In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

/pdf/review-of-deep-learning-concepts-cnn-architectures-hpbk62qzc2.pdf

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Medical data widely exist in the hospital and personal life, usually across institutions and regions. They have essential diagnostic value and therapeutic significance. The disclosure of patient information causes people’s panic, therefore, medical data security solution is very crucial for intelligent health care. The emergence of federated learning (FL) provides an effective solution, which only transmits model parameters, breaking through the bottleneck of medical data sharing, protecting data security, and avoiding economic losses. Meanwhile, the neural architecture search (NAS) has become a popular method to automatically search the optimal neural architecture for solving complex practical problems. However, few papers have combined the FL and NAS for simultaneous privacy protection and model architecture selection. Convolutional neural network (CNN) has outstanding performance in the image recognition field. Combining CNN and fuzzy rough sets can effectively improve the interpretability of deep neural networks. This article aims to develop a multiobjective convolutional interval type-2 fuzzy rough FL model based on NAS (CIT2FR-FL-NAS) for medical data security with an improved multiobjective evolutionary algorithm. We test the proposed framework on the LC25000 lung and colon histopathological image dataset. Experimental verification demonstrates that the designed multiobjective CIT2FR-FL-NAS framework can achieve high accuracy superior to state-of-the-art models and reduce network complexity under the condition of protecting medical data security.

Federated Neural Architecture Search for Medical Data Security

Literature review: efficient deep neural networks techniques for medical image analysis

Over the past year, the world's attention has focused on combating COVID-19 disease, but the other threat waiting at the door-antimicrobial resistance should not be forgotten. Although making the diagnosis rapidly and accurately is crucial in preventing antibiotic resistance development, bacterial identification techniques include some challenging processes. To address this challenge, we proposed a deep neural network (DNN) that can discriminate antibiotic-resistant bacteria using surface-enhanced Raman spectroscopy (SERS). Stacked autoencoder (SAE)-based DNN was used for the rapid identification of methicillin-resistant Staphylococcus aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) bacteria using a label-free SERS technique. The performance of the DNN was compared with traditional classifiers. Since the SERS technique provides high signal-to-noise ratio (SNR) data, some subtle differences were found between MRSA and MSSA in relative band intensities. SAE-based DNN can learn features from raw data and classify them with an accuracy of 97.66%. Moreover, the model discriminates bacteria with an area under curve (AUC) of 0.99. Compared to traditional classifiers, SAE-based DNN was found superior in accuracy and AUC values. The obtained results are also supported by statistical analysis. These results demonstrate that deep learning has great potential to characterize and detect antibiotic-resistant bacteria by using SERS spectral data.

/pdf/drug-resistant-staphylococcus-aureus-bacteria-detection-by-57qg6fskau.pdf

Qingchen Zhang

Papers

Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement and perspectives

A deep residual computation model for heterogeneous data learning in smart Internet of Things