Characteristics of Sodium Alginate/Antarctic Krill Protein Composite Fiber Based on Cellulose Nanocrystals Modification: Rheology, Hydrogen Bond, Crystallization, Strength, and Water-Resistance.

The purpose of adding cellulose nanocrystals (CNCs) into sodium alginate (SA) and Antarctic krill protein (AKP) system is to use the ionic cross-linking of SA and AKP and the dynamic hydrogen-bonding between them and CNCs to construct multiple cross-linking structures, to improve the water-resistance and strength of SA/AKP/CNCs composite fiber. Based on the structural viscosity index in rheological theory, the ratio of spinning solution and temperature were optimized by studying the structural viscosity index of the solution under different CNCs content and temperature, then the composite fiber was prepared by wet spinning. We found that when the content of CNCs is 0.

Online Active Learning Ensemble Framework for Drifted Data Streams.

In practical applications, data stream classification faces significant challenges, such as high cost of labeling instances and potential concept drifting. We present a new online active learning ensemble framework for drifting data streams based on a hybrid labeling strategy that includes the following: 1) an ensemble classifier, which consists of a long-term stable classifier and multiple dynamic classifiers (a multilevel sliding window model is used to create and update the dynamic classifiers to effectively process both the gradual drift type and sudden drift type data stream) and 2) active learning, which takes a nonfixed labeling budget, supports on-demand request labeling, and adopts an uncertainty strategy and random strategy to label instances. The decision threshold of the uncertainty strategy is adjusted dynamically, i.