Search

Automated social text annotation is the task of suggesting a set of tags for shared documents on social media platforms. The automated annotation process can reduce users’ cognitive overhead in tagging and improve tag management for better search, browsing, and recommendation of documents. It can be formulated as a multilabel classification problem. We propose a novel deep learning-based method for this problem and design an attention-based neural network with semantic-based regularization, which can mimic users’ reading and annotation behavior to formulate better document representation, leveraging the semantic relations among labels. The network separately models the title and the content of each document and injects an explicit, title-guided attention mechanism into each sentence. To exploit the correlation among labels, we propose two semantic-based loss regularizers, i.e., similarity and subsumption, which enforce the output of the network to conform to label semantics. The model with the semantic-based loss regularizers is referred to as the joint multilabel attention network (JMAN). We conducted a comprehensive evaluation study and compared JMAN to the state-of-the-art baseline models, using four large, real-world social media data sets. In terms of F1, JMAN significantly outperformed bidirectional gated recurrent unit (Bi-GRU) relatively by around 12.8%–78.6% and the hierarchical attention network (HAN) by around 3.9%–23.8%. The JMAN model demonstrates advantages in convergence and training speed. Further improvement of performance was observed against latent Dirichlet allocation (LDA) and support vector machine (SVM). When applying the semantic-based loss regularizers, the performance of HAN and Bi-GRU in terms of F1 was also boosted. It is also found that dynamic update of the label semantic matrices (JMANd) has the potential to further improve the performance of JMAN but at the cost of substantial memory and warrants further study. [ABSTRACT FROM AUTHOR]

An accurate measurement of the solar irradiance is of significance for evaluating and developing of solar renewable energy systems. Soft sensors are used to provide feasible and economical alternatives to costly physical measurement instruments (e.g., pyranometers and pyrheliometers). Conventional soft-sensing methods assume that input data are identically and independently distributed (i.i.d.) and calculate an estimate of the solar irradiance via a regression model. However, different ambient temperatures result in various current–voltage characteristics, meaning that the i.i.d. assumption is violated. To improve the estimation accuracy, a field-support vector regression soft sensor is proposed to estimate the irradiance levels from photovoltaic (PV) electrical characteristics. The soft sensing system groups its input data into several fields in accordance with ambient temperatures. By transforming the original data into a style-free and i.i.d. space, the soft sensing model achieves better estimation performance. The proposed soft sensor can be easily implemented through a PV module, a thermometer, a current sensor, and a DSP development board. It is validated by simulations and experimental prototyping using real outdoor measurements. [ABSTRACT FROM AUTHOR]