Unsupervised collaborative learning based on Optimal Transport theory

Ben-Bouazza, Fatima-Ezzahraa; Bennani, Younès; Cabanès, Guénaël; Touzani, Abdelfettah

doi:10.1515/jisys-2020-0068

Cited by 5 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cephalometry, a field of study focused on craniofacial analysis, centers around the meticulous identification of craniofacial landmarks. This crucial process involves the precise detection of cephalometric landmarks on the cephalogram, serving as the fundamental initial stage in conducting any cephalometric analysis [5] [6] [7] In the past few years, the field of deep learning has witnessed the emergence of highly sophisticated models that have demonstrated exceptional capabilities in this particular domain [8] [9] [10]. The advent of these models has brought about a paradigm shift in the field, presenting ingenious approaches to tackle the complex challenge of landmark identification.…”

Section: Motivationmentioning

confidence: 99%

Cephalometric Landmarks Identification Through an Object Detection-based Deep Learning Model

Tafala,

Ben-Bouazza,

Edder

et al. 2024

IJACSA

View full text Add to dashboard Cite

In the field of orthodontics, the accurate identification of cephalometric landmarks in dental radiography plays a crucial role in ensuring precise diagnoses and efficient treatment planning. Previous studies have demonstrated the impressive capabilities of advanced deep learning models in this particular domain. However, due to the ever-changing technological landscape, it is imperative to consistently investigate and explore emerging algorithms to further improve efficiency in this field. The present study centers around the assessment of the effectiveness of YOLOv8, the most recent version of the 'You Only Look Once (YOLO)' algorithm series, with a particular emphasis on its autonomous capability to accurately identify cephalometric landmarks. In this study, a thorough examination was conducted to evaluate the YOLOv8 algorithm efficiency in detecting cephalometric landmarks. The assessments encompassed various aspects such as precision, adaptability in challenging conditions, and a comparative analysis with alternative algorithms. The predefined proximities of 2mm, 2.5mm, and 3mm were utilized for the comparisons. By focusing on its potential as a noteworthy breakthrough, the investigation seeks to ascertain whether the recent enhancements indeed bring about a significant stride in the precise identification of cephalometric landmarks.

show abstract

Section: Motivationmentioning

confidence: 99%

Cephalometric Landmarks Identification Through an Object Detection-based Deep Learning Model

Tafala,

Ben-Bouazza,

Edder

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Sensors with limited data processing capabilities are used for data collecting. Due to this, edge devices were developed and are now capable of processing data, cleansing data, and many other functions in addition to acting as sensors [12]. PdM techniques are very similar to medical diagnostic techniques.…”

Section: Introductionmentioning

confidence: 99%

An Internet of Things-based Predictive Maintenance Architecture for Intensive Care Unit Ventilators

Manchadi,

BEN-BOUAZZA,

Dehbi

et al. 2024

IJACSA

View full text Add to dashboard Cite

Intensive care units commonly utilize mechanical ventilators to treat patients with different medical conditions, which are crucial for patient care and survival. ICU ventilators have evolved through four distinct generations, each displaying unique features. Despite progress made since the 1940s, contemporary designs are insufficient to meet the increasing needs of patients and hospitals. Malfunctions in mechanical ventilators pose significant dangers to patients, highlighting the importance of focusing on their safety, security, precision, and dependability. Our study aims to address the significant issue at hand. Furthermore, the IoT industry has garnered significant attention because of rapid progress in smart devices, sensors, and actuators. The healthcare industry has seen a notable increase in health data as a result of the growing utilization of IoT and cloud computing technologies. To enhance growth, new models and distributed data analytics strategies must be developed to fully utilize the value of the vast datasets generated, including the incorporation of embedded machine learning. The study focuses on conducting Pareto and Failure Modes and Effects Analysis (FMECA) on ventilators in a specific hospital's ICU, specifically those manufactured by the same company and unit. The analysis aims to identify the most critical and failure-prone component. Subsequently, we propose an IoT-focused framework for a predictive maintenance system implemented at the component level. The architecture comprises a monitoring framework and a data analytics module to predict potential system failures in advance, enhancing overall reliability.

show abstract