TY - JOUR A1 - Landwehr, Niels A1 - Kuehn, Nicolas M. A1 - Scheffer, Tobias A1 - Abrahamson, Norman A. T1 - A Nonergodic Ground-Motion Model for California with Spatially Varying Coefficients JF - Bulletin of the Seismological Society of America N2 - Traditional probabilistic seismic-hazard analysis as well as the estimation of ground-motion models (GMMs) is based on the ergodic assumption, which means that the distribution of ground motions over time at a given site is the same as their spatial distribution over all sites for the same magnitude, distance, and site condition. With a large increase in the number of recorded ground-motion data, there are now repeated observations at given sites and from multiple earthquakes in small regions, so that assumption can be relaxed. We use a novel approach to develop a nonergodic GMM, which is cast as a varying-coefficient model (VCM). In this model, the coefficients are allowed to vary by geographical location, which makes it possible to incorporate effects of spatially varying source, path, and site conditions. Hence, a separate set of coefficients is estimated for each source and site coordinate in the data set. The coefficients are constrained to be similar for spatially nearby locations. This is achieved by placing a Gaussian process prior on the coefficients. The amount of correlation is determined by the data. The spatial correlation structure of the model allows one to extrapolate the varying coefficients to a new location and trace the corresponding uncertainties. The approach is illustrated with the Next Generation Attenuation-West2 data set, using only Californian records. The VCM outperforms a traditionally estimated GMM in terms of generalization error and leads to a reduction in the aleatory standard deviation by similar to 40%, which has important implications for seismic-hazard calculations. The scaling of the model with respect to its predictor variables such as magnitude and distance is physically plausible. The epistemic uncertainty associated with the predicted ground motions is small in places where events or stations are close and large where data are sparse. Y1 - 2016 U6 - https://doi.org/10.1785/0120160118 SN - 0037-1106 SN - 1943-3573 VL - 106 SP - 2574 EP - 2583 PB - Seismological Society of America CY - Albany ER - TY - JOUR A1 - Sawade, Christoph A1 - Bickel, Steffen A1 - von Oertzen, Timo A1 - Scheffer, Tobias A1 - Landwehr, Niels T1 - Active evaluation of ranking functions based on graded relevance JF - Machine learning N2 - Evaluating the quality of ranking functions is a core task in web search and other information retrieval domains. Because query distributions and item relevance change over time, ranking models often cannot be evaluated accurately on held-out training data. Instead, considerable effort is spent on manually labeling the relevance of query results for test queries in order to track ranking performance. We address the problem of estimating ranking performance as accurately as possible on a fixed labeling budget. Estimates are based on a set of most informative test queries selected by an active sampling distribution. Query labeling costs depend on the number of result items as well as item-specific attributes such as document length. We derive cost-optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs. KW - Information retrieval KW - Ranking KW - Active evaluation Y1 - 2013 U6 - https://doi.org/10.1007/s10994-013-5372-5 SN - 0885-6125 VL - 92 IS - 1 SP - 41 EP - 64 PB - Springer CY - Dordrecht ER - TY - JOUR A1 - Abdelwahab, Ahmed A1 - Landwehr, Niels T1 - Deep Distributional Sequence Embeddings Based on a Wasserstein Loss JF - Neural processing letters N2 - Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a feature vector produced by a deep neural network and Euclidean distance or cosine similarity defines distances between these vectors. This paper studies deep distributional embeddings of sequences, where the embedding of a sequence is given by the distribution of learned deep features across the sequence. The motivation for this is to better capture statistical information about the distribution of patterns within the sequence in the embedding. When embeddings are distributions rather than vectors, measuring distances between embeddings involves comparing their respective distributions. The paper therefore proposes a distance metric based on Wasserstein distances between the distributions and a corresponding loss function for metric learning, which leads to a novel end-to-end trainable embedding model. We empirically observe that distributional embeddings outperform standard vector embeddings and that training with the proposed Wasserstein metric outperforms training with other distance functions. KW - Metric learning KW - Sequence embeddings KW - Deep learning Y1 - 2022 U6 - https://doi.org/10.1007/s11063-022-10784-y SN - 1370-4621 SN - 1573-773X PB - Springer CY - Dordrecht ER - TY - JOUR A1 - Schirrmann, Michael A1 - Landwehr, Niels A1 - Giebel, Antje A1 - Garz, Andreas A1 - Dammer, Karl-Heinz T1 - Early detection of stripe rust in winter wheat using deep residual neural networks JF - Frontiers in plant science : FPLS N2 - Stripe rust (Pst) is a major disease of wheat crops leading untreated to severe yield losses. The use of fungicides is often essential to control Pst when sudden outbreaks are imminent. Sensors capable of detecting Pst in wheat crops could optimize the use of fungicides and improve disease monitoring in high-throughput field phenotyping. Now, deep learning provides new tools for image recognition and may pave the way for new camera based sensors that can identify symptoms in early stages of a disease outbreak within the field. The aim of this study was to teach an image classifier to detect Pst symptoms in winter wheat canopies based on a deep residual neural network (ResNet). For this purpose, a large annotation database was created from images taken by a standard RGB camera that was mounted on a platform at a height of 2 m. Images were acquired while the platform was moved over a randomized field experiment with Pst-inoculated and Pst-free plots of winter wheat. The image classifier was trained with 224 x 224 px patches tiled from the original, unprocessed camera images. The image classifier was tested on different stages of the disease outbreak. At patch level the image classifier reached a total accuracy of 90%. To test the image classifier on image level, the image classifier was evaluated with a sliding window using a large striding length of 224 px allowing for fast test performance. At image level, the image classifier reached a total accuracy of 77%. Even in a stage with very low disease spreading (0.5%) at the very beginning of the Pst outbreak, a detection accuracy of 57% was obtained. Still in the initial phase of the Pst outbreak with 2 to 4% of Pst disease spreading, detection accuracy with 76% could be attained. With further optimizations, the image classifier could be implemented in embedded systems and deployed on drones, vehicles or scanning systems for fast mapping of Pst outbreaks. KW - yellow rust KW - monitoring KW - deep learning KW - wheat crops KW - image recognition KW - camera sensor KW - ResNet KW - smart farming Y1 - 2021 U6 - https://doi.org/10.3389/fpls.2021.469689 SN - 1664-462X VL - 12 PB - Frontiers Media CY - Lausanne ER - TY - JOUR A1 - Landwehr-Kenzel, Sybille A1 - Zobel, Anne A1 - Hoffmann, Henrike A1 - Landwehr, Niels A1 - Schmueck-Henneresse, Michael A1 - Schachtner, Thomas A1 - Roemhild, Andy A1 - Reinke, Petra T1 - Ex vivo expanded natural regulatory T cells from patients with end-stage renal disease or kidney transplantation are useful for autologous cell therapy JF - Kidney international : official journal of the International Society of Nephrology N2 - Novel concepts employing autologous, ex vivo expanded natural regulatory T cells (nTreg) for adoptive transfer has potential to prevent organ rejection after kidney transplantation. However, the impact of dialysis and maintenance immunosuppression on the nTreg phenotype and peripheral survival is not well understood, but essential when assessing patient eligibility. The current study investigates regulatory T-cells in dialysis and kidney transplanted patients and the feasibility of generating a clinically useful nTreg product from these patients. Heparinized blood from 200 individuals including healthy controls, dialysis patients with end stage renal disease and patients 1, 5, 10, 15, 20 years after kidney transplantation were analyzed. Differentiation and maturation of nTregs were studied by flow cytometry in order to compare dialysis patients and kidney transplanted patients under maintenance immunosuppression to healthy controls. CD127 expressing CD4(+)CD25(high)FoxP3(+) nTregs were detectable at increased frequencies in dialysis patients with no negative impact on the nTreg end product quality and therapeutic usefulness of the ex vivo expanded nTregs. Further, despite that immunosuppression mildly altered nTreg maturation, neither dialysis nor pharmacological immunosuppression or previous acute rejection episodes impeded nTreg survival in vivo. Accordingly, the generation of autologous, highly pure nTreg products is feasible and qualifies patients awaiting or having received allogenic kidney transplantation for adoptive nTreg therapy. Thus, our novel treatment approach may enable us to reduce the incidence of organ rejection and reduce the need of long-term immunosuppression. KW - adoptive T-cell transfer KW - autologous cell therapy KW - end-stage renal disease KW - kidney transplantation KW - regulatory T cells Y1 - 2018 U6 - https://doi.org/10.1016/j.kint.2018.01.021 SN - 0085-2538 SN - 1523-1755 VL - 93 IS - 6 SP - 1452 EP - 1464 PB - Elsevier CY - New York ER - TY - JOUR A1 - Drimalla, Hanna A1 - Landwehr, Niels A1 - Hess, Ursula A1 - Dziobek, Isabel T1 - From face to face BT - the contribution of facial mimicry to cognitive and emotional empathy JF - Cognition and Emotion N2 - Despite advances in the conceptualisation of facial mimicry, its role in the processing of social information is a matter of debate. In the present study, we investigated the relationship between mimicry and cognitive and emotional empathy. To assess mimicry, facial electromyography was recorded for 70 participants while they completed the Multifaceted Empathy Test, which presents complex context-embedded emotional expressions. As predicted, inter-individual differences in emotional and cognitive empathy were associated with the level of facial mimicry. For positive emotions, the intensity of the mimicry response scaled with the level of state emotional empathy. Mimicry was stronger for the emotional empathy task compared to the cognitive empathy task. The specific empathy condition could be successfully detected from facial muscle activity at the level of single individuals using machine learning techniques. These results support the view that mimicry occurs depending on the social context as a tool to affiliate and it is involved in cognitive as well as emotional empathy. KW - Facial mimicry KW - empathy KW - emotional KW - cognitive KW - complex emotions Y1 - 2019 U6 - https://doi.org/10.1080/02699931.2019.1596068 SN - 0269-9931 SN - 1464-0600 VL - 33 IS - 8 SP - 1672 EP - 1686 PB - Routledge, Taylor & Francis Group CY - Abingdon ER - TY - JOUR A1 - Hempel, Sabrina A1 - Adolphs, Julian A1 - Landwehr, Niels A1 - Janke, David A1 - Amon, Thomas T1 - How the selection of training data and modeling approach affects the estimation of ammonia emissions from a naturally ventilated dairy barn—classical statistics versus machine learning JF - Sustainability N2 - Environmental protection efforts can only be effective in the long term with a reliable quantification of pollutant gas emissions as a first step to mitigation. Measurement and analysis strategies must permit the accurate extrapolation of emission values. We systematically analyzed the added value of applying modern machine learning methods in the process of monitoring emissions from naturally ventilated livestock buildings to the atmosphere. We considered almost 40 weeks of hourly emission values from a naturally ventilated dairy cattle barn in Northern Germany. We compared model predictions using 27 different scenarios of temporal sampling, multiple measures of model accuracy, and eight different regression approaches. The error of the predicted emission values with the tested measurement protocols was, on average, well below 20%. The sensitivity of the prediction to the selected training dataset was worse for the ordinary multilinear regression. Gradient boosting and random forests provided the most accurate and robust emission value predictions, accompanied by the second-smallest model errors. Most of the highly ranked scenarios involved six measurement periods, while the scenario with the best overall performance was: One measurement period in summer and three in the transition periods, each lasting for 14 days. KW - livestock KW - air pollutant KW - emission modeling KW - emission inventory KW - regression KW - artificial neural network KW - random forest KW - gradient boosting KW - Gaussian process KW - training sample Y1 - 2020 U6 - https://doi.org/10.3390/su12031030 SN - 2071-1050 VL - 12 IS - 3 PB - MDPI CY - Basel ER - TY - JOUR A1 - Gautam, Khem Raj A1 - Zhang, Guoqiang A1 - Landwehr, Niels A1 - Adolphs, Julian T1 - Machine learning for improvement of thermal conditions inside a hybrid ventilated animal building JF - Computers and electronics in agriculture : COMPAG online ; an international journal N2 - In buildings with hybrid ventilation, natural ventilation opening positions (windows), mechanical ventilation rates, heating, and cooling are manipulated to maintain desired thermal conditions. The indoor temperature is regulated solely by ventilation (natural and mechanical) when the external conditions are favorable to save external heating and cooling energy. The ventilation parameters are determined by a rule-based control scheme, which is not optimal. This study proposes a methodology to enable real-time optimum control of ventilation parameters. We developed offline prediction models to estimate future thermal conditions from the data collected from building in operation. The developed offline model is then used to find the optimal controllable ventilation parameters in real-time to minimize the setpoint deviation in the building. With the proposed methodology, the experimental building's setpoint deviation improved for 87% of time, on average, by 0.53 degrees C compared to the current deviations. KW - Animal building KW - Natural ventilation KW - Automatically controlled windows KW - Machine learning KW - Optimization Y1 - 2021 U6 - https://doi.org/10.1016/j.compag.2021.106259 SN - 0168-1699 SN - 1872-7107 VL - 187 PB - Elsevier Science CY - Amsterdam [u.a.] ER - TY - JOUR A1 - Camargo, Tibor de A1 - Schirrmann, Michael A1 - Landwehr, Niels A1 - Dammer, Karl-Heinz A1 - Pflanz, Michael T1 - Optimized deep learning model as a basis for fast UAV mapping of weed species in winter wheat crops JF - Remote sensing / Molecular Diversity Preservation International (MDPI) N2 - Weed maps should be available quickly, reliably, and with high detail to be useful for site-specific management in crop protection and to promote more sustainable agriculture by reducing pesticide use. Here, the optimization of a deep residual convolutional neural network (ResNet-18) for the classification of weed and crop plants in UAV imagery is proposed. The target was to reach sufficient performance on an embedded system by maintaining the same features of the ResNet-18 model as a basis for fast UAV mapping. This would enable online recognition and subsequent mapping of weeds during UAV flying operation. Optimization was achieved mainly by avoiding redundant computations that arise when a classification model is applied on overlapping tiles in a larger input image. The model was trained and tested with imagery obtained from a UAV flight campaign at low altitude over a winter wheat field, and classification was performed on species level with the weed species Matricaria chamomilla L., Papaver rhoeas L., Veronica hederifolia L., and Viola arvensis ssp. arvensis observed in that field. The ResNet-18 model with the optimized image-level prediction pipeline reached a performance of 2.2 frames per second with an NVIDIA Jetson AGX Xavier on the full resolution UAV image, which would amount to about 1.78 ha h(-1) area output for continuous field mapping. The overall accuracy for determining crop, soil, and weed species was 94%. There were some limitations in the detection of species unknown to the model. When shifting from 16-bit to 32-bit model precision, no improvement in classification accuracy was observed, but a strong decline in speed performance, especially when a higher number of filters was used in the ResNet-18 model. Future work should be directed towards the integration of the mapping process on UAV platforms, guiding UAVs autonomously for mapping purpose, and ensuring the transferability of the models to other crop fields. KW - ResNet KW - deep residual networks KW - UAV imagery KW - embedded systems KW - crop KW - monitoring KW - image classification KW - site-specific weed management KW - real-time mapping Y1 - 2021 U6 - https://doi.org/10.3390/rs13091704 SN - 2072-4292 VL - 13 IS - 9 PB - MDPI CY - Basel ER - TY - JOUR A1 - Cilia, Elisa A1 - Landwehr, Niels A1 - Passerini, Andrea T1 - Relational feature mining with hierarchical multitask kFOIL JF - Fundamenta informaticae N2 - We introduce hierarchical kFOIL as a simple extension of the multitask kFOIL learning algorithm. The algorithm first learns a core logic representation common to all tasks, and then refines it by specialization on a per-task basis. The approach can be easily generalized to a deeper hierarchy of tasks. A task clustering algorithm is also proposed in order to automatically generate the task hierarchy. The approach is validated on problems of drug-resistance mutation prediction and protein structural classification. Experimental results show the advantage of the hierarchical version over both single and multi task alternatives and its potential usefulness in providing explanatory features for the domain. Task clustering allows to further improve performance when a deeper hierarchy is considered. Y1 - 2011 U6 - https://doi.org/10.3233/FI-2011-604 SN - 0169-2968 VL - 113 IS - 2 SP - 151 EP - 177 PB - IOS Press CY - Amsterdam ER -