Ensemble Deep Learning Framework for Situational Aspects-Based Annotation and Classification of International Student’s Tweets during COVID-19

As the COVID-19 pandemic swept the globe, social media platforms became an essential source of information and communication for many. International students, particularly, turned to Twitter to express their struggles and hardships during this difficult time. To better understand the sentiments and experiences of these international students, we developed the Situational Aspect-Based Annotation and Classification (SABAC) text mining framework. This framework uses a three-layer approach, combining baseline Deep Learning (DL) models with Machine Learning (ML) models as meta-classifiers to accurately predict the sentiments and aspects expressed in tweets from our collected Student-COVID-19 dataset. Using the proposed aspect2class annotation algorithm, we labeled bulk unlabeled tweets according to their contained aspect terms. However, we also recognized the challenges of reducing data’s high dimensionality and sparsity to improve performance and annotation on unlabeled datasets. To address this issue, we proposed the Volatile Stopwords Filtering (VSF) technique to reduce sparsity and enhance classifier performance. The resulting Student-COVID Twitter dataset achieved a sophisticated accuracy of 93.21% when using the random forest as a meta-classifier. Through testing on three benchmark datasets, we found that the SABAC ensemble framework performed exceptionally well. Our findings showed that international students during the pandemic faced various issues, including stress, uncertainty, health concerns, financial stress, and difficulties with online classes and returning to school. By analyzing and summarizing these annotated tweets, decision-makers can better understand and address the real-time problems international students face during the ongoing pandemic.     

Experimental evaluation and theoretical prediction of elastic properties and failure of C/C-SiC composite

The paper presents experimental characterization and theoretical predictions of elastic and failure properties of continuous carbon fiber reinforced silicon carbide (C/C-SiC) composite fabricated by Liquid Silicon Infiltration (LSI). Its mechanical properties were determined under uniaxial tensile, compression, and pure shear loads in two sets of principal coordinate systems, 0°–90° and ±45°, respectively. The properties measured in the 0°–90° coordinate system were employed as the input data to predict their counterparts in the ±45° coordinate system. Through coordinate transformations of stress and strain tensors, the elastic constants and stress-strain behaviors were predicted and found to be in good agreement with the experimental results. In the same way, three different failure criteria, maximum stress, Tsai-Wu, and maximum strain, have been selected for the evaluation of the failure of C/C-SiC as a type of genuinely orthotropic material. Based on the comparisons with experimental results, supported by necessary practical justifications, the Tsai-Wu criterion was found to offer a reasonable prediction of the strengths, which can be assisted by the maximum stress criterion to obtain an indicative prediction of the respective failure modes.     

Schutzzielorientierte brandschutztechnische Bemessung für mehrgeschossige Gebäude

Performance – based fire safety design of multi‐storey buildings. In most countries fire design of multi‐storey buildings is still based on the standard temperature‐time curve (ISO 834) which is supposed to cover real fire scenarios on the safe side. A fire safety design considering more realistic natural fires and the redundancies of entire structural systems is risk‐oriented as well as economical. Using international experience and test results and ongoing research of iBMB, a design fire is developed and so‐called real fire curves are derived. They serve as a basis for general calculation methods (according to the Eurocodes) which are able to grasp the real behaviour of structural systems in a fire. A probabilistic safety concept guarantees the necessary reliability of the design taking the probability of fire development, the boundary conditions of life safety and the uncertainties of the design parameters into account.     

Production of Cationic Starch Ethers Using an Improved Dry Process

Cationic starch ethers have been established as additives in the paper industry for many years. A number of production processes are known and documented in numerous patents and articles. Whereas in the past starches were predominantly etherified in aqueous suspension, a trend has lately been observed towards a “dry” cationisation. Apart from the commercial aspects, the advantages of a “dry” reaction control lie in the ecological sphere as well. The advantages of the dry process for producing cationic starch ethers will be discussed here and compared with the “slurry” process. In so doing, particular attention will be paid to a dry process developed by our company since it is gaining nowadays more and more commercial relevance.