1. Grelier, Erwan and Mitteau, Rapha ël and Moncada, Victor (2022) Deep learning and image processing for the automated analysis of thermal events on the first wall and divertor of fusion reactors. Plasma Physics and Controlled Fusion 64(10): 104010 https://doi.org/10.1088/1361-6587/ac9015, IOP Full Text PDF:C\:\\Users\\VG270101\\Zotero\\storage\\45D7YAKG\\Grelier et al. - 2022 - Deep learning and image processing for the automat.pdf:application/pdf, Publisher: IOP Publishing, September, A multi-stage process that detects, tracks and classifies thermal events automatically using thermal imaging of the inside of fusion reactors is presented. The process relies on the Cascade R-CNN algorithm for the detection and classification and on the SORT algorithm for the tracking. The process is trained using a dataset of 325 thermal events distributed in seven classes, manually annotated from 20 infrared movies of the inside of the WEST tokamak. This dataset is created using user-friendly annotation tools, based on simple thresholding. The performance of the process is evaluated using modified indicators that emphasize the importance of the detection of the hottest zones of the hot spots. The modified mean average precision on a test dataset establishes at 27%., https://dx.doi.org/10.1088/1361-6587/ac9015, 0741-3335
2. Gabor, Hidy The {Tversky} loss function and its modifications for medical image segmentation. https://math-projects.elte.hu/media/works/187/report/tversky_loss_and_variants.pdf
3. Salehi, Seyed Sadegh Mohseni and Erdogmus, Deniz and Gholipour, Ali. Tversky loss function for image segmentation using {3D} fully convolutional deep networks. Number: arXiv:1706.05721 arXiv:1706.05721 [cs]. Computer Science - Computer Vision and Pattern Recognition, 2017, June, arXiv, Fully convolutional deep neural networks carry out excellent potential for fast and accurate image segmentation. One of the main challenges in training these networks is data imbalance, which is particularly problematic in medical imaging applications such as lesion segmentation where the number of lesion voxels is often much lower than the number of non-lesion voxels. Training with unbalanced data can lead to predictions that are severely biased towards high precision but low recall (sensitivity), which is undesired especially in medical applications where false negatives are much less tolerable than false positives. Several methods have been proposed to deal with this problem including balanced sampling, two step training, sample re-weighting, and similarity loss functions. In this paper, we propose a generalized loss function based on the Tversky index to address the issue of data imbalance and achieve much better trade-off between precision and recall in training 3D fully convolutional deep neural networks. Experimental results in multiple sclerosis lesion segmentation on magnetic resonance images show improved F2 score, Dice coefficient, and the area under the precision-recall curve in test data. Based on these results we suggest Tversky loss function as a generalized framework to effectively train deep neural networks., 10.48550/arXiv.1706.05721
4. Courtois, X. and Aumeunier, MH. and Balorin, C. and Migozzi, J. B. and Houry, M. and Blanckaert, K. and Moudden, Y. and Pocheau, C. and Saille, A. and Hugot, E. and Marcos, M. and Vives, S. (2019) Full coverage infrared thermography diagnostic for {WEST} machine protection. Fusion Engineering and Design 146: 2015--2020 https://doi.org/10.1016/j.fusengdes.2019.03.090, ScienceDirect Snapshot:C\:\\Users\\VG270101\\Zotero\\storage\\XB32SEE5\\S0920379619304120.html:text/html;Texte int égral:C\:\\Users\\VG270101\\Zotero\\storage\\E6C4FI98\\Courtois et al. - 2019 - Full coverage infrared thermography diagnostic for.pdf:application/pdf, Infrared thermography, Plasma facing component, Safe operation, Temperature monitoring, September, The WEST platform aims at testing ITER like W divertor targets in an integrated tokamak environment. To operate long plasma discharges, IR thermography is required to monitor the main plasma facing components by means of real time surface temperature measurements, while providing essential data for various physics studies. To monitor the new divertor targets, the WEST IR thermography protection system has been deeply renewed, to match the new tokamak configuration. It consists of 7 endoscopes located in upper ports viewing the whole lower divertor and the 5 heating devices. Electronic devices and computers allow data storage of ≈3 Gb/s IR images and real time video frames processing at 50 Hz rate, to ensure the protection of the main plasma facing components during plasma discharges by a feedback control of the power injected by the heating systems. Each endoscope provides 2 views covering 2 divertor sectors of 30 ° (toroidally) and 1 view of a heating antenna. Each optical line is composed of a tight entrance window followed by a head objective which forms an image transported through the endoscope by a series of 4 optical relays and mirrors, up to a camera objective. Finally, 12 IR cameras specially developed for WEST environment capture the thermographic data, at the wavelength of 3.9 μm, with a 640 × 512 pixels frame size. The paper describes the design constraints and diagnostic technologies: optics, mechanics, electronics, hard & software, cameras. Tvhe laboratory characterization procedures (Modulation Transfer Function, slit response, calibration), and the measurement performance results are given (spatial resolution, temperature threshold). Finally, first results obtained during experimental campaigns in WEST are presented., https://www.sciencedirect.com/science/article/pii/S0920379619304120, 0920-3796, {SI}:{SOFT}-30
5. Mitteau, R. and Belafdil, C. and Balorin, C. and Courtois, X. and Moncada, V. and Nouailletas, R. and Santraine, B. (2021) {WEST} operation with real time feed back control based on wall component temperature toward machine protection in a steady state tungsten environment. Fusion Engineering and Design 165: 112223 https://doi.org/10.1016/j.fusengdes.2020.112223, ScienceDirect Snapshot:C\:\\Users\\VG270101\\Zotero\\storage\\3G6DX9WK\\S0920379620307717.html:text/html;Version soumise:C\:\\Users\\VG270101\\Zotero\\storage\\5FL7856I\\Mitteau et al. - 2021 - WEST operation with real time feed back control ba.pdf:application/pdf, Infrared diagnostic, Plasma control system, Plasma facing components, Wall hot spot management, Wall monitoring system, April, A real time Wall Monitoring System (WMS) is used on the WEST tokamak during the C4 experimental campaign. The WMS uses the wall surface temperatures from 6 fields of view of the Infrared viewing system. It extracts the raw digital data from selected areas, converts it to temperatures using the calibration and write it on the shared memory network being used by the Plasma Control System (PCS). The PCS feeds back to actuators, namely the injected power from 5 antennae's of the lower hybrid and ion cyclotron resonance radiofrequency (RF) heating systems. WMS activates feed back control 63 times during C4, which is 14 % of the plasma discharges. It activates mainly as the result of a direct RF loss to the upper divertor pipes. The feedback control maintains the wall temperature within the operation envelope during 97 % of the occurrences, while enabling plasma discharge continuation. The false positive rate establishes at 0.2 %. WMS significantly facilitated the operation path to high power operation during C4, by managing the technical risks to critical wall components., https://www.sciencedirect.com/science/article/pii/S0920379620307717, 0920-3796