Recent years have witnessed a rapid development of automated methods for skin lesion diagnosis and classification. Due to an increasing deployment such systems in clinics, it has become important develop more robust system towards various Out-of-Distribution (OOD) samples (unknown lesions conditions). However, the current deep learning models trained classification tend classify these OOD incor...

This paper proposes an intelligent credit card fraud detection model for detecting fraud from highly imbalanced and anonymous credit card transaction datasets. The class imbalance problem is handled by finding legal as well as fraud transaction patterns for each customer by using frequent itemset mining. A matching algorithm is also proposed to find to which pattern (legal or fraud) the incomin...

Recently, the Bitcoin-underlying blockchain technology gained prominence as a solution that offers the realization of distributed trust-free systems, where economic transactions are guaranteed by the underlying blockchain. We are still at an early stage and thus require a deeper understanding of how the blockchain potentials can be realized, and what are the opportunities and challenges in so d...

Perforated paper products As you can imagine, it would be somewhat inconvenient to have a computer that forgot everything it knew if its operator turned it off before stepping out for a bite of lunch. Similarly, imagine a programmer's frustration if, after spending countless hours using a Switch Panel to enter a program, the janitor carelessly disconnected the computer in order to vacuum the of...