METHODS: Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well.
RESULTS: Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%.
CONCLUSION: The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals.
METHODS: Housewives aged 18 to 59 years old from the MyBFF@home study were selected and pain was measured using the Visual Analogue Scale (VAS) questionnaire. VAS measured the pain intensity at different parts of the body (score of 0-10). Data were collected at base line, 3 months and 6 months among the housewives in both the control and intervention group. Pain scores and other variables (age, Body Mass Index (BMI) and waist circumference) were analysed using SPSS version 22.
RESULTS: A total of 328 housewives completed the VAS questionnaires at baseline, while 185 (56.4%) of housewives completed the VAS at 3 months and 6 months. A decreasing trend of mean pain score in both groups after 6 months was observed. However, the intervention group showed a consistent decreasing trend of pain score mainly for back pain. In the control group, there was a slight increment of score in back pain from baseline towards the 6 months period. Older housewives in both groups (aged 50 years and above) had a higher mean score of leg pain (2.86, SD: 2.82) compared to the other age group. Higher BMI was significantly associated with pain score in both groups.
CONCLUSION: There were some changes in the level of body pain among the housewives before and after the intervention. Older obese women had a higher pain score compared to younger obese women. Pain was associated with BMI and change in BMI appears to be beneficial in reducing body pain among overweight and obese individuals.