RESUMEN
Human motion detection technology holds significant potential in medicine, health care, and physical exercise. This study introduces a novel approach to human activity recognition (HAR) using convolutional neural networks (CNNs) designed for individual sensor types to enhance the accuracy and address the challenge of diverse data shapes from accelerometers, gyroscopes, and barometers. Specific CNN models are constructed for each sensor type, enabling them to capture the characteristics of their respective sensors. These adapted CNNs are designed to effectively process varying data shapes and sensor-specific characteristics to accurately classify a wide range of human activities. The late-fusion technique is employed to combine predictions from various models to obtain comprehensive estimates of human activity. The proposed CNN-based approach is compared to a standard support vector machine (SVM) classifier using the one-vs-rest methodology. The late-fusion CNN model showed significantly improved performance, with validation and final test accuracies of 99.35 and 94.83% compared to the conventional SVM classifier at 87.07 and 83.10%, respectively. These findings provide strong evidence that combining multiple sensors and a barometer and utilizing an additional filter algorithm greatly improves the accuracy of identifying different human movement patterns.
RESUMEN
BACKGROUND: Coronary artery diseases remain the leading cause of death in the world. The management of this condition has improved remarkably in the recent years owing to the development of new technical tools and multicentric registries. OBJECTIVE: The aim of this study is to investigate the in-hospital and 1-year clinical outcomes of patients treated with percutaneous coronary intervention (PCI) in Tunisia. METHODS: We will conduct a prospective multicentric observational study with patients older than 18 years who underwent PCI between January 31, 2020 and June 30, 2020. The primary end point is the occurrence of a major adverse cardiovascular event, defined as cardiovascular death, myocardial infarction, cerebrovascular accident, or target vessel revascularization with either repeat PCI or coronary artery bypass grafting (CABG). The secondary end points are procedural success rate, stent thrombosis, and the rate of redo PCI/CABG for in-stent restenosis. RESULTS: In this study, the demographic profile and the general risk profile of Tunisian patients who underwent PCI and their end points will be analyzed. The complexity level of the procedures and the left main occlusion, bifurcation occlusion, and chronic total occlusion PCI will be analyzed, and immediate as well as long-term results will be determined. The National Tunisian Registry of PCI (NATURE-PCI) will be the first national multicentric registry of angioplasty in Africa. For this study, the institutional ethical committee approval was obtained (0223/2020). This trial consists of 97 cardiologists and 2498 patients who have undergone PCI with a 1-year follow-up period. Twenty-eight catheterization laboratories from both public (15 laboratories) and private (13 laboratories) sectors will enroll patients after receiving informed consent. Of the 2498 patients, 1897 (75.9%) are managed in the public sector and 601 (24.1%) are managed in the private sector. The COVID-19 pandemic started in Tunisia in March 2020; 719 patients (31.9%) were included before the COVID-19 pandemic and 1779 (60.1%) during the pandemic. The inclusion of patients has been finished, and we expect to publish the results by the end of 2022. CONCLUSIONS: This study would add data and provide a valuable opportunity for real-world clinical epidemiology and practice in the field of interventional cardiology in Tunisia with insights into the uptake of PCI in this limited-income region. TRIAL REGISTRATION: Clinicaltrials.gov NCT04219761; https://clinicaltrials.gov/ct2/show/NCT04219761. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/24595.