Related Experiment Video
Updated: May 25, 2026
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
Binary particle swarm optimization for feature selection in detection of infants with hypothyroidism
Insights
This study shows Binary Particle Swarm Optimization improves infant hypothyroidism detection from cry signals. The method achieved 99.65% accuracy, aiding early diagnosis of thyroid hormone deficiency.
Area of Science:
- Biomedical Engineering
- Computational Intelligence
- Neonatal Health
Background:
- Infant hypothyroidism, a condition of insufficient thyroid hormone production, presents unique cry characteristics due to physiological changes like an enlarged liver.
- Distinguishing these cries from healthy infants is crucial for early diagnosis and intervention.
Purpose of the Study:
- To investigate the efficacy of Binary Particle Swarm Optimization (BPSO) for feature selection in classifying infant cry signals.
- To evaluate the performance of a MultiLayer Perceptron (MLP) classifier with BPSO-optimized Mel Frequency Cepstral Coefficients (MFCCs) for hypothyroidism detection.
Main Methods:
- Feature extraction was performed using MFCCs from infant cry signals.
- BPSO was employed for optimal feature selection from the extracted MFCCs.
- The MLP classifier's performance was assessed by varying the number of selected MFCCs and network parameters.
Main Results:
- BPSO significantly enhanced the classification accuracy of the MLP classifier.
- The computational load of the MLP classifier was reduced through BPSO-based feature selection.
- The highest classification accuracy reached 99.65% using 11 BPSO-optimized MFCCs, 36 filter banks, and 5 hidden nodes.
Conclusions:
- BPSO is an effective technique for improving the accuracy and efficiency of hypothyroidism detection in infants using cry signal analysis.
- The optimized MLP classifier demonstrates high potential for non-invasive, early diagnosis of infant hypothyroidism.
Abstract:
Hypothyroidism in infants is caused by the insufficient production of hormones by the thyroid gland. Due to stress in the chest cavity as a result of the enlarged liver, their cry signals are unique and can be distinguished from the healthy infant cries. This study investigates the effect of feature selection with Binary Particle Swarm Optimization on the performance of MultiLayer Perceptron classifier in discriminating between the healthy infants and infants with hypothyroidism from their cry signals. The feature extraction process was performed on the Mel Frequency Cepstral coefficients. Performance of the MLP classifier was examined by varying the number of coefficients. It was found that the BPSO enhances the classification accuracy while reducing the computation load of the MLP classifier. The highest classification accuracy of 99.65% was achieved for the MLP classifier, with 36 filter banks, 5 hidden nodes and 11 BPS optimised MFC coefficients.
