Abstract
COVID-19 has been spread around the world and has caused a huge number of deaths. Early detection of this disease is the most efficient way to prevent its rapid spread. Due to the development of internet technology and edge intelligence, developing an early detection system for COVID-19 in the medical environment of the Internet of Things (IoT) can effectively alleviate the spread of the disease. In this paper, a detection algorithm is developed, which can detect COVID-19 effectively by utilizing the features from Chest X-ray (CXR) images. First, a pre-trained model (ResNet18) is adopted for feature extraction. Then, a discrete social learning particle swarm optimization algorithm (DSLPSO) is proposed for feature selection. By filtering redundant and irrelevant features, the dimensionality of the feature vector is reduced. Finally, the images are classified by a Support Vector Machine (SVM) for COVID-19 detection. Experimental results show that the proposed algorithm can achieve competitive performance with fewer features, which is suitable for edge computing devices with lower computation power.
- [1] . 2020. The continuing 2019-nCoV epidemic threat of novel coronaviruses to global health - The latest 2019 novel coronavirus outbreak in Wuhan, China. Int. J. Infect. Dis. IJID Off. Publ. Int. Soc. Infect. Dis. 91, (2020), 264–266.
DOI: https://doi.org/10.1016/j.ijid.2020.01.009Google ScholarCross Ref
- [2] . 2020. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in Wuhan, China. JAMA 323, 11 (2020), 1061–1069.
DOI: https://doi.org/10.1001/jama.2020.1585Google ScholarCross Ref
- [3] . 2020. Sample-efficient deep learning for COVID-19 diagnosis based on CT scans. medRxiv (2020), 2020.04.13.20063941.
DOI: https://doi.org/10.1101/2020.04.13.20063941Google Scholar - [4] . 2020. COVID-19 detection using deep learning models to exploit social mimic optimization and structured chest X-ray images using fuzzy color and stacking approaches. Comput. Biol. Med. 121, (2020), 103805.
DOI: https://doi.org/10.1016/j.compbiomed.2020.103805Google ScholarCross Ref
- [5] World Health Organization. 2020. Laboratory testing for 2019 novel coronavirus (2019-nCoV) in suspected human cases. Retrieved from https://www.who.int/publications/i/item/10665-331501.Google Scholar
- [6] . 2018. Deep learning for image-based cancer detection and diagnosis − A survey. Pattern Recognit. 83, (2018), 134–149.
DOI: https://doi.org/10.1016/j.patcog.2018.05.014Google ScholarCross Ref
- [7] . 2019. Multi-modal deep learning model for auxiliary diagnosis of Alzheimer's disease. Neurocomputing 361, (2019), 185–195.
DOI: https://doi.org/10.1016/j.neucom.2019.04.093Google ScholarCross Ref
- [8] . 2020. Adaptive feature selection guided deep forest for COVID-19 classification with chest CT. IEEE J. Biomed. Health Inform. 24, 10 (2020), 2798–2805.
DOI: https://doi.org/10.1109/JBHI.2020.3019505Google ScholarCross Ref
- [9] . 2019. Smart-edge-CoCaCo: AI-enabled smart edge with joint computation, caching, communication in heterogeneous IoT. IEEE Netw 33, 2 (2019), 58–64.
DOI: https://doi.org/10.1109/MNET.2019.1800235Google ScholarCross Ref
- [10] . 2020. Explainable AI and mass surveillance system-based healthcare framework to combat COVID-I9 like pandemics. IEEE Netw 34, 4 (2020), 126–132.
DOI: https://doi.org/10.1109/MNET.011.2000458Google ScholarCross Ref
- [11] . 2020. COVID-19 Networking demand: An auction-based mechanism for automated selection of edge computing services. IEEE Trans. Netw. Sci. Eng. (2020), 1–1.
DOI: https://doi.org/10.1109/TNSE.2020.3026637Google Scholar - [12] . 2016. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision, Pattern Recognition (CVPR) 770–778.
DOI: https://doi.org/10.1109/CVPR.2016.90Google ScholarCross Ref
- [13] . 2020. COVID-Classifier: An automated machine learning model to assist in the diagnosis of COVID-19 infection in chest x-ray images. MedRxiv Prepr. Serv. Health Sci. (2020), 2020.05.09.20096560.
DOI: https://doi.org/10.1101/2020.05.09.20096560Google Scholar - [14] . 2020. COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images. Retrieved from https://arxiv.org/abs/2003.11055.Google Scholar
- [15] . 2020. Detection of coronavirus disease (COVID-19) based on deep features. (2020).
DOI: https://doi.org/10.20944/preprints202003.0300.v1Google Scholar - [16] . 2019. Transfusion: Understanding Transfer Learning for Medical Imaging. Retrieved from https://arxiv.org/abs/1902.07208. Google Scholar
Digital Library
- [17] . 2009. ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision, Pattern Recognition 248–255.
DOI: https://doi.org/10.1109/CVPR.2009.5206848Google Scholar - [18] 2020. Brain tumor detection using fusion of hand crafted and deep learning features. Cogn. Syst. Res. 59, (2020), 221–230.
DOI: https://doi.org/10.1016/j.cogsys.2019.09.007Google ScholarDigital Library
- [19] . 2019. A comparative study of deep learning architectures on melanoma detection. Tissue Cell 58, (2019), 76–83.
DOI: https://doi.org/10.1016/j.tice.2019.04.009Google ScholarCross Ref
- [20] 2018. The skin cancer classification using deep convolutional neural network. Multimed. Tools Appl. 77, 8 (2018), 9909–9924.
DOI: https://doi.org/10.1007/s11042-018-5714-1 Google ScholarDigital Library
- [21] . 1997. Feature selection for classification. Intell. Data Anal. 1, 3 (1997), 131–156. Google Scholar
Digital Library
- [22] . 2012. Manipulating data and dimension reduction methods: Feature selection. In Computational Complexity: Theory, Techniques, and Applications, (ed.). Springer New York, New York, NY, 1790–1800.
DOI: https://doi.org/10.1007/978-1-4614-1800-9_115Google ScholarCross Ref
- [23] . 2005. Toward integrating feature selection algorithms for classification and clustering. IEEE Trans. Knowl. Data Eng 17, 4 (2005), 491–502.
DOI: https://doi.org/10.1109/TKDE.2005.66 Google ScholarDigital Library
- [24] . 2016. A survey on evolutionary computation approaches to feature selection. IEEE Trans. Evol. Comput 20, 4 (2016), 606–626.
DOI: https://doi.org/10.1109/TEVC.2015.2504420Google ScholarDigital Library
- [25] . 1997. A discrete binary version of the particle swarm algorithm. In 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, 4104–4108 vol. 5.
DOI: https://doi.org/10.1109/ICSMC.1997.637339Google ScholarCross Ref
- [26] . 2020. A hyper learning binary dragonfly algorithm for feature selection: A COVID-19 case study. Knowl.-Based Syst. (2020), 106553.
DOI: https://doi.org/10.1016/j.knosys.2020.106553Google Scholar - [27] . 2015. A competitive swarm optimizer for large scale optimization. IEEE Trans. Cybern 45, 2 (2015), 191–204.
DOI: https://doi.org/10.1109/TCYB.2014.2322602Google ScholarCross Ref
- [28] . 2018. Feature selection for high-dimensional classification using a competitive swarm optimizer. Soft Comput 22, 3 (2018), 811–822.
DOI: https://doi.org/10.1007/s00500-016-2385-6Google ScholarCross Ref
- [29] 2014. Binary bat algorithm. Neural Comput. Appl. 25, 3 (2014), 663–681.
DOI: https://doi.org/10.1007/s00521-013-1525-5 Google ScholarDigital Library
- [30] . 2015. A social learning particle swarm optimization algorithm for scalable optimization. Inf. Sci. 291, (2015), 43–60.
DOI: https://doi.org/10.1016/j.ins.2014.08.039 Google ScholarDigital Library
- [31] . 2010. A novel set-based particle swarm optimization method for discrete optimization problems. IEEE Trans. Evol. Comput. 14, 2 (2010), 278–300.
DOI: https://doi.org/10.1109/TEVC.2009.2030331 Google ScholarDigital Library
- [32] . 2004. Overfitting in wrapper-based feature subset selection: The harder you try the worse it gets. In International Conference on Innovative Techniques and Applications of Artificial Intelligence, Springer 33–43.
DOI: https://doi.org/10.1007/1-84628-102-4_3.Google Scholar - [33] . 2020. An evolutionary algorithm for large-scale sparse multiobjective optimization problems. IEEE Trans. Evol. Comput 24, 2 (2020), 380–393.
DOI: https://doi.org/10.1109/TEVC.2019.2918140Google ScholarCross Ref
- [34] . 2020. Chest X-ray. Retrieved from www.kaggle.com/prashant268/chest-xray-covid19-pneumonia.Google Scholar
- [35] . 2018. MobileNetV2: Inverted residuals, linear bottlenecks. In 2018 IEEE/CVF Conference on Computer Vision, Pattern Recognition 4510–4520.
DOI: https://doi.org/10.1109/CVPR.2018.00474Google ScholarCross Ref
- [36] . 2018. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In 2018 IEEE/CVF Conference on Computer Vision, Pattern Recognition 6848–6856.
DOI: https://doi.org/10.1109/CVPR.2018.00716Google ScholarCross Ref
- [37] . 2016. SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and <0.5MB Model Size. Retrieved from https://arxiv.org/abs/1602.07360.Google Scholar
- [38] . 1991. Instance-based learning algorithms. Mach. Learn 6, 1 (1991), 37–66.
DOI: https://doi.org/10.1007/BF00153759 Google ScholarDigital Library
- [39] . 2004. Extreme learning machine: A new learning scheme of feedforward neural networks. In 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541) 985–990 2.
DOI: https://doi.org/10.1109/IJCNN.2004.1380068Google ScholarCross Ref
- [40] . 2020. Multimodal MR image synthesis using gradient prior and adversarial learning. IEEE J. Sel. Top. Signal Process 14, 6 (2020), 1176–1188.
DOI: https://doi.org/10.1109/JSTSP.2020.3013418Google ScholarCross Ref
- [41] . 2020. Deep learning for the identification of bruised apples by fusing 3D deep features for apple grading systems. Mech. Syst. Signal Process. 145, (2020), 106922.
DOI: https://doi.org/10.1016/j.ymssp.2020.106922Google ScholarCross Ref
- [42] . 2019. Scene classification via learning a multi-branch convolutional network. In 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) 2555–2559.
DOI: https://doi.org/10.1109/SMC.2019.8914533Google ScholarDigital Library
- [43] . 2021. Progressive global perception and local polishing network for lung infection egmentation of COVID-19 CT Images. Pattern Recognition 120, (2021), 108168.Google Scholar
Cross Ref
- [44] . 2018. Book title recognition for smart library with deep learning. In Mobile Multimedia/Image Processing, Security, and Applications 2018, International Society for Optics and Photonics, 106680A.
DOI: https://doi.org/10.1117/12.2312245Google Scholar - [45] . 2017. A noisy sparse convolution neural network based on stacked auto-encoders. In 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 3457–3461.
DOI: https://doi.org/10.1109/SMC.2017.8123165Google ScholarCross Ref
Index Terms
A COVID-19 Detection Algorithm Using Deep Features and Discrete Social Learning Particle Swarm Optimization for Edge Computing Devices
Recommendations
Accurate detection of COVID-19 using deep features based on X-Ray images and feature selection methods
AbstractCOVID-19 is a severe epidemic affecting the whole world. This epidemic, which has a high mortality rate, affects the health systems and the economies of countries significantly. Therefore, ending the epidemic is one of the most ...
Highlights- Deep learning models and traditional machine learning methods were used together.
Using Fuzzy Clustering with Deep Learning Models for Detection of COVID-19 Disinformation
Since the beginning of 2020, the COVID-19 pandemic has killed millions of people around the world, leading to a worldwide panic that has fueled the rapid and widespread dissemination of COVID-19-related disinformation on social media. The phenomenon, ...
Euclidean Particle Swarm Optimization
ICINIS '09: Proceedings of the 2009 Second International Conference on Intelligent Networks and Intelligent SystemsParticle swarm optimization (PSO) is a swarm intelligence algorithm, has been successfully applied to many engineering optimization problems and shown its high search speed in these applications. However, as the dimension and the number of local optima ...






Comments