ABSTRACT
In recent years, a plethora of algorithms have been devised for efficient human activity recognition. Most of these algorithms consider basic human activities and neglect postural transitions because of their subsidiary occurrence and short duration. However, postural transitions assume a significant part in the enforcement of an activity recognition framework and cannot be neglected. This work proposes a hybrid multi-model activity recognition approach that employs basic and transition activities by utilizing multiple deep learning models simultaneously. For final classification, a dynamic decision fusion module is introduced. The experiments are performed on the publicly available datasets. The proposed approach achieved a classification accuracy of 96.11% and 98.38% for the transition and basic activities, respectively. The outcomes show that the proposed method is superior to the state-of-the-art methods in terms of accuracy and precision.
Subject(s)
Deep Learning , Algorithms , Human Activities , Humans , Recognition, PsychologyABSTRACT
BACKGROUND AND PURPOSE: A three module online self-paced educational resource was developed for entry to practice students transitioning from the classroom to their inpatient practicums. The objective of this study was to determine the benefits of the transition modules on students' self-perceived competency as related to onsite performance and reduction in anxiety during their inpatient practicum. EDUCATIONAL ACTIVITY AND SETTING: Evaluations of the three transition modules were conducted in two phases via electronic surveys distributed to final year advanced pharmacy practice students and focus group members including faculty, pharmacy practice educators, and pharmacy residents. FINDINGS: Based on our findings, the modules addressed common learning needs. While 69.7% of student respondents from Phase II of the evaluation found the modules to have positively impacted their onsite performance, only 24.7% believed the modules reduced their anxiety. DISCUSSION: The study indicates that students found the modules to be relevant to inpatient practice and of appropriate difficulty. Although most students perceived the modules to enhance performance on practicum, student anxiety levels appeared to remain unchanged. SUMMARY: Based on feedback and results, it may be beneficial to expose students to transition modules earlier in the curriculum in tandem with other inpatient preparatory activities. The results from this study may be of interest or benefit other universities and healthcare educators pursuing work on transition activities.