Classifying requirements is crucial for automatically handling natural language requirements. The performance of existing automatic classification approaches diminishes when applied to unseen projects because requirements usually vary in wording and style. The main problem is poor generalization. We propose NoRBERT that fine-tunes BERT, a language model that has proven useful for transfer learning. We apply our approach to different tasks in the domain of requirements classification. We achieve similar or better results (F 1 -scores of up to 94%) on both seen and unseen projects for classifying functional and non-functional requirements on the PROMISE NFR dataset. NoRBERT outperforms recent approaches at classifying nonfunctional requirements subclasses. The most frequent classes are classified with an average F 1 -score of 87%. In an unseen project setup on a relabeled PROMISE NFR dataset, our approach achieves an improvement of 15 percentage points in average F 1score compared to recent approaches. Additionally, we propose to classify functional requirements according to the included concerns, i.e., function, data, and behavior. We labeled the functional requirements in the PROMISE NFR dataset and applied our approach. NoRBERT achieves an F 1 -score of up to 92%. Overall, NoRBERT improves requirements classification and can be applied to unseen projects with convincing results.

No abstract

Municipal wastewater treatment commonly involves mechanical, biological and chemical treatment steps to protect humans and the environment from adverse effects. Membrane technology has gained increasing attention as an alternative to conventional wastewater treatment due to increased urbanization. Among the available membrane technologies, microfiltration (MF) and forward osmosis (FO) have been selected for this study due to their specific characteristics, such as compactness and efficient removal of particles. In this study, two treatment concepts were evaluated with regard to their specific electricity, energy and area demands. Both concepts would fulfil the Swedish discharge demands for small- and medium-sized wastewater treatment plants at full scale: (1) direct MF and (2) direct FO with seawater as the draw solution. The framework of this study is based on a combination of data obtained from bench- and pilot-scale experiments applying direct MF and FO, respectively. Additionally, available complementary data from a Swedish full-scale wastewater treatment plant and the literature were used to evaluate the concepts in depth. The results of this study indicate that both concepts are net positive with respect to electricity and energy, as more biogas can be produced compared to that using conventional wastewater treatment. Furthermore, the specific area demand is significantly reduced. This study demonstrates that municipal wastewater could be treated in a more energy- and area-efficient manner with techniques that are already commercially available and with future membrane technology.