AIH’s Master of Business Information System (MBIS) team of students who participated in the MBIS5015 Capstone Project unit in 2022 had the very first Student Conference Publication with the paper “Skin Disease Detection as Unsupervised-Classification with Autoencoder and Experience-Based Augmented Intelligence (AI),” Kushal Pokhrel, Suman Giri, Sudip Karki, and Cesar Sanin.
Congratulations to all the authors for this remarkable inaugural achievement.
Here is the abstract for those who’d like to know more.
In this paper, we propose an Artificial Neural Network using an auto-encoder trained with fewer images but increases accuracy based on experience Augmented Intelligence. Most neural network systems use a large number of training sets to achieve a well-performing model and spend great efforts on pre-processing and training times to create a static model. In our case, we propose a system that uses just 4% images per class training set compared to most models and learns with each iteration of being used, interacting with the user, and acquiring experience to increase the accuracy. The average accuracy rate is increased at a 1.33% rate per every 20 user experiences. The proposed model offers advantages in creating dynamic experience-based augmented intelligence models.