article · IEEE Access
Convolutional neural networks have transformed automated vision tasks, enabling breakthroughs in facial recognition, self-driving systems, and complex medical diagnostics. While standard two-dimensional and three-dimensional configurations achieve high performance, they remain ill-suited for domain-specific applications requiring the capture of temporal dynamics and dependencies, such as time series forecasting and signal identification. One-dimensional convolutional neural networks have emerged to process one-dimensional signals effectively, leading to competitive models across multiple fields. A comprehensive overview details the historical progression, structural mechanics, and architectural designs of these one-dimensional networks. It covers recent progress across more than twelve separate application domains, alongside key obstacles that affect the training and operational deployment of these models. Understanding these design principles and technical barriers provides clearer guidance for refining sequential and signal-based deep learning systems.
Many real-world systems rely on sequential measurements, from health diagnostics to operational sensors, rather than static pictures. Two-dimensional vision algorithms often fail to process these dynamic signals efficiently. Examining the progress and hurdles of one-dimensional neural networks helps engineers select appropriate models for time series data, improving automated processing and predictive accuracy across diverse technological domains.
One-dimensional networks are relevant to developers and industry partners building systems for time series forecasting, signal identification, autonomous driving, and medical diagnostics. Because this work reviews existing architectures and operational hurdles rather than introducing a single product, the technology spans varied readiness levels across twelve distinct domains, ranging from early research to deployed systems facing active training and integration challenges.
AI-generated from the published abstract. Always read the original work before citing.
Deep learning architectures have brought about new heights in computer vision, with the most common approach being the Convolutional Neural Network (CNN). Through CNN, tasks previously deemed unattainable, including facial recognition, autonomous driving systems, and sophisticated medical diagnostics, among others can now be achieved. Convolutional layers, non-linear processing units, and subsampling layers are used in conjunction throughout the several learning phases that make up CNN’s structure. Generally, 2D and 3D CNNs have been used to achieve impressive results across numerous areas, and several survey papers have been published to review their state-of-the-art applications. However, they are unsuitable in some domain-specific areas where temporal dynamics and dependencies must be captured. Examples of such domains are time series prediction and signal identification, which necessitates the use of one-dimensional signals. Recently, 1D-CNN has evolved and has been used to develop various state-of-the-art models that cut across numerous research fields. However, there has been no survey paper detailing the evolution and advancements in the applications of the 1D-CNN to several computer vision tasks. In addressing this gap, this paper provides the first exhaustive survey to examine the historical development of 1D-CNNs and elucidate their structural intricacies and architectural frameworks. It also highlights recent advancements in their applications across more than twelve distinct domains. Furthermore, this paper provides an overview of the significant challenges impacting the current state-of-the-art 1D-CNN training and deployment while highlighting potential directions for future research exploration. By carrying out this survey, researchers across several fields can have a comprehensive understanding of the evolution, structural intricacies, and recent advancements in the applications of 1D-CNNs across various computer vision tasks. This paper also equip researchers with the knowledge needed to address the significant challenges faced in the current state-of-the-art 1D-CNN hurdles.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3433513
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
