2022
DOI: 10.1039/d2ra03722j
|View full text |Cite
|
Sign up to set email alerts
|

RamanNet: a lightweight convolutional neural network for bacterial identification based on Raman spectra

Abstract: We propose a novel CNN model named RamanNet for rapid and accurate identification of bacteria at the species-level based on Raman spectra. Compared to previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
12
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(13 citation statements)
references
References 26 publications
(47 reference statements)
1
12
0
Order By: Relevance
“…ResNet architecture [50] fixes this problem by introducing skip connections. ResNet and its modifications have been successfully applied to classify Raman spectra, outperforming shallow models by a large margin, as shown by other authors [23], [51], [52], [53] and in our previous work [51].…”
Section: Introduction and Problem Statementmentioning
confidence: 63%
See 1 more Smart Citation
“…ResNet architecture [50] fixes this problem by introducing skip connections. ResNet and its modifications have been successfully applied to classify Raman spectra, outperforming shallow models by a large margin, as shown by other authors [23], [51], [52], [53] and in our previous work [51].…”
Section: Introduction and Problem Statementmentioning
confidence: 63%
“…2. The ensemble architecture we propose surpasses the current state-of-the-art closed-world DNNs, which achieve accuracies of 82.2±0.3%[23], 84.7 ±0.3%[53], and 86.7± 0.4% [52], respectively. This remarkable performance motivates us to utilize an ensemble of ResNet models augmented with an SE attention mechanism not only in the closed-world setting but also in subsequent open-world settings considered in the next Sections.…”
Section: Introduction and Problem Statementmentioning
confidence: 99%
“…We pre-train the models on the reference data and finetune them on the finetuning data set. (c) Comparison of accuracy with different articles using the same data set. ,,, …”
Section: Methodsmentioning
confidence: 99%
“…Chi-Sing Ho and colleagues achieved an average accuracy of 82.2% in classifying 30 bacterial subtypes using ResNet-8 . Subsequently, analysts further improved the strain classification accuracy using modified ResNet models on the same open-accessed data. ,, Within these works, the Scale-Adaptive Deep Model achieved an 85.9% accuracy without data augmentation and an 86.7% accuracy with data augmentation …”
Section: Introductionmentioning
confidence: 97%
See 1 more Smart Citation