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.
METHODS: This is a population-based secondary data analysis using the national mortality registry from 2004 to 2014. Past trend estimation was conducted using Murtagh's minimum and maximum methods and Gómez-Batiste's method. The estimated palliative care needs were stratified by age groups, gender and administrative states in Malaysia. With this, the projection of palliative care needs up to 2030 was conducted under the assumption that annual change remains constant.
RESULTS: The palliative care needs in Malaysia followed an apparent upward trend over the years regardless of the estimation methods. Murtagh's minimum estimation method showed that palliative care needs grew 40% from 71 675 cases in 2004 to 100 034 cases in 2014. The proportion of palliative care needs in relation to deaths hovered at 71% in the observed years. In 2030, Malaysia should anticipate the population needs to be at least 239 713 cases (240% growth from 2014), with the highest needs among age group ≥80-year-old in both genders. Sarawak, Perak, Johor, Selangor and Kedah will become the top five Malaysian states with the highest number of needs in 2030.
CONCLUSION: The need for palliative care in Malaysia will continue to rise and surpass its service provision. This trend demands a stepped-up provision from the national health system with advanced integration of palliative care services to narrow the gap between needs and supply.