With the recent advancements in analysing high volume, complex and unstructured data, modern learning methods are playing an increasingly critical role in the field of personalised medicine. Personalised medicine, which refers to providing tailored medical treatment to individual patients through the identification of common features, including their genetics, inheritance, and lifestyle, has attracted the attention of many researchers over the recent years. This review paper provides an overview of the research progress in application of learning methods with the focus on deep learning in personalised medicine. In particular, three domains of applications are reviewed, including drug development, disease characteristics identification, and therapeutics effect prediction. The main objective of this survey is to consider the applied methods in detail and to offer insights into their pros and cons. Although having demonstrated advantages in coping with data complexity and nonlinearity, and in recognising features and associating structural data, the studied learning methods are not a panacea to all the medical problems. Hence, we discuss the existing research challenges and clarify the future study directions.
Industry 4.0 aims to transform chemical and biochemical processes into intelligent systems via the integration of digital components with the actual physical units involved. This process can be thought of as addition of a central nervous system with a sensing and control monitoring of components and regulating the performance of the individual physical assets (processes, units, etc.) involved. Established technologies central to the digital integrating components are smart sensing, mobile communication, Internet of Things, modelling and simulation, advanced data processing, storage and analysis, advanced process control, artificial intelligence and machine learning, cloud computing, and virtual and augmented reality. An essential element to this transformation is the exploitation of large amounts of historical process data and large volumes of data generated in real-time by smart sensors widely used in industry. Exploitation of the information contained in these data requires the use of advanced machine learning and artificial intelligence technologies integrated with more traditional modelling techniques. The purpose of this paper is twofold: a) to present the state-of-the-art of the aforementioned technologies, and b) to present a strategic plan for their integration toward the goal of an autonomous smart plant capable of self-adaption and self-regulation for short- and long-term production management.
This article proposes a novel method to optimise the Dynamic Architecture Neural Network (DAN2) adapted for a multi-task learning problem. The multi-task learning neural network adopts a multi-head and serial architecture with DAN2 layers acting as the basic subroutine. Adopting a dynamic architecture, the layers are added consecutively starting from a minimal initial structure. The optimisation method adopts an iterative heuristic scheme that sequentially optimises the shared layers and the task-specific layers until the solver converges to a small tolerance. Application of the method has demonstrated the applicability of the algorithm to simulated datasets. Comparable results to Artificial Neural Networks (ANNs) have been obtained in terms of accuracy and speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.