2. Background
For the reader’s convenience, we briefly explain the technologies that were employed in this section.
Several fall detection systems exist in literature. A recent review of the fall detection systems in [
5] categorizes them as follows: (i) wearable devices, (ii) ambient systems, (iii) image processing systems and (iv) combined systems. Wearable devices provide a cheaper and more practical solution in terms of freedom of movement and energy consumption. The aim of most fall detection systems is not only to detect a fall but also to inform concerned authorities in case of an urgent medical emergency. Most of the latest algorithms for fall detection use machine learning [
6] and deep learning algorithms [
7].
Deep learning became prominent in computer vision (CV) when a deep learning convolution neural network, AlexNet, outperformed its competitors in the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) in 2012 during an image classification task. Before the wide spread recognition of deep learning, features from the data had to be hand crafted and then fed into a machine learning model. Deep learning in general and convolutional neural networks (CNNs) in particular, have revolutionized the field by not only detecting the features themselves but the features selected by them have been proven to be more significant than those crafted by hand [
8].
According to [
9], “transfer learning is a machine learning method where a learning model developed for a first learning task is reused as the starting point for a learning model in a second learning task.”
It can also be defined as the ability of a system to recognize and apply knowledge and skills learned in previous domains/tasks to novel domains/tasks, which share some commonality [
10]. Transfer learning has been formally defined and categorized in [
10]. The problem statement, notation and definition used here are also taken from [
10]. A domain
is comprised of two components: a feature space
and a marginal probability
, where
. Similarly, given a specific domain,
, a task consists of two components: a label space
and an objective predictive function
(denoted by
), which is not observed but can be learned from the training data, which consist of pairs
, where
and
. The function
can be used to predict the corresponding label,
, of a new instance x. From a probabilistic viewpoint, f(x) can be written as
.
Formally transfer learning is defined as, “Given a source domain and learning task , a target domain and learning task , transfer learning aims to help improve the learning of the target predictive function (.) in using the knowledge in and , where , or .”
Transferring knowledge from one domain to another using transfer learning is not only of theoretical interest, but also of great practical importance, as it can spare a lot of training time and resources and by reducing the data necessary in a domain, it can make learning feasible at all. In our work we have transferred the knowledge gained from training neural networks with natural images to the domain of synthetic, artificial medical images in order to classify images, that were created as a result of pre-processing medical data such as ECG data.
3. Related Work and Our Contribution
This section reviews the work that has been previously done to detect falls using different methods and highlights our contribution to the field. Many surveys and reviews, such as [
11,
12,
13], exist in literature which describe different fall detection techniques, standard experimental protocols for fall simulations and their relative advantages and disadvantages. Detecting fall comes under the vast umbrella of human activity recognition (HAR). HAR is usually considered a computer vision (CV) problem where CV algorithms are used on images or videos to distinguish one activity from another. However, other device-free solutions based on, e.g., radio signals, such as received signal strength (RSSI) or channel state information (CSI) exist; see, e.g., [
14,
15,
16]. Alternatively, wearable sensors provide a resource friendly and practical solution to real time activity recognition, e.g., in particular the rising popularity of gadgets such as smartwatches is an indicator for this trend. Many studies like [
17,
18] infuse readings from accelerometers and ECG sensors at decision level to determine an activity. Though the wavelet transform has been previously used for analyzing ECG signals for detecting different cardiac conditions as reviewed in [
19], it has never been used separately to differentiate a fall from non-fall. Similarly [
20] analyzes the impact of body movements on ambulatory ECG frequency spectrum. It also uses artificial neural networks to classify different body movements.
The ECG signals predict the overall health of the human body. A considerable amount of effort has already been contributed to the area of fall detection using accelerometers and gyroscopes. Some studies, such as that in [
21], have used different machine learning techniques on these sensor readings to predict and detect the fall. Few studies use ECG signals to predict the falls like in [
22], but our study uses the frequency-time domain of the ECG signals by computing their continuous wavelet transform (CWT) coefficients and converting them into scalograms. The overall idea is mainly inspired by [
23] where a convolutional neural network (CNN) has been trained on scalograms to differentiate between different heart diseases using ECG signals. Similar approach was used in our study to differentiate between falls and no-falls ECG signals.
The CNN we utilize has also been used in [
24] to extract features for bio-metric purposes using gait features from sensor data. However, in our work, for the first time we classify the following activities using ECG signals:
Fall,
Resting, and general
Daily Activities, i.e., we distinguish not only
Fall from
Resting but also
Fall from
Daily Activities, where
Daily Activities refer to generic daily activities performed by the subjects. The fall risk using heart rate variability in combination with data mining techniques is assessed in [
25].
In this paper, we have tried to explore the research question, “Can a fall be detected by using only ECG signals?” by collecting the ECG signals of people falling and then applying our proposed algorithm on the signals. The purpose of this study is to use the biomedical electrical signals of the heart via electrocardiogram to train a deep neural network to analyze and observe the patterns of ECG before and during the fall. Although a lot of work has already been done to detect falls using accelerometers and gyroscopes along with heart rate variability, the focus of this study has been to use ECG as the only factor to determine the presence of fall. Here we are not referring to the cases where cause of the fall is due to a specific heart condition.
This study has explored the less studied field of ECG signals for fall detection by applying machine learning techniques in it. It is based partially on [
26] but extends the results obtained therein substantially.
In the field of medical imaging, finding an appropriate amount of data has always been a challenge. That is mainly due to two reasons: Firstly, because of strict data privacy issues, and secondly, finding a large group of volunteers for conducting experiments can be challenging. A data augmentation technique for time series called slicing was used to enhance the limited dataset.
For the machine learning domain, we used transfer learning and compared two of the popular pre-trained networks for image classification—AlexNet and GoogLeNet. We have demonstrated that it could be really beneficial to use a pre-trained network in medical imaging domain as it does not require a lot of data. However, we would like to emphasize that it is an initial study with a focus on the proof of concept in a laboratory set up. It is not conclusive enough to be deployed but it does provide a strong baseline for further workt.
Author Contributions
Conceptualization L.L.B., F.S.B., J.S. and M.F.W.; methodology F.S.B., J.S. and M.F.W.; validation F.S.B.; formal analysis F.S.B., J.S. and M.F.W.; resources F.S.B.; data curation L.L.B., and F.S.B.; writing—original draft preparation F.S.B.; writing—review and editing J.S., I.M.-B., D.G.-U. and M.F.W.; visualization F.S.B.; supervision J.S., I.M.-B., D.G.-U. and M.F.W. All authors have read and agreed to the published version of the manuscript.
Funding
This research was funded by the research support program of Fb2, Frankfurt University of Applied Sciences. The research of D.G.-U. has been supported in part by the Spanish MICINN under grants PGC2018-096504-B-C33 and RTI2018-100754-B-I00, the European Union under the 2014-2020 ERDF Operational Programme and the Department of Economy, Knowledge, Business and University of the Regional Government of Andalusia (project FEDER-UCA18-108393). The research of I.M.-B. has been supported in part by the European Commission (ERDF), the Spanish Ministry of Science, Innovation and Universities [RTI2018-093608-BC33].
Institutional Review Board Statement
Our study was conducted with healthy volunteers. Each participant gave written consent to allow measurement data and images to be anonymized and used for publications. A risk assessment was established with assistance from the medical doctor, safety officer and occupational safety specialist of the university, which includes safety precautions to minimize all possible injury risks. These precautions had to be strictly respected, and all participants were instructed and encouraged to follow our instructions before starting the tests to prevent injury. Our study was conducted in accordance with the ethical principles of the Declaration of Helsinki.
Informed Consent Statement
Informed consent was obtained from all subjects involved in the study.
Data Availability Statement
Acknowledgments
We thank the volunteers who participated in the fall detection experiments for their time and effort. Their valuable input has lead to beneficial results which were critical to this study. We are thankful to Lorena Gutiérrez-Madroñal from the Department of Computer Science and Engineering, University of Cádiz for her software and assistance in the initial filtration of the raw ECG sensor files. We would also like to thank Sameen Arshad for her insight during the validation of ECG sensor readings and for her medical advice on ECG analysis.
Conflicts of Interest
The authors declare no conflict of interest.
Abbreviations
The following abbreviations are used in this manuscript:
ADC | Analog to Digital Conversion |
BLE | Bluetooth Low Energy |
CNN | Convolutional Neural Network |
CPU | Central Processing Unit |
CV | Computer Vision |
CWT | Continuous Wavelet Transform |
DA | Daily Activities |
ECG | Electrocardiogram |
FIR | Finite Impulse Response |
GPU | Graphics Processing Unit |
HAR | Human Activity Recognition |
IIR | Infinite Impulse Response |
ILR | Initial Learning Rate |
LSTM | Long Short-Term Memory |
PLI | Power Line Interface |
RMSprop | Root Mean Square Propagation |
SGDM | Stochastic Gradient Descent with Momentum |
References
- World Health Organization. WHO Global Report on Falls Prevention in Older Age; WHO: Geneva, Switzerland, 2007. [Google Scholar]
- Allcock, L.M.; O’Shea, D. Diagnostic yield and development of a Neuro cardiovascular investigation unit for older adults in a district hospital. J. Gerontol. Ser. A Biol. Sci. Med Sci. 2000, 55, M458–M462. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Tinetti, M.E. Factors Associated with Serious Injury During Falls by Ambulatory Nursing Home Residents. J. Am. Geriatr. Soc. 1987, 35, 644–648. [Google Scholar] [CrossRef] [PubMed]
- Wild, D.; Nayak, U.S.; Isaacs, B. How dangerous are falls in old people at home? Br. Med. J. 1981, 282, 266–268. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wang, Z.; Ramamoorthy, V.; Gal, U.; Guez, A. Possible Life Saver: A Review on Human Fall Detection Technology. Robotics 2020, 9, 55. [Google Scholar] [CrossRef]
- Genoud, D.; Cuendet, V.; Torrent, J. Soft Fall Detection Using Machine Learning in Wearable Devices. In Proceedings of the 2016 IEEE 30th International Conference on Advanced Information Networking and Applications (AINA), Crans-Montana, Switzerland, 23–25 March 2016; pp. 501–505. [Google Scholar] [CrossRef]
- Lu, N.; Wu, Y.; Feng, L.; Song, J. Deep Learning for Fall Detection: Three-Dimensional CNN Combined with LSTM on Video Kinematic Data. IEEE J. Biomed. Health Inform. 2019, 23, 314–323. [Google Scholar] [CrossRef]
- Lundervold, A.S.; Lundervold, A. An overview of deep learning in medical imaging focusing on MRI. Z. Med. Phys. 2019, 29, 102–127. [Google Scholar] [CrossRef]
- Tan, C.; Sun, F.; Kong, T.; Zhang, W.; Yang, C.; Liu, C. A Survey on Deep Transfer Learning. In Artificial Neural Networks and Machine Learning— ICANN 2018; Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I., Eds.; Springer International Publishing: Berlin/Heidelberg, Germany, 2018; pp. 270–279. [Google Scholar]
- Pan, S.J.; Yang, Q. A Survey on Transfer Learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–1359. [Google Scholar] [CrossRef]
- Xu, T.; Zhou, Y.; Zhu, J. New Advances and Challenges of Fall Detection Systems: A Survey. Appl. Sci. 2018, 8, 418. [Google Scholar] [CrossRef] [Green Version]
- Igual, R.; Medrano, C.; Plaza, I. Challenges, issues and trends in fall detection systems. Biomed. Eng. Online 2013, 12, 66. [Google Scholar] [CrossRef] [Green Version]
- Vallabh, P.; Malekian, R. Fall detection monitoring systems: A comprehensive review. J. Ambient. Intell. Humaniz. Comput. 2018, 9, 1809–1833. [Google Scholar] [CrossRef]
- Wang, Y.; Jiang, X.; Cao, R.; Wang, X. Robust Indoor Human Activity Recognition Using Wireless Signals. Sensors 2015, 15, 17195–17208. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Damodaran, N.; Schäfer, J. Device Free Human Activity Recognition using WiFi Channel State Information. In Proceedings of the 2019 IEEE SmartWorld, Ubiquitous Intelligence Computing, Advanced Trusted Computing, Scalable Computing Communications, Cloud Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom /IOP/SCI), Leicester, UK, 19–23 August 2019; pp. 1069–1074. [Google Scholar] [CrossRef]
- Damodaran, N.; Haruni, E.; Kokhkharova, M.; Schäfer, J. Device free human activity and fall recognition using WiFi channel state information (CSI). CCF Trans. Pervasive Comput. Interact. 2020, 2, 1–17. [Google Scholar] [CrossRef] [Green Version]
- Jia, R.; Liu, B. Human daily activity recognition by fusing accelerometer and multi-lead ECG data. In Proceedings of the 2013 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2013), KunMing, China, 5–8 August 2013; pp. 1–4. [Google Scholar] [CrossRef]
- Castro, D.; Coral, W.; Rodriguez, C.; Cabra, J.; Colorado, J. Wearable-Based Human Activity Recognition Using an IoT Approach. J. Sens. Actuator Netw. 2017, 6, 28. [Google Scholar] [CrossRef] [Green Version]
- Addison, P.S. Wavelet transforms and the ECG: A review. Physiol. Meas. 2005, 26, R155–R199. [Google Scholar] [CrossRef] [Green Version]
- Kher, D.R.; Pawar, T.; Thakar, D. Impact Analysis of Body Movements on Wearable Ambulatory Electrocardiogram; OMICS International: Hyderabad, India, 2015. [Google Scholar] [CrossRef]
- Turan, A.; Barshan, Ö.; Barshan, B. Detecting Falls with Wearable Sensors Using Machine Learning Technique. Sensors 2014, 14, 10691–10708. [Google Scholar]
- Md Shahiduzzaman. Fall detection by Acceleromeer and Heart rate variability Measurement. Glob. J. Comput. Sci. Technol. G Interdiscip. 2015, 15. Available online: https://computerresearch.org/index.php/computer/article/view/1328 (accessed on 29 January 2021).
- MathWorks. Classify Time Series Using Wavelet Analysis and Deep Learning. Available online: https://de.mathworks.com/help/wavelet/examples/signal-classification-with-wavelet-analysis-and-convolutional-neural-networks.html (accessed on 20 August 2018).
- Hoang, H.V.; Tran, M. DeepSense-Inception: Gait Identification from Inertial Sensors with Inception-like Architecture and Recurrent Network. In Proceedings of the 2017 13th International Conference on Computational Intelligence and Security (CIS), Hong Kong, China, 15–18 December 2017; pp. 594–598. [Google Scholar] [CrossRef]
- Melillo, P.; Castaldo, R.; Sannino, G.; Orrico, A.; de Pietro, G.; Pecchia, L. Wearable technology and ECG processing for fall risk assessment, prevention and detection. In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 25–29 August 2015; pp. 7740–7743. [Google Scholar] [CrossRef]
- Butt, F.S. Fall Detection Using Machine Learning Techniques on ECG Signals. Master’s Thesis, Frankfurt University of Applied Sciences, Frankfurt am Main, Germany, 2019. [Google Scholar]
- Kim, Y.G.; Shin, D.; Park, M.Y.; Lee, S.; Jeon, M.S.; Yoon, D.; Park, R.W. ECG-ViEW II, a freely accessible electrocardiogram database. PLoS ONE 2017, 12, e0176222. [Google Scholar] [CrossRef]
- Goldberger, A.L.; Amaral, L.A.N.; Glass, L.; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K.; Stanley, H.E. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000, 101, e215–e220. [Google Scholar] [CrossRef] [Green Version]
- La Blunda, L.; Corral-Plaza, D.; Wagner, M.; Ortiz, G.; Medina-Bulo, I. Distributed real-time based human activity analysis system. In Proceedings of the 16th International Conference on Applied Computing in Cagliari (ITALY), Cagliari, Italy, 7–9 November 2019; Volume 6. [Google Scholar]
- La Blunda, L. Fall event Analysis based on sensor fusion. In Proceedings of the Las Jornadas Predoctorales de la Escuela Superior de Ingeniería (JORPRESI), Cádiz, Spain, 2 November 2017. [Google Scholar]
- La Blunda, L.; Gutiérrez-Madroñal, L.; Wagner, M.F.; Medina-Bulo, I. A Wearable Fall Detection System Based on Body Area Networks. IEEE Access 2020, 8, 193060–193074. [Google Scholar] [CrossRef]
- World Medical Association. World Medical Association Declaration of Helsinki: Ethical principles for medical research involving human subjects. JAMA 2013, 310, 2191–2194. [Google Scholar] [CrossRef] [Green Version]
- Dickinson, D.F. The normal ECG in childhood and adolescence. Heart 2005, 91, 1626–1630. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Sucerquia, A.; López, J.; Vargas-Bonilla, J.F. SisFall: A Fall and Movement Dataset. Sensors 2017, 17, 198. [Google Scholar] [CrossRef]
- Fleming, J.; Brayne, C. Inability to get up after falling, subsequent time on floor, and summoning help: Prospective cohort study in people over 90. BMJ 2008, 337. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Jing, N. Detecting Human Falls with a 3-Axis Digital Accelerometer. Analog Dialogue 2009, 43, 3. [Google Scholar]
- Roggen, D.; Calatroni, A.; Rossi, M.; Holleczek, T.; Förster, K.; Tröster, G.; Lukowicz, P.; Bannach, D.; Pirkl, G.; Ferscha, A.; et al. Collecting complex activity datasets in highly rich networked sensor environments. In Proceedings of the 2010 Seventh International Conference on Networked Sensing Systems (INSS), Kassel, Germany, 15–18 June 2010; pp. 233–240. [Google Scholar] [CrossRef] [Green Version]
- Ordóñez, F.J.; Roggen, D. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors 2016, 16, 115. [Google Scholar] [CrossRef] [Green Version]
- Reiss, A.; Stricker, D. Physical Activity Monitoring Data Set. 2012. Available online: http://archive.ics.uci.edu/ml/datasets/PAMAP2+Physical+Activity+Monitoring (accessed on 2 February 2021).
- Zappi, P.; Lombriser, C.; Stiefmeier, T.; Farella, E.; Roggen, D.; Benini, L.; Tröster, G. Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection. In European Conference on Wireless Sensor Networks; Springer: Berlin/Heidelberg, Germany, 2008; pp. 17–33. [Google Scholar]
- Guan, Y.; Plötz, T. Ensembles of Deep LSTM Learners for Activity Recognition Using Wearables. In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies; ACM: New York, NY, USA, 2017; Volume 1. [Google Scholar] [CrossRef] [Green Version]
- Analog to Digital Conversion. Available online: https://learn.sparkfun.com/tutorials/analog-to-digital-conversion/all (accessed on 2 December 2018).
- Manivel, K.; Ravindran, R.S. Noise Removal for Baseline wander and power line in Electrocardiograph Signals. Int. J. Adv. Res. Electr. Electron. Instrum. Eng. 2015, 4, 1114–1122. [Google Scholar]
- Das, N.; Chakraborty, M. Performance Analysis of FIR and IIR filters for ECG Signal De-noising based on SNR. In Proceedings of the 2017 Third International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Kolkata, India, 3–5 November 2017. [Google Scholar]
- Zhang, D. Wavelet Approach for ECG Baseline Wander Correction and Noise Reduction. In Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, 1–4 September 2005; pp. 1105–1108. [Google Scholar]
- Ara, I.; Hossain, M.N.; Mahbub, S.Y. Baseline drift removal and de-noising of the ECG signal using Wavelet Transform. Int. J. Comput. Appl. 2014, 95, 15–17. [Google Scholar] [CrossRef]
- Lenis, G.; Pilia, N.; Loewe, A.; Schulze, W.H.W.; Dössel, O. Comparison of Baseline Wander Removal Techniques considering the preservation of ST changes in the Ischemic ECG: A simulation Study. Comput. Math. Methods Med. 2017, 2017, 9295029. [Google Scholar] [CrossRef]
- Sanjit, K.M. Digital Signal Processing; McGraw-Hill: New York, NY, USA, 1998. [Google Scholar]
- Milchevski, A.; Guse, M. Performance Evaluation of FIR and IIR Filtering of ECG Signals. In International Conference on ICT Innovations; Springer: Berlin/Heidelberg, Germany, 2016; pp. 103–112. [Google Scholar]
- Rani, S.; Kaur, A.; Ubhi, J.S. Comparative study of FIR and IIR filters for the removal of Baseline noises from ECG signal. Int. J. Comput. Sci. Inf. Technol. 2011, 2, 1105–1108. [Google Scholar]
- Yosinski, J.; Clune, J.; Bengio, Y.; Lipson, H. How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems 27; Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2014; pp. 3320–3328. [Google Scholar]
- ImageNet. Available online: http://www.image-net.org/ (accessed on 7 December 2018).
- Shin, H.; Roth, H.R.; Gao, M.; Lu, L.; Xu, Z.; Nogues, I.; Yao, J.; Mollura, D.J.; Summers, R.M. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans. Med Imaging 2016, 35, 1285–1298. [Google Scholar] [CrossRef] [Green Version]
- Visualize Activations of a Convolutional Neural Network. Available online: https://de.mathworks.com/help/deeplearning/examples/visualize-activations-of-a-convolutional-neural-network.html (accessed on 10 December 2018).
- Kher, R. Wearable Ambulatory Electrocardiogram (ECG) and EEG Dataset. IEEE Dataport. 2020. [Google Scholar] [CrossRef]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going Deeper with Convolutions. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems; Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2012; Volume 25, pp. 1097–1105. [Google Scholar]
- Iwana, B.K.; Uchida, S. An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks. arXiv 2020, arXiv:2007.15951. [Google Scholar]
- Cui, Z.; Chen, W.; Chen, Y. Multi-Scale Convolutional Neural Networks for Time Series Classification. arXiv 2016, arXiv:1603.06995. [Google Scholar]
- Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; pp. 248–255. [Google Scholar]
- Robbins, H.; Monro, S. A stochastic approximation method. Ann. Math. Stat. 1951, 22, 400–407. [Google Scholar] [CrossRef]
- Qian, N. On the momentum term in gradient descent learning algorithms. Neural Netw. 1999, 12, 145–151. [Google Scholar] [CrossRef]
- Geoffrey Hinton, N.S.; Swersky, K. Neural Networks for Machine Learning Online Course. Available online: https://www.classcentral.com/course/neuralnets-398 (accessed on 2 February 2021).
- Tan, M.; Le, Q.V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv 2020, arXiv:1905.11946. [Google Scholar]
| Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).