Non-negative Matrix Factorization (NMF) methods offer an appealing unsupervised learning method for real-time analysis of streaming spectral data in time-sensitive data collection, such as $\textit{in situ}$ characterization of materials. However, canonical NMF methods are optimized to reconstruct a full dataset as closely as possible, with no underlying requirement that the reconstruction produces components or weights representative of the true physical processes. In this work, we demonstrate how constraining NMF weights or components, provided as known or assumed priors, can provide significant improvement in revealing true underlying phenomena. We present a PyTorch based method for efficiently applying constrained NMF and demonstrate this on several synthetic examples. When applied to streaming experimentally measured spectral data, an expert researcher-in-the-loop can provide and dynamically adjust the constraints. This set of interactive priors to the NMF model can, for example, contain known or identified independent components, as well as functional expectations about the mixing of components. We demonstrate this application on measured X-ray diffraction and pair distribution function data from $\textit{in situ}$ beamline experiments. Details of the method are described, and general guidance provided to employ constrained NMF in extraction of critical information and insights during $\textit{in situ}$ and high-throughput experiments.

The damage to cellular towers during natural and man-made disasters can disturb the communication services for cellular users. One solution to the problem is using unmanned aerial vehicles to augment the desired communication network. The paper demonstrates the design of a UAV-Assisted Imitation Learning (UnVAIL) communication system that relays the cellular users' information to a neighbor base station. Since the user equipment (UEs) are equipped with buffers with limited capacity to hold packets, UnVAIL alternates between different UEs to reduce the chance of buffer overflow, positions itself optimally close to the selected UE to reduce service time, and uncovers a network pathway by acting as a relay node. UnVAIL utilizes Imitation Learning (IL) as a data-driven behavioral cloning approach to accomplish an optimal scheduling solution. Results demonstrate that UnVAIL performs similar to a human expert knowledge-based planning in communication timeliness, position accuracy, and energy consumption with an accuracy of 97.52% when evaluated on a developed simulator to train the UAV.

The growing integration of distributed energy resources (DERs) in distribution grids raises various reliability issues due to DER's uncertain and complex behaviors. With a large-scale DER penetration in distribution grids, traditional outage detection methods, which rely on customers report and smart meters' last gasp signals, will have poor performance, because the renewable generators and storages and the mesh structure in urban distribution grids can continue supplying power after line outages. To address these challenges, we propose a data-driven outage monitoring approach based on the stochastic time series analysis with a theoretical guarantee. Specifically, we prove via power flow analysis that the dependency of time-series voltage measurements exhibits significant statistical changes after line outages. This makes the theory on optimal change-point detection suitable to identify line outages. However, existing change point detection methods require post-outage voltage distribution, which is unknown in distribution systems. Therefore, we design a maximum likelihood estimator to directly learn the distribution parameters from voltage data. We prove that the estimated parameters-based detection also achieves the optimal performance, making it extremely useful for fast distribution grid outage identifications. Furthermore, since smart meters have been widely installed in distribution grids and advanced infrastructure (e.g., PMU) has not widely been available, our approach only requires voltage magnitude for quick outage identification. Simulation results show highly accurate outage identification in eight distribution grids with 14 configurations with and without DERs using smart meter data.

Most solar applications and systems can be reliably used to generate electricity and power in many homes and offices. Recently, there is an increase in many solar required systems that can be found not only in electricity generation but other applications such as solar distillation, water heating, heating of buildings, meteorology and producing solar conversion energy. Prediction of solar radiation is very significant in order to accomplish the previously mentioned objectives. In this paper, the main target is to present an algorithm that can be used to predict an hourly activity of solar radiation. Using a dataset that consists of temperature of air, time, humidity, wind speed, atmospheric pressure, direction of wind and solar radiation data, an Artificial Neural Network (ANN) model is constructed to effectively forecast solar radiation using the available weather forecast data. Two models are created to efficiently create a system capable of interpreting patterns through supervised learning data and predict the correct amount of radiation present in the atmosphere. The results of the two statistical indicators: Mean Absolute Error (MAE) and Mean Squared Error (MSE) are performed and compared with observed and predicted data. These two models were able to generate efficient predictions with sufficient performance accuracy.

Because most machine learning (ML) algorithms are designed for numerical inputs, efficiently encoding categorical variables is a crucial aspect during data analysis. An often encountered problem are high cardinality features, i.e. unordered categorical predictor variables with a high number of levels. We study techniques that yield numeric representations of categorical variables which can then be used in subsequent ML applications. We focus on the impact of those techniques on a subsequent algorithm's predictive performance, and -- if possible -- derive best practices on when to use which technique. We conducted a large-scale benchmark experiment, where we compared different encoding strategies together with five ML algorithms (lasso, random forest, gradient boosting, k-nearest neighbours, support vector machine) using datasets from regression, binary- and multiclass- classification settings. Throughout our study, regularized versions of target encoding (i.e. using target predictions based on the feature levels in the training set as a new numerical feature) consistently provided the best results. Traditional encodings that make unreasonable assumptions to map levels to integers (e.g. integer encoding) or to reduce the number of levels (possibly based on target information, e.g. leaf encoding) before creating binary indicator variables (one-hot or dummy encoding) were not as effective.

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time consuming solution that poses strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention based models for LC&CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

Staying ahead of the technology curve means strengthening your competitive advantage. That is why we give you data-driven innovation insights into the mobility industry. This time, you get to discover 5 hand-picked startups developing artificial intelligence (AI) solutions. The insights of this data-driven analysis are derived from the Big Data & Artificial Intelligence-powered StartUs Insights Discovery Platform, covering 1.379.000 The platform gives you an exhaustive overview of emerging technologies & relevant startups within a specific field in just a few clicks.

All this means that utilities, policy makers and regulatory bodies need to start thinking about what role they want to play when it comes to decentralized energy resources. The patchwork of distributed energy producers will depend on coordination and management. Utilities can take the lead here as they face a shrinking pool of customers purchasing electricity as more homes and businesses become energy producers themselves – thanks to rooftop solar panels and the like. Already, the size of a median power plant in Europe has fallen from 800 megawatts in 2012 to 562 megawatts in 2020, and BloombergNEF projects this will plummet to 32 megawatts by 2050.

Google is adding more information to Search and Maps about businesses that offer options for grocery delivery and pickup. The information is getting added to search automatically, which means there's no work needed on the part of businesses, but it's an update worth being aware of. This addition to Google Search and Maps is rolling out as part of a larger update which includes a number of other useful features. We'll look at the other features at the end of this article – let's first go over the enhancements to Google My Business profiles. Google is bringing shopping information to stores' business profiles to assist people with finding convenient grocery delivery and pickup options.

Carbon emission is one of the biggest causes of environment pollution today. Globally, governments are making efforts on a war footing to reduce carbon emissions. Leveraging artificial intelligence can boost these efforts as it can analyze data, uncover patterns that humans might miss out, and recommend appropriate actions. It is believed that artificial intelligence can help reduce the emission of greenhouse gases by nearly 16%. According to Capgemini Research Institute, by 2030 artificial intelligence can help organizations across sectors such as retail, automotive, and consumer goods to meet upto 45% of the targets as set out by the Paris Agreement.