METHODS: We used data from the AIDS Care Cohort to Evaluate Exposure to Survival Services study, a long-running community-recruited cohort of PLWH who use illicit drugs linked to comprehensive HIV clinical records. The longitudinal relationship between daily pill burden and the odds of ≥95% adherence to ART among ART-exposed individuals was analyzed using multivariable generalized linear mixed-effects modeling, adjusting for sociodemographic, behavioural, and structural factors linked to adherence.
RESULTS: Between December 2005 and May 2014, the study enrolled 770 ART-exposed participants, including 257 (34%) women, with a median age of 43 years. At baseline, 437 (56.7%) participants achieved ≥95% adherence in the previous 180 days. Among all interview periods, the median adherence was 100% (interquartile range 71%-100%). In a multivariable model, a greater number of pills per day was negatively associated with ≥95% adherence (adjusted odds ratio [AOR] 0.87 per pill, 95% confidence interval [CI] 0.84-0.91). Further analysis showed that once-a-day ART regimens were positively associated with optimal adherence (AOR 1.39, 95% CI 1.07-1.80).
CONCLUSIONS: In conclusion, simpler dosing demands (ie, fewer pills and once-a-day single tablet regimens) promoted optimal adherence among PLWH who use drugs. Our findings highlight the need for simpler dosing to be encouraged explicitly for PWUD with multiple adherence barriers.
OBJECTIVES: This paper discusses activity detection and analysis (ADA) using security robots in workplaces. The application scenario of this method relies on processing image and sensor data for event and activity detection. The events that are detected are classified for its abnormality based on the analysis performed using the sensor and image data operated using a convolution neural network. This method aims to improve the accuracy of detection by mitigating the deviations that are classified in different levels of the convolution process.
RESULTS: The differences are identified based on independent data correlation and information processing. The performance of the proposed method is verified for the three human activities, such as standing, walking, and running, as detected using the images and sensor dataset.
CONCLUSION: The results are compared with the existing method for metrics accuracy, classification time, and recall.