Browse Articles

A Taste of Sweetness in Bioplastics

Tsai et al. | Apr 05, 2019

A Taste of Sweetness in Bioplastics

Sweet potatoes are one of the most common starches in Taiwan, and sweet potato peels hold significant potential to make biodegradable plastics which can alleviate the environmental impact of conventional petroleum-based plastics. In this paper, Tsai et al created starch-based bioplastics derived from sweet potato peels and manipulated the amount of added glycerol to alter the plastic’s strength and flexibility properties. Their results indicated that higher concentrations of glycerol yield more malleable plastics, providing insights into how recycled agricultural waste material might be used to slow down the rate of pollution caused by widespread production of conventional plastics.

Read More...

A Crossover Study Comparing the Effect of a Processed vs. Unprocessed Diet on the Spatial Learning Ability of Zebrafish

Banga et al. | Sep 18, 2022

A Crossover Study Comparing the Effect of a Processed vs. Unprocessed Diet on the Spatial Learning Ability of Zebrafish

The authors compared the short-term effects of processed versus unprocessed food on spatial learning and survival in zebrafish, given the large public concern regarding processed foods. By randomly assigning zebrafish to a diet of brine shrimp flakes (processed) or live brine shrimp (unprocessed), the authors show while there is no immediate effect on a fish's decision process between the two diets, there are significant correlations between improved learning and stress response with the unprocessed diet.

Read More...

Recognition of animal body parts via supervised learning

Kreiman et al. | Oct 28, 2023

Recognition of animal body parts via supervised learning
Image credit: Kreiman et al. 2023

The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.

Read More...

Search Articles

Search articles by title, author name, or tags

Clear all filters

Popular Tags

Browse by school level