Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 5
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The paper analyses the distorted data of an electronic nose in recognizing the gasoline bio-based additives. Different tools of data mining, such as the methods of data clustering, principal component analysis, wavelet transformation, support vector machine and random forest of decision trees are applied. A special stress is put on the robustness of signal processing systems to the noise distorting the registered sensor signals. A special denoising procedure based on application of discrete wavelet transformation has been proposed. This procedure enables to reduce the error rate of recognition in a significant way. The numerical results of experiments devoted to the recognition of different blends of gasoline have shown the superiority of support vector machine in a noisy environment of measurement.

Go to article

Authors and Affiliations

Stanisław Osowski
Krzysztof Siwek
Download PDF Download RIS Download Bibtex

Abstract

Measurements of pollutants scavenged from air masses over southern Svalbard in summer precipitation are presented. Rainfall was sampled in July and August 2002 at Calypsobyen, Bellsund. Specific conductivity (SpC) and pH were measured and ion concentrations were determined by ion chromatography. Ions of marine origin were subtracted, assuming that all chlorides were of marine origin. The FLEXTRA trajectory model was applied to discover the sources of air masses arriving at Svalbard and track the paths of pollutant transport. Average (v/w) rainfall pH was 4.94, mean SpC amounted to 34.8 µS cm-1. Total dissolved solids concentration (TDS) ranged from 12.6 to 67 mg L-1, with ions of marine origin (Cl-, Na+, Mg2+) prevailing. Rains with the highest percentage of marine salts occurred with winds from the East at above average velocities. Non-sea salt (nss) sulphate concentrations ranged from 0.5 µeq L-1 to 23 µeq L-1, (v/w) average was 17 µeq L-1. Nitrate concentrations ranged from 0 to 24 µeq L-1. The highest concentrations of nss-SO42- and NO3- were measured on 25 August, when the highest rainfall occurred (27 mm) and pH was the lowest (4.65). Rainfall at Calypsobyen deposited 194 kg km-2 of acidifying anions and 263 kg km-2 of base cations over the recording period. The polluted air masses were mostly from northern and central Europe. Rainfalls scavenging air masses formed over Greenland and Norwegian Seas displayed similar concentrations, being probably polluted by SOx and NOx from ship emissions.

Go to article

Authors and Affiliations

Wiesława Ewa Krawczyk
Stefan A. Bartoszewski
Krzysztof Siwek
Download PDF Download RIS Download Bibtex

Abstract

For brain tumour treatment plans, the diagnoses and predictions made by medical doctors and radiologists are dependent on medical imaging. Obtaining clinically meaningful information from various imaging modalities such as computerized tomography (CT), positron emission tomography (PET) and magnetic resonance (MR) scans are the core methods in software and advanced screening utilized by radiologists. In this paper, a universal and complex framework for two parts of the dose control process – tumours detection and tumours area segmentation from medical images is introduced. The framework formed the implementation of methods to detect glioma tumour from CT and PET scans. Two deep learning pre-trained models: VGG19 and VGG19-BN were investigated and utilized to fuse CT and PET examinations results. Mask R-CNN (region-based convolutional neural network) was used for tumour detection – output of the model is bounding box coordinates for each object in the image – tumour. U-Net was used to perform semantic segmentation – segment malignant cells and tumour area. Transfer learning technique was used to increase the accuracy of models while having a limited collection of the dataset. Data augmentation methods were applied to generate and increase the number of training samples. The implemented framework can be utilized for other use-cases that combine object detection and area segmentation from grayscale and RGB images, especially to shape computer-aided diagnosis (CADx) and computer-aided detection (CADe) systems in the healthcare industry to facilitate and assist doctors and medical care providers.
Go to article

Bibliography

  1.  Cancer Research UK Statistics from the 5th of March 2020. [Online]. https://www.cancerresearchuk.org/health-professional/cancer- statistics/statistics-by-cancer-type/brain-other-cns-and-intracranial-tumours/incidence#ref-
  2.  E. Kot, Z. Krawczyk, K. Siwek, and P.S. Czwarnowski, “U-Net and Active Contour Methods for Brain Tumour Segmentation and Visualization,” 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, United Kingdom, 2020, pp. 1‒7, doi: 10.1109/ IJCNN48605.2020.9207572.
  3.  J. Kim, J. Hong, H. Park, “Prospects of deep learning for medical imaging,” Precis. Future. Med. 2(2), 37–52 (2018), doi: 10.23838/ pfm.2018.00030.
  4.  E. Kot, Z. Krawczyk, and K. Siwek, “Brain Tumour Detection and Segmentation Using Deep Learning Methods,” in Computational Problems of Electrical Engineering, 2020.
  5.  A.F. Tamimi and M. Juweid, “Epidemiology and Outcome of Glioblastoma,” in: Glioblastoma [Online]. Brisbane (AU): Codon Publications, 2017, doi: 10.15586/codon.glioblastoma.2017.ch8.
  6.  A. Krizhevsky, I. Sutskever, and G.E. Hinton, “ImageNet classification with deep convolutional neural networks,” in: Advances in Neural Information Processing Systems, 2012, p. 1097‒1105.
  7.  M.A. Al-masni, et al., “Detection and classification of the breast abnormalities in digital mammograms via regional Convolutional Neural Network,” 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Seogwipo, 2017, pp. 1230‒1233, doi: 10.1109/EMBC.2017.8037053.
  8.  P. Yin, R. Yuan, Y. Cheng, and Q. Wu, “Deep Guidance Network for Biomedical Image Segmentation,” IEEE Access 8, 116106‒116116 (2020), doi: 10.1109/ACCESS.2020.3002835.
  9.  R. Sindhu, G. Jose, S. Shibon, and V. Varun, “Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans”, Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 105751I, 2018, doi: 10.1117/12.2293699.
  10.  R. Ezhilarasi and P. Varalakshmi, “Tumor Detection in the Brain using Faster R-CNN,” 2018 2nd International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), Palladam, India, 2018, pp. 388‒392, doi: 10.1109/I-SMAC.2018.8653705.
  11.  S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-timeobject detection with region proposal networks,” in Advances in neuralinformation processing systems, 2015, pp. 91–99.
  12.  S. Liu, H. Zheng, Y. Feng, and W. Li, “Prostate cancer diagnosis using deeplearning with 3D multiparametric MRI,” in Proceedings of Medical Imaging 2017: Computer-Aided Diagnosis, vol. 10134, Bellingham: International Society for Optics and Photonics (SPIE), 2017. p. 1013428.
  13.  M. Gurbină, M. Lascu, and D. Lascu, “Tumor Detection and Classification of MRI Brain Image using Different Wavelet Transforms and Support Vector Machines,” in 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), Budapest, Hungary, 2019, pp. 505‒508, doi: 10.1109/TSP.2019.8769040.
  14.  H. Dong, G. Yang, F. Liu, Y. Mo, and Y. Guo, “Automatic brain tumor detection and segmentation using U-net based fully convolutional networks,” in: Medical image understanding and analysis, pp. 506‒517, eds. Valdes Hernandez M, Gonzalez-Castro V, Cham: Springer, 2017.
  15.  O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, vol 9351, doi: 10.1007/978-3-319- 24574-4_28.
  16.  K. Hu, C. Liu, X. Yu, J. Zhang, Y. He, and H. Zhu, “A 2.5D Cancer Segmentation for MRI Images Based on U-Net,” in 2018 5th International Conference on Information Science and Control Engineering (ICISCE), Zhengzhou, 2018, pp. 6‒10, doi: 10.1109/ICISCE.2018.00011.
  17.  H.N.T.K. Kaldera, S.R. Gunasekara, and M.B. Dissanayake, “Brain tumor Classification and Segmentation using Faster R-CNN,” Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, 2019, pp. 1‒6, doi: 10.1109/ ICASET.2019.8714263.
  18.  B. Stasiak, P. Tarasiuk, I. Michalska, and A. Tomczyk, “Application of convolutional neural networks with anatomical knowledge for brain MRI analysis in MS patients”, Bull. Pol. Acad. Sci. Tech. Sci. 66(6), 857–868 (2018), doi: 10.24425/bpas.2018.125933.
  19.  L. Hui, X. Wu, and J. Kittler, “Infrared and Visible Image Fusion Using a Deep Learning Framework,” 24th International Conference on Pattern Recognition (ICPR), Beijing, 2018, pp. 2705‒2710, doi: 10.1109/ICPR.2018.8546006.
  20.  K. Simonyan and A. Zisserman, “Very deep convolutional networks for largescale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  21.  M. Simon, E. Rodner, and J. Denzler, “ImageNet pre-trained models with batch normalization,” arXiv preprint arXiv:1612.01452, 2016.
  22.  VGG19-BN model implementation. [Online]. https://pytorch.org/vision/stable/_modules/torchvision/models/vgg.html
  23.  D. Jha, M.A. Riegler, D. Johansen, P. Halvorsen, and H.D. Johansen, “DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation,” 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), Rochester, MN, USA, 2020, pp. 558‒564, doi: 10.1109/CBMS49503.2020.00111.
  24.  Jupyter notebook with fusion code. [Online]. https://github.com/ekote/computer-vision-for-biomedical-images-processing/blob/master/ papers/polish_acad_of_scienc_2020_2021/fusion_PET_CT_2020.ipynb
  25.  E. Geremia et al., “Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images”, NeuroImage 57(2), 378‒390 (2011).
  26.  D. Anithadevi and K. Perumal, “A hybrid approach based segmentation technique for brain tumor in MRI Images,” Signal Image Process.: Int. J. 7(1), 21‒30 (2016), doi: 10.5121/sipij.2016.7103.
  27.  S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” arXiv preprint arXiv:1502.03167.
  28.  S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137‒1149, (2017), doi: 10.1109/TPAMI.2016.2577031.
  29.  T-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. Lawrence Zitnick, “Microsoft COCO: common objects incontext” in Computer Vision – ECCV 2014, 2014, p. 740–755.
  30.  Original Mask R-CNN model. [Online]. https://github.com/matterport/Mask_RCNN/releases/tag/v2.0
  31.  Mask R-CNN model. [Online]. https://github.com/ekote/computer-vision-for-biomedical-images-processing/releases/tag/1.0, doi: 10.5281/ zenodo.3986798.
  32.  T. Les, T. Markiewicz, S. Osowski, and M. Jesiotr, “Automatic reconstruction of overlapped cells in breast cancer FISH images,” Expert Syst. Appl. 137, 335‒342 (2019), doi: 10.1016/j.eswa.2019.05.031.
  33.  J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation”, Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2015, pp. 3431‒3440.
  34.  The U-Net architecture adjusted to 64£64 input image size. [Online]. http://bit.ly/unet64x64
Go to article

Authors and Affiliations

Estera Kot
1
Zuzanna Krawczyk
1
Krzysztof Siwek
1
Leszek Królicki
2
Piotr Czwarnowski
2

  1. Warsaw University of Technology, Faculty of Electrical Engineering, Pl. Politechniki 1, 00-661 Warsaw, Poland
  2. Medical University of Warsaw, Nuclear Medicine Department, ul. Banacha 1A, 02-097 Warsaw, Poland
Download PDF Download RIS Download Bibtex

Abstract

Spitsbergen glaciers react rapidly to changes in the polar environment, which is expressed in differences in extent of their fronts and surface geometry. The Scott Glacier, which is situated in the NW part of Wedel Jarlsberg Land, is an example of the glacier that has undergone almost continuous recession since the Little Ice Age, interrupted by surges. The variations in recession are characterised based on multiannual data with particularly consideration of the period 1990–2005 and the season 2005/2006. Acceleration of front recession and lowering the surface was found only within the tongue up to a height of about 220 m a.s.l. Whereas, in the area situated in the zone of rock steps and above in the ablation zone, the change of glacier surface ablation (Dh) has been recorded compared to the mean annual recession for the period 1990–2005. Moreover, for the upper firn field, the positive surface ablation (DhS7 = +0.19 m) was observed. As the result of progressive reduction of the Scott Glacier mass, with the participation of other factors (bedrock relief among others), new surfaces of roche moutonnée are uncovering particularly in the tongue zone.

Go to article

Authors and Affiliations

Piotr Zagórski
Krzysztof Siwek
Andrzej Gluza
Stefan A. Bartoszewski

This page uses 'cookies'. Learn more