Author: Sin Chi Chiu

Recently in the Washington State University, researchers have created a new method to identify antimicrobial-resistance (AMR). The new method uses game theory to choose the important features to be used in their machine learning model. While there were many attempts in identifying AMR with machine learning, there was never a good strategy to identify the important features to be used. 

Most of the strategies used in the past had either resulted in high computational overhead or low accuracy. However researchers found out using game theory they can now include features that are poorly predictive as single variables, which are traditionally rejected. The method uses the behavior of different features and consider how they behave together as a whole. Using the data generated from game theory, they can then train their machine learning model to accurately predict AMR. The resulting algorithm has an accuracy ranging from 93% – 99% as shown in the figure below. 

“This novel game theory approach is especially powerful because features are chosen on the basis of how well they work together as a whole to identify likely antimicrobial-resistance genes — taking into account both the relevance and interdependency of features,” – Broschat, one of the researchers in developing this new method of identifying AMR.

Source:
Abu Sayed Chowdhury, Douglas R. Call, Shira L. Broschat. Antimicrobial Resistance Prediction for Gram-Negative Bacteria via Game Theory-Based Feature Evaluation. Scientific Reports, 2019; 9 (1) DOI: 10.1038/s41598-019-50686-z 

The academic journal published by IEEE(Institute of Electrical and Electronics Engineers) proposed a new model to improve the quality of community discovery. This new proposed model addresses some of the limitations that traditional methods had and produces result with higher correspondence with the ground truth communities.

Traditionally, community discovery methods treat network structure as a static topology. They neglect the interaction between the information factor, as they only represent the possibility of interaction between users. However modern microblogging networks applications like Twitter, are extremly dynamic in content distribution and topological structure. The flow of information that is not considered in traditional methods could be applied to microblogging networks to better determine user interest community.

The proposed method uses multiple different data analysis algorithms to filter and integrate information interactions between users. It then uses machine learning strategy to analyze information to dynamically updates the characteristic of the network to cluster the community. 

This is interesting to me because, as we have learnt in class, sometimes data are lost in translation. This method takes some of the missing information into account and analyze them before translation. The resulting communities have higher correspondence and accuracy, which can provide more information than traditional methods.

Reference:

Jiang, Liang, et al. “An Efficient Evolutionary User Interest Community Discovery Model in Dynamic Social Networks for Internet of People.” IEEE Internet of Things Journal, 2019, pp. 1–1., doi:10.1109/jiot.2019.2893625.