Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Model for Assessing Network Asset Vulnerability Using QPSO-LightGBM

Xinyu Li, Yu Gu, Chenwei Wang, Peng Zhao

TL;DR

SpiroFi introduces a contactless pulmonary function monitoring approach using WiFi CSI to extract chest-wall motion and map it to standard lung-function indices ($FEV1$, $FVC$, $FEV1/FVC$). The system employs CSI-ratio phase-offset removal, respiration-focused denoising, and a Bayesian regularized neural network with hand-crafted features to predict lung indices, supported by personalized and group training strategies. In-lab results with healthy participants show errors around 1.6–4.4%, while clinic data from elders reveal higher variability ($FVC$/$FEV1$ errors around 13–14%), mitigated by gender-based grouping and motion-removal techniques. The work demonstrates the potential for a low-cost, daily PFT solution using commodity WiFi, with strong clinical promise pending larger-scale validation.

Abstract

With the continuous development of computer technology and network technology, the scale of the network continues to expand, the network space tends to be complex, and the application of computers and networks has been deeply into politics, the military, finance, electricity, and other important fields. When security events do not occur, the vulnerability assessment of these high-risk network assets can be actively carried out to prepare for rainy days, to effectively reduce the loss caused by security events. Therefore, this paper proposes a multi-classification prediction model of network asset vulnerability based on quantum particle swarm algorithm-Lightweight Gradient Elevator (QPSO-LightGBM). In this model, based on using the Synthetic minority oversampling technique (SMOTE) to balance the data, quantum particle swarm optimization (QPSO) was used for automatic parameter optimization, and LightGBM was used for modeling. Realize multi-classification prediction of network asset vulnerability. To verify the rationality of the model, the proposed model is compared with the model constructed by other algorithms. The results show that the proposed model is better in various predictive performance indexes.

A Model for Assessing Network Asset Vulnerability Using QPSO-LightGBM

TL;DR

SpiroFi introduces a contactless pulmonary function monitoring approach using WiFi CSI to extract chest-wall motion and map it to standard lung-function indices (, , ). The system employs CSI-ratio phase-offset removal, respiration-focused denoising, and a Bayesian regularized neural network with hand-crafted features to predict lung indices, supported by personalized and group training strategies. In-lab results with healthy participants show errors around 1.6–4.4%, while clinic data from elders reveal higher variability (/ errors around 13–14%), mitigated by gender-based grouping and motion-removal techniques. The work demonstrates the potential for a low-cost, daily PFT solution using commodity WiFi, with strong clinical promise pending larger-scale validation.

Abstract

With the continuous development of computer technology and network technology, the scale of the network continues to expand, the network space tends to be complex, and the application of computers and networks has been deeply into politics, the military, finance, electricity, and other important fields. When security events do not occur, the vulnerability assessment of these high-risk network assets can be actively carried out to prepare for rainy days, to effectively reduce the loss caused by security events. Therefore, this paper proposes a multi-classification prediction model of network asset vulnerability based on quantum particle swarm algorithm-Lightweight Gradient Elevator (QPSO-LightGBM). In this model, based on using the Synthetic minority oversampling technique (SMOTE) to balance the data, quantum particle swarm optimization (QPSO) was used for automatic parameter optimization, and LightGBM was used for modeling. Realize multi-classification prediction of network asset vulnerability. To verify the rationality of the model, the proposed model is compared with the model constructed by other algorithms. The results show that the proposed model is better in various predictive performance indexes.
Paper Structure (26 sections, 12 equations, 20 figures, 6 tables, 3 algorithms)

This paper contains 26 sections, 12 equations, 20 figures, 6 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Preliminary
  3. Spirometry and Lung Function Indices
  4. Channel State Information
  5. Spirometry Using CSI
  6. System Design
  7. System Overview
  8. Phase Offset Remover
  9. Chest Wall Motion Tracker
  10. Respiration detection
  11. Noisy motion remover
  12. Chest wall motion mapping
  13. Lung Function Estimator
  14. Network
  15. Data augmentation.
  16. ...and 11 more sections

Figures (20)

  • Figure 1: Current clinic and home-use spirometers.
  • Figure 2: Spirometry test.
  • Figure 3: Spirometry via WiFi sensing
  • Figure 4: WiFi CSI is a time series matrices of MIMO-OFDM channels. It captures multi-path channel variations, including amplitude attenuation and phase shifts, in spatial, frequency, and time domains ma2019wifi.
  • Figure 5: System overview.
  • ...and 15 more figures