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.
OBJECTIVE: The aim of this study is to identify the postoperative ISIC changes relative to preoperative ISIC after OHS, and determine their predictors, including patient characteristics factors and IS performance parameters such as inspiration volumes (ISv) and frequencies (ISf).
METHODS: This is a prospective study with blinding procedures involving 95 OHS patients, aged 52.8±11.5 years, whose ISIC was measured preoperatively (PreopISIC) until fifth postoperative day (POD), while ISv and ISf monitored with an electronic device from POD1-POD4. Regression models were used to identify predictors of POD1 ISIC, POD2- POD5 ISIC increments, and the odds of attaining PreopISIC by POD5.
RESULTS: The ISIC reduced to 41% on POD1, increasing thereafter to 57%, 75%, 91%, and 106% from POD2-POD5 respectively. Higher PreopISIC (B=-0.01) significantly predicted lower POD1 ISIC, and, together with hyperlipedemia (B=11.52), which significantly predicted higher POD1 ISIC, explained 13% of variance. ISv at relative percentages of PreopISIC from POD1-POD4 (BPOD1=0.60, BPOD2=0.56, BPOD3=0.49, BPOD4=0.50) significantly predicted ISIC of subsequent PODs with variances at 23%, 24%, 17% and 25% respectively, but no association was elicited for ISf. IS performance findings facilitated proposal of a postoperative IS therapy target guideline. Higher ISv (B=0.05) also increased odds of patients recovering to preoperative ISIC on POD5 while higher PreopISIC (B=- 0.002), pain (B=-0.72) and being of Indian race (B=-1.73) decreased its odds.
CONCLUSION: ISv appears integral to IS therapy efficacy after OHS and the proposed therapy targets need further verification through randomized controlled trials.