Otwarty dostęp

Research and optimisation of a deep learning model for positive thinking meditation based on bio-signal processing

Yukun Zhu

Yukun Zhu

School of Integrated Circuit, Wuxi Vocational College of Science and TechnologyWuxi, China
Wyszukaj tego autora
Sciendo|Google Scholar
Zhu, Yukun
, 
Haiyan Zhang

Haiyan Zhang

School of Integrated Circuit, Wuxi Vocational College of Science and TechnologyWuxi, China
Wyszukaj tego autora
Sciendo|Google Scholar
Zhang, Haiyan
, 
Bing Liu

Bing Liu

School of Integrated Circuit, Wuxi Vocational College of Science and TechnologyWuxi, China
Wyszukaj tego autora
Sciendo|Google Scholar
Liu, Bing
 oraz 
Junyan Dou

Junyan Dou

School of Integrated Circuit, Wuxi Vocational College of Science and TechnologyWuxi, China
Wyszukaj tego autora
Sciendo|Google Scholar
Dou, Junyan
  
17 mar 2025
Research and optimisation of a deep learning model for positive thinking meditation based on bio-signal processing's Cover Image
O artykule
Poprzedni artykuł
Następny artykuł
Zacytuj
Pobierz okładkę
Data publikacji: 17 mar 2025
Otrzymano: 30 paź 2024
Przyjęty: 05 lut 2025
DOI: https://doi.org/10.2478/amns-2025-0157
Słowa kluczowe
© 2025 Yukun Zhu et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Light plate structure design
Light plate structure design

Figure 2.

The sequence of changes in concentration of oxygen and hemoglobin
The sequence of changes in concentration of oxygen and hemoglobin

Figure 3.

Original brain electrical signal time domain and frequency domain waveform
Original brain electrical signal time domain and frequency domain waveform

Figure 4.

The time domain and frequency domain waveform after processing
The time domain and frequency domain waveform after processing

Figure 5.

Changes in the concentration of oxygen and hemoglobin
Changes in the concentration of oxygen and hemoglobin

Figure 6.

The mindfulness meditation state and the confusion matrix display of test 1
The mindfulness meditation state and the confusion matrix display of test 1

Figure 7.

The mindfulness meditation state and the confusion matrix display of test 32
The mindfulness meditation state and the confusion matrix display of test 32

Figure 8.

The classification effect of the model on the data set
The classification effect of the model on the data set

The classification effect of data enhancement

Before After
Evaluation index ACC 0.73 0.91
Kappa 0.62 0.89
MF1 0.68 0.87
F1 values per class S1 0.71 0.83
S2 0.66 0.86
S3 0.64 0.89
S4 0.69 0.84
S5 0.67 0.85
S6 0.63 0.82
S7 0.61 0.83
S8 0.65 0.81
REM 0.71 0.84

Confusion matrix index

Confusion Matrix True value
Positive Negative
Predictive value Positive TP FP
Negative FN TN

Performance comparison of different models

Model ACC R Kappa F1
GoogleNet 0.914 0.853 0.732 0.802
PLS-DA 0.923 0.864 0.748 0.831
SVM 0.936 0.831 0.751 0.879
Random forest 0.945 0.879 0.769 0.893
BP 0.962 0.842 0.798 0.905
Depth learning 0.910 0.857 0.803 0.914
Integrated network 0.994 0.931 0.874 0.957
Język:
Angielski
Częstotliwość wydawania:
1 razy w roku
Dziedziny czasopisma:
Nauki biologiczne, Nauki biologiczne, inne, Matematyka, Matematyka stosowana, Matematyka ogólna, Fizyka, Fizyka, inne
Kanał RSS czasopisma