-1; 978-3-031-97557-8 Zasoby:DOIURLSFX
5	Artykuł 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa SPP-SegNet and SE-DenseNet201: a dual-model approach for cervical cell segmentation and classification. Cancers. 2025, vol. 17, nr 13, art. 2177, s. 1-13. ISSN: 2072-6694 Zasoby:DOIURLSFX
6	Artykuł 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa A systematic review of effective data augmentation in cervical cancer detection. International Journal of Electronics and Telecommunications. 2025, vol. 71, nr 2, s. 369-377. ISSN: 2300-1933 Zasoby:DOIURLSFX
7	Referat konferencyjny 2025 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Enhancing cervical cell classification with DenseNet201 and spatial attention mechanism. W: Advances in Dependable Systems and Networks : Proceedings of the Twentieth International Conference on Dependability of Computer Systems DepCoS-RELCOMEX, June 30 – July 3, 2025, Brunów, Poland / eds. Wojciech Zamojski [i in.]. Cham : Springer Nature Switzerland AG, cop. 2025. s. 229-236. ISBN: 978-3-031-92733-1; 978-3-031-92734-8 Zasoby:DOIURLSFX
8	Referat konferencyjny 2024 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Cervical cell segmentation and classification using U-Net and hybrid VGG19-AlexNet architecture. W: 2024 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), Bahir Dar, Ethiopia, November 18-20, 2024 / eds. Esubalew Alemneh, Fisseha Mekuria, Ethiopia Nigussie. Danvers, MA : IEEE, cop. 2024. s. 37-42. ISBN: 979-8-3315-2780-8; 979-8-3315-2779-2 Zasoby:DOIURL
9	Artykuł 2024 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Classification of cervical cells from the Pap smear image using the RES_DCGAN data augmentation and ResNet50V2 with self-attention architecture. Neural Computing & Applications. 2024, vol. 36, s. 21801-21815. ISSN: 0941-0643; 1433-3058 Zasoby:DOIURLSFX
10	Artykuł 2024 Betelhem Wubineh Andrzej Rusiecki Krzysztof Halawa Segmentation and classification techniques for pap smear images in detecting cervical cancer: a systematic review. IEEE Access. 2024, vol. 12, s. 118195-118213. ISSN: 2169-3536 Zasoby:DOIURLSFX

All employee publications