Skip to content
Research Article Open access CC BY 4.0

Development of a COVID-19 Patients’ Fatality Prediction System Using Swarm Intelligent Convolution Neural Network

A. E. A. Kareem, O. A. Odeniyi, N. T. A. Lawal

Asian Journal of Research in Computer Science · pp. 12–35 · Published 6 Jun 2023

10.9734/ajrcos/2023/v16i2336

Abstract

Aims: This work aims to develop a system that can be used to accurately and timely predict the fatality of a positively tested COVID-19 patient through the use of a deep learning technique – a swarm intelligent convolutional neural network. Methodology: The dataset used in this study was acquired from the Kaggle repository database. The dataset contains the Lung Chest X-Ray images of COVID-19 patients. The images were pre- processed to obtain the desired image quality for further processing. This was followed by segmenting the pre-processed images. An Enhanced Firefly Algorithm (EFA) was formulated by applying the roulette wheel selection procedure to model the movement process of the firefly as a deterministic process to assist the standard Firefly Algorithm (FA) and application of Chaotic Sinusoidal Map Function to model the attractive process of the firefly which establishes a balance between exploration and exploitation in FA. The EFA was applied to optimize Convolution Neural Network (CNN) hyper-parameters (number of layers, number of filters per layer, filter size and batch size). The segmented result was subsequently presented to EFA-CNN feature extraction and prediction of COVID-19 patient fatality cases. The formulated deep learning models (EFA-CNN and CNN) were implemented using Matrix Laboratory 2020a software. The implemented models were evaluated using specificity, sensitivity, false positive rate, accuracy, and recognition time/rate to determine the performance of the developed models. Results: The findings revealed that the EFA-CNN model performs better in the prediction of COVID-19 patients’ fatality compared to the CNN model. It was also discovered that the formulated EFA applied to select optimal values of the hyper-parameters for the CNN architecture accounted for improved recognition accuracy and reduced recognition time of the developed COVID-19 Patients’ Fatality Prediction System. Conclusion: The system developed will assist both the government and healthcare workers in providing the needed computational capability for the prediction of the fatality level of a positively tested COVID-19 patient.

COVID-19 deep learning feature extraction fatality level prediction

References (66)

  1. 1 Gradient-based learning applied to document recognition [DOI]
  2. 2 Advances in neural information processing systems 7 [DOI]
  3. 3 Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study [DOI]
  4. 4 A Fast Learning Algorithm for Deep Belief Nets [DOI]
  5. 5 Representation Learning: A Review and New Perspectives [DOI]
  6. 6 Opinion Mining and Sentiment Analysis [DOI]
  7. 7 Greedy Layer-Wise Training of Deep Networks [DOI]
  8. 8 Firefly Algorithms for Multimodal Optimization [DOI]
  9. 9 IEEE Transactions on Pattern Analysis and Machine Intelligence [DOI]
  10. 10 Face recognition: a convolutional neural-network approach [DOI]
  11. 11 Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions [DOI]
  12. 12 Middle East respiratory syndrome [DOI]
  13. 13 Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] [DOI]
  14. 14 Firefly Algorithm, Lévy Flights and Global Optimization [DOI]
  15. 15 Pneumonia of unknown aetiology in Wuhan, China: potential for international spread via commercial air travel [DOI]
  16. 16 Scaling learning algorithms towards AI
  17. 17 Mixed variable structural optimization using Firefly Algorithm [DOI]
  18. 18 Evolving Deep Convolutional Neural Networks for Image Classification [DOI]
  19. 19 Multiobjective firefly algorithm for continuous optimization [DOI]
  20. 20 Deep Learning and Its Applications to Signal and Information Processing [Exploratory DSP [DOI]
  21. 21 Predicting COVID-19 Incidence Through Analysis of Google Trends Data in Iran: Data Mining and Deep Learning Pilot Study [DOI]
  22. 22 Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran [DOI]
  23. 23 Skin cancer diagnosis based on optimized convolutional neural network [DOI]
  24. 24 A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification [DOI]
  25. 25 Evolutionary convolutional neural networks: An application to handwriting recognition [DOI]
  26. 26 A modified firefly algorithm for UCAV path planning
  27. 27 Autonomous deep learning: A genetic DCNN designer for image classification [DOI]
  28. 28 Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm [DOI]
  29. 29 Hyper-Parameter Selection in Convolutional Neural Networks Using Microcanonical Optimization Algorithm [DOI]
  30. 30 Optimal allocation and sizing of Distributed Generation in distribution system via Firefly Algorithm [DOI]
  31. 31 Three-Dimensional Path Planning Method for Autonomous Underwater Vehicle Based on Modified Firefly Algorithm [DOI]
  32. 32 Multi-objective Environmental/Economic Dispatch using firefly technique [DOI]
  33. 33 Convolutional Neural Network Architecture Design by the Tree Growth Algorithm Framework [DOI]
  34. 34 Hand gesture recognition using neural network based techniques [DOI]
  35. 35 Deep Convolutional Neural Networks for facial expression recognition [DOI]
  36. 36 An improved dynamic discrete firefly algorithm for blind image steganalysis [DOI]
  37. 37 Parameter Optimization for Membership Functions of Type-2 Fuzzy Controllers for Autonomous Mobile Robots Using the Firefly Algorithm [DOI]
  38. 38 A hybrid chaos firefly algorithm for three-dimensional irregular packing problem [DOI]
  39. 39 Optimal Recognition Model Based on Convolutional Neural Networks and Fuzzy Gravitational Search Algorithm Method [DOI]
  40. 40 Optimization for Deep Convolutional Neural Networks: How Slim Can It Go? [DOI]
  41. 41 Can Deep Neural Networks Discover Meaningful Pattern Features? [DOI]
  42. 42 Inverse identification of modified Johnson–Cook model for cutting titanium alloy Ti6Al4V using firefly algorithm [DOI]
  43. 43 Filter Size Optimization on a Convolutional Neural Network Using FGSA [DOI]
  44. 44 Modified Approach of Firefly Algorithm for Non-Minimum Phase Systems [DOI]
  45. 45 Object-based feature extraction for hyperspectral data using firefly algorithm [DOI]
  46. 46 A power system restoration method using voltage source converter–high-voltage direct current technology, aided by time-series neural network with firefly algorithm [DOI]
  47. 47 Very Deep Convolutional Networks for Large-Scale Image Recognition [DOI]
  48. 48 Improving neural networks by preventing co-adaptation of feature detectors [DOI]
  49. 49 AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery [DOI]
  50. 50 Learning Deep Architectures for AI [DOI]
  51. 51 To mask or not to mask: Modeling the potential for face mask use by the general public to curtail the COVID-19 pandemic [DOI]
  52. 52 Supervised Machine Learning Models for Prediction of COVID-19 Infection using Epidemiology Dataset [DOI]
  53. 53 Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network [DOI]
  54. 54 Machine-learning classification of texture features of portable chest X-ray accurately classifies COVID-19 lung infection [DOI]
  55. 55 Optimization of Convolutional Neural Networks Architectures Using PSO for Sign Language Recognition [DOI]
  56. 56 Optimization of Convolutional Neural Networks Using the Fuzzy Gravitational Search Algorithm [DOI]
  57. 57 [Retracted] Gender‐Based Deep Learning Firefly Optimization Method for Test Data Generation [DOI]
  58. 58 Multi Objective Optimization of Process Parameters by Firefly Algorithm during the Friction Stir Welding of Metal Matrix Composites [DOI]
  59. 59 A proposal to use the inverse problem for determining parameters in a constitutive model for concrete [DOI]
  60. 60 A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models [DOI]
  61. 61 Survey data of COVID-19-related Knowledge, Risk Perceptions and Precautionary Behavior among Nigerians [DOI]
  62. 62 COVID-19 Outbreak Prediction with Machine Learning [DOI]
  63. 63 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA) [DOI]
  64. 64 A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification [DOI]
  65. 65 Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification [DOI]
  66. 66 A hybrid differential evolution approach to designing deep convolutional neural networks for image classification [DOI]

Cited by 2

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

Hamed Khalili, Maria A. Wimmer · Life · 2024

Showing 1 of 2 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

16

Page views

0

PDF downloads

2

Outbound clicks

2

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.