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.
AIH Senior Lecturer, Dr. Md Rafiqul Islam and his co-authors have been awarded the Best Paper Award at the 27th International Conference on Information Visualisation (IV 2023), hosted by Tampere University, Finland for their research paper “SIDVis: Designing Visual Interactive System for Analyzing Suicide Ideation Detection”.
Congratulations Rafiqul on such a wonderful achievement!
Here is the abstract for those who’d like to know more –
Suicide is a critical global issue that demands a comprehensive examination of factors such as mental illness, substance abuse, financial stress, and trauma. Effectively identifying individuals at risk is vital for intervention and prevention efforts. However, distinguishing suicidal ideation (SID) from non-suicidal language poses challenges. Existing research has addressed this issue, but limited attention has been given to visually interpretable and interactive systems tailored for SID.
This study contributes to responsible AI by leveraging deep learning and machine learning techniques to enhance SID detection, enabling proactive interventions and support. In this paper, we introduce SIDVis, an interactive visualisation system that improves performance and interpretability at the same time.
The rigorous evaluation demonstrates that SIDVis not only outperforms existing methods in terms of accuracy but also provides an explanation for the responsible use of the underlying AI approach, demonstrating its potential to improve SID detection and intervention strategies.