1D convolutional neural networks and applications: A survey

Kıranyaz, Serkan; Avcı, Onur; Abdeljaber, Osama; İnce, Türker; Gabbouj, Moncef; Inman, Daniel J.

doi:10.1016/j.ymssp.2020.107398

Cited by 1,430 publications

(711 citation statements)

References 63 publications

Supporting

Mentioning

514

Contrasting

Unclassified

Order By: Relevance

“…Recent studies show that 1D‐CNNs with relatively shallow architectures (i.e. a small number of hidden layers and perceptrons) can learn challenging tasks involving 1D features [50]. On the other hand, the 2D‐CNNs model requires more profound, more in‐depth architecture for training and implementation.…”

Section: Related Workmentioning

confidence: 99%

Multi‐model deep learning approach for collaborative filtering recommendation system

Aljunid

Huchaiah

2020

CAAI trans. intell. technol.

View full text Add to dashboard Cite

As a result of a huge volume of implicit feedback such as browsing and clicks, many researchers are involving in designing recommender systems (RSs) based on implicit feedback. Though implicit feedback is too challenging, it is highly applicable to use in building recommendation systems. Conventional collaborative filtering techniques such as matrix decomposition, which consider user preferences as a linear combination of user and item latent features, have limited learning capacities, hence suffer from a cold start and data sparsity problems. To tackle these problems, the research direction towards considering the integration of conventional collaborative filtering with deep neural networks to maps user and item features. Conversely, the scalability and the sparsity of the data affect the performance of the methods and limit the worthiness of the results of the recommendations. Therefore, the authors proposed a multi‐model deep learning (MMDL) approach by integrating user and item functions to construct a hybrid RS and significant improvement. The MMDL approach combines deep autoencoder with a one‐dimensional convolution neural network model that learns user and item features to predict user preferences. From detail experimentation on two real‐world datasets, the proposed work exhibits substantial performance when compared to the existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi‐model deep learning approach for collaborative filtering recommendation system

Aljunid

Huchaiah

2020

CAAI trans. intell. technol.

View full text Add to dashboard Cite

show abstract

“…One-dimensional convolutional neural networks (1D-CNN) are being used to great effect in time series processing [3]. Hannum et al show a convolutional network can outperform cardiologists in heart arrhythmia detection [4].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Deep Neural Network and Reconstructed Phase Space Approach to Classifying 12-lead ECGs

Kaftan

Povinelli

2020

2020 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

The aim of this work is to classify 12-lead ECGs into 26 classes, including normal sinus rhythm, atrial fibrillation, left bundle branch block, and ST-segment depression and elevation. This work is team Marquette's submission to the PhysioNet/Computing in Cardiology Challenge 2020. Our approach is to apply two modelling techniques: a reconstructed phase space-Gaussian mixture model (RPS-GMM) method and a one-dimensional convolutional neural network. The one-dimensional convolutional neural network consists of 11 layers consisting of both convolutional and fully connected layers. It takes inputs of varying lengths to output a single diagnosis and is trained from scratch within the competition time limits. Our second method, the RPS-GMM approach, embeds each ECG lead into an 11-dimensional space and classifies using a maximum likelihood classifier. While we propose and discuss two methods only the deep convolutional neural network was used in our submissions. The RPS-GMM approach was not scored as it exceeded the competition training time limit. We achieved a score of 0.492 on the test data, but were not ranked due to omissions in the submission. Next steps include reducing the training time of the RPS-GMM approach and ensembling the two methods.

show abstract

“…Any central processing unit application on a standard computer is sufficient and relatively fast to train compact 1D-CNNs containing several hidden layers, each with multiple neurons (usually <50). Due to their low calculation requirements, compact 1D-CNNs are particularly suitable for real-time and low-cost applications, especially on mobile or handheld devices [58-60].…”

Section: Introductionmentioning

confidence: 99%

“…In 1D-CNN applications, the raw EEG signal is presented as an input to the CNN model as a numeric data form that makes the EEG signal graph [58-60]. Although CNN models eliminate the need for manual feature extraction, they can produce a reliable estimate only with a large number of data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Epileptic Seizure Using Pretrained Deep Convolutional Neural Network and Transfer Learning

2020

View full text Add to dashboard Cite

Introduction: The diagnosis of epilepsy takes a certain process, depending entirely on the attending physician. However, the human factor may cause erroneous diagnosis in the analysis of the EEG signal. In the past 2 decades, many advanced signal processing and machine learning methods have been developed for the detection of epileptic seizures. However, many of these methods require large data sets and complex operations. Methods: In this study, an end-to-end machine learning model is presented for detection of epileptic seizure using the pretrained deep two-dimensional convolutional neural network (CNN) and the concept of transfer learning. The EEG signal is converted directly into visual data with a spectrogram and used directly as input data. Results: The authors analyzed the results of the training of the proposed pretrained AlexNet CNN model. Both binary and ternary classifications were performed without any extra procedure such as feature extraction. By performing data set creation from short-term spectrogram graphic images, the authors were able to achieve 100% accuracy for binary classification for epileptic seizure detection and 100% for ternary classification. Discussion/Conclusion: The proposed automatic identification and classification model can help in the early diagnosis of epilepsy, thus providing the opportunity for effective early treatment.

show abstract

1D convolutional neural networks and applications: A survey

Cited by 1,430 publications

References 63 publications

Multi‐model deep learning approach for collaborative filtering recommendation system

Multi‐model deep learning approach for collaborative filtering recommendation system

A Deep Neural Network and Reconstructed Phase Space Approach to Classifying 12-lead ECGs

Detection of Epileptic Seizure Using Pretrained Deep Convolutional Neural Network and Transfer Learning

Contact Info

Product

Resources

About