Methods: This cross-sectional study involved 227 adults aged 40 to 59 years at low-cost housing flats in suburban area of Cheras, Kuala Lumpur. Data collection involved food frequency questionnaire (FFQ) for polyphenols and international physical activity questionnaire (IPAQ). Subjects were measured for anthropometric parameters including height, weight, waist and neck circumferences (NC), and body fat percentage. The polyphenol intake from the diet was estimated using local polyphenol database built according to PHENOL-EXPLORER.
Results: The average intake of polyphenol of subjects was 1815 (672) mg/day. The main food sources of polyphenol were coffee with milk, followed by chocolate milk and red beans. A higher polyphenol intake according to quartile was significantly associated with a lower neck circumference (χ2 = 8.30, P = 0.040), waist circumference (χ2 = 8.45, P = 0.038) and body fat percentage (χ2 = 8.06, P = 0.045). Binomial logistic regression analysis showed that the association remained significant for the neck circumference (P = 0.032), after controlling for age, household income, energy intake and physical activity level. More subjects with normal NC had higher intake of polyphenols (50th percentile and above). In contrast, subjects with high NC showed lower percentiles of polyphenols intake (50th percentile and below).
Conclusion: The result showed that polyphenol intake was associated with neck circumference and thus it can be suggested that polyphenol intake is associated with obesity.
METHODS: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance's ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge.
RESULTS: The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED.
CONCLUSIONS: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.