This paper reviews non-intrusive load monitoring (NILM) approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e., data with sampling rates lower than the AC base frequency. The overall purpose of this review is, firstly, to gain an overview on the state of the research up to November 2020, and secondly, to identify worthwhile open research topics. Accordingly, we first review the many degrees of freedom of these approaches, what has already been done in the literature, and compile the main characteristics of the reviewed publications in an extensive overview table. The second part of the paper discusses selected aspects of the literature and corresponding research gaps. In particular, we do a performance comparison with respect to reported mean absolute error (MAE) and F1-scores and observe different recurring elements in the best performing approaches, namely data sampling intervals below 10 s, a large field of view, the usage of generative adversarial network (GAN) losses, multi-task learning, and post-processing. Subsequently, multiple input features, multi-task learning, and related research gaps are discussed, the need for comparative studies is highlighted, and finally, missing elements for a successful deployment of NILM approaches based on deep neural networks are pointed out. We conclude the review with an outlook on possible future scenarios.

Discourse parsing could not yet take full advantage of the neural NLP revolution, mostly due to the lack of annotated datasets. We propose a novel approach that uses distant supervision on an auxiliary task (sentiment classification), to generate abundant data for RSTstyle discourse structure prediction. Our approach combines a neural variant of multipleinstance learning, using document-level supervision, with an optimal CKY-style tree generation algorithm. In a series of experiments, we train a discourse parser (for only structure prediction) on our automatically generated dataset and compare it with parsers trained on human-annotated corpora (news domain RST-DT and Instructional domain). Results indicate that while our parser does not yet match the performance of a parser trained and tested on the same dataset (intra-domain), it does perform remarkably well on the much more difficult and arguably more useful task of inter-domain discourse structure prediction, where the parser is trained on one domain and tested/applied on another one.

The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RSTstyle discourse parsing. In this work, we present a novel scalable methodology to automatically generate discourse treebanks using distant supervision from sentiment-annotated datasets, creating and publishing MEGA-DT, a new large-scale discourse-annotated corpus. Our approach generates discourse trees incorporating structure and nuclearity for documents of arbitrary length by relying on an efficient heuristic beam-search strategy, extended with a stochastic component. Experiments on multiple datasets indicate that a discourse parser trained on our MEGA-DT treebank delivers promising inter-domain performance gains when compared to parsers trained on human-annotated discourse corpora.

Grazing incidence small-angle X-ray scattering (GISAXS) is used for nondestructive characterization of colloidal crystals of different numbers of hexagonally dense packed layers fabricated by convective self-assembly. Whereas small crystallites with random orientation were obtained in case of monolayers, the scattering data obtained from multilayer samples revealed colloidal domains over areas of a few centimeters where the single crystalline domains are mainly aligned along the growth direction. The data indicates an increasing degree of self-organization going from monolayers to multilayers. Within the multilayer samples, the stacking sequence of the hexagonally packed layers is evaluated using a numerical model for fitting the X-ray scattering data containing the stacking parameter, a. Compared with an expected complete random stacking with a = 0.5, the fitted stacking parameter, a = 0.63 ± 0.01, averaged over a sample area of about 1 mm(2) indicates a preference for a cubic stacking sequence. This value is smaller than reported by various local probe techniques.