Search

In this study, chitin nanofiber (ChNF) was deacetylated on the crystalline surface by NaOH treatment, leading to the fibrillation of mostly individualized nanofibers with high aspect ratio. The small diameter and high strength of chitin nanofibers make them promising reinforcing fillers for composites. Herein by introducing into the gelatin, surface-deacetylated chitin nanofiber (S-ChNF)/gelatin nanocomposites were fabricated in different component ratios using immersion method followed with drying. Due to the reinforcing effect attributed to S-ChNF, mechanical properties of the S-ChNF/gelatin were significantly improved in both stress and Young's modulus while still maintaining high transparency regardless of nanofiber content. Morphology and Fourier-transform infrared characterization revealed that S-ChNF preserved nanonetwork structures in the gelatin matrix and exhibited good compatibility through hydrogen bonding, which further confirmed the improvement in mechanical properties. Therefore, these S-ChNF/gelatin nanocomposites based on biocompatible and biodegradable raw materials have potential applications in biomedical and food packaging industries.

Additional file 1. Supplementary information includes Supplemental Method, seven Supplemental figures, five Supplemental tables.

Evolutionary algorithms have achieved great performance among a wide range of optimization problems. In this degree project, the network optimization problem has been reformulated and solved in an evolved way. A feasible evolutionary framework has been designed and implemented to train neural networks in supervised learning scenarios. Under the structure of evolutionary algorithms, a well-defined fitness function is applied to evaluate network parameters, and a carefully derived form of approximate gradients is used for updating parameters. Performance of the framework has been tested by training two different types of networks, linear affine networks and convolutional networks, for a flash call verification task.Under this application scenario, whether a flash call verification will be successful or not will be predicted by a network, which is inherently a binary classification problem. Furthermore, its performance has also been compared with traditional backpropagation optimizers from two aspects: accuracy and time consuming. The results show that this framework is able to push a network training process to converge into a certain level. During the training process, despite of noises and fluctuations, both accuracies and losses converge roughly under the same pattern as in backpropagation. Besides, the evolutionary algorithm seems to have higher updating efficiency per epoch at the first training stage before converging. While with respect to fine tuning, it doesn’t work as good as backpropagation in the final convergence period. Evolutionära algoritmer uppnår bra prestanda för ett stort antal olika typer av optimeringsproblem. I detta examensprojekt har ett nätverksoptimeringsproblem lösts genom omformulering och vidareutveckling av angreppssättet. Ett förslag till ramverk har utformats och implementerats för att träna neuronnätverk i övervakade inlärningsscenarier. För evolutionära algoritmer används en väldefinierad träningsfunktion för att utvärdera nätverksparametrar, och en noggrant härledd form av approximerade gradienter används för att uppdatera parametrarna. Ramverkets prestanda har testats genom att träna två olika typer av linjära affina respektive konvolutionära neuronnätverk, för optimering av telefonnummerverifiering. I detta applikationsscenario förutses om en telefonnummerverifiering kommer att lyckas eller inte med hjälp av ett neuronnätverk som i sig är ett binärt klassificeringsproblem. Dessutom har dess prestanda också jämförts med traditionella backpropagationsoptimerare från två aspekter: noggrannhet och hastighet. Resultaten visar att detta ramverk kan driva en nätverksträningsprocess för att konvergera till en viss nivå. Trots brus och fluktuationer konvergerar både noggrannhet och förlust till ungefär under samma mönster som i backpropagation. Dessutom verkar den evolutionära algoritmen ha högre uppdateringseffektivitet per tidsenhet i det första träningsskedet innan den konvergerar. När det gäller finjustering fungerar det inte lika bra som backpropagation under den sista konvergensperioden.

Chitin and gelatin are biodegradable and biocompatible polymers which have gained much attention applied as bio-based materials. In this study, Chitin nanofiber (ChNF)/gelatin nanocomposite was synthesized by immersion method followed with drying at room temperature. The ChNF content in the ChNF/gelatin was controlled in a broad range by changing the concentration of gelatin solutions from 2, 5 to 10% during the immersion processes. The prepared ChNF/gelatin showed uniformly nanofiber network structures which embedded inside the gelatin matrix. The UV measurement indicated that the transmittance of ChNF was increased to as high as 88.7% from 65% at 600 nm, regardless of nanofiber content. Young’s modulus of the 50.2%-ChNF/gelatin (with the ChNF content of 50.2%) was around 5192 MPa, which was almost two times higher than that of the pure gelatin. This mechanical improvement was attributed to the reinforcing effect from ChNF nano-networks as well as the formation of hydrogen bondings between gelatin and chitin moleculars. Therefore, with the highly transparent and improved mechanical properties, the prepared ChNF/gelatin nanocomposite films may offer promising and broad prospects in the field of food packaging and bio-medical industrials.