[{"quality_controlled":"1","type":"journal_article","intvolume":" 146","year":"2024","date_updated":"2024-02-06T11:16:09Z","publication":"Pattern Recognition","user_id":"224375","volume":146,"publisher":"Elsevier BV","_id":"4050","publication_status":"published","date_created":"2023-12-18T23:37:19Z","title":"Adaptive local Principal Component Analysis improves the clustering of high-dimensional data","project":[{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"status":"public","language":[{"iso":"eng"}],"doi":"10.1016/j.patcog.2023.110030","citation":{"bibtex":"@article{Migenda_Möller_Schenck_2024, title={Adaptive local Principal Component Analysis improves the clustering of high-dimensional data}, volume={146}, DOI={10.1016/j.patcog.2023.110030}, number={110030}, journal={Pattern Recognition}, publisher={Elsevier BV}, author={Migenda, Nico and Möller, Ralf and Schenck, Wolfram}, year={2024} }","ieee":"N. Migenda, R. Möller, and W. Schenck, “Adaptive local Principal Component Analysis improves the clustering of high-dimensional data,” Pattern Recognition, vol. 146, 2024.","alphadin":"Migenda, Nico ; Möller, Ralf ; Schenck, Wolfram: Adaptive local Principal Component Analysis improves the clustering of high-dimensional data. In: Pattern Recognition Bd. 146, Elsevier BV (2024)","chicago":"Migenda, Nico, Ralf Möller, and Wolfram Schenck. “Adaptive Local Principal Component Analysis Improves the Clustering of High-Dimensional Data.” Pattern Recognition 146 (2024). https://doi.org/10.1016/j.patcog.2023.110030.","mla":"Migenda, Nico, et al. “Adaptive Local Principal Component Analysis Improves the Clustering of High-Dimensional Data.” Pattern Recognition, vol. 146, 110030, Elsevier BV, 2024, doi:10.1016/j.patcog.2023.110030.","ama":"Migenda N, Möller R, Schenck W. Adaptive local Principal Component Analysis improves the clustering of high-dimensional data. Pattern Recognition. 2024;146. doi:10.1016/j.patcog.2023.110030","short":"N. Migenda, R. Möller, W. Schenck, Pattern Recognition 146 (2024).","apa":"Migenda, N., Möller, R., & Schenck, W. (2024). Adaptive local Principal Component Analysis improves the clustering of high-dimensional data. Pattern Recognition, 146. https://doi.org/10.1016/j.patcog.2023.110030"},"publication_identifier":{"issn":["00313203"]},"author":[{"id":"218473","orcid":"0000-0002-7223-1735","first_name":"Nico","full_name":"Migenda, Nico","last_name":"Migenda"},{"full_name":"Möller, Ralf","first_name":"Ralf","last_name":"Möller"},{"id":"224375","orcid":"0000-0003-3300-2048","first_name":"Wolfram","full_name":"Schenck, Wolfram","last_name":"Schenck"}],"article_number":"110030","department":[{"_id":"103"}]},{"quality_controlled":"1","type":"conference","year":"2023","date_updated":"2024-02-07T05:46:53Z","publication":"2023 International Joint Conference on Neural Networks (IJCNN)","user_id":"220548","publisher":"IEEE","_id":"4293","publication_status":"published","date_created":"2024-02-06T11:00:04Z","title":"Object View Prediction with Aleatoric Uncertainty for Robotic Grasping","project":[{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"conference":{"location":"Gold Coast, Australia","name":"2023 International Joint Conference on Neural Networks (IJCNN)","end_date":"2023-06-23","start_date":"2023-06-18"},"status":"public","language":[{"iso":"eng"}],"citation":{"alphadin":"Schwan, Constanze ; Schenck, Wolfram: Object View Prediction with Aleatoric Uncertainty for Robotic Grasping. In: 2023 International Joint Conference on Neural Networks (IJCNN) : IEEE, 2023, S. 1–8","chicago":"Schwan, Constanze, and Wolfram Schenck. “Object View Prediction with Aleatoric Uncertainty for Robotic Grasping.” In 2023 International Joint Conference on Neural Networks (IJCNN), 1–8. IEEE, 2023. https://doi.org/10.1109/IJCNN54540.2023.10191465.","bibtex":"@inproceedings{Schwan_Schenck_2023, title={Object View Prediction with Aleatoric Uncertainty for Robotic Grasping}, DOI={10.1109/IJCNN54540.2023.10191465}, booktitle={2023 International Joint Conference on Neural Networks (IJCNN)}, publisher={IEEE}, author={Schwan, Constanze and Schenck, Wolfram}, year={2023}, pages={1–8} }","ieee":"C. Schwan and W. Schenck, “Object View Prediction with Aleatoric Uncertainty for Robotic Grasping,” in 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, 2023, pp. 1–8.","short":"C. Schwan, W. Schenck, in: 2023 International Joint Conference on Neural Networks (IJCNN), IEEE, 2023, pp. 1–8.","apa":"Schwan, C., & Schenck, W. (2023). Object View Prediction with Aleatoric Uncertainty for Robotic Grasping. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1–8). Gold Coast, Australia: IEEE. https://doi.org/10.1109/IJCNN54540.2023.10191465","mla":"Schwan, Constanze, and Wolfram Schenck. “Object View Prediction with Aleatoric Uncertainty for Robotic Grasping.” 2023 International Joint Conference on Neural Networks (IJCNN), IEEE, 2023, pp. 1–8, doi:10.1109/IJCNN54540.2023.10191465.","ama":"Schwan C, Schenck W. Object View Prediction with Aleatoric Uncertainty for Robotic Grasping. In: 2023 International Joint Conference on Neural Networks (IJCNN). IEEE; 2023:1-8. doi:10.1109/IJCNN54540.2023.10191465"},"doi":"10.1109/IJCNN54540.2023.10191465","publication_identifier":{"eisbn":["978-1-6654-8867-9"]},"author":[{"full_name":"Schwan, Constanze","first_name":"Constanze","last_name":"Schwan"},{"orcid":"0000-0003-3300-2048","id":"224375","last_name":"Schenck","full_name":"Schenck, Wolfram","first_name":"Wolfram"}],"page":"1-8","department":[{"_id":"103"}]},{"status":"public","abstract":[{"lang":"eng","text":" Despite the availability and ease of collecting a large amount of free, unlabeled data, the expensive and time-consuming labeling process is still an obstacle to labeling a sufficient amount of training data, which is essential for building supervised learning models. Here, with low labeling cost, the active learning (AL) technique could be a solution, whereby a few, high-quality data points are queried by searching for the most informative and representative points within the instance space. This strategy ensures high generalizability across the space and improves classification performance on data we have never seen before. In this paper, we provide a survey of recent studies on active learning in the context of classification. This survey starts with an introduction to the theoretical background of the AL technique, AL scenarios, AL components supported with visual explanations, and illustrative examples to explain how AL simply works and the benefits of using AL. In addition to an overview of the query strategies for the classification scenarios, this survey provides a high-level summary to explain various practical challenges with AL in real-world settings; it also explains how AL can be combined with various research areas. Finally, the most commonly used AL software packages and experimental evaluation metrics with AL are also discussed.\r\n "}],"project":[{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"date_created":"2023-04-18T21:54:19Z","title":"A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions","_id":"2774","publication_status":"published","department":[{"_id":"103"}],"article_number":"820","publication_identifier":{"eissn":["2227-7390"]},"author":[{"last_name":"Tharwat","full_name":"Tharwat, Alaa","first_name":"Alaa"},{"last_name":"Schenck","full_name":"Schenck, Wolfram","first_name":"Wolfram","orcid":"0000-0003-3300-2048","id":"224375"}],"citation":{"ieee":"A. Tharwat and W. Schenck, “A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions,” Mathematics, vol. 11, no. 4, 2023.","bibtex":"@article{Tharwat_Schenck_2023, title={A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions}, volume={11}, DOI={10.3390/math11040820}, number={4820}, journal={Mathematics}, publisher={MDPI AG}, author={Tharwat, Alaa and Schenck, Wolfram}, year={2023} }","chicago":"Tharwat, Alaa, and Wolfram Schenck. “A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions.” Mathematics 11, no. 4 (2023). https://doi.org/10.3390/math11040820.","alphadin":"Tharwat, Alaa ; Schenck, Wolfram: A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. In: Mathematics Bd. 11, MDPI AG (2023), Nr. 4","ama":"Tharwat A, Schenck W. A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. Mathematics. 2023;11(4). doi:10.3390/math11040820","mla":"Tharwat, Alaa, and Wolfram Schenck. “A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions.” Mathematics, vol. 11, no. 4, 820, MDPI AG, 2023, doi:10.3390/math11040820.","short":"A. Tharwat, W. Schenck, Mathematics 11 (2023).","apa":"Tharwat, A., & Schenck, W. (2023). A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions. Mathematics, 11(4). https://doi.org/10.3390/math11040820"},"doi":"10.3390/math11040820","language":[{"iso":"eng"}],"year":"2023","intvolume":" 11","main_file_link":[{"open_access":"1","url":"https://www.mdpi.com/2227-7390/11/4/820"}],"type":"journal_article","oa":"1","quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"volume":11,"publisher":"MDPI AG","publication":"Mathematics","user_id":"224375","issue":"4","date_updated":"2024-02-06T11:16:40Z"},{"publication":"PLOS ONE","user_id":"213480","publisher":"Public Library of Science (PLoS)","volume":18,"issue":"8","article_type":"original","date_updated":"2024-02-06T11:02:55Z","year":"2023","main_file_link":[{"open_access":"1"}],"intvolume":" 18","oa":"1","type":"journal_article","funded_apc":"1","quality_controlled":"1","department":[{"_id":"103"}],"author":[{"id":"214493","orcid":"0000-0002-4864-4978","last_name":"Grimmelsmann","first_name":"Nils","full_name":"Grimmelsmann, Nils"},{"last_name":"Mechtenberg","first_name":"Malte","full_name":"Mechtenberg, Malte","id":"218573","orcid":"0000-0002-8958-0931"},{"id":"224375","orcid":"0000-0003-3300-2048","last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram"},{"orcid":"0000-0003-2454-3897","id":"231466","full_name":"Meyer, Hanno Gerd","first_name":"Hanno Gerd","last_name":"Meyer"},{"last_name":"Schneider","full_name":"Schneider, Axel","first_name":"Axel","orcid":"0000-0002-6632-3473","id":"213480"}],"publication_identifier":{"eissn":["1932-6203"]},"article_number":"e0289549","doi":"10.1371/journal.pone.0289549","citation":{"alphadin":"Grimmelsmann, Nils ; Mechtenberg, Malte ; Schenck, Wolfram ; Meyer, Hanno Gerd ; Schneider, Axel: sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters. In: PLOS ONE Bd. 18, Public Library of Science (PLoS) (2023), Nr. 8","chicago":"Grimmelsmann, Nils, Malte Mechtenberg, Wolfram Schenck, Hanno Gerd Meyer, and Axel Schneider. “SEMG-Based Prediction of Human Forearm Movements Utilizing a Biomechanical Model Based on Individual Anatomical/ Physiological Measures and a Reduced Set of Optimization Parameters.” PLOS ONE 18, no. 8 (2023). https://doi.org/10.1371/journal.pone.0289549.","bibtex":"@article{Grimmelsmann_Mechtenberg_Schenck_Meyer_Schneider_2023, title={sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters}, volume={18}, DOI={10.1371/journal.pone.0289549}, number={8e0289549}, journal={PLOS ONE}, publisher={Public Library of Science (PLoS)}, author={Grimmelsmann, Nils and Mechtenberg, Malte and Schenck, Wolfram and Meyer, Hanno Gerd and Schneider, Axel}, year={2023} }","ieee":"N. Grimmelsmann, M. Mechtenberg, W. Schenck, H. G. Meyer, and A. Schneider, “sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters,” PLOS ONE, vol. 18, no. 8, 2023.","apa":"Grimmelsmann, N., Mechtenberg, M., Schenck, W., Meyer, H. G., & Schneider, A. (2023). sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters. PLOS ONE, 18(8). https://doi.org/10.1371/journal.pone.0289549","short":"N. Grimmelsmann, M. Mechtenberg, W. Schenck, H.G. Meyer, A. Schneider, PLOS ONE 18 (2023).","mla":"Grimmelsmann, Nils, et al. “SEMG-Based Prediction of Human Forearm Movements Utilizing a Biomechanical Model Based on Individual Anatomical/ Physiological Measures and a Reduced Set of Optimization Parameters.” PLOS ONE, vol. 18, no. 8, e0289549, Public Library of Science (PLoS), 2023, doi:10.1371/journal.pone.0289549.","ama":"Grimmelsmann N, Mechtenberg M, Schenck W, Meyer HG, Schneider A. sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters. PLOS ONE. 2023;18(8). doi:10.1371/journal.pone.0289549"},"language":[{"iso":"eng"}],"abstract":[{"text":" \r\n For assistive devices such as active orthoses, exoskeletons or other close-to-body robotic-systems, the immediate prediction of biological limb movements based on biosignals in the respective control system can be used to enable intuitive operation also by untrained users e.g. in healthcare, rehabilitation or industrial scenarios. Surface electromyography (sEMG) signals from the muscles that drive the limbs can be measured before the actual movement occurs and, hence, can be used as source for predicting limb movements. The aim of this work was to create a model that can be adapted to a new user or movement scenario with little measurement and computing effort. Therefore, a biomechanical model is presented that predicts limb movements of the human forearm based on easy to measure sEMG signals of the main muscles involved in forearm actuation (\r\n lateral\r\n and\r\n long head\r\n of\r\n triceps\r\n and\r\n short\r\n and\r\n long head\r\n of\r\n biceps\r\n ). The model has 42 internal parameters of which 37 were attributed to 8 individually measured physiological measures (location of\r\n acromion\r\n at the shoulder,\r\n medial/lateral epicondyles\r\n as well as\r\n olecranon\r\n at the elbow, and\r\n styloid processes\r\n of\r\n radius/ulna\r\n at the wrist; maximum muscle forces of\r\n biceps\r\n and\r\n triceps\r\n ). The remaining 5 parameters are adapted to specific movement conditions in an optimization process. The model was tested in an experimental study with 31 subjects in which the prediction quality of the model was assessed. The quality of the movement prediction was evaluated by using the normalized mean absolute error (nMAE) for two arm postures (lower, upper), two load conditions (2 kg, 4 kg) and two movement velocities (slow, fast). For the resulting 8 experimental combinations the nMAE varied between nMAE = 0.16 and nMAE = 0.21 (lower numbers better). An additional quality score (QS) was introduced that allows direct comparison between different movements. This score ranged from QS = 0.25 to QS = 0.40 (higher numbers better) for the experimental combinations. The above formulated aim was achieved with good prediction quality by using only 8 individual measurements (easy to collect body dimensions) and the subsequent optimization of only 5 parameters. At the same time, just easily accessible sEMG measurement locations are used to enable simple integration, e.g. in exoskeletons. This biomechanical model does not compete with models that measure all sEMG signals of the muscle heads involved in order to achieve the highest possible prediction quality.\r\n \r\n ","lang":"eng"}],"status":"public","project":[{"_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b","name":"Institut für Systemdynamik und Mechatronik"},{"_id":"72dfeb62-b436-11ed-9513-f39505d26204","name":"CareTech OWL - Zentrum für Gesundheit, Soziales und Technologie"}],"date_created":"2023-08-22T09:51:09Z","title":"sEMG-based prediction of human forearm movements utilizing a biomechanical model based on individual anatomical/ physiological measures and a reduced set of optimization parameters","_id":"3453","publication_status":"published"},{"language":[{"iso":"eng"}],"citation":{"short":"K. Vandevoorde, L. Vollenkemper, C. Schwan, M. Kohlhase, W. Schenck, Sensors 22 (2022).","apa":"Vandevoorde, K., Vollenkemper, L., Schwan, C., Kohlhase, M., & Schenck, W. (2022). Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks. Sensors, 22(7). https://doi.org/10.3390/s22072481","ama":"Vandevoorde K, Vollenkemper L, Schwan C, Kohlhase M, Schenck W. Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks. Sensors. 2022;22(7). doi:10.3390/s22072481","mla":"Vandevoorde, Koenraad, et al. “Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks.” Sensors, vol. 22, no. 7, 2481, MDPI AG, 2022, doi:10.3390/s22072481.","chicago":"Vandevoorde, Koenraad, Lukas Vollenkemper, Constanze Schwan, Martin Kohlhase, and Wolfram Schenck. “Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks.” Sensors 22, no. 7 (2022). https://doi.org/10.3390/s22072481.","alphadin":"Vandevoorde, Koenraad ; Vollenkemper, Lukas ; Schwan, Constanze ; Kohlhase, Martin ; Schenck, Wolfram: Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks. In: Sensors Bd. 22, MDPI AG (2022), Nr. 7","ieee":"K. Vandevoorde, L. Vollenkemper, C. Schwan, M. Kohlhase, and W. Schenck, “Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks,” Sensors, vol. 22, no. 7, 2022.","bibtex":"@article{Vandevoorde_Vollenkemper_Schwan_Kohlhase_Schenck_2022, title={Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks}, volume={22}, DOI={10.3390/s22072481}, number={72481}, journal={Sensors}, publisher={MDPI AG}, author={Vandevoorde, Koenraad and Vollenkemper, Lukas and Schwan, Constanze and Kohlhase, Martin and Schenck, Wolfram}, year={2022} }"},"file":[{"content_type":"application/pdf","file_size":2869767,"date_updated":"2022-04-04T10:07:48Z","file_name":"sensors-22-02481-v3.pdf","file_id":"1800","access_level":"open_access","date_created":"2022-04-04T10:07:48Z","relation":"main_file","success":1,"creator":"kvandevoorde"}],"_id":"1799","urn":"urn:nbn:de:hbz:bi10-17992","title":"Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks","date_created":"2022-04-04T10:08:43Z","issue":"7","publication":"Sensors","quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"oa":"1","type":"journal_article","intvolume":" 22","doi":"10.3390/s22072481","article_number":"2481","author":[{"id":"242844","last_name":"Vandevoorde","first_name":"Koenraad","full_name":"Vandevoorde, Koenraad"},{"id":"245570","full_name":"Vollenkemper, Lukas","first_name":"Lukas","last_name":"Vollenkemper"},{"first_name":"Constanze","full_name":"Schwan, Constanze","last_name":"Schwan"},{"last_name":"Kohlhase","full_name":"Kohlhase, Martin","first_name":"Martin","orcid":"0009-0002-9374-0720","id":"226669"},{"last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram","id":"224375","orcid":"0000-0003-3300-2048"}],"publication_identifier":{"eissn":["1424-8220"]},"publication_status":"published","has_accepted_license":"1","file_date_updated":"2022-04-04T10:07:48Z","status":"public","abstract":[{"text":" Humans learn movements naturally, but it takes a lot of time and training to achieve expert performance in motor skills. In this review, we show how modern technologies can support people in learning new motor skills. First, we introduce important concepts in motor control, motor learning and motor skill learning. We also give an overview about the rapid expansion of machine learning algorithms and sensor technologies for human motion analysis. The integration between motor learning principles, machine learning algorithms and recent sensor technologies has the potential to develop AI-guided assistance systems for motor skill training. We give our perspective on this integration of different fields to transition from motor learning research in laboratory settings to real world environments and real world motor tasks and propose a stepwise approach to facilitate this transition.\r\n ","lang":"eng"}],"date_updated":"2024-03-27T14:01:14Z","volume":22,"publisher":"MDPI AG","user_id":"245590","main_file_link":[{"open_access":"1","url":"https://www.mdpi.com/1424-8220/22/7/2481"}],"year":"2022","keyword":["motor learning","motor skill learning","assistance system","artificial intelligence","machine learning","pose estimation","action recognition","human motion analysis"]},{"publication":"2022 International Joint Conference on Neural Networks (IJCNN)","user_id":"245590","publisher":"IEEE","date_updated":"2023-06-19T15:01:12Z","year":"2022","type":"conference","quality_controlled":"1","publication_identifier":{"eisbn":["978-1-7281-8671-9"]},"author":[{"id":"239296","first_name":"Zafran Hussain","full_name":"Shah, Zafran Hussain","last_name":"Shah"},{"first_name":"Marcel","full_name":"Muller, Marcel","last_name":"Muller"},{"full_name":"Hammer, Barbara","first_name":"Barbara","last_name":"Hammer"},{"full_name":"Huser, Thomas","first_name":"Thomas","last_name":"Huser"},{"id":"224375","orcid":"0000-0003-3300-2048","last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram"}],"page":"1-10","citation":{"apa":"Shah, Z. H., Muller, M., Hammer, B., Huser, T., & Schenck, W. (2022). Impact of different loss functions on denoising of microscopic images. In 2022 International Joint Conference on Neural Networks (IJCNN) (pp. 1–10). Padua, Italy: IEEE. https://doi.org/10.1109/IJCNN55064.2022.9892936","short":"Z.H. Shah, M. Muller, B. Hammer, T. Huser, W. Schenck, in: 2022 International Joint Conference on Neural Networks (IJCNN), IEEE, 2022, pp. 1–10.","ama":"Shah ZH, Muller M, Hammer B, Huser T, Schenck W. Impact of different loss functions on denoising of microscopic images. In: 2022 International Joint Conference on Neural Networks (IJCNN). IEEE; 2022:1-10. doi:10.1109/IJCNN55064.2022.9892936","mla":"Shah, Zafran Hussain, et al. “Impact of Different Loss Functions on Denoising of Microscopic Images.” 2022 International Joint Conference on Neural Networks (IJCNN), IEEE, 2022, pp. 1–10, doi:10.1109/IJCNN55064.2022.9892936.","chicago":"Shah, Zafran Hussain, Marcel Muller, Barbara Hammer, Thomas Huser, and Wolfram Schenck. “Impact of Different Loss Functions on Denoising of Microscopic Images.” In 2022 International Joint Conference on Neural Networks (IJCNN), 1–10. IEEE, 2022. https://doi.org/10.1109/IJCNN55064.2022.9892936.","alphadin":"Shah, Zafran Hussain ; Muller, Marcel ; Hammer, Barbara ; Huser, Thomas ; Schenck, Wolfram: Impact of different loss functions on denoising of microscopic images. In: 2022 International Joint Conference on Neural Networks (IJCNN) : IEEE, 2022, S. 1–10","ieee":"Z. H. Shah, M. Muller, B. Hammer, T. Huser, and W. Schenck, “Impact of different loss functions on denoising of microscopic images,” in 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1–10.","bibtex":"@inproceedings{Shah_Muller_Hammer_Huser_Schenck_2022, title={Impact of different loss functions on denoising of microscopic images}, DOI={10.1109/IJCNN55064.2022.9892936}, booktitle={2022 International Joint Conference on Neural Networks (IJCNN)}, publisher={IEEE}, author={Shah, Zafran Hussain and Muller, Marcel and Hammer, Barbara and Huser, Thomas and Schenck, Wolfram}, year={2022}, pages={1–10} }"},"doi":"10.1109/IJCNN55064.2022.9892936","language":[{"iso":"eng"}],"conference":{"location":"Padua, Italy","name":"2022 International Joint Conference on Neural Networks (IJCNN)"},"status":"public","title":"Impact of different loss functions on denoising of microscopic images","date_created":"2023-05-20T15:51:00Z","_id":"2945","publication_status":"published"},{"quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"type":"journal_article","oa":"1","intvolume":" 34","main_file_link":[{"url":"https://link.springer.com/article/10.1007/s00521-021-06753-6","open_access":"1"}],"year":"2022","date_updated":"2023-06-19T14:59:18Z","issue":"8","publisher":"Springer Science and Business Media LLC","volume":34,"user_id":"245590","publication":"Neural Computing and Applications","_id":"2944","publication_status":"published","date_created":"2023-05-20T15:44:58Z","title":"Open set task augmentation facilitates generalization of deep neural networks trained on small data sets","status":"public","abstract":[{"text":" Abstract - \r\n Many application scenarios for image recognition require learning of deep networks from small sample sizes in the order of a few hundred samples per class. Then, avoiding overfitting is critical. Common techniques to address overfitting are transfer learning, reduction of model complexity and artificial enrichment of the available data by, e.g., data augmentation. A key idea proposed in this paper is to incorporate additional samples into the training that do not belong to the classes of the target task. This can be accomplished by formulating the original classification task as an open set classification task. While the original closed set classification task is not altered at inference time, the recast as open set classification task enables the inclusion of additional data during training. Hence, the original closed set classification task is augmented with an open set task during training. We therefore call the proposed approach open set task augmentation. In order to integrate additional task-unrelated samples into the training, we employ the entropic open set loss originally proposed for open set classification tasks and also show that similar results can be obtained with a modified sum of squared errors loss function. Learning with the proposed approach benefits from the integration of additional “unknown” samples, which are often available, e.g., from open data sets, and can then be easily integrated into the learning process. We show that this open set task augmentation can improve model performance even when these additional samples are rather few or far from the domain of the target task. The proposed approach is demonstrated on two exemplary scenarios based on subsets of the ImageNet and Food-101 data sets as well as with several network architectures and two loss functions. We further shed light on the impact of the entropic open set loss on the internal representations formed by the networks. Open set task augmentation is particularly valuable when no additional data from the target classes are available—a scenario often faced in practice.\r\n ","lang":"eng"}],"language":[{"iso":"eng"}],"citation":{"apa":"Zai El Amri, W., Reinhart, F., & Schenck, W. (2022). Open set task augmentation facilitates generalization of deep neural networks trained on small data sets. Neural Computing and Applications, 34(8), 6067–6083. https://doi.org/10.1007/s00521-021-06753-6","short":"W. Zai El Amri, F. Reinhart, W. Schenck, Neural Computing and Applications 34 (2022) 6067–6083.","ama":"Zai El Amri W, Reinhart F, Schenck W. Open set task augmentation facilitates generalization of deep neural networks trained on small data sets. Neural Computing and Applications. 2022;34(8):6067-6083. doi:10.1007/s00521-021-06753-6","mla":"Zai El Amri, Wadhah, et al. “Open Set Task Augmentation Facilitates Generalization of Deep Neural Networks Trained on Small Data Sets.” Neural Computing and Applications, vol. 34, no. 8, Springer Science and Business Media LLC, 2022, pp. 6067–83, doi:10.1007/s00521-021-06753-6.","chicago":"Zai El Amri, Wadhah, Felix Reinhart, and Wolfram Schenck. “Open Set Task Augmentation Facilitates Generalization of Deep Neural Networks Trained on Small Data Sets.” Neural Computing and Applications 34, no. 8 (2022): 6067–83. https://doi.org/10.1007/s00521-021-06753-6.","alphadin":"Zai El Amri, Wadhah ; Reinhart, Felix ; Schenck, Wolfram: Open set task augmentation facilitates generalization of deep neural networks trained on small data sets. In: Neural Computing and Applications Bd. 34, Springer Science and Business Media LLC (2022), Nr. 8, S. 6067–6083","ieee":"W. Zai El Amri, F. Reinhart, and W. Schenck, “Open set task augmentation facilitates generalization of deep neural networks trained on small data sets,” Neural Computing and Applications, vol. 34, no. 8, pp. 6067–6083, 2022.","bibtex":"@article{Zai El Amri_Reinhart_Schenck_2022, title={Open set task augmentation facilitates generalization of deep neural networks trained on small data sets}, volume={34}, DOI={10.1007/s00521-021-06753-6}, number={8}, journal={Neural Computing and Applications}, publisher={Springer Science and Business Media LLC}, author={Zai El Amri, Wadhah and Reinhart, Felix and Schenck, Wolfram}, year={2022}, pages={6067–6083} }"},"doi":"10.1007/s00521-021-06753-6","page":"6067-6083","publication_identifier":{"eissn":["1433-3058"],"issn":["0941-0643"]},"author":[{"first_name":"Wadhah","full_name":"Zai El Amri, Wadhah","last_name":"Zai El Amri"},{"last_name":"Reinhart","full_name":"Reinhart, Felix","first_name":"Felix"},{"first_name":"Wolfram","full_name":"Schenck, Wolfram","last_name":"Schenck","id":"224375","orcid":"0000-0003-3300-2048"}]},{"place":"Berlin, Heidelberg","year":"2022","main_file_link":[{"url":"https://link.springer.com/chapter/10.1007/978-3-662-64283-2_21","open_access":"1"}],"type":"conference","oa":"1","quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"publisher":"Springer Berlin Heidelberg","publication":"Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020","user_id":"245590","date_updated":"2023-06-19T14:07:57Z","editor":[{"last_name":"Jasperneite","full_name":"Jasperneite, Jürgen","first_name":"Jürgen"},{"last_name":"Lohweg","full_name":"Lohweg, Volker","first_name":"Volker"}],"status":"public","abstract":[{"lang":"eng","text":" Abstract - \r\n State-of-the-art methods in image-based robotic grasping use deep convolutional neural networks to determine the robot parameters that maximize the probability of a stable grasp given an image of an object. Despite the high accuracy of these models they are not applied in industrial order picking tasks to date. One of the reasons is the fact that the generation of the training data for these models is expensive. Even though this could be solved by using a physics simulation for training data generation, another even more important reason is that the features that lead to the prediction made by the model are not human-readable. This lack of interpretability is the crucial factor why deep networks are not found in critical industrial applications. In this study we suggest to reformulate the task of robotic grasping as three tasks that are easy to assess from human experience. For each of the three steps we discuss the accuracy and interpretability. We outline how the proposed three-step model can be extended to depth images. Furthermore we discuss how interpretable machine learning models can be chosen for the three steps in order to be applied in a real-world industrial environment.\r\n "}],"date_created":"2023-04-18T21:54:22Z","title":"Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking","publication_status":"published","_id":"2776","series_title":"Technologien für die intelligente Automation","page":"291-303","author":[{"full_name":"Schwan, Constanze","first_name":"Constanze","last_name":"Schwan"},{"id":"224375","orcid":"0000-0003-3300-2048","first_name":"Wolfram","full_name":"Schenck, Wolfram","last_name":"Schenck"}],"publication_identifier":{"issn":["2522-8579"],"eisbn":["978-3-662-64283-2"],"isbn":["978-3-662-64282-5"],"eissn":["2522-8587"]},"citation":{"alphadin":"Schwan, Constanze ; Schenck, Wolfram: Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking. In: Jasperneite, J. ; Lohweg, V. (Hrsg.): Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020, Technologien für die intelligente Automation. Berlin, Heidelberg : Springer Berlin Heidelberg, 2022, S. 291–303","chicago":"Schwan, Constanze, and Wolfram Schenck. “Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking.” In Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020, edited by Jürgen Jasperneite and Volker Lohweg, 291–303. Technologien für die intelligente Automation. Berlin, Heidelberg: Springer Berlin Heidelberg, 2022. https://doi.org/10.1007/978-3-662-64283-2_21.","bibtex":"@inproceedings{Schwan_Schenck_2022, place={Berlin, Heidelberg}, series={Technologien für die intelligente Automation}, title={Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking}, DOI={10.1007/978-3-662-64283-2_21}, booktitle={Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020}, publisher={Springer Berlin Heidelberg}, author={Schwan, Constanze and Schenck, Wolfram}, editor={Jasperneite, Jürgen and Lohweg, VolkerEditors}, year={2022}, pages={291–303}, collection={Technologien für die intelligente Automation} }","ieee":"C. Schwan and W. Schenck, “Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking,” in Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020, 2022, pp. 291–303.","apa":"Schwan, C., & Schenck, W. (2022). Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking. In J. Jasperneite & V. Lohweg (Eds.), Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020 (pp. 291–303). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-662-64283-2_21","short":"C. Schwan, W. Schenck, in: J. Jasperneite, V. Lohweg (Eds.), Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020, Springer Berlin Heidelberg, Berlin, Heidelberg, 2022, pp. 291–303.","mla":"Schwan, Constanze, and Wolfram Schenck. “Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking.” Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020, edited by Jürgen Jasperneite and Volker Lohweg, Springer Berlin Heidelberg, 2022, pp. 291–303, doi:10.1007/978-3-662-64283-2_21.","ama":"Schwan C, Schenck W. Design of Interpretable Machine Learning Tasks for the Application to Industrial Order Picking. In: Jasperneite J, Lohweg V, eds. Kommunikation und Bildverarbeitung in der Automation. Ausgewählte Beiträge der Jahreskolloquien KommA und BVAu 2020. Technologien für die intelligente Automation. Berlin, Heidelberg: Springer Berlin Heidelberg; 2022:291-303. doi:10.1007/978-3-662-64283-2_21"},"doi":"10.1007/978-3-662-64283-2_21","language":[{"iso":"ger"}]},{"year":"2022","intvolume":" 10","main_file_link":[{"open_access":"1","url":"https://www.mdpi.com/2227-7390/10/7/1068"}],"oa":"1","type":"journal_article","quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"publisher":"MDPI AG","volume":10,"user_id":"245590","publication":"Mathematics","issue":"7","date_updated":"2023-06-19T14:06:24Z","status":"public","abstract":[{"lang":"eng","text":" Despite the availability of a large amount of free unlabeled data, collecting sufficient training data for supervised learning models is challenging due to the time and cost involved in the labeling process. The active learning technique we present here provides a solution by querying a small but highly informative set of unlabeled data. It ensures high generalizability across space, improving classification performance with test data that we have never seen before. Most active learners query either the most informative or the most representative data to annotate them. These two criteria are combined in the proposed algorithm by using two phases: exploration and exploitation phases. The former aims to explore the instance space by visiting new regions at each iteration. The second phase attempts to select highly informative points in uncertain regions. Without any predefined knowledge, such as initial training data, these two phases improve the search strategy of the proposed algorithm so that it can explore the minority class space with imbalanced data using a small query budget. Further, some pseudo-labeled points geometrically located in trusted explored regions around the new labeled points are added to the training data, but with lower weights than the original labeled points. These pseudo-labeled points play several roles in our model, such as (i) increasing the size of the training data and (ii) decreasing the size of the version space by reducing the number of hypotheses that are consistent with the training data. Experiments on synthetic and real datasets with different imbalance ratios and dimensions show that the proposed algorithm has significant advantages over various well-known active learners.\r\n "}],"date_created":"2023-04-18T21:54:20Z","title":"A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data","publication_status":"published","_id":"2775","article_number":"1068","author":[{"last_name":"Tharwat","full_name":"Tharwat, Alaa","first_name":"Alaa"},{"id":"224375","orcid":"0000-0003-3300-2048","first_name":"Wolfram","full_name":"Schenck, Wolfram","last_name":"Schenck"}],"publication_identifier":{"eissn":["2227-7390"]},"doi":"10.3390/math10071068","citation":{"alphadin":"Tharwat, Alaa ; Schenck, Wolfram: A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data. In: Mathematics Bd. 10, MDPI AG (2022), Nr. 7","chicago":"Tharwat, Alaa, and Wolfram Schenck. “A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data.” Mathematics 10, no. 7 (2022). https://doi.org/10.3390/math10071068.","bibtex":"@article{Tharwat_Schenck_2022, title={A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data}, volume={10}, DOI={10.3390/math10071068}, number={71068}, journal={Mathematics}, publisher={MDPI AG}, author={Tharwat, Alaa and Schenck, Wolfram}, year={2022} }","ieee":"A. Tharwat and W. Schenck, “A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data,” Mathematics, vol. 10, no. 7, 2022.","short":"A. Tharwat, W. Schenck, Mathematics 10 (2022).","apa":"Tharwat, A., & Schenck, W. (2022). A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data. Mathematics, 10(7). https://doi.org/10.3390/math10071068","mla":"Tharwat, Alaa, and Wolfram Schenck. “A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data.” Mathematics, vol. 10, no. 7, 1068, MDPI AG, 2022, doi:10.3390/math10071068.","ama":"Tharwat A, Schenck W. A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data. Mathematics. 2022;10(7). doi:10.3390/math10071068"},"language":[{"iso":"eng"}]},{"type":"conference","quality_controlled":"1","place":"Cham","year":"2022","date_updated":"2023-06-17T11:37:40Z","publisher":"Springer International Publishing","user_id":"216459","publication":"Collaborative Networks in Digitalization and Society 5.0","date_created":"2023-03-10T08:37:50Z","title":"Collaborative System for Question Answering in German Case Law Documents","_id":"2569","publication_status":"published","status":"public","editor":[{"last_name":"Camarinha-Matos","full_name":"Camarinha-Matos, Luis M.","first_name":"Luis M."},{"full_name":"Ortiz, Angel","first_name":"Angel","last_name":"Ortiz"},{"full_name":"Boucher, Xavier","first_name":"Xavier","last_name":"Boucher"},{"first_name":"A. Luís","full_name":"Osório, A. Luís","last_name":"Osório"}],"abstract":[{"lang":"eng","text":"Legal systems form the foundation of democratic states. Nevertheless, it is nearly impossible for individuals to extract specific information from comprehensive legal documents. We present a human-centered and AI-supported system for semantic question answering (QA) in the German legal domain. Our system is built on top of human collaboration and natural language processing (NLP)-based legal information retrieval. Laypersons and legal professionals re ceive information supporting their research and decision-making by collaborating with the system and its underlying AI methods to enable a smarter society. The internal AI is based on state-of-the-art methods evaluating complex search terms, considering words and phrases specific to German law. Subsequently, relevant documents or answers are ranked and graphically presented to the human. In ad dition to the novel system, we publish the first annotated data set for QA in the German legal domain. The experimental results indicate that our semantic QA workflow outperforms existing approaches.KeywordsQuestion answeringInformation retrievalHuman-AI interface designAI-supported decision makingLegal research"}],"conference":{"name":" 23rd IFIP WG 5.5 Working Conference on Virtual Enterprises, PRO-VE 2022","location":"Lisbon, Portugal","end_date":"2022-09-21","start_date":"2022-09-19"},"doi":"10.1007/978-3-031-14844-6_24","citation":{"bibtex":"@inproceedings{Hoppe_Migenda_Pelkmann_Hötte_Schenck_2022, place={Cham}, series={IFIP Advances in Information and Communication Technology}, title={Collaborative System for Question Answering in German Case Law Documents}, DOI={10.1007/978-3-031-14844-6_24}, booktitle={Collaborative Networks in Digitalization and Society 5.0}, publisher={Springer International Publishing}, author={Hoppe, Christoph and Migenda, Nico and Pelkmann, David and Hötte, Daniel Antonius and Schenck, Wolfram}, editor={Camarinha-Matos, Luis M. and Ortiz, Angel and Boucher, Xavier and Osório, A. LuísEditors}, year={2022}, pages={303–312}, collection={IFIP Advances in Information and Communication Technology} }","ieee":"C. Hoppe, N. Migenda, D. Pelkmann, D. A. Hötte, and W. Schenck, “Collaborative System for Question Answering in German Case Law Documents,” in Collaborative Networks in Digitalization and Society 5.0, Lisbon, Portugal, 2022, pp. 303–312.","alphadin":"Hoppe, Christoph ; Migenda, Nico ; Pelkmann, David ; Hötte, Daniel Antonius ; Schenck, Wolfram: Collaborative System for Question Answering in German Case Law Documents. In: Camarinha-Matos, L. M. ; Ortiz, A. ; Boucher, X. ; Osório, A. L. (Hrsg.): Collaborative Networks in Digitalization and Society 5.0, IFIP Advances in Information and Communication Technology. Cham : Springer International Publishing, 2022, S. 303–312","chicago":"Hoppe, Christoph, Nico Migenda, David Pelkmann, Daniel Antonius Hötte, and Wolfram Schenck. “Collaborative System for Question Answering in German Case Law Documents.” In Collaborative Networks in Digitalization and Society 5.0, edited by Luis M. Camarinha-Matos, Angel Ortiz, Xavier Boucher, and A. Luís Osório, 303–12. IFIP Advances in Information and Communication Technology. Cham: Springer International Publishing, 2022. https://doi.org/10.1007/978-3-031-14844-6_24.","mla":"Hoppe, Christoph, et al. “Collaborative System for Question Answering in German Case Law Documents.” Collaborative Networks in Digitalization and Society 5.0, edited by Luis M. Camarinha-Matos et al., Springer International Publishing, 2022, pp. 303–12, doi:10.1007/978-3-031-14844-6_24.","ama":"Hoppe C, Migenda N, Pelkmann D, Hötte DA, Schenck W. Collaborative System for Question Answering in German Case Law Documents. In: Camarinha-Matos LM, Ortiz A, Boucher X, Osório AL, eds. Collaborative Networks in Digitalization and Society 5.0. IFIP Advances in Information and Communication Technology. Cham: Springer International Publishing; 2022:303-312. doi:10.1007/978-3-031-14844-6_24","short":"C. Hoppe, N. Migenda, D. Pelkmann, D.A. Hötte, W. Schenck, in: L.M. Camarinha-Matos, A. Ortiz, X. Boucher, A.L. Osório (Eds.), Collaborative Networks in Digitalization and Society 5.0, Springer International Publishing, Cham, 2022, pp. 303–312.","apa":"Hoppe, C., Migenda, N., Pelkmann, D., Hötte, D. A., & Schenck, W. (2022). Collaborative System for Question Answering in German Case Law Documents. In L. M. Camarinha-Matos, A. Ortiz, X. Boucher, & A. L. Osório (Eds.), Collaborative Networks in Digitalization and Society 5.0 (pp. 303–312). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-031-14844-6_24"},"language":[{"iso":"eng"}],"series_title":"IFIP Advances in Information and Communication Technology","page":"303-312","publication_identifier":{"issn":["1868-4238"],"eisbn":["978-3-031-14844-6"],"isbn":["978-3-031-14843-9"],"eissn":["1868-422X"]},"author":[{"last_name":"Hoppe","full_name":"Hoppe, Christoph","first_name":"Christoph"},{"orcid":"0000-0002-7223-1735","id":"218473","last_name":"Migenda","full_name":"Migenda, Nico","first_name":"Nico"},{"last_name":"Pelkmann","first_name":"David","full_name":"Pelkmann, David","id":"217023"},{"last_name":"Hötte","first_name":"Daniel Antonius","full_name":"Hötte, Daniel Antonius"},{"id":"224375","orcid":"0000-0003-3300-2048","last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram"}]},{"article_number":"B168","publication_identifier":{"eissn":["2327-9125"]},"author":[{"id":"239296","first_name":"Zafran Hussain","full_name":"Shah, Zafran Hussain","last_name":"Shah"},{"last_name":"Müller","first_name":"Marcel","full_name":"Müller, Marcel"},{"first_name":"Tung-Cheng","full_name":"Wang, Tung-Cheng","last_name":"Wang"},{"last_name":"Scheidig","full_name":"Scheidig, Philip Maurice","first_name":"Philip Maurice"},{"orcid":"0000-0002-6632-3473","id":"213480","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-6632-3473/work/94914657","full_name":"Schneider, Axel","first_name":"Axel","last_name":"Schneider"},{"full_name":"Schüttpelz, Mark","first_name":"Mark","last_name":"Schüttpelz"},{"first_name":"Thomas","full_name":"Huser, Thomas","last_name":"Huser"},{"last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-3300-2048/work/94914472","id":"224375","orcid":"0000-0003-3300-2048"}],"doi":"10.1364/PRJ.416437","citation":{"ama":"Shah ZH, Müller M, Wang T-C, et al. Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images. Photonics Research. 2021;9(5). doi:10.1364/PRJ.416437","mla":"Shah, Zafran Hussain, et al. “Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images.” Photonics Research, vol. 9, no. 5, B168, The Optical Society, 2021, doi:10.1364/PRJ.416437.","short":"Z.H. Shah, M. Müller, T.-C. Wang, P.M. Scheidig, A. Schneider, M. Schüttpelz, T. Huser, W. Schenck, Photonics Research 9 (2021).","apa":"Shah, Z. H., Müller, M., Wang, T.-C., Scheidig, P. M., Schneider, A., Schüttpelz, M., … Schenck, W. (2021). Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images. Photonics Research, 9(5). https://doi.org/10.1364/PRJ.416437","ieee":"Z. H. Shah et al., “Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images,” Photonics Research, vol. 9, no. 5, 2021.","bibtex":"@article{Shah_Müller_Wang_Scheidig_Schneider_Schüttpelz_Huser_Schenck_2021, title={Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images}, volume={9}, DOI={10.1364/PRJ.416437}, number={5B168}, journal={Photonics Research}, publisher={The Optical Society}, author={Shah, Zafran Hussain and Müller, Marcel and Wang, Tung-Cheng and Scheidig, Philip Maurice and Schneider, Axel and Schüttpelz, Mark and Huser, Thomas and Schenck, Wolfram}, year={2021} }","chicago":"Shah, Zafran Hussain, Marcel Müller, Tung-Cheng Wang, Philip Maurice Scheidig, Axel Schneider, Mark Schüttpelz, Thomas Huser, and Wolfram Schenck. “Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images.” Photonics Research 9, no. 5 (2021). https://doi.org/10.1364/PRJ.416437.","alphadin":"Shah, Zafran Hussain ; Müller, Marcel ; Wang, Tung-Cheng ; Scheidig, Philip Maurice ; Schneider, Axel ; Schüttpelz, Mark ; Huser, Thomas ; Schenck, Wolfram: Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images. In: Photonics Research Bd. 9, The Optical Society (2021), Nr. 5"},"language":[{"iso":"eng"}],"status":"public","project":[{"_id":"72dfeb62-b436-11ed-9513-f39505d26204","name":"CareTech OWL - Zentrum für Gesundheit, Soziales und Technologie"},{"_id":"edf53067-b368-11ed-bde2-9f34a4102af5","name":"TransCareTech - Transformation in Care & Technology"},{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"date_created":"2021-06-03T19:35:46Z","title":"Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images","_id":"1201","publication_status":"published","volume":9,"publisher":"The Optical Society","publication":"Photonics Research","user_id":"245590","issue":"5","date_updated":"2023-05-30T15:19:56Z","year":"2021","intvolume":" 9","main_file_link":[{"open_access":"1","url":"https://doi.org/10.1364/PRJ.416437"}],"oa":"1","type":"journal_article"},{"year":"2021","type":"conference","user_id":"249199","publication":"2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","publisher":"IEEE","date_updated":"2023-05-10T13:46:05Z","conference":{"location":"Laguna Hills, CA, USA","name":"2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)"},"status":"public","date_created":"2023-03-10T08:38:44Z","title":"Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents","publication_status":"published","_id":"2570","author":[{"last_name":"Hoppe","first_name":"Christoph","full_name":"Hoppe, Christoph"},{"id":"217023","full_name":"Pelkmann, David","first_name":"David","last_name":"Pelkmann"},{"id":"218473","orcid":"0000-0002-7223-1735","last_name":"Migenda","first_name":"Nico","full_name":"Migenda, Nico"},{"first_name":"Daniel Antonius","full_name":"Hotte, Daniel Antonius","last_name":"Hotte"},{"full_name":"Schenck, Wolfram","first_name":"Wolfram","last_name":"Schenck","orcid":"0000-0003-3300-2048","id":"224375"}],"publication_identifier":{"eisbn":["978-1-6654-3736-3"]},"page":"29-32","citation":{"ieee":"C. Hoppe, D. Pelkmann, N. Migenda, D. A. Hotte, and W. Schenck, “Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents,” in 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Laguna Hills, CA, USA, 2021, pp. 29–32.","bibtex":"@inproceedings{Hoppe_Pelkmann_Migenda_Hotte_Schenck_2021, title={Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents}, DOI={10.1109/AIKE52691.2021.00011}, booktitle={2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)}, publisher={IEEE}, author={Hoppe, Christoph and Pelkmann, David and Migenda, Nico and Hotte, Daniel Antonius and Schenck, Wolfram}, year={2021}, pages={29–32} }","chicago":"Hoppe, Christoph, David Pelkmann, Nico Migenda, Daniel Antonius Hotte, and Wolfram Schenck. “Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents.” In 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 29–32. IEEE, 2021. https://doi.org/10.1109/AIKE52691.2021.00011.","alphadin":"Hoppe, Christoph ; Pelkmann, David ; Migenda, Nico ; Hotte, Daniel Antonius ; Schenck, Wolfram: Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents. In: 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) : IEEE, 2021, S. 29–32","ama":"Hoppe C, Pelkmann D, Migenda N, Hotte DA, Schenck W. Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents. In: 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE). IEEE; 2021:29-32. doi:10.1109/AIKE52691.2021.00011","mla":"Hoppe, Christoph, et al. “Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents.” 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), IEEE, 2021, pp. 29–32, doi:10.1109/AIKE52691.2021.00011.","short":"C. Hoppe, D. Pelkmann, N. Migenda, D.A. Hotte, W. Schenck, in: 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), IEEE, 2021, pp. 29–32.","apa":"Hoppe, C., Pelkmann, D., Migenda, N., Hotte, D. A., & Schenck, W. (2021). Towards Intelligent Legal Advisors for Document Retrieval and Question-Answering in German Legal Documents. In 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) (pp. 29–32). Laguna Hills, CA, USA: IEEE. https://doi.org/10.1109/AIKE52691.2021.00011"},"doi":"10.1109/AIKE52691.2021.00011","language":[{"iso":"eng"}]},{"conference":{"name":"2021 IEEE 26th International Conference on Emerging Technologies and Factory Automation (ETFA)","location":"Vasteras, Sweden"},"status":"public","title":"Advanced Data Analytics Platform for Manufacturing Companies","date_created":"2023-03-10T08:39:39Z","publication_status":"published","_id":"2571","author":[{"full_name":"Voigt, Tim","first_name":"Tim","last_name":"Voigt","id":"220691"},{"orcid":"0000-0002-7223-1735","id":"218473","full_name":"Migenda, Nico","first_name":"Nico","last_name":"Migenda"},{"id":"218388","full_name":"Schöne, Marvin","first_name":"Marvin","last_name":"Schöne"},{"id":"217023","last_name":"Pelkmann","first_name":"David","full_name":"Pelkmann, David"},{"last_name":"Fricke","full_name":"Fricke, Matthias","first_name":"Matthias"},{"last_name":"Schenck","full_name":"Schenck, Wolfram","first_name":"Wolfram","orcid":"0000-0003-3300-2048","id":"224375"},{"id":"226669","last_name":"Kohlhase","first_name":"Martin","full_name":"Kohlhase, Martin"}],"publication_identifier":{"eisbn":["978-1-7281-2989-1"]},"page":"01-08","citation":{"ieee":"T. Voigt et al., “Advanced Data Analytics Platform for Manufacturing Companies,” in 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), Vasteras, Sweden, 2021, pp. 01–08.","bibtex":"@inproceedings{Voigt_Migenda_Schöne_Pelkmann_Fricke_Schenck_Kohlhase_2021, title={Advanced Data Analytics Platform for Manufacturing Companies}, DOI={10.1109/ETFA45728.2021.9613499}, booktitle={2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )}, publisher={IEEE}, author={Voigt, Tim and Migenda, Nico and Schöne, Marvin and Pelkmann, David and Fricke, Matthias and Schenck, Wolfram and Kohlhase, Martin}, year={2021}, pages={01–08} }","chicago":"Voigt, Tim, Nico Migenda, Marvin Schöne, David Pelkmann, Matthias Fricke, Wolfram Schenck, and Martin Kohlhase. “Advanced Data Analytics Platform for Manufacturing Companies.” In 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), 01–08. IEEE, 2021. https://doi.org/10.1109/ETFA45728.2021.9613499.","alphadin":"Voigt, Tim ; Migenda, Nico ; Schöne, Marvin ; Pelkmann, David ; Fricke, Matthias ; Schenck, Wolfram ; Kohlhase, Martin: Advanced Data Analytics Platform for Manufacturing Companies. In: 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ) : IEEE, 2021, S. 01–08","ama":"Voigt T, Migenda N, Schöne M, et al. Advanced Data Analytics Platform for Manufacturing Companies. In: 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ). IEEE; 2021:01-08. doi:10.1109/ETFA45728.2021.9613499","mla":"Voigt, Tim, et al. “Advanced Data Analytics Platform for Manufacturing Companies.” 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), IEEE, 2021, pp. 01–08, doi:10.1109/ETFA45728.2021.9613499.","apa":"Voigt, T., Migenda, N., Schöne, M., Pelkmann, D., Fricke, M., Schenck, W., & Kohlhase, M. (2021). Advanced Data Analytics Platform for Manufacturing Companies. In 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ) (pp. 01–08). Vasteras, Sweden: IEEE. https://doi.org/10.1109/ETFA45728.2021.9613499","short":"T. Voigt, N. Migenda, M. Schöne, D. Pelkmann, M. Fricke, W. Schenck, M. Kohlhase, in: 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), IEEE, 2021, pp. 01–08."},"doi":"10.1109/ETFA45728.2021.9613499","language":[{"iso":"eng"}],"year":"2021","type":"conference","publication":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","user_id":"249199","publisher":"IEEE","date_updated":"2023-05-10T13:45:11Z"},{"language":[{"iso":"eng"}],"doi":"10.1145/3460824.3460825","citation":{"chicago":"Steinmann, Luca, Nico Migenda, Tim Voigt, Martin Kohlhase, and Wolfram Schenck. “Variational Autoencoder Based Novelty Detection for Real-World Time Series.” In 2021 3rd International Conference on Management Science and Industrial Engineering, 1–7. New York, NY, USA: ACM, 2021. https://doi.org/10.1145/3460824.3460825.","alphadin":"Steinmann, Luca ; Migenda, Nico ; Voigt, Tim ; Kohlhase, Martin ; Schenck, Wolfram: Variational Autoencoder based Novelty Detection for Real-World Time Series. In: 2021 3rd International Conference on Management Science and Industrial Engineering. New York, NY, USA : ACM, 2021, S. 1–7","ieee":"L. Steinmann, N. Migenda, T. Voigt, M. Kohlhase, and W. Schenck, “Variational Autoencoder based Novelty Detection for Real-World Time Series,” in 2021 3rd International Conference on Management Science and Industrial Engineering, Osaka Japan, 2021, pp. 1–7.","bibtex":"@inproceedings{Steinmann_Migenda_Voigt_Kohlhase_Schenck_2021, place={New York, NY, USA}, title={Variational Autoencoder based Novelty Detection for Real-World Time Series}, DOI={10.1145/3460824.3460825}, booktitle={2021 3rd International Conference on Management Science and Industrial Engineering}, publisher={ACM}, author={Steinmann, Luca and Migenda, Nico and Voigt, Tim and Kohlhase, Martin and Schenck, Wolfram}, year={2021}, pages={1–7} }","apa":"Steinmann, L., Migenda, N., Voigt, T., Kohlhase, M., & Schenck, W. (2021). Variational Autoencoder based Novelty Detection for Real-World Time Series. In 2021 3rd International Conference on Management Science and Industrial Engineering (pp. 1–7). New York, NY, USA: ACM. https://doi.org/10.1145/3460824.3460825","short":"L. Steinmann, N. Migenda, T. Voigt, M. Kohlhase, W. Schenck, in: 2021 3rd International Conference on Management Science and Industrial Engineering, ACM, New York, NY, USA, 2021, pp. 1–7.","ama":"Steinmann L, Migenda N, Voigt T, Kohlhase M, Schenck W. Variational Autoencoder based Novelty Detection for Real-World Time Series. In: 2021 3rd International Conference on Management Science and Industrial Engineering. New York, NY, USA: ACM; 2021:1-7. doi:10.1145/3460824.3460825","mla":"Steinmann, Luca, et al. “Variational Autoencoder Based Novelty Detection for Real-World Time Series.” 2021 3rd International Conference on Management Science and Industrial Engineering, ACM, 2021, pp. 1–7, doi:10.1145/3460824.3460825."},"page":"1-7","author":[{"last_name":"Steinmann","full_name":"Steinmann, Luca","first_name":"Luca"},{"first_name":"Nico","full_name":"Migenda, Nico","last_name":"Migenda","id":"218473","orcid":"0000-0002-7223-1735"},{"full_name":"Voigt, Tim","first_name":"Tim","last_name":"Voigt","id":"220691"},{"id":"226669","last_name":"Kohlhase","full_name":"Kohlhase, Martin","first_name":"Martin"},{"orcid":"0000-0003-3300-2048","id":"224375","last_name":"Schenck","full_name":"Schenck, Wolfram","first_name":"Wolfram"}],"publication_identifier":{"isbn":["9781450388887"]},"publication_status":"published","_id":"2572","title":"Variational Autoencoder based Novelty Detection for Real-World Time Series","date_created":"2023-03-10T08:40:15Z","status":"public","conference":{"start_date":"2021-04-02","end_date":"2021-04-04","name":"MSIE 2021: 2021 3rd International Conference on Management Science and Industrial Engineering","location":"Osaka Japan"},"date_updated":"2023-05-10T13:44:02Z","publisher":"ACM","publication":"2021 3rd International Conference on Management Science and Industrial Engineering","user_id":"249199","type":"conference","place":"New York, NY, USA","year":"2021"},{"year":"2021","intvolume":" 16","type":"journal_article","publisher":"Public Library of Science (PLoS)","volume":16,"user_id":"249199","publication":"PLOS ONE","issue":"3","date_updated":"2023-05-10T13:40:20Z","status":"public","abstract":[{"text":" “Principal Component Analysis” (PCA) is an established linear technique for dimensionality reduction. It performs an orthonormal transformation to replace possibly correlated variables with a smaller set of linearly independent variables, the so-called principal components, which capture a large portion of the data variance. The problem of finding the optimal number of principal components has been widely studied for offline PCA. However, when working with streaming data, the optimal number changes continuously. This requires to update both the principal components and the dimensionality in every timestep. While the continuous update of the principal components is widely studied, the available algorithms for dimensionality adjustment are limited to an increment of one in neural network-based and incremental PCA. Therefore, existing approaches cannot account for abrupt changes in the presented data. The contribution of this work is to enable in neural network-based PCA the continuous dimensionality adjustment by an arbitrary number without the necessity to learn all principal components. A novel algorithm is presented that utilizes several PCA characteristics to adaptivly update the optimal number of principal components for neural network-based PCA. A precise estimation of the required dimensionality reduces the computational effort while ensuring that the desired amount of variance is kept. The computational complexity of the proposed algorithm is investigated and it is benchmarked in an experimental study against other neural network-based and incremental PCA approaches where it produces highly competitive results.\r\n ","lang":"eng"}],"date_created":"2021-06-03T19:35:49Z","title":"Adaptive dimensionality reduction for neural network-based online principal component analysis","_id":"1203","publication_status":"published","article_number":"e0248896","publication_identifier":{"eissn":["1932-6203"]},"author":[{"orcid":"0000-0002-7223-1735","id":"218473","last_name":"Migenda","full_name":"Migenda, Nico","first_name":"Nico"},{"last_name":"Möller","full_name":"Möller, Ralf","first_name":"Ralf"},{"last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-3300-2048/work/94914468","id":"224375","orcid":"0000-0003-3300-2048"}],"doi":"10.1371/journal.pone.0248896","citation":{"bibtex":"@article{Migenda_Möller_Schenck_2021, title={Adaptive dimensionality reduction for neural network-based online principal component analysis}, volume={16}, DOI={10.1371/journal.pone.0248896}, number={3e0248896}, journal={PLOS ONE}, publisher={Public Library of Science (PLoS)}, author={Migenda, Nico and Möller, Ralf and Schenck, Wolfram}, year={2021} }","ieee":"N. Migenda, R. Möller, and W. Schenck, “Adaptive dimensionality reduction for neural network-based online principal component analysis,” PLOS ONE, vol. 16, no. 3, 2021.","alphadin":"Migenda, Nico ; Möller, Ralf ; Schenck, Wolfram: Adaptive dimensionality reduction for neural network-based online principal component analysis. In: PLOS ONE Bd. 16, Public Library of Science (PLoS) (2021), Nr. 3","chicago":"Migenda, Nico, Ralf Möller, and Wolfram Schenck. “Adaptive Dimensionality Reduction for Neural Network-Based Online Principal Component Analysis.” PLOS ONE 16, no. 3 (2021). https://doi.org/10.1371/journal.pone.0248896.","mla":"Migenda, Nico, et al. “Adaptive Dimensionality Reduction for Neural Network-Based Online Principal Component Analysis.” PLOS ONE, vol. 16, no. 3, e0248896, Public Library of Science (PLoS), 2021, doi:10.1371/journal.pone.0248896.","ama":"Migenda N, Möller R, Schenck W. Adaptive dimensionality reduction for neural network-based online principal component analysis. PLOS ONE. 2021;16(3). doi:10.1371/journal.pone.0248896","short":"N. Migenda, R. Möller, W. Schenck, PLOS ONE 16 (2021).","apa":"Migenda, N., Möller, R., & Schenck, W. (2021). Adaptive dimensionality reduction for neural network-based online principal component analysis. PLOS ONE, 16(3). https://doi.org/10.1371/journal.pone.0248896"},"language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"doi":"10.1016/j.swevo.2021.100952","citation":{"apa":"Tharwat, A., & Schenck, W. (2021). Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques. Swarm and Evolutionary Computation, 67. https://doi.org/10.1016/j.swevo.2021.100952","short":"A. Tharwat, W. Schenck, Swarm and Evolutionary Computation 67 (2021).","mla":"Tharwat, Alaa, and Wolfram Schenck. “Population Initialization Techniques for Evolutionary Algorithms for Single-Objective Constrained Optimization Problems: Deterministic vs. Stochastic Techniques.” Swarm and Evolutionary Computation, vol. 67, 100952, Elsevier BV, 2021, doi:10.1016/j.swevo.2021.100952.","ama":"Tharwat A, Schenck W. Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques. Swarm and Evolutionary Computation. 2021;67. doi:10.1016/j.swevo.2021.100952","alphadin":"Tharwat, Alaa ; Schenck, Wolfram: Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques. In: Swarm and Evolutionary Computation Bd. 67, Elsevier BV (2021)","chicago":"Tharwat, Alaa, and Wolfram Schenck. “Population Initialization Techniques for Evolutionary Algorithms for Single-Objective Constrained Optimization Problems: Deterministic vs. Stochastic Techniques.” Swarm and Evolutionary Computation 67 (2021). https://doi.org/10.1016/j.swevo.2021.100952.","bibtex":"@article{Tharwat_Schenck_2021, title={Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques}, volume={67}, DOI={10.1016/j.swevo.2021.100952}, number={100952}, journal={Swarm and Evolutionary Computation}, publisher={Elsevier BV}, author={Tharwat, Alaa and Schenck, Wolfram}, year={2021} }","ieee":"A. Tharwat and W. Schenck, “Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques,” Swarm and Evolutionary Computation, vol. 67, 2021."},"article_number":"100952","author":[{"last_name":"Tharwat","full_name":"Tharwat, Alaa","first_name":"Alaa"},{"orcid":"0000-0003-3300-2048","id":"224375","full_name":"Schenck, Wolfram","first_name":"Wolfram","last_name":"Schenck"}],"publication_identifier":{"issn":["22106502"]},"publication_status":"published","_id":"2777","date_created":"2023-04-18T21:54:23Z","title":"Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques","status":"public","date_updated":"2023-04-19T06:09:24Z","volume":67,"publisher":"Elsevier BV","user_id":"216066","publication":"Swarm and Evolutionary Computation","type":"journal_article","intvolume":" 67","year":"2021"},{"year":"2021","intvolume":" 167","type":"journal_article","publisher":"Elsevier BV","volume":167,"publication":"Expert Systems with Applications","user_id":"237837","date_updated":"2021-06-03T19:41:15Z","status":"public","title":"A conceptual and practical comparison of PSO-style optimization algorithms","date_created":"2021-06-03T19:35:47Z","publication_status":"published","_id":"1202","article_number":"114430","author":[{"last_name":"Tharwat","full_name":"Tharwat, Alaa","first_name":"Alaa"},{"last_name":"Schenck","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-3300-2048/work/94914470","full_name":"Schenck, Wolfram","first_name":"Wolfram","orcid":"0000-0003-3300-2048","id":"224375"}],"publication_identifier":{"issn":["09574174"]},"doi":"10.1016/j.eswa.2020.114430","citation":{"short":"A. Tharwat, W. Schenck, Expert Systems with Applications 167 (2021).","apa":"Tharwat, A., & Schenck, W. (2021). A conceptual and practical comparison of PSO-style optimization algorithms. Expert Systems with Applications, 167. https://doi.org/10.1016/j.eswa.2020.114430","mla":"Tharwat, Alaa, and Wolfram Schenck. “A Conceptual and Practical Comparison of PSO-Style Optimization Algorithms.” Expert Systems with Applications, vol. 167, 114430, Elsevier BV, 2021, doi:10.1016/j.eswa.2020.114430.","ama":"Tharwat A, Schenck W. A conceptual and practical comparison of PSO-style optimization algorithms. Expert Systems with Applications. 2021;167. doi:10.1016/j.eswa.2020.114430","alphadin":"Tharwat, Alaa ; Schenck, Wolfram: A conceptual and practical comparison of PSO-style optimization algorithms. In: Expert Systems with Applications Bd. 167, Elsevier BV (2021)","chicago":"Tharwat, Alaa, and Wolfram Schenck. “A Conceptual and Practical Comparison of PSO-Style Optimization Algorithms.” Expert Systems with Applications 167 (2021). https://doi.org/10.1016/j.eswa.2020.114430.","bibtex":"@article{Tharwat_Schenck_2021, title={A conceptual and practical comparison of PSO-style optimization algorithms}, volume={167}, DOI={10.1016/j.eswa.2020.114430}, number={114430}, journal={Expert Systems with Applications}, publisher={Elsevier BV}, author={Tharwat, Alaa and Schenck, Wolfram}, year={2021} }","ieee":"A. Tharwat and W. Schenck, “A conceptual and practical comparison of PSO-style optimization algorithms,” Expert Systems with Applications, vol. 167, 2021."},"language":[{"iso":"eng"}]},{"date_updated":"2023-05-30T15:14:55Z","publisher":"Cold Spring Harbor Laboratory","user_id":"245590","type":"working_paper","oa":"1","main_file_link":[{"open_access":"1","url":"https://doi.org/10.1101/2020.10.27.352633"}],"year":"2020","language":[{"iso":"eng"}],"doi":"https://doi.org/10.1101/2020.10.27.352633","citation":{"alphadin":"Shah, Zafran Hussain ; Müller, Marcel ; Wang, Tung-Cheng ; Scheidig, Philip Maurice ; Schneider, Axel ; Schüttpelz, Mark ; Huser, Thomas ; Schenck, Wolfram: Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images : Cold Spring Harbor Laboratory, 2020","chicago":"Shah, Zafran Hussain, Marcel Müller, Tung-Cheng Wang, Philip Maurice Scheidig, Axel Schneider, Mark Schüttpelz, Thomas Huser, and Wolfram Schenck. Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images. Cold Spring Harbor Laboratory, 2020. https://doi.org/10.1101/2020.10.27.352633.","bibtex":"@book{Shah_Müller_Wang_Scheidig_Schneider_Schüttpelz_Huser_Schenck_2020, title={Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images}, DOI={https://doi.org/10.1101/2020.10.27.352633}, publisher={Cold Spring Harbor Laboratory}, author={Shah, Zafran Hussain and Müller, Marcel and Wang, Tung-Cheng and Scheidig, Philip Maurice and Schneider, Axel and Schüttpelz, Mark and Huser, Thomas and Schenck, Wolfram}, year={2020} }","ieee":"Z. H. Shah et al., Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images. Cold Spring Harbor Laboratory, 2020.","apa":"Shah, Z. H., Müller, M., Wang, T.-C., Scheidig, P. M., Schneider, A., Schüttpelz, M., … Schenck, W. (2020). Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images. Cold Spring Harbor Laboratory. https://doi.org/10.1101/2020.10.27.352633","short":"Z.H. Shah, M. Müller, T.-C. Wang, P.M. Scheidig, A. Schneider, M. Schüttpelz, T. Huser, W. Schenck, Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images, Cold Spring Harbor Laboratory, 2020.","mla":"Shah, Zafran Hussain, et al. Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images. Cold Spring Harbor Laboratory, 2020, doi:https://doi.org/10.1101/2020.10.27.352633.","ama":"Shah ZH, Müller M, Wang T-C, et al. Deep-Learning Based Denoising and Reconstruction of Super-Resolution Structured Illumination Microscopy Images. Cold Spring Harbor Laboratory; 2020. doi:https://doi.org/10.1101/2020.10.27.352633"},"author":[{"id":"239296","full_name":"Shah, Zafran Hussain","first_name":"Zafran Hussain","last_name":"Shah"},{"last_name":"Müller","first_name":"Marcel","full_name":"Müller, Marcel"},{"last_name":"Wang","full_name":"Wang, Tung-Cheng","first_name":"Tung-Cheng"},{"last_name":"Scheidig","full_name":"Scheidig, Philip Maurice","first_name":"Philip Maurice"},{"last_name":"Schneider","first_name":"Axel","full_name":"Schneider, Axel","id":"213480","orcid":"0000-0002-6632-3473"},{"first_name":"Mark","full_name":"Schüttpelz, Mark","last_name":"Schüttpelz"},{"full_name":"Huser, Thomas","first_name":"Thomas","last_name":"Huser"},{"id":"224375","orcid":"0000-0003-3300-2048","last_name":"Schenck","first_name":"Wolfram","full_name":"Schenck, Wolfram"}],"publication_status":"published","_id":"2778","date_created":"2023-04-18T21:54:24Z","title":"Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images","project":[{"name":"CareTech OWL - Zentrum für Gesundheit, Soziales und Technologie","_id":"72dfeb62-b436-11ed-9513-f39505d26204"},{"_id":"edf53067-b368-11ed-bde2-9f34a4102af5","name":"TransCareTech - Transformation in Care & Technology"},{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"status":"public","abstract":[{"lang":"eng","text":" Abstract - \r\n Super-resolution structured illumination microscopy (SR-SIM) provides an up to two-fold enhanced spatial resolution of fluorescently labeled samples. The reconstruction of high quality SR-SIM images critically depends on patterned illumination with high modulation contrast. Noisy raw image data, e.g. as a result of low excitation power or low exposure times, result in reconstruction artifacts. Here, we demonstrate deep-learning based SR-SIM image denoising that results in high quality reconstructed images. A residual encoding-decoding convolution neural network (RED-Net) was used to successfully denoise computationally reconstructed noisy SR-SIM images. We also demonstrate the entirely deep-learning based denoising and reconstruction of raw SIM images into high-resolution SR-SIM images. Both image reconstruction methods prove to be very robust against image reconstruction artifacts and generalize very well over various noise levels. The combination of computational reconstruction and subsequent denoising via RED-Net shows very robust performance during inference after training even if the microscope settings change.\r\n "}]},{"publication":"2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","user_id":"249199","publisher":"IEEE","date_updated":"2023-05-10T13:39:56Z","year":"2020","type":"conference","author":[{"orcid":"0000-0002-7223-1735","id":"218473","last_name":"Migenda","full_name":"Migenda, Nico","first_name":"Nico"},{"last_name":"Schenck","full_name":"Schenck, Wolfram","first_name":"Wolfram","orcid":"0000-0003-3300-2048","id":"224375"}],"publication_identifier":{"eisbn":["978-1-7281-8956-7"]},"page":"1579-1586","citation":{"apa":"Migenda, N., & Schenck, W. (2020). Adaptive Dimensionality Reduction for Local Principal Component Analysis. In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) (pp. 1579–1586). Vienna, Austria: IEEE. https://doi.org/10.1109/ETFA46521.2020.9212129","short":"N. Migenda, W. Schenck, in: 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2020, pp. 1579–1586.","ama":"Migenda N, Schenck W. Adaptive Dimensionality Reduction for Local Principal Component Analysis. In: 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE; 2020:1579-1586. doi:10.1109/ETFA46521.2020.9212129","mla":"Migenda, Nico, and Wolfram Schenck. “Adaptive Dimensionality Reduction for Local Principal Component Analysis.” 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2020, pp. 1579–86, doi:10.1109/ETFA46521.2020.9212129.","chicago":"Migenda, Nico, and Wolfram Schenck. “Adaptive Dimensionality Reduction for Local Principal Component Analysis.” In 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 1579–86. IEEE, 2020. https://doi.org/10.1109/ETFA46521.2020.9212129.","alphadin":"Migenda, Nico ; Schenck, Wolfram: Adaptive Dimensionality Reduction for Local Principal Component Analysis. In: 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) : IEEE, 2020, S. 1579–1586","ieee":"N. Migenda and W. Schenck, “Adaptive Dimensionality Reduction for Local Principal Component Analysis,” in 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 2020, pp. 1579–1586.","bibtex":"@inproceedings{Migenda_Schenck_2020, title={Adaptive Dimensionality Reduction for Local Principal Component Analysis}, DOI={10.1109/ETFA46521.2020.9212129}, booktitle={2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)}, publisher={IEEE}, author={Migenda, Nico and Schenck, Wolfram}, year={2020}, pages={1579–1586} }"},"doi":"10.1109/ETFA46521.2020.9212129","language":[{"iso":"eng"}],"conference":{"location":"Vienna, Austria","name":"2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)"},"status":"public","date_created":"2023-03-10T08:41:14Z","title":"Adaptive Dimensionality Reduction for Local Principal Component Analysis","publication_status":"published","_id":"2574"},{"type":"journal_article","intvolume":" 210","year":"2020","date_updated":"2021-06-03T19:41:09Z","publisher":"Elsevier BV","volume":210,"user_id":"237837","publication":"Knowledge-Based Systems","_id":"1204","publication_status":"published","title":"Balancing Exploration and Exploitation: A novel active learner for imbalanced data","date_created":"2021-06-03T19:35:50Z","status":"public","language":[{"iso":"eng"}],"citation":{"ama":"Tharwat A, Schenck W. Balancing Exploration and Exploitation: A novel active learner for imbalanced data. Knowledge-Based Systems. 2020;210. doi:10.1016/j.knosys.2020.106500","mla":"Tharwat, Alaa, and Wolfram Schenck. “Balancing Exploration and Exploitation: A Novel Active Learner for Imbalanced Data.” Knowledge-Based Systems, vol. 210, 106500, Elsevier BV, 2020, doi:10.1016/j.knosys.2020.106500.","apa":"Tharwat, A., & Schenck, W. (2020). Balancing Exploration and Exploitation: A novel active learner for imbalanced data. Knowledge-Based Systems, 210. https://doi.org/10.1016/j.knosys.2020.106500","short":"A. Tharwat, W. Schenck, Knowledge-Based Systems 210 (2020).","ieee":"A. Tharwat and W. Schenck, “Balancing Exploration and Exploitation: A novel active learner for imbalanced data,” Knowledge-Based Systems, vol. 210, 2020.","bibtex":"@article{Tharwat_Schenck_2020, title={Balancing Exploration and Exploitation: A novel active learner for imbalanced data}, volume={210}, DOI={10.1016/j.knosys.2020.106500}, number={106500}, journal={Knowledge-Based Systems}, publisher={Elsevier BV}, author={Tharwat, Alaa and Schenck, Wolfram}, year={2020} }","chicago":"Tharwat, Alaa, and Wolfram Schenck. “Balancing Exploration and Exploitation: A Novel Active Learner for Imbalanced Data.” Knowledge-Based Systems 210 (2020). https://doi.org/10.1016/j.knosys.2020.106500.","alphadin":"Tharwat, Alaa ; Schenck, Wolfram: Balancing Exploration and Exploitation: A novel active learner for imbalanced data. In: Knowledge-Based Systems Bd. 210, Elsevier BV (2020)"},"doi":"10.1016/j.knosys.2020.106500","article_number":"106500","author":[{"last_name":"Tharwat","full_name":"Tharwat, Alaa","first_name":"Alaa"},{"orcid":"0000-0003-3300-2048","id":"224375","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-3300-2048/work/94914460","full_name":"Schenck, Wolfram","first_name":"Wolfram","last_name":"Schenck"}],"publication_identifier":{"issn":["09507051"]}}]