Abstract
In the field of sensors, in areas such as industrial, clinical, or environment, it is common to find one dimensional (1D) formatted data (e.g., electrocardiogram, temperature, power consumption). A very promising technique for modelling this information is the use of One Dimensional Convolutional Neural Networks (1D CNN), which introduces a new challenge, namely how to define the best architecture for a 1D CNN. This manuscript addresses the concept of One Dimensional Neural Architecture Search (1D NAS), an approach that automates the search for the best combination of Neuronal Networks hyperparameters (model architecture), including both structural and training hyperparameters, for optimising 1D CNNs. This work includes the implementation of search processes for 1D CNN architectures based on five strategies: greedy, random, Bayesian, hyperband, and genetic approaches to perform, collect, and analyse the results obtained by each strategy scenario. For the analysis, we conducted 125 experiments, followed by a thorough evaluation from multiple perspectives, including the best-performing model in terms of accuracy, consistency, variability, total running time, and computational resource consumption. Finally, by presenting the optimised 1D CNN architecture, the results for the manuscript’s research question (a real-life clinical case) were provided.
Highlights
Convolutional Neural Networks (CNN) is a specific class of deep neural networks and perhaps the most popular algorithm among the deep learning environments
CNNs, as well as a search strategies comparison analysis, which certainly will benefit the community on 1D data modelling with the use of optimised 1D CNNs
The performance measured by the accuracy of the network was crucial for the success of the research, and the need for defining the optimal 1D CNN architecture for the problem arose
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Since the emergence of deep learning-based algorithms, the traditional machine learning techniques were limited to process data in raw format, which required careful feature engineering and extraction expertise to transform natural data into tabular forms (handcrafted features space). This process can achieve levels of complexity that often lead to information loss. The deep learning concept was first introduced in 2006 by a group of researchers of the Canadian Institute for Advanced Research (CIFAR) It refers to models composed by multiple processing layers, and each layer can learn representations with multiple levels of abstraction, capturing the full complexity within the data. Deep learning has recently been used successfully in many fields such as visual object recognition, speech and audio processing, natural language processing, object detection, among others [7,8,9,10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
