Enabling Intelligent IoTs for Histopathology Image Analysis Using Convolutional Neural Networks.

Medical imaging is an essential data source that has been leveraged worldwide in healthcare systems. In pathology, histopathology images are used for cancer diagnosis, whereas these images are very complex and their analyses by pathologists require large amounts of time and effort. On the other hand, although convolutional neural networks (CNNs) have produced near-human results in image processing tasks, their processing time is becoming longer and they need higher computational power. In this paper, we implement a quantized ResNet model on two histopathology image datasets to optimize the inference power consumption. We analyze classification accuracy, energy estimation, and hardware utilization metrics to evaluate our method. First, the original RGB-colored images are utilized for the training phase, and then compression methods such as channel reduction and sparsity are applied. Our results show an accuracy increase of 6% from RGB on 32-bit (baseline) to the optimized representation of sparsity on RGB with a lower bit-width, i.e., <8:8>. For energy estimation on the used CNN model, we found that the energy used in RGB color mode with 32-bit is considerably higher than the other lower bit-width and compressed color modes. Moreover, we show that lower bit-width implementations yield higher resource utilization and a lower memory bottleneck ratio. This work is suitable for inference on energy-limited devices, which are increasingly being used in the Internet of Things (IoT) systems that facilitate healthcare systems.

Efficient QCA Exclusive-or and Multiplexer Circuits Based on a Nanoelectronic-Compatible Designing Approach.

Quantum-dot cellular automata (QCA) are a transistorless computation approach which encodes binary information via configuration of charges among quantum dots. The fundamental QCA logic primitives are majority and inverter gates which can be utilized to design various QCA circuits. This study presents a novel approach to designing efficient QCA-based circuits based on Boolean expressions achieved from reconfiguration of five-input and three-input majority gates. Whereas the multiplexer and Exclusive-or are the most important fundamental logical circuits in digital systems, designing efficient and single layer structures without coplanar cross-over wiring is advantageous in QCA technology. In order to demonstrate the efficiency and usefulness of the proposed approach, simple and dense multiplexer and Exclusive-or structures are implemented. The proposed designs have significant improvement in terms of area, complexity, latency, and gate count in comparison to previous designs. The correct logical functionalities of presented structures have been authenticated using QCA designer tool.