Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements
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 Ne...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/7990 |
| _version_ | 1827674641208967168 |
|---|---|
| author | João Rala Cordeiro António Raimundo Octavian Postolache Pedro Sebastião |
| author_facet | João Rala Cordeiro António Raimundo Octavian Postolache Pedro Sebastião |
| author_sort | João Rala Cordeiro |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T04:45:11Z |
| format | Article |
| id | doaj.art-29dc8950c1d3411fa95e00f6c39971fd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:45:11Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-29dc8950c1d3411fa95e00f6c39971fd2023-11-23T03:02:17ZengMDPI AGSensors1424-82202021-11-012123799010.3390/s21237990Neural Architecture Search for 1D CNNs—Different Approaches Tests and MeasurementsJoão Rala Cordeiro0António Raimundo1Octavian Postolache2Pedro Sebastião3Instituto de Telecomunicações (IT-IUL), Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, PortugalInstituto de Telecomunicações (IT-IUL), Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, PortugalInstituto de Telecomunicações (IT-IUL), Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, PortugalDepartment of Information Science and Technology, Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, PortugalIn 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.https://www.mdpi.com/1424-8220/21/23/7990Neural Architecture Search1D CNN1D NASCNN hyperparametersCNN architecture tuningtests and measurements |
| spellingShingle | João Rala Cordeiro António Raimundo Octavian Postolache Pedro Sebastião Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements Sensors Neural Architecture Search 1D CNN 1D NAS CNN hyperparameters CNN architecture tuning tests and measurements |
| title | Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements |
| title_full | Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements |
| title_fullStr | Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements |
| title_full_unstemmed | Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements |
| title_short | Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements |
| title_sort | neural architecture search for 1d cnns different approaches tests and measurements |
| topic | Neural Architecture Search 1D CNN 1D NAS CNN hyperparameters CNN architecture tuning tests and measurements |
| url | https://www.mdpi.com/1424-8220/21/23/7990 |
| work_keys_str_mv | AT joaoralacordeiro neuralarchitecturesearchfor1dcnnsdifferentapproachestestsandmeasurements AT antonioraimundo neuralarchitecturesearchfor1dcnnsdifferentapproachestestsandmeasurements AT octavianpostolache neuralarchitecturesearchfor1dcnnsdifferentapproachestestsandmeasurements AT pedrosebastiao neuralarchitecturesearchfor1dcnnsdifferentapproachestestsandmeasurements |