Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. A significant part of generator diagnosis relies on Partial Discharge (PD) measurements, because the main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. A study of all stator failure mechanisms reveals that more than 85 % of them involve the presence of PD activity. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Québec has been collecting more than 33 000 unlabeled PD measurement files over the last decades. Up to now, this diagnostic technique has been quantified based on global PD amplitudes and integrated PD energy irrespective of the source of the PD signal. Several PD sources exist and they all have different relative risk, but in order to recognize the nature of the PD, or its source, the judgement of experts is required. In this paper, we propose a new method based on visual data analysis to build a PD source classifier with a minimum of labeled data. A convolutional variational autoencoder has been used to help experts to visually select the best training data set in order to improve the performances of the PD source classifier.

Power transformers (PTs) play a vital role in the electrical power system. Assessing their health to predict their remaining useful life is essential to optimise maintenance. Scheduling the right maintenance for the right equipment at the right time is the ultimate goal of any power system utility. Optimal maintenance has a number of benefits: human and social, by limiting sudden service interruptions, and economic, due to the direct and indirect costs of unscheduled downtime. PT now produces large amounts of easily accessible data due to the increasing use of IoT, sensors, and connectivity between physical assets. As a result, power transformer prognostics and health management (PT-PHM) methods are increasingly moving towards artificial intelligence (AI) techniques, with several hundreds of scientific papers published on the topic of PT-PHM using AI techniques. On the other hand, the world of AI is undergoing a new evolution towards a third generation of AI models: large-scale foundation models. What is the current state of research in PT-PHM? What are the trends and challenges in AI and where do we need to go for power transformer prognostics and health management? This paper provides a comprehensive review of the state of the art in PT-PHM by analysing more than 200 papers, mostly published in scientific journals. Some elements to guide PT-PHM research are given at the end of the document.