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: The study protocol contains two successive phases, nootropic and therapeutic, in which two BV doses (D1; 0.25 and D2: 0.5 mg/kg i.p.) were used. In the nootropic phase, treatment groups were compared statistically with a normal group. Meanwhile, in the therapeutic phase, BV was administered to scopolamine (1mg/kg) to induce amnesia-like AD in a rat model in which therapeutic groups were compared with a positive group (donepezil; 1mg/kg i.p.). Behavioral analysis was performed after each phase by Working Memory (WM) and Long-Term Memory (LTM) assessments using radial arm maze (RAM) and passive avoidance tests (PAT). Neurogenic factors; Brain-derived neurotrophic factor (BDNF), and Doublecortin (DCX) were measured in plasma using ELISA and Immunohistochemistry analysis of hippocampal tissues, respectively.
RESULTS: During the nootropic phase, treatment groups demonstrated a significant (P < 0.05) reduction in RAM latency times, spatial WM errors, and spatial reference errors compared with the normal group. In addition, the PA test revealed a significant (P < 0.05) enhancement of LTM after 72 hours in both treatment groups; D1 and D2. In the therapeutic phase, treatment groups reflected a significant (P < 0.05) potent enhancement in the memory process compared with the positive group; less spatial WM errors, spatial reference errors, and latency time during the RAM test, and more latency time after 72 hours in the light room. Moreover, results presented a marked increase in the plasma level of BDNF, as well as increased hippocampal DCX-positive data in the sub-granular zone within the D1 and D2 groups compared with the negative group (P < 0.05) in a dose-dependent manner.
CONCLUSION: This study revealed that injecting BV enhances and increases the performance of both WM and LTM. Conclusively, BV has a potential nootropic and therapeutic activity that enhances hippocampal growth and plasticity, which in turn improves WM and LTM. Given that this research was conducted using scopolamine-induced amnesia-like AD in rats, it suggests that BV has a potential therapeutic activity for the enhancement of memory in AD patients in a dose-dependent manner but further investigations are needed.
METHODS: Pre- and post-participation questionnaires were distributed to near-peer tutors after their clinical skills teaching sessions with Phase I undergraduate medical students. The Peer Tutor Assessment Instrument questionnaires were distributed to the 1) students, and to the 2) near-peer tutors (junior and senior) after each teaching and learning session for self-evaluation.
RESULTS: The senior near-peer tutors felt that their participation in the programme had enhanced their skills (p=0.03). As a whole, the near-peer tutors were more motivated (Pre 5.32±0.46; Post 5.47±0.50; p=0.210) to participate in future teaching sessions but did not expect that having teaching experiences would make teaching as their major career path in the future (Pre 4.63±1.07; Post 4.54±0.98; p=0.701). The senior near-peer tutors were evaluated significantly higher by the students (p=0.0001). Students' evaluations of near-peer tutors on the domain of critical analysis was higher than self-evaluations (p=0.003).
CONCLUSIONS: Generally, the near-peer tutors perceived that they have benefited most in their skills enhancement and these near-peer tutors were scored highly by the students. However, senior near-peer tutors do not perceive that the programme has a lasting impact on their choice of career path.
Methods: Subjects' food intakes were calculated by using dietary history questionnaire and food frequency questionnaire for polyphenols. The subjects' mental health and cognitive status were measured by general health questionnaire-28 (GHQ-28) and Rey's auditory verbal learning test (RAVLT).
Results: More than 40% of middle-aged adults were identified as having signs of poor mental health. A total of 67.9% of the subjects had poor cognitive status according to RAVLT immediate recall. Hierarchical binary logistic regression indicated that fat intake was associated with somatic symptoms for both men [adjusted odds ratio (AOR) = 1.04; P < 0.05] and women (AOR = 1.06; P < 0.05). Intake of lignan (AOR = 1.071; P < 0.05) was associated with better RAVLT immediate recall among women. Additionally, high cholesterol (AOR = 3.14; P < 0.05) was associated with poor score of RAVLT delayed recall for women.
Conclusions: Early detection of poor mental health and cognitive is crucial to prevent Alzheimer's disease in old age.