 The study aimed to design an algorithm based on the unsupervised isolation forest model to classify sigma quality into three grades, validated on labeled data sets, and applied on real-world data to evaluate its efficacy in reducing false alarm rate and selecting signal segments for further research. The ECG SQA model achieved 94.97% and 95.58% accuracy on the validation and test sets, respectively, while the Respiratory SQA model achieved 81.06% and 86.2% accuracy on the validation and test sets, respectively. The algorithm was superior to self-organizing maps and achieved moderate performance when compared with supervised models. The example case showed that the algorithm could correctly classify signal quality even with complex pathological changes in the signals, and the application results indicated that specific types of arrhythmia false alarms such as tachycardia, atrial premature beat, and ventricular premature beat could be significantly reduced with the help of the algorithm. This article was authored by Haorin Su, Wei Yen, Kulan, and others. We are article.tv, links in the description below.