An Optimal Transport Framework for Collaborative Multi-view Clustering

Ben-Bouazza, Fatima-Ezzahraa; Bennani, Younès; El Hamri, Mourad

doi:10.1007/978-3-030-95239-6_5

Cited by 2 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, predictive maintenance systems should be highly scalable, resilient, and fault-tolerant to process and store big data in an effective manner [10]. Through the use of information and communication technologies, specifically intelligent devices (such as IoT sensors, edge devices, and computing), data collection has increased as a result of the incorporation of autonomous and smart systems where data and advanced data analytics (i.e., big data, artificial intelligence (AI) / Machine Learning (ML)) can be used [11]. With this development, PdM solutions, such as those for estimating remaining usable life, detecting anomalies, and monitoring machine health (condition), also increased.…”

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

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

show abstract

“…Recently, many multi-view clustering methods have been developed. Existing works about multiview subspace clustering can be divided into different categories, i.e., non-negative matrix factorization (NMF) framework [6][7][8][9], collaborative clustering methods [10][11][12], co-training methods [13][14][15], self-expressive based methods [16,17] and deep-learning-based methods [18,19]. NMF-based methods aim to obtain the partitioning of the data by a low-rank decomposition of the data matrix, and it is proved to be effective where the subspaces of data points are independent of each other.…”

Section: Introductionmentioning

confidence: 99%

Deep Multi-View Clustering Based on Reconstructed Self-Expressive Matrix

Shi,

Zhao

2023

Applied Sciences

View full text Add to dashboard Cite

Deep Multi-view Subspace Clustering is a powerful unsupervised learning technique for clustering multi-view data, which has achieved significant attention during recent decades. However, most current multi-view clustering methods rely on learning self-expressive layers to obtain the ultimate clustering results, where the size of the self-expressive matrix increases quadratically with the number of input data points, making it difficult to handle large-scale datasets. Moreover, since multiple views are rich in information, both consistency and specificity of the input images need to be considered. To solve these problems, we propose a novel deep multi-view clustering approach based on the reconstructed self-expressive matrix (DCRSM). We use a reconstruction module to approximate self-expressive coefficients using only a small number of training samples, while the conventional self-expressive model must train the network with entire datasets. We also use shared layers and specific layers to integrate consistent and specific information of features to fuse information between views. The proposed DCRSM is extensively evaluated on multiple datasets, including Fashion-MNIST, COIL-20, COIL-100, and YTF. The experimental results demonstrate its superiority over several existing multi-view clustering methods, achieving an improvement between 1.94% and 4.2% in accuracy and a maximum improvement of 4.5% in NMI across different datasets. Our DCRSM also yields competitive results even when trained by 50% samples of the whole datasets.

show abstract

An Optimal Transport Framework for Collaborative Multi-view Clustering

Cited by 2 publications

References 26 publications

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

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

Deep Multi-View Clustering Based on Reconstructed Self-Expressive Matrix

Contact Info

Product

Resources

About