# Respiratory sound 2-class classification on ICBHI 2017 (80/20)

Source: [Respiratory sound 2-class classification on ICBHI 2017 (80/20)](<https://www.sota2.com/research/sota/respiratory-sound-2-class-classification-on-icbhi-2017-80-20>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:04:39.048Z

Evaluation of respiratory sound classification performance, specifically distinguishing between 2 classes, using the ICBHI 2017 dataset with an 80/20 split.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Respiratory sound 2-class classification |
| Dataset (including any stated split) | ICBHI 2017 (80/20) |
| Metric | Specificity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Specificity](<https://www.sota2.com/research/sota/respiratory-sound-2-class-classification-on-icbhi-2017-80-20.md?metric=Specificity>): Higher is better; unit: PERCENT.

- [Sensitivity](<https://www.sota2.com/research/sota/respiratory-sound-2-class-classification-on-icbhi-2017-80-20.md?metric=Sensitivity>): Higher is better; unit: PERCENT.

- [Performance Score](<https://www.sota2.com/research/sota/respiratory-sound-2-class-classification-on-icbhi-2017-80-20.md?metric=Performance%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Specificity | Result date | Report paper |
| --- | --- | --- | --- |
| RespireNet (CNN base) | 0.833 | Not recorded | 68fa69e41e209131cea249dc |
| RespireNet (CNN+CBA+BRC+FT) | 0.809 | Not recorded | 68fa69e41e209131cea249dc |
| RespireNet (CNN+CBA+BRC) | 0.764 | Not recorded | 68fa69e41e209131cea249dc |

### RespireNet (CNN base)

Specificity: 0.833. Result ID: 698def1cffc3901de099a480.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

Recorded evaluation configuration: {"architecture":"CNN"}. This record does not assert independent reproduction.

### RespireNet (CNN+CBA+BRC+FT)

Specificity: 0.809. Result ID: 698def1cffc3901de099a482.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

Recorded evaluation configuration: {"architecture":"CNN","augmentation":"Concatenation-based augmentation","clipping":"Blank region clipping","fine-tuning":"device specific"}. This record does not assert independent reproduction.

### RespireNet (CNN+CBA+BRC)

Specificity: 0.764. Result ID: 698def1cffc3901de099a481.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e41e209131cea249dc.md>)

Recorded evaluation configuration: {"architecture":"CNN","augmentation":"Concatenation-based augmentation","clipping":"Blank region clipping"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.