ARTIFICIAL NEURAL NETWORK BASED CLASSIFICATION SYSTEM FOR LUNG NODULES THROUGH COMPUTED TOMOGRAPHY SCAN

Abstract

An energy- and area-efficient solution for tolerating the stuck-at faults induced by an endurance problem in secureresistive
main memory. A large number of memory locations with stuck-at faults might be used in the suggested
technique to appropriately store the data by using the rotational shift operation and the random properties of the
encrypted data encoded by the Advanced Encryption Standard (AES). The suggested method's energy usage is much
lower than that of other previously presented approaches because of its straightforward hardware implementation.
The error correction code (ECC) and error correction pointer (ECP) are two more error correction techniques that
may be used in conjunction with this one. The suggested approach is put into practice in a main memory system
based on phase-change memory (PCM) and contrasted with three error-tolerating techniques in order to determine
its effectiveness. The findings show that the suggested approach provides 82% energy savings over the state-of-theart
technique for a stuck-at fault incidence rate of 10−2 and an uncorrected bit error rate of 2 × 10−3. More broadly,
we demonstrate that the fault coverage of the suggested approach is comparable to the state-of-the-art method using
a simulation analysis methodology.