-
1دورية أكاديمية
المؤلفون: Haberfehlner, Helga, van de Ven, Shankara S., van der Burg, Sven A., Huber, Florian, Georgievska, Sonja, Aleo, Ignazio, Harlaar, Jaap, Bonouvrié, Laura A., van der Krogt, Marjolein M., Buizer, Annemieke I.
المصدر: Haberfehlner , H , van de Ven , S S , van der Burg , S A , Huber , F , Georgievska , S , Aleo , I , Harlaar , J , Bonouvrié , L A , van der Krogt , M M & Buizer , A I 2023 , ' Towards automated video-based assessment of dystonia in dyskinetic cerebral palsy : A novel approach using markerless motion tracking and machine learning ' , Frontiers in Robotics and AI , vol. 10 , 1108114 . https://doi.org/10.3389/frobt.2023.1108114Test
الوصف: Introduction: Video-based clinical rating plays an important role in assessing dystonia and monitoring the effect of treatment in dyskinetic cerebral palsy (CP). However, evaluation by clinicians is time-consuming, and the quality of rating is dependent on experience. The aim of the current study is to provide a proof-of-concept for a machine learning approach to automatically assess scoring of dystonia using 2D stick figures extracted from videos. Model performance was compared to human performance. Methods: A total of 187 video sequences of 34 individuals with dyskinetic CP (8–23 years, all non-ambulatory) were filmed at rest during lying and supported sitting. Videos were scored by three raters according to the Dyskinesia Impairment Scale (DIS) for arm and leg dystonia (normalized scores ranging from 0–1). Coordinates in pixels of the left and right wrist, elbow, shoulder, hip, knee and ankle were extracted using DeepLabCut, an open source toolbox that builds on a pose estimation algorithm. Within a subset, tracking accuracy was assessed for a pretrained human model and for models trained with an increasing number of manually labeled frames. The mean absolute error (MAE) between DeepLabCut’s prediction of the position of body points and manual labels was calculated. Subsequently, movement and position features were calculated from extracted body point coordinates. These features were fed into a Random Forest Regressor to train a model to predict the clinical scores. The model performance trained with data from one rater evaluated by MAEs (model-rater) was compared to inter-rater accuracy. Results: A tracking accuracy of 4.5 pixels (approximately 1.5 cm) could be achieved by adding 15–20 manually labeled frames per video. The MAEs for the trained models ranged from 0.21 ± 0.15 for arm dystonia to 0.14 ± 0.10 for leg dystonia (normalized DIS scores). The inter-rater MAEs were 0.21 ± 0.22 and 0.16 ± 0.20, respectively. Conclusion: This proof-of-concept study shows the potential of using stick figures extracted ...
الإتاحة: https://doi.org/10.3389/frobt.2023.1108114Test
https://research.vumc.nl/en/publications/4a782403-c47e-402c-9b41-32e5f647eb09Test
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85150366436&origin=inwardTest
https://www.ncbi.nlm.nih.gov/pubmed/36936408Test -
2دورية أكاديمية
المؤلفون: Shan, Xu, Steele-Dunne, Susan, Huber, Manuel, Hahn, Sebastian, Wagner, Wolfgang, Bonan, Bertrand, Albergel, Clement, Calvet, Jean-Christophe, Ku, Ou, Georgievska, Sonja
المصدر: Remote Sensing of Environment ; volume 279, page 113116 ; ISSN 0034-4257
مصطلحات موضوعية: Computers in Earth Sciences, Geology, Soil Science
الإتاحة: https://doi.org/10.1016/j.rse.2022.113116Test
https://api.elsevier.com/content/article/PII:S0034425722002309?httpAccept=text/xmlTest
https://api.elsevier.com/content/article/PII:S0034425722002309?httpAccept=text/plainTest -
3مؤتمر
المؤلفون: Santuari, Luca, Georgievska, Sonja, Kuzniar, Arnold, Shneider, Carl, Mehrem, Sarah, Schaefers, Tilman, Kloosterman, Wigard, de Ridder, Jeroen
مصطلحات موضوعية: structural variant detection, deep learning, somatic variant, whole genome sequencing, cancer mutations
الوصف: Poster presented at the Dutch Bioinformatics & Systems Biology Conference, BioSB 2020, on October 27th-28th, 2020. ; This work was supported by the Netherlands eScience Center (Grant Number: 027016G03) and was carried out on the Dutch national e-infrastructure with the support of SURF Foundation.
العلاقة: https://zenodo.org/record/4593061Test; https://doi.org/10.5281/zenodo.4593061Test; oai:zenodo.org:4593061
الإتاحة: https://doi.org/10.5281/zenodo.4593061Test
https://doi.org/10.5281/zenodo.1254880Test
https://zenodo.org/record/4593061Test -
4تقرير
المؤلفون: Georgievska, Sonja, Andova, Suzana
المصدر: EPTCS 28, 2010, pp. 99-113
مصطلحات موضوعية: Computer Science - Logic in Computer Science
الوصف: We define a testing equivalence in the spirit of De Nicola and Hennessy for reactive probabilistic processes, i.e. for processes where the internal nondeterminism is due to random behaviour. We characterize the testing equivalence in terms of ready-traces. From the characterization it follows that the equivalence is insensitive to the exact moment in time in which an internal probabilistic choice occurs, which is inherent from the original testing equivalence of De Nicola and Hennessy. We also show decidability of the testing equivalence for finite systems for which the complete model may not be known.
الوصول الحر: http://arxiv.org/abs/1006.5100Test
-
5تقرير
المؤلفون: Georgievska, Sonja, Andova, Suzana
مصطلحات موضوعية: Computer Science - Logic in Computer Science
الوصف: A central paradigm behind process semantics based on observability and testing is that the exact moment of occurring of an internal nondeterministic choice is unobservable. It is natural, therefore, for this property to hold when the internal choice is quantified with probabilities. However, ever since probabilities have been introduced in process semantics, it has been a challenge to preserve the unobservability of the random choice, while not violating the other laws of process theory and probability theory. This paper addresses this problem. It proposes two semantics for processes where the internal nondeterminism has been quantified with probabilities. The first one is based on the notion of testing, i.e. interaction between the process and its environment. The second one, the probabilistic ready trace semantics, is based on the notion of observability. Both are shown to coincide. They are also preserved under the standard operators.
Comment: 24 pagesالوصول الحر: http://arxiv.org/abs/0907.1540Test
-
6دورية أكاديمية
المؤلفون: Sundararajan, Kalaivani, Georgievska, Sonja, te Lindert, Bart H.W., Gehrman, Philip R., Ramautar, Jennifer, Mazzotti, Diego R., Sabia, Séverine, Weedon, Michael N., van Someren, Eus J.W., Ridder, Lars, Wang, Jian, van Hees, Vincent T.
المصدر: Sundararajan , K , Georgievska , S , te Lindert , B H W , Gehrman , P R , Ramautar , J , Mazzotti , D R , Sabia , S , Weedon , M N , van Someren , E J W , Ridder , L , Wang , J & van Hees , V T 2021 , ' Sleep classification from wrist-worn accelerometer data using random forests ' , Scientific Reports , vol. 11 , no. 1 , 24 . https://doi.org/10.1038/s41598-020-79217-xTest
الوصف: Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning (F1-score > 93.31 %), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour (r =. 60). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data.
الإتاحة: https://doi.org/10.1038/s41598-020-79217-xTest
https://research.vumc.nl/en/publications/040b1208-baf1-4d7f-8a07-e045fb3a72ceTest
http://www.scopus.com/inward/record.url?scp=85098993077&partnerID=8YFLogxKTest -
7دورية أكاديمية
المؤلفون: Renaud, Nicolas, Geng, Cunliang, Georgievska, Sonja, Ambrosetti, Francesco, Ridder, Lars, Marzella, Dario F., Réau, Manon F., Bonvin, Alexandre M. J. J., Xue, Li C.
المساهمون: Netherlands eScience Center, SURF Open Lab “Machine learning enhanced HPC applications” grant, Radboud Universitair Medisch Centrum, EC | Horizon 2020 Framework Programme
المصدر: Nature Communications ; volume 12, issue 1 ; ISSN 2041-1723
مصطلحات موضوعية: General Physics and Astronomy, General Biochemistry, Genetics and Molecular Biology, General Chemistry, Multidisciplinary
الوصف: Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression. We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive with, or outperforms, state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.
الإتاحة: https://doi.org/10.1038/s41467-021-27396-0Test
https://www.nature.com/articles/s41467-021-27396-0.pdfTest
https://www.nature.com/articles/s41467-021-27396-0Test -
8مؤتمر
المؤلفون: David, Sina, Georgievska, Sonja, Geng, Cunliang, Liu, Yang, Punt, Michiel
المصدر: David , S , Georgievska , S , Geng , C , Liu , Y & Punt , M 2023 , ' Using Deep learning to personalize stroke rehabilitation ' , International Society of Biomechanics , Fukuoka , Japan , 30/07/23 - 3/08/23 .
وصف الملف: application/pdf
-
9مؤتمر
المؤلفون: Santuari, Luca, Georgievska, Sonja, Shneider, Carl, Kuzniar, Arnold, Schaefers, Tilman, Kloosterman, Wigard, de Ridder, Jeroen
مصطلحات موضوعية: structural variant detection, deep learning, somatic variant, whole genome sequencing, cancer mutations
الوصف: Poster presented at the Dutch Bioinformatics & Systems Biology Conference, BioSB 2019, in Lunteren, the Netherlands, on April 2nd-3rd, 2019. ; This work was supported by the Netherlands eScience Center (Grant Number: 027016G03) and was carried out on the Dutch national e-infrastructure with the support of SURF Foundation.
العلاقة: https://zenodo.org/record/4593020Test; https://doi.org/10.5281/zenodo.4593020Test; oai:zenodo.org:4593020
الإتاحة: https://doi.org/10.5281/zenodo.4593020Test
https://doi.org/10.5281/zenodo.1254880Test
https://zenodo.org/record/4593020Test -
10مؤتمر
المؤلفون: Santuari, Luca, Georgievska, Sonja, Shneider, Carl, Kuzniar, Arnold, Schaefers, Tilman, Kloosterman, Wigard, de Ridder, Jeroen
مصطلحات موضوعية: structural variant detection, deep learning, somatic variant, whole genome sequencing, cancer mutations
الوصف: Poster presented at the Dutch Bioinformatics & Systems Biology Conference, BioSB 2018, in Lunteren, the Netherlands, on May 15th and 16th, 2018.
العلاقة: https://zenodo.org/record/1254881Test; https://doi.org/10.5281/zenodo.1254881Test; oai:zenodo.org:1254881
الإتاحة: https://doi.org/10.5281/zenodo.1254881Test
https://doi.org/10.5281/zenodo.1254880Test
https://zenodo.org/record/1254881Test
