Search

Grammatical knowledge has often been investigated in wug tests, in which participants inflect pseudo-words. It was argued that in inflecting these pseudo-words, speakers apply their knowledge of word formation. However, it remains unclear what exactly this knowledge is and how it is learned. According to one theory, the knowledge is best characterised as abstractions that specify how units are combined. Another theory maintains that it is best characterised by memory-based analogy. In both cases the knowledge is learned by association based on positive evidence alone. In this paper, we model the classification of pseudo-words to Maltese plurals using a shallow neural network trained with an error-driven learning algorithm. We demonstrate that the classifications mirror those of Maltese speakers in a wug test. Our results indicate that speakers rely on gradient knowledge of a relation between the phonetics of whole words and plural classes, which is learned in an error-driven way. [ABSTRACT FROM AUTHOR]

The growing integration of AI in agriculture necessitates access to diverse data sets for training artificial intelligence (AI) systems. Manufacturers often face challenges due to a perceived shortage of valid data sets, highlighting the need for centralized platforms offering high-quality data. While global AI regulations are yet to be established, existing laws govern data collection, creation, labeling, and processing for AI training in various legal systems. The absence of explicit AI laws prompts a call for platforms supplying data to adhere to relevant regulations, especially in areas where AI controls devices interacting with humans, such as collision warning systems in yard tractors and robots. Compliance is crucial, given the complexity of rules governing data sets featuring people, animals, and buildings. The paper focuses on how to check the compliant data sets in Germany's legal context, focusing on situations in farm yards. People are often visible on such data sets; thus, the data set must preserve the right to informational self-determination and one's image, which is prevalent in many legal systems. Images portraying people typically qualify as personal data, requiring careful anonymization to address privacy concerns. The paper uses artificial neural networks (ANN) to remove images that contradict people's rights on one's image; thus, data sets that comply with data protection laws can be created. It also addresses the lesser-explored issue of the right to one's image in German law. Though AI training may not be impeded, dissemination via digital platforms must adhere to legal boundaries, even if metadata is absent. The paper suggests an AI solution to identify images within legal limits, detect violations, and modify them to create a legally compliant data set respecting the right to one's image. • Discussing legal conform data sets for the agricultural application domain. • Providing a data set of 2694 images covering the categories: – class (I) not legally compliant and – class (II) legally compliant on the right to one's image; cf. Fig. 1. • Identifying the gap in ANN data sets and models for law compliance checks. • Train and benchmark ANN models for checking law compliance – on the right to one's image; – cf. Tab. 1, Tab. 2, and Fig. 3. • Promoting the importance of AI-based law compliance checks for – detecting violations against the law and – developing compliant AI systems in agriculture. [ABSTRACT FROM AUTHOR]

Integrating enormous quantities of wind energy into the electrical system requires precise planning and forecasting. This paper presents a novel framework for wind power forecasting, which establishes a new standard for accuracy and reliability. It uses advanced deep neural networks and a stacking ensemble mechanism to make probabilistic forecasts. These forecasts address wind speed volatility and variability, which continue to be key issues in producing consistently accurate wind power forecasts despite advances in deep learning. Base learners generate forecasts that include lower and upper bounds, as well as median prediction intervals. The Huber regressor, also known as the Meta-learner, combines projections from many models to reduce susceptibility to extreme values. Expanding window cross-validation is used in performance evaluation, with a focus on Mean Absolute Error, Mean Squared Error (MSE), Symmetric Mean Absolute Percentage Error, Prediction Interval Coverage Probability, and Average Interval Width for one, two, and three step ahead predictions. The model's stability is measured by the standard deviation of MSE throughout each validation window. Additionally, the Diebold–Mariano test is used to validate the Meta-learner's predictive accuracy in contrast to other advanced models and the seasonal naïve benchmark. This study found that the meta model outperformed all other models in eight of the nine forecasts tested, indicating its effectiveness in medium-range forecasting. In Germany, it exceeded Temporal Fusion Transformer by two and three steps ahead, with 22% and 34% improvements, respectively. Indeed, this study not only provides a reliable prediction tool, but also lays foundations for efficient and effective energy management and policy planning in the renewable energy industry. • Deep neural network architectures are applied to probabilistic wind power forecasting. • Transformer and artificial neural network approaches combined with conformal prediction intervals is proposed. • A window cross-validation scheme on wind power forecasting is evaluated. • Wind power data from Germany, the UK, and the Netherlands are used for forecasting purposes. • SHAP and LIME analyses perform the explanatory analysis of the variables in the meta-learner's predictions. [ABSTRACT FROM AUTHOR]

• Soil reflectance composites were generated with Sentinel-2 L2A data. • A multi-channel CNN learning framework for soil organic carbon prediction is proposed. • A dual input deep learning architecture improves the predictions. • The framework produced results that can be interpreted. The Copernicus Sentinel-2 multispectral imagery data may be aggregated to extract large-scale, bare soil, reflectance composites, which enable soil mapping applications. In this paper, this approach was tested in the German federal state of Bavaria, to provide estimations for soil organic carbon (SOC). Different temporal ranges were considered for the generation of the composites, including multi-annual and seasonal ranges. A novel multi-channel convolutional neural network (CNN) is proposed. By leveraging the advantages of deep learning techniques, it utilizes complementary information from different spectral pre-treatment techniques. The SOC predictions indicated little dissimilarity amongst the different composites, with the best performance attained for the six-year composite containing only spring months (RMSE = 12.03 g C · kg−1, R2 = 0.64, RPIQ = 0.89). It has been demonstrated that these outcomes outperform other well-known machine learning techniques. An ablation analysis was accordingly performed to evaluate the interplay of the CNN's different components to disentangle the advantages of each aspect of the proposed framework. Finally, a DUal inPut deep LearnIng architecture, named DUPLICITE, is proposed, which concatenates deep spectral features derived from the CNN mentioned earlier, as well as topographical and environmental covariates through an artificial neural network (ANN) to exploit their complementarity. The proposed approach was demonstrated to provide an improvement in the overall prediction performance (RMSE = 11.60 gC · kg−1, R2 = 0.67, RPIQ = 0.92). [ABSTRACT FROM AUTHOR]

Evidence-based STI (science, technology, and innovation) policy making requires accurate indicators of innovation in order to promote economic growth. However, traditional indicators from patents and questionnaire-based surveys often lack coverage, granularity as well as timeliness and may involve high data collection costs, especially when conducted at a large scale. Consequently, they struggle to provide policy makers and scientists with the full picture of the current state of the innovation system. In this paper, we propose a first approach on generating web-based innovation indicators which may have the potential to overcome some of the shortcomings of traditional indicators. Specifically, we develop a method to identify product innovator firms at a large scale and very low costs. We use traditional firm-level indicators from a questionnaire-based innovation survey (German Community Innovation Survey) to train an artificial neural network classification model on labelled (product innovator/no product innovator) web texts of surveyed firms. Subsequently, we apply this classification model to the web texts of hundreds of thousands of firms in Germany to predict whether they are product innovators or not. We then compare these predictions to firm-level patent statistics, survey extrapolation benchmark data, and regional innovation indicators. The results show that our approach produces reliable predictions and has the potential to be a valuable and highly cost-efficient addition to the existing set of innovation indicators, especially due to its coverage and regional granularity. [ABSTRACT FROM AUTHOR]

The estimation of the electrical power output and energy yield of high concentration photovoltaic (HCPV) modules is a hard task because of the many parameters involved. In this work, we propose the usage of an Artificial Neural Networks (ANN) method to estimate the maximum power output of a FLATCON® CPV-module manufactured by Fraunhofer ISE. The advantage of the ANN is that it is a part of the Artificial Intelligence Deep Learning domain, which makes it easy to model complex systems. A detailed knowledge about the underlying module technology is not necessary. In this work, various meteorological parameters are tested as inputs of the ANN including spectral matching ratios for considering the spectral variation of the solar irradiance to evaluate the maximum power output of the HCPV module under study. Eleven scenarios considering different combinations of input parameters have been investigated. It is demonstrated that the ANN gives excellent results and allows for an accurate prediction of the HCPV module's instantaneous power output with only a few amount of data used on training the ANN. The model has been tested using the measured data set of a FLATCON® CPV-module located on the rooftop of the Fraunhofer ISE in Freiburg, Germany. The module has been electrically characterized outdoors in the period from April 2013 to April 2014. The accuracy of the proposed ANN approach was analyzed using this measurement data in combination with error metrics. It was found that the best agreement between the measured and the predicted maximum power output was achieved when using direct normal irradiance, wind speed, ambient temperature and spectral matching ratios as input. The normalized root mean square error for the maximum power output over one year is found to be between 2.2 and 4.6%. The deviation of the modelled energy yield to the measured one is in the range of 0.2–2.2%. • We use ANN method to predict the maximum power output of a FLATCON® CPV-module. • The accuracy of model used was validated through measurements and metrics errors. • The spectral effect of DNI through the use of SMRs has improved the model performance. • The knowledge of module technology is not necessary for performance prediction. • Only small amount of data are needed for performance prediction using this approach. Short Abstract: This paper uses the artificial Neural Networks model to estimate the electrical power and the energy yield of high concentration photovoltaic modules. The model has been verified using a whole year measurement data of power output of FLATCON CPV Module manufactured by Fraunhofer ISE, Germany. A best agreement between the measured and computed energy output was found trough the analysis of eleven scenarios where different input parameters were combined. [ABSTRACT FROM AUTHOR]

Abstract Background Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field. Methods An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC). Results Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1%, specificity of 60.0% and an ROC of 0.67 (range = 0.538–0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4%, specificity of 64.4% and an ROC of 0.769 (range = 0.613–0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark. Conclusions We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification. Highlights • This paper provides the first open access melanoma classification benchmark for both non-dermoscopic and dermoscopic images. • Algorithms can now be easily compared to the performance of dermatologists in terms of sensitivity, specificity and ROC. • The melanoma benchmark allows comparability between algorithms of different publications and provides a new reference standard. [ABSTRACT FROM AUTHOR]

Weather is a pivotal factor for crop production as it is highly volatile and can hardly be controlled by farm management practices. Since there is a tendency towards increased weather extremes in the future, understanding weather-related yield factors becomes increasingly important not only for yield prediction, but also for the design of insurance products. Although insurance products mitigate financial losses for farmers, they suffer from considerable basis risk, i.e., a discrepancy between losses and the indemnity payment. The objective of this paper was to explore the potential of machine learning for estimating the relationship between crop yield and weather conditions at the farm level and to use it as a tool for reducing basis risk in index insurance applications. An artificial neural network was set up and calibrated to a rich set of farm-level yield data in Germany, covering the period from 2003 to 2018. A nonlinear regression model, which uses rainfall, temperature, and soil moisture as explanatory variables for yield deviations, served as a benchmark. The empirical application revealed that compared with traditional estimation approaches, the gain in forecasting precision by using machine learning techniques was substantial. Moreover, the use of regionalized models and disaggregated high-resolution weather data improved the performance of artificial neural networks. A considerable part of yield variability at the farm level, however, could not be captured by statistical methods which solely use "big weather data". Our findings have important implications for the design of weather-index based insurance because they document that a rather high level of basis risk remains if insurance products are based on an estimation of the weather-yield relationship. [Display omitted] • Due to increasing weather extremes in the future, understanding weather-related yield factors becomes more important. • This paper explores the potential of machine learning for estimating farm-level yield losses and basis risk reduction. • Use of high-resolution weather data improves the performance of artificial neural networks for estimating yield losses. • More homogenous insurance zones can reduce the basis risk and improve estimation precision. • The findings have implications for the design of weather-index based insurances because a rather high level of basis risk remains. [ABSTRACT FROM AUTHOR]

In this paper, we present a review of various computational experiments concerning neural network (NN) models developed for regional employment forecasting. NNs are nowadays widely used in several fields because of their flexible specification structure. A series of NN experiments is presented in the paper, using two data sets on German NUTS-3 districts. Individual forecasts are computed by our models for each district in order to answer the following question: How relevant are NN parameters in comparison to NN structure? Comprehensive testing of these parameters is limited in the literature. Building on different specifications of NN models-in terms of explanatory variables and NN structures-we propose a systematic choice of NN learning parameters and internal functions by means of a sensitivity analysis. Our results show that different combinations of NN parameters provide significantly varying statistical performance and forecasting power. Finally, we note that the sets of parameters chosen for a given model specification cannot be light-heartedly applied to different or more complex models. [ABSTRACT FROM AUTHOR]

• This paper explores probabilistic extensions to Deep Learning algorithms and their application on energy time series forecasting. • The methods tested are concrete Dropouts, deep Ensembles, bayesian neural Networks, deep gaussian Processes, and functional neural processes. • The methods are evaluated in terms of calibration, sharpness, and how well they indicate a lack of knowledge (Epistemic Uncertainty). • Good epistemic uncertainty estimates were given using functional neural Processes, deep Ensembles, and deep gaussian processes methods, while concrete dropouts and bayesian neural networks needed tunning for better performance. • The application of the methods was feasible for energy time series forecasting, and they produced good estimates of their confidence in a forecast. Deep Learning methods are widely successful and continue to be applied in new fields, including forecasting for energy time series. However, they lack an indication of their confidence in predictions, which helps evaluate, interpret, and improve the forecasting. This paper explores probabilistic extensions to Deep Learning algorithms and their application on energy time series forecasting. The methods tested are Concrete Dropouts, Deep Ensembles, Bayesian Neural Networks, Deep Gaussian Processes, and Functional Neural Processes. For evaluation, two load forecasting scenarios are considered: 1-hour-ahead and 24-hour-ahead load forecasting. The methods are evaluated in terms of calibration, sharpness, and how well they indicate a lack of knowledge (Epistemic Uncertainty). As a reference, simple Neural Network and Quantile Regression models are used. Also, the ARIMA model and Persistence model are implemented to compare the results. Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Continuous Ranked Probability Score (CRPS) are computed to measure the error performance. Based on endogenous load time series in Germany, the results showed that Concrete Dropout, Deep Ensembles, and Bayesian Neural Networks performed similarly well and better than the reference methods. They also indicated that the simpler Concrete Dropout and Deep Ensembles have an advantage in both speed and convergence time. Good Epistemic Uncertainty estimates were given using Functional Neural Processes, Deep Ensembles, and Deep Gaussian Processes methods, while Concrete dropouts and Bayesian Neural Networks needed tunning for better performance. The application of the methods was feasible for energy time series forecasting, and they produced good estimates of their confidence in a forecast. [ABSTRACT FROM AUTHOR]

This paper develops and applies neural network (NN) models to forecast regional employment patterns in Germany. Computer-aided optimization tools that imitate natural biological evolution to find the solution that best fits the given case (namely, genetic algorithms, GAs) are also used to detect the best NN structure. GA techniques are compared with more `traditional' techniques which require the supervision of experienced analysts. We test the performance of these techniques on a panel of 439 districts in West and East Germany. Since the West and East datasets have different time spans, the models are estimated separately for West and East Germany. The results show that the West and East NN models perform with different degrees of precision, mainly because of the different time spans of the two datasets. Automatic techniques for the choice of the NN architecture do not seem to outperform selection procedures based on the supervision of expert analysts. [ABSTRACT FROM AUTHOR]

In this paper, we present the estimation of surface NO 2 concentrations over Germany using a machine learning approach. TROPOMI satellite observations of tropospheric NO 2 vertical column densities (VCDs) and several meteorological parameters are used to train the neural network model for the prediction of surface NO 2 concentrations. The neural network model is validated against ground-based in situ air quality monitoring network measurements and regional chemical transport model (CTM) simulations. Neural network estimation of surface NO 2 concentrations show good agreement with in situ monitor data with Pearson correlation coefficient (R) of 0.80. The results also show that the machine learning approach is performing better than regional CTM simulations in predicting surface NO 2 concentrations. We also performed a sensitivity analysis for each input parameter of the neural network model. The validated neural network model is then used to estimate surface NO 2 concentrations over Germany from 2018 to 2020. Estimated surface NO 2 concentrations are used to investigate the spatio-temporal characteristics, such as seasonal and weekly variations of NO 2 in Germany. The estimated surface NO 2 concentrations provide comprehensive information of NO 2 spatial distribution which is very useful for exposure estimation. We estimated the annual average NO 2 exposure for 2018, 2019 and 2020 is 15.53, 15.24 and 13.27 µ g/m 3 , respectively. While the annual average NO 2 concentration of 2018, 2019 and 2020 is only 12.79, 12.60 and 11.15 µ g/m 3 . In addition, we used the surface NO 2 data set to investigate the impacts of the coronavirus disease 2019 (COVID-19) pandemic on ambient NO 2 levels in Germany. In general, 10–30% lower surface NO 2 concentrations are observed in 2020 compared to 2018 and 2019, indicating the significant impacts of a series of restriction measures to reduce the spread of the virus. [ABSTRACT FROM AUTHOR]

One month-ahead electricity prices open up a great potential for manufacturing companies that aim at reducing energy costs. On the machine level, an energy cost-oriented scheduling can be realized through determining the least electricity cost-intensive launch times for job processing during a day. To obtain reliable price information at production planning stage in advance, well-performing forecast models are required. In this paper, we apply a Weighted Nearest Neighbor (WNN) approach, a TBATS approach, and a Deep Feedforward Neural Network (DFNN) approach to forecast EPEX Spot day-ahead electricity prices of the European Energy Exchange in Germany/Austria, while accounting for a forecast horizon of up to one month. Model performances are compared by means of established error measures as well as by adjusted error measures to better interpret results from a production planner's point of view. For evaluation purposes, 1357 different forecasts were computed for each of the methods, allowing valid conclusions as to their performance. The results show that all approaches lead to acceptable accuracies. However, the DFNN outperforms WNN and TBATS, providing well-fitting forecasts even 29 days ahead. Image 1 • Artificial Neural Networks outperform TBATS and Weighted Nearest Neighbor. • Forecast results are highly applicable for mid-term production planning purposes. • Neural Network forecasts for longer terms are almost as precise as for shorter ones. • On average, only 5% of the adjusted forecasts exceed the limit of a 10.00 EUR error. [ABSTRACT FROM AUTHOR]