Istanbul Technical University

Signal Processing for Computational Intelligence Group

SP4CING Research Outcomes in 2020

For many of us, the year 2020 was arguably one of the hardest one in our lives. Still, it was a productive year for the Signal Processing for Computational Intelligence Research Group members. Our group members defended one PhD thesis and six master of science theses in the past year. We have one patent application granted, twelve papers published and/or accepted for publication in peer-reviewed journals and conference proceedings. Three group members received national awards and international recognition. Our research continues to receive attention all around the world. At SP4CING, we strive to produce more and better research outcomes in terms of quality and quantity in 2021. We are indebted to Istanbul Technical University and all organizations that fund our research. Wish you all a healthy and happy new year.

PhD Theses


  1. PhD Thesis: Sparse Matrix Decomposition and Low Rank Based Techniques for Anomaly Detection in Hyperspectral Images - Dr. Fatma Küçük

MS Theses


  1. Noise Removal of Thermal Images Using Deep Learning Approach - Ahmet Çapcı
  2. Bulanık Su Altı Görüntülerinde Derin Öğrenme Tabanlı Balık Tespiti - Tansel Akgül
  3. Continual Learning with Sparse Progressive Neural Networks - Esra Ergün
  4. Deep Learning Based Segmentation Pipeline for Label-free Phase-contrast Microscopy Images - Aydın Ayanzadeh
  5. Drone and Bird Classification Using Convolutional Neural Networks - Eda Karala
  6. Geomagnetic Signal Analysis Based Classification of Earthquake Magnitudes - Shabnam D. Dilmaghani

Patent


  1. Ç. Dinçkal, B.U. Töreyin, S. Küçükali, "Short-term Wind Speed and Turbulence Intensity Estimation Method with Online Adaptive Learning Method." Türk Patent Enstitüsü, Patent No. 2017 08743. 21 Oct. 2020

Papers


  1. Myelin Detection in Fluorescence Microscopy Images Using Machine Learning. Journal Paper (Published): Yetiş, S. Ç., Çapar, A., Ekinci, D. A., Ayten, U. E., Kerman, B. E., & Töreyin, B. U. (2020). Myelin detection in fluorescence microscopy images using machine learning. Journal of Neuroscience Methods, 346, 108946.
  2. Online Paper: Çapar A, Çimen Yetiş S, Aladağ Z et al. A multi-spectral myelin annotation tool for machine learning based myelin quantification [version 1; peer review: awaiting peer review]. F1000Research 2020, 9:1492 (https://doi.org/10.12688/f1000research.27139.1)
  3. Journal Paper (in Press): S. Tuna, B. U. Töreyin, M. Demiralp, J. Ren, H. Zhao and S. Marshall, "Iterative Enhanced Multivariance Products Representation for Effective Compression of Hyperspectral Images," in IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2020.3031016.

National Conferences


  1. Kabakçı KA, Töreyin BU, Okatan M. "Estimation of Noise Standard Deviation Using an Otsu-Based Approach in Extracellular Neural Recordings." 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 2020, in press
  2. Akgul T, Calık N, Töreyin BU. " Deep Learning-Based Fish Detection in Turbid Underwater Images." 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 2020, in press
  3. Ayanzadeh A, Özuysal ÖY, Okvur DP, Önal S , Ünay D, Töreyin BU, " Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images" 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 2020, in press
  4. Ergün E, Töreyin BU, "Continual Learning with Sparse Progressive Neural Networks" 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 2020, in press
  5. Keser RK, Nallbani I, Calık N, Ayanzadeh A, Töreyin BU. "Graph Embedding For Link Prediction Using Residual Variational Graph Autoencoders." 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 2020, in press
  6. B.N.Wiysobunri, H.S.Erden, B.U.Töreyin, "A Deep Learning Approach to Fault Detection and Classification in Data Centers", Ulusal Yüksek Başarımlı Hesaplama Konferansı, Ankara, 2020.
  7. E.Kayan, T.Kavuşan, S.Önal, D.P.Okvur, Ö.Yalçın-Özuysal, B.U.Töreyin, D.Ünay, "Faz-Kontrast Mikroskopi Görüntü Serilerinden Hücre Hareketliligi Analizi Ön-Çalısması," TIP-Tekno 2020, Antalya.
  8. B.Mayalı, O.Şaylığ, Ö.Yalçın-Özuysal, D.P.Okvur, B.U.Töreyin, D.Ünay, "Yara İyilȩsmesi Mikroskopi Görüntü Serilerinin Otomatik Analizi - Bir Ön-Çalı̧sma," TIP-Tekno 2020, Antalya.

International Conferences

  1. S.Aslan, U.Güdükbay, B.U.Töreyin, A.E.Çetin, "Deep Convolutional Generative Adversarial Networks For Flame Detection In Video," in Proc. of the 12th International Conference on Computational Collective Intelligence - ICCCI-2020, Vietnam, Nov. 2020.
  2. I. Turkmen, G. Dursun, U. Ozkaya, A. Capar, B. Muezinoglu, B.U Töreyin, " Can Artificial Intelligence Help Cervical Cytopathologist To Detect High-grade Squamous Intraepithelial Lesions On The Atrophic Background?", ESPD - Digital Pathology, Porto, Portugal, 2020.

Awards and Recognitions

  1. Dr. Abdulkerim Çapar's Argenit won the first prize of “National-International Fundings (Ulusal-Uluslararası Destekler)” in “BEETECH Technology Prizes” organized by ITU ARI Teknokent.
  2. Prof. Töreyin is listed among the top 2% scientists in his primary sub-field, namely signal processing (classified under networking and telecommunications), based on citation counts in 2019 in the Scopus database and other related metrics proposed in the paper (http://dx.doi.org/10.17632/btchxktzyw.2) . Based on the scope of his papers, his secondary sub-field is determined to be artificial intelligence and image processing.
  3. Beltus Nkwawir Wiysobunri's project entitled as "An Ensemble Deep Learning System for the Automatic Detection of Covid-19 in X-Ray Images" is ranked first in the Science Category of "2020 International Student Academy Awards" organized by the Presidency for Turks Abroad and Related Communities of Turkey. Click here to read the technical description of the project