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.
METHOD: Communities living in 20 hotspot and 20 non-hotspot areas in Selangor were chosen in this study where 406 participants were randomly selected to answer questionnaires distributed at their housing areas. Total marks of each categories were compared using t-test.
RESULT: Results show that there were significant mean differences in marks in Knowledge (p value: 0.003; 15.41 vs. 14.55) and Attitude (p value: < 0.001; 11.41 vs. 10.33), but not Practice (p value 0.101; 10.83 vs. 10.47) categories between communities of non-hotspot and hotspot areas. After considering two confounding variables which are education level and household income, different mean marks are found to be significant in Knowledge when education level acts as a covariate and Attitude when both act as covariates.
CONCLUSION: Overall results show that people living in non-hotspot areas had better knowledge and attitude than people living in hotspot areas, but no difference was found in practice. This suggests that public health education should be done more frequently with people with a low education background and low household income, especially in hotspot areas to fight dengue outbreak and make dengue cases decrease effectively.