Jinan Charafeddine

@article{xiao_3803,

title = {Metric learning-enhanced semi-supervised Graph Convolutional Network for multi-view learning},

author = {Huaiyuan Xiao and Fadi Dornaika and Jinan Charafeddine and Bi Jingjun},

url = {https://www.sciencedirect.com/science/article/pii/S1566253525004932?via%3Dihub},

year  = {2025},

date = {2025-12-01},

journal = {Information Fusion},

volume = {124},

pages = {103420},

abstract = {Multi-view learning utilizes data from diverse perspectives or modalities, integrating complementary infor

mation from various sources. It plays a crucial role in intelligent systems and finds extensive applications in 

fields such as computer vision, recommender systems, and natural language processing. With the increasing 

complexity and heterogeneity of real-world data, the integration of Graph Convolutional Networks (GCNs) in 

multi-view learning scenarios is becoming increasingly important. Despite the advances in GCNs, it remains a 

major challenge to effectively generalize models and improve their stability across different data views. In this 

paper, we present a novel framework, the Enhanced Triplet Loss Based Semi-Supervised Graph Convolutional 

Network for Multi-View Learning (MV-TriGCN), which addresses these challenges through three primary 

innovations. First, we propose an enhanced triplet loss for deep metric learning tailored to the hidden features 

of GCNs based on semi-hard negative sample selection. Second, view graphs are constructed using the classical 

KNN scheme and a semi-supervised flexible method to improve the diversity of data structure representation 

resulting in a more stable hypothesis space. Moreover, we learn an end-to-end multi-view GCN by merging all 

available graphs and utilizing the aggregated cross-entropy losses and deep metric losses. Finally, we introduce 

a stepwise training strategy that allows the model to adapt to the losses during different optimization phases. 

Extensive experiments show that our method outperforms existing state-of-the-art approaches in terms of  accuracy and stability},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3847,

title = {Towards Dynamic Self-Training for Scalable Semi-Supervised Learning on Graphs},

author = {Fadi Dornaika and Zoulfakar IBRAHIM and Jinan Charafeddine and Alireza Bosaghzadeh},

url = {http://dx.doi.org/10.1016/j.neucom.2025.131223},

year  = {2025},

date = {2025-11-01},

journal = {Neurocomputing},

volume = {654},

pages = {131223},

abstract = {In the realm of graph-based semi-supervised learning (GSSL), traditional methodologies often struggle to effectively handle labeled samples and scale to accommodate large datasets. To increase supervision information in semi-supervised learning, the self-training paradigm is often used, mainly in datasets with moderate sizes. On the other hand, the use of anchors was adopted with large datasets. In this research endeavor, we propose a novel framework for GSSL that leverages a novel self-training principle tailored for very large datasets, and introduces an advanced method for automatic graph construction using anchors. Our approach focuses on utilizing generated labels of random batches of unlabeled samples, subsequently incorporating these predictions into the training set to enhance the model's accuracy. Pseudo-labeling, a specific instance of self-training, assigns pseudo-labels to the most confidently predicted unlabeled examples, treating them as ground truth during the training phase. By constructing anchor-to-anchor affinity graphs that incorporate both feature and label information, our method facilitates robust learning on large-scale datasets. Through comprehensive experimentation across diverse large datasets, our approach demonstrates its efficacy in achieving scalable and reliable semi-supervised learning outcomes. These findings represent a significant advancement in the field of GSSL, with wide-ranging implications for various applications across different domains. Our method not only addresses the scalability issue but also ensures the effective integration of both labeled and pseudo labeled data, thereby enhancing the overall learning process.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{peng_3810,

title = {Multi-view learning with graph convolution networks adopting diverse graphs and genuine deep feature fusion},

author = {Guowen Peng and Fadi Dornaika and Jinan Charafeddine},

url = {http://dx.doi.org/10.1007/s10462-025-11301-y},

year  = {2025},

date = {2025-07-01},

journal = {Artificial Intelligence Review},

volume = {58},

pages = {290},

abstract = {Multi-view data significantly enhances the accuracy of machine learning algorithms by providing a comprehensive representation of object features. Despite their potential, research on the use of Graph Convolutional Networks (GCNs) for processing node connectivity and data features remains limited. Existing methods mainly focus on weighted summation of graph matrices, with only a few approaches effectively integrating the feature information into the graph structures. To overcome these limitations, this paper proposes a novel deep learning architecture: the Feature Fusion and Multi-Graph Fusion Learning Framework (MGCN-FN). The framework consists of two core modules: Feature Fusion Network (FFN): Designed to extract and consolidate key features from multiple views. Multi-Graph Fusion Network (MGFN): Constructs multiple graphs for each view and jointly optimizes both the graph weights and the GCN model. Extensive experiments on various multi-view datasets show that MGCN-FN achieves superior performance compared to state-of-the-art methods, especially on semi-supervised multi-view classification tasks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{jingjun_3817,

title = {Linear projection fused graph-based semi-supervised learning on multi-view data},

author = {Bi Jingjun and Fadi Dornaika and Jinan Charafeddine},

url = {http://dx.doi.org/10.1007/s10462-025-11313-8},

year  = {2025},

date = {2025-07-01},

journal = {Artificial Intelligence Review},

volume = {58},

pages = {309},

abstract = {In recent years, the surge in data-driven applications across various domains has spurred heightened interest in semi-supervised learning applied to graphs. This surge is attributed to the ubiquitous presence of graph data structures in real-world contexts, such as social networks' interpersonal relationships, recommender systems' user behavior graphs, and bioinformatics' molecular interaction networks. However, for certain data types like images, not only is there a dearth of explicit graph structure, but also the existence of multiple view description methods complicates matters further. The intricacies of multi-view data pose challenges in directly applying traditional semi-supervised learning techniques to graphs. Consequently, researchers have begun exploring the fusion of semi-supervised learning with deep learning to leverage its wealth of information and enhance model efficacy. Effectively amalgamating graph structures with multi-view data remains a challenging problem necessitating further research. This paper introduces the Linear projection Fused Graph-based Semi-supervised Classification (LFGSC) method tailored for multi-view data, building upon the Graph Convolutional Network (GCN) architecture. Firstly, for each view, we leverage a semi-supervised approach that provides the concurrent estimation of the corresponding graph and the flexible linear data representations in a low-dimensional feature space. Subsequently, an adaptive and unified graph is generated, followed by the utilization of a fully connected network to fuse the projected features further and reduce dimensionality. Finally, the fused features and graph are inputted into a GCN to conduct semi-supervised classification. During training, the model incorporates cross-entropy loss, manifold regularization loss, graph auto-encoder loss, and supervised contrastive loss. Leveraging linear transformation significantly diminishes the input feature dimensions for GCN, thereby achieving high accuracy while substantially reducing computational overhead. Furthermore, experimental results conducted on various bench-marked multi-view image datasets demonstrate the superiority of LFGSC over existing semi-supervised learning methods for multi-view scenarios. (Source code: https://github.com/BiJingjun/LFGSC.)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{peng_3611,

title = {CGCN-FMF:1D convolutional neural network based feature fusion and multi graph fusion for semi-supervised learning},

author = {Guowe Peng and Fadi Dornaika and Jinan Charafeddine},

url = {http://dx.doi.org/10.1016/j.eswa.2025.127194},

year  = {2025},

date = {2025-06-01},

journal = {Expert Systems With Applications},

volume = {277},

pages = {127194},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3790,

title = {Deep Feature Disentanglement for Supervised Contrastive Learning: Application to Image Classification},

author = {Fadi Dornaika and B Wang and Jinan Charafeddine},

url = {https://link.springer.com/article/10.1007/s12559-025-10430-4},

year  = {2025},

date = {2025-06-01},

journal = {Cognitive Computation},

volume = {17},

pages = {117},

abstract = {In machine learning, deep metric learning from original data is essential, with supervised contrastive learning being a notable approach. This method aims to form a deep feature space where similar samples from the same class are clustered together, while dissimilar samples from different classes are separated. However, a common limitation of contrastive learning methods is that they utilize the entire feature space for data embedding and often neglect the within-class variability. To overcome this limitation, we propose a novel supervised contrastive learning method that decomposes deep features into two distinct components: common features, which encapsulate the essential, class-defining characteristics, and style features, which capture the within-class variability and nuanced differences. Additionally, we enhance this approach by introducing an overlapping field that synergistically integrates elements from both feature spaces, enabling a more comprehensive and robust feature representation. Our experiments with different image datasets and deep encoders, including CNNs and transformers, show that our approach outperforms traditional single-feature contrastive methods. On the CIFAR100 and PASCAL VOC databases, traditional supervised contrastive learning achieved accuracy rates of 75.5% and 51.41%, respectively, while our method improved them to 77.81% and 59.38%, respectively. We present an algorithm for deep contrastive learning that utilizes two feature spaces: one for encoding common class features and another for capturing within-class variability. This is achieved by partitioning the features of the last layer of the encoder into (i) a common field and (ii) a style field. Our loss function contrasts the common features while summarizing the style features within the same class so that the style field can capture the intra-class variability.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{jabbar_al-allaq_3796,

title = {A Comprehensive Review of Cutting-Edge Disaster Response: UAVs Equipped with FSO-Based Communications},

author = {Zaid Jabbar Al-Allaq and Wafaa Shakir and Jinan Charafeddine},

url = {https://link.springer.com/article/10.1007/s11277-025-11782-8#citeas},

year  = {2025},

date = {2025-06-01},

journal = {Wireless Personal Communications},

volume = {141},

pages = {29-394},

abstract = {Unmanned aerial vehicles (UAVs) equipped with free-space optical (FSO) communications have emerged as pivotal technological assets in disaster management. Traditional communication infrastructures often fail during severe disaster scenarios, resulting in delayed or ineffective emergency response efforts. Consequently, the integration of unmanned aerial vehicles with free-space optical communication technologies has emerged as an essential innovation in disaster response management. UAVs provide agile and rapidly deployable platforms, while FSO technology offers high-bandwidth, secure, and interference-resistant communication links. This comprehensive review systematically explores the current state and advanced integration strategies of UAVs equipped with FSO communication in disaster scenarios. Initially, the paper establishes the research context, identifying challenges associated with conventional disaster communications. Subsequently, the necessity for this review is articulated through a critical examination of the limitations faced by existing terrestrial systems. The paper clearly delineates various aspects of UAV-FSO integration by providing essential background information on disasters and conventional emergency communication systems, elaborating on the roles, benefits, and applications of UAVs specifically in disaster management contexts, and introducing FSO technology with its operational principles and advantages. Furthermore, it critically examines existing challenges and technical limitations of UAV-based FSO systems, including atmospheric disturbances and alignment issues. Recent technological advancements and mitigation strategies, such as intelligent reflecting surfaces, quantum key distribution, and machine learning integration, are discussed to enhance system reliability and performance. Detailed performance metrics such as bit error rate (BER) and outage probability are analyzed for evaluating UAV-FSO systems. Finally, the review addresses the latest contributions and innovations in the field, emphasizing future research directions and open challenges, and concludes by summarizing the transformative potential of integrating UAVs with FSO communications, advocating for continued research and practical application to improve disaster response capabilities globally.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3401,

title = {Semi-supervised learning for multi-view and non-graph data using Graph Convolutional Networks},

author = {Fadi Dornaika and Jinan Charafeddine and Huaiyuan Xiao and Jingjun Bi},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0893608025000978?via%3Dihub},

year  = {2025},

date = {2025-05-01},

journal = {Neural Networks},

volume = {185},

pages = {107218},

abstract = {Semi-supervised learning with a graph-based approach has become increasingly popular in machine learning, particularly when dealing with situations where labeling data is a costly process. Graph Convolution Networks (GCNs) have been widely employed in semi-supervised learning, primarily on graph-structured data like citations and social networks. However, there exists a significant gap in applying these methods to non-graph multi-view data, such as collections of images. To bridge this gap, we introduce a novel deep semi-supervised multi-view classification model tailored specifically for non-graph data. This model independently reconstructs individual graphs using a powerful semi-supervised approach and subsequently merges them adaptively into a unified consensus graph. The consensus graph feeds into a unified GCN framework incorporating a label smoothing constraint.

To assess the efficacy of the proposed model, experiments were conducted across seven multi-view image datasets. Results demonstrate that this model excels in both the graph generation and semi-supervised classification phases, consistently outperforming classical GCNs and other existing semi-supervised multi-view classification approaches. 1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3653,

title = {One-phase multi-view clustering with unified graph and data representation convolution},

author = {Fadi Dornaika and Jinan Charafeddine},

url = {http://dx.doi.org/10.1007/s00500-025-10533-y},

year  = {2025},

date = {2025-05-01},

journal = {Soft Computing},

volume = {29},

pages = {4335-4356},

abstract = {The goal of multi-view clustering is to partition unlabeled objects into disjoint clusters or groups using consistent and complementary information provided by the different features of the same object. Most existing methods perform this clustering task sequentially: Computation of the individual or consistent graph matrices, spectral embedding, and clustering. In this work, we present an approach that can overcome some of the limitations of previous multiview clustering methods. We introduce a single objective function whose minimization can jointly determine the consistent graph matrix for all views, the unified spectral data representation, the soft cluster indices, and the view weights. We present a constraint term that relates the cluster indices to the convolution of the consistent spectral data representations over the consistent graph. The method we present has two interesting features that are not simultaneously present in recent work. First, the cluster indices can be estimated directly without the need for an additional clustering step, which depends heavily on initialization. Second, the soft cluster indices are directly linked to the kernel representation of the features of the views. Moreover, our proposed method automatically determines the weights of each view, thus requiring fewer hyperparameters. A series of experiments have been conducted on real datasets. These demonstrate the efficiency of the proposed method, which compares favorably to many multi-view clustering methods.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3466,

title = {Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data},

author = {Fadi Dornaika and Jingjun Bi and Jinan Charafeddine},

url = {http://dx.doi.org/10.1007/s12559-025-10428-y},

year  = {2025},

date = {2025-03-01},

journal = {Cognitive Computation},

volume = {17},

pages = {73},

abstract = {Semi-supervised learning with a graph-based approach has gained prominence in machine learning, particularly in scenarios

where labeling data involves substantial costs. Graph convolution networks (GCNs) have found widespread application in

semi-supervised learning, predominantly on graph-structured data such as citation and social networks. However, a noticeable

gap exists in the application of these methods to non-graph multi-view data, such as collections of images. In an effort to

address this gap, we introduce two innovative deep semi-supervised multi-view classification models specifically tailored for

non-graph data. Both models share a common architecture, leveraging GCNs and integrating a label smoothing constraint.

The primary distinction lies in the construction of the consensus similarity graph. The first model directly reconstructs the

consensus graph from different views using a specialized objective function designed for flexible graph-based semi-supervised

classification. In contrast, the second model independently reconstructs individual graphs and subsequently adaptively merges

them into a unified consensus graph. Our experiments encompass various multiple-view image datasets. The results consis-

tently demonstrate the superior performance of our proposed approach compared to traditional fusion methods with GCNs. In

this research, we present two approaches for tackling semi-supervised classification challenges involving multiple views. One

method is named Semi-supervised Classification with a Unified Graph (SCUG), and the other is referred to as Semi-supervised

Classification with a Fused Graph (SC-Fused). Both methods share a common semi-supervised classification process, utilizing

the GCN framework and incorporating label smoothing. However, the key distinction lies in the construction of the similarity

graph. Unlike traditional ad hoc graph construction approaches, our proposed methods, SCUG and SC-Fused, estimate the

unified graph or individual graphs, respectively, alongside the labels. This results in more optimized graphs that benefit from

data smoothing and the semi-supervised context.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{shakir_3613,

title = {Empowering MIMO-FSO Systems: RIS Technology for Enhanced Performance in Challenging Conditions},

author = {Wafaa Shakir and Jinan Charafeddine},

url = {https://ieeexplore.ieee.org/document/10937202},

year  = {2025},

date = {2025-03-01},

volume = {28},

number = {6},

pages = {1 - 1},

abstract = {This paper presents a novel analytical framework to enhance the performance of reconfigurable intelligent surfaces (RIS)-integrated multiple-input-multiple-output (MIMO) free-space optical (FSO) communication systems. The study addresses critical challenges such as atmospheric turbulence, misalignment, and signal attenuation. It introduces a series-based approach to model the combined effects of Gamma-Gamma turbulence, generalized Rician pointing errors, and RIS size-related constraints. In contrast to previous studies, which often rely on oversimplified or idealized channel models, this framework provides closed-form expressions for the first time for the probability density function and cumulative distribution function of the end-to-end channel specifically designed for RIS-empowered (RIS-E) MIMO-FSO systems. These expressions capture the complex interactions between channel impairments and system parameters, enabling accurate performance evaluation in real-world deployments. The derived formulations provide key performance metrics, including outage probability, average bit error rate, ergodic capacity, data rate, and energy efficiency, for a variety of system configurations. Practical diversity combining techniques such as equal gain combining, maximal ratio combining, and selection combining are rigorously analyzed. In addition, asymptotic analyses at high signal-to-noise ratios offer simplified expressions that provide valuable insights into coding gain, diversity order, and system behavior under extreme conditions. A key contribution of this work is the investigation of the optimization of RIS placement, which improves signal alignment and reduces the outage probability, even under challenging atmospheric conditions. In addition, the study highlights the computational efficiency of the proposed framework through a detailed complexity analysis that confirms its feasibility for practical, large-scale applications. Monte Carlo simulations validate the theoretical findings, demonstrating strong agreement with the analytical results. These results confirm the transformative potential of RIS technology in mitigating turbulence-induced fading and misalignment. This research establishes RIS-E MIMO-FSO systems as a robust, energy-efficient solution for next-generation, high-bandwidth optical networks. Additionally, it provides practical deployment guidelines, ensuring the effective integration of RIS technology into real-world wireless communication infrastructures, thereby advancing the development of resilient and high-performance optical communication systems.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_3269,

title = {Unified Multi-view Data Clustering: Simultaneous Learning of Consensus Coefficient Matrix and Similarity Graph},

author = {Fadi Dornaika and Sally El Hajjar and Jinan Charafeddine and Nagore Barrena},

url = {https://link.springer.com/article/10.1007/s12559-024-10392-z},

year  = {2025},

date = {2025-01-01},

journal = {Cognitive Computation},

volume = {17},

number = {38},

abstract = {Integrating data from multiple sources or views has become increasingly common in data analysis, particularly in fields

like healthcare, finance, and social sciences. However, clustering such multi-view data poses unique challenges due to the

heterogeneity and complexity of the data sources. Traditional clustering methods are often unable to effectively leverage the

information from different views, leading to suboptimal clustering results. To address this challenge, multi-view clustering

techniques have been developed, aiming to integrate information from multiple views to improve clustering performance.

These techniques typically involve learning a similarity matrix for each view and then combining these matrices to form

a consensus similarity matrix, which is subsequently used for clustering. However, existing approaches often suffer from

limitations such as the need for manual tuning of parameters and the inability to effectively capture the underlying structure

of the data. In this paper, we propose a novel approach for multi-view clustering that addresses these limitations by jointly

learning the consensus coefficient matrix and similarity graph. Unlike existing methods that follow a sequential approach

of first learning the coefficient matrix and then constructing the similarity graph, our approach simultaneously learns both

matrices, ensuring a more regularized consensus graph. Additionally, our method automatically adjusts the weight of each

view, eliminating the need for manual parameter tuning. Our approach involves several key steps. First, we formulate an

optimization problem that jointly optimizes the consensus coefficient matrix, unified spectral projection matrix, coefficient

matrix, and soft cluster assignment matrix. We then propose an efficient algorithm to solve this optimization problem, which

involves iteratively updating the matrices until convergence. To learn the consensus coefficient matrix and similarity graph, we

leverage techniques from matrix factorization and graph-based learning. Specifically, we use a self-representation technique

to learn the coefficient matrix (regularization graPh) and a graph regularization technique to learn the similarity graph. By

jointly optimizing these matrices, we ensure that the resulting consensus graph is more regularized and better captures the

underlying structure of the data. We evaluate our approach on several public image datasets, comparing it against state-of-the-

art multi-view clustering methods. Our experimental results demonstrate that our approach consistently outperforms existing

methods in terms of clustering accuracy and robustness. Additionally, we conduct sensitivity analysis to evaluate the impact

of different hyperparameters on the clustering performance. We present a novel approach for multi-view data clustering

that jointly learns the consensus coefficient matrix and similarity graph. By simultaneously optimizing these matrices, our

approach achieves better clustering performance compared to existing methods. Our results demonstrate the effectiveness and

robustness of our approach across different datasets, highlighting its potential for real-world applications in various domain.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{abou_ali_3271,

title = {Enhancing Generalization and Mitigating Overfitting in Deep Learning for Brain Cancer Diagnosis from MRI},

author = {Mohamad Abou Ali and Jinan Charafeddine and Fadi Dornaika and Ignacio Arganda?Carreras},

url = {https://link.springer.com/article/10.1007/s00723-024-01743-y},

year  = {2025},

date = {2025-01-01},

journal = {Applied Magnetic Resonance},

abstract = {Brain cancer represents a significant global health challenge with increasing inci-

dence and mortality rates. Magnetic Resonance Imaging (MRI) plays a pivotal role

in early detection and treatment planning. This study adopts a systematic approach

across four phases: (1) Optimal Model Selection using the Adam optimizer, empha-

sizing accuracy metrics, weight computation, early stopping, and ReduceLROn-

Plateau techniques. (2) Real-world Scenario Simulation through synthetic per-

turbed datasets created by applying noise, blur (to simulate various magnetic field

strengths: 1T, 1.5T, 3T), and patient motion artifacts (mimicking MRI scanning

motion effects) to the testing data from the BT-MRI dataset, an online published

brain tumor MRI dataset. (3) Optimization involving a range of optimizers (Adam,

Adagrad, Nadam, RMSprop, SGD) and online augmentation techniques (AutoMix,

CutMix, LGCOAMix, PatchUp). (4) Solution Exploration integrating Gaussian

Noise and Blur as augmentation strategies during training to enhance model gener-

alization under diverse conditions. Initial evaluations achieved strong performance,

consistently reaching 99.45% accuracy on the BT-MRI dataset. However, testing

against synthetic perturbed datasets mimicking real-world conditions revealed chal-

lenges in maintaining robust model performance. Despite employing diverse opti-

mization methods and advanced augmentation techniques, this study identifies per-

sistent challenges in ensuring model robustness with synthetic perturbed datasets.

Notably, the integration of Gaussian Noise and Blur during training significantly

improved model resilience. This research underscores the critical role of method-

ological rigor and innovative augmentation strategies in advancing deep learning

applications for precise brain cancer diagnosis using MRI.},

keywords = {},

pubstate = {online},

tppubtype = {article}

}

@article{sun_3024,

title = {LCAMix: Local-and-contour aware grid mixing based data augmentation for medical image segmentation},

author = {Danyang Sun and Fadi Dornaika and Jinan Charafeddine},

url = {https://pdf.sciencedirectassets.com/272144/1-s2.0-S1566253524X00068/1-s2.0-S1566253524002628/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEBcaCXVzLWVhc3QtMSJHMEUCIB%2Bm2yVgKP%2BTa1w1tSg%2FydrF%2Fvb0NtGUi2OtE0dCfm5ZAiEAvS5zznXIlJGGqU0uDk6urwemR%2FjBXI8flOEVsv%2Bqi7MqvAUIj%2F%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FARAFGgwwNTkwMDM1NDY4NjUiDGlNeMR%2BKpLBIx%2FJkiqQBUxi37rUay01aPHdPyUjlEmZScIOm09oNOKMm2j4kAJ%2BBXu4xZ6ts%2FYVWeKloZ9bKO688mVLpZYW96XCoW8DS9E%2FGvhCoLNFgFEV35VB1ai8O7M21%2BlU%2Br8%2FcPbj77ypLNC%2BKDWJV0NPrB1DKOvao6ZpbspbrdK4kPspEAzZ%2FVkFT%2FKiopgMXf6iniq2tANtPaizXkk%2BZaNSAGIFt9OmCXMk6H7VYJALKEF4ZJm9kBslRj5nE5Y6edtx2JSSptvlujKMXhJbwjIiUiX7Ui1B4pUWDVtzmLpVcElBM78VwS0H8TKlHXBl5pyVDCym%2Fp2r%2BZbZdJWW6ZWgrqb26Dqc%2F22RSCtts8Lm%2Fs8vSHEc2cfI2mYpPSj5gL51yaDqoZyA9JcEBsQRAecvv%2F8RkbvtzMzuNBRjn4V8HoQR137Q2pYM%2FJgAly5tkgk5KS8JB2jb%2BaTA88ZJLx6YSDeqJdX2PXwyB1XvrrRy8oUgMmff8s2zVgT1f1dX5iPmZ1jtYEVu40cdvJ88ac8j4zAfWQPmBb%2FvfXWd%2BDVOp7h8ftVwQnI7bLDlFBXbhH3oVb%2FFpJ3Bw3DFakM7j%2FSOVug7DP8dC9h8Dj2oIOW8C4QAgdCeHaDRMfh2F7VZjw3FZf3i631%2BAdBp8r4d4XkYeREmbmiovEoVWBBHoYD6RTIK9lp37AmDnhFSAMr2LEmzG2NypUQ3Hwb7zLu4thOxdGz5MBApBAh44ukY8YuN1ufa38eyKRtCUO%2Fxd2kuIIJ2LVXa3bQYug5Lx%2B9KIKhgqxCrwptvf8OaxtQ5FoYhuqNU0pL1Chohou2d1vld8RViOconvLl0VWMsZ5YyP9ZxaM0xtzdz9jZQUUyYOV92u8ehS7ie1qwrMNDAwrIGOrEBxpUgPvpVhdMKearFfabKLjWh5dtniMHIFTE5cSfjDp3cUuAHaEMlV2m22S1E7%2B%2BqLhJRHUxrx0Ahj9AgijOS6Ej7rGG3xGTKGOnhYGjvrjhMzhpYH7bBR2UDVY%2Ff5JnU3IqbM8%2BmzPkwAtPDE4f74N3zJ3CUErPd4nF0UOXyQABK0JE3XGOZmeqIIDshevKKQuAQWWCmCYyGaPWgjtPkrFNgDEqhkhXN4QWxs%2FJfC2Tb&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20240524T152432Z&X-Amz-SignedHeaders=host&X-Amz-Expires=299&X-Amz-Credential=ASIAQ3PHCVTY4RJ4ZEGT%2F20240524%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Signature=49fff6e8e4aa2160d63ba58a605230103a570a99a899c33049a2447724567bf6&hash=cf866cff1fcd93c461170f4149fdcc586b3e8c5bd13fbef0361db16227b04cc0&host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&pii=S1566253524002628&tid=spdf-53f47d50-21b1-4fa1-a93b-92addbddb736&sid=5b8e3010830f534aec5849b2797ace9af2f9gxrqb&type=client&tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t&ua=001156565a0352015207&rr=888e4b0cfc530203&cc=fr},

year  = {2024},

date = {2024-10-01},

journal = {Information Fusion},

volume = {110},

pages = {102484},

abstract = {Medical image segmentation often faces challenges related to overfitting, primarily due to the limited and complex training samples. This challenge often prompts the use of self-supervised learning and data augmentation. However, self-supervised learning requires well-defined hand-crafted tasks and multiple training stages. On the other hand, basic image augmentation techniques like cropping, rotation, and flipping, effective for natural scene images, have limited efficacy for medical images due to their isotropic nature.



While regional dropout regularization data augmentation methods have proven effective in image recognition tasks, their application in image segmentation is not as extensively studied. Additionally, existing augmentation methods often operate on square regions, leading to the loss of crucial contour information. This is particularly problematic for medical image segmentation tasks dealing with regions of interest characterized by intricate shapes. In this work, we introduce LCAMix, a novel data augmentation approach designed for medical image segmentation. LCAMix operates by blending two images and their segmentation masks based on their superpixels, incorporating a local-and-contour-aware strategy. The training process on augmented images adopts two auxiliary pretext tasks: firstly, classifying local superpixels in augmented images using an adaptive focal margin, leveraging segmentation ground truth masks as prior knowledge; secondly, reconstructing the two source images using mixed superpixels as mutual masks, emphasizing spatial sensitivity. Our method stands out as a simple, one-stage, model-agnostic, and plug-and-play data augmentation solution applicable to various segmentation tasks. Notably, it requires no external data or additional models. Extensive experiments validate its superior performance across diverse medical segmentation datasets and tasks. The source codes are available at https://github.com/DanielaPlusPlus/DataAug4Medical.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{alirezazadeh_3188,

title = {Mises-Fisher similarity-based boosted additive angular margin loss for breast cancer classification},

author = {Pandar Alirezazadeh and Fadi Dornaika and Jinan Charafeddine},

url = {https://link.springer.com/article/10.1007/s10462-024-10963-4#citeas},

year  = {2024},

date = {2024-10-01},

journal = {Artificial Intelligence Review},

volume = {57},

pages = {326},

abstract = {To enhance the accuracy of breast cancer diagnosis, current practices rely on biopsies and microscopic examinations. However, this approach is known for being time-consuming, tedious, and costly. While convolutional neural networks (CNNs) have shown promise for their efficiency and high accuracy, training them effectively becomes challenging in real-world learning scenarios such as class imbalance, small-scale datasets, and label noises. Angular margin-based softmax losses, which concentrate on the angle between features and classifiers embedded in cosine similarity at the classification layer, aim to regulate feature representation learning. Nevertheless, the cosine similarity's lack of a heavy tail impedes its ability to compactly regulate intra-class feature distribution, limiting generalization performance. Moreover, these losses are constrained to target classes when margin penalties are applied, which may not always optimize effectiveness. Addressing these hurdles, we introduce an innovative approach termed MF-BAM (Mises-Fisher Similarity-based Boosted Additive Angular Margin Loss), which extends beyond traditional cosine similarity and is anchored in the von Mises-Fisher distribution. MF-BAM not only penalizes the angle between deep features and their corresponding target class weights but also considers angles between deep features and weights associated with non-target classes. Through extensive experimentation on the BreaKHis dataset, MF-BAM achieves outstanding accuracies of 99.92%, 99.96%, 100.00%, and 98.05% for magnification levels of ×40, ×100, ×200, and ×400, respectively. Furthermore, additional experiments conducted on the BACH dataset for breast cancer classification, as well as on the LFW and YTF datasets for face recognition, affirm the generalization capability of our proposed loss function.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{shakir_3063,

title = {Novel Approximate Distribution of the Generalized Turbulence Channels for MIMO FSO Communications},

author = {Wafaa Shakir and Ali Mahdi and Hani Hamdan and Jinan Charafeddine and Haitham Satai and Radouane Akrache and Samir Hadad and Jinane Sayah},

url = {https://ieeexplore.ieee.org/document/10568928},

year  = {2024},

date = {2024-08-01},

journal = {Ieee Photonics Journal},

volume = {16},

number = {4},

pages = {1 - 15},

abstract = {In this paper, we develop an innovative series representation for the sum of Rician non-zero boresight pointing error random variates based on the k - ? distribution, which is suitable for multiple-input multiple-output (MIMO) transmission for the first time. Then, using this new representation, we introduce a novel closed-form probability density function (PDF) approximation for the sum of Gamma-Gamma random variates with generalized pointing errors and atmospheric attenuation of MIMO free-space optical (FSO) communications. Statistical Kolmogorov-Smirnov tests confirm the accuracy of this approximation over a wide range of channel conditions. The significance of this approximation is emphasized by deriving closed-form expressions for the ergodic capacity, outage probability, and average bit error rate (BER) using Meijer's G-function. This paper provides a comprehensive analysis of the performance of MIMO FSO systems utilizing the equal gain combining (EGC) diversity technique under various conditions, such as different numbers of transmitter and receiver, turbulence intensities, the effects of non-zero boresight pointing errors, and path attenuation. The results show that using MIMO technology with more transmitters and receivers significantly improves the performance of FSO communication compared to other diversity techniques, including single input single output (SISO), and multiple input single output (MISO) systems. Detailed evaluations of the ergodic capacity, outage probability, and average BER performance at high signal-to-noise ratios provide additional insights. Monte-Carlo simulation results demonstrate the accuracy of the proposed approach.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dornaika_2943,

title = {Towards unsupervised radiograph clustering for COVID-19: The use of graph-based multi-view clustering},

author = {Fadi Dornaika and Sally El Hajjar and Jinan Charafeddine},

url = {https://www.sciencedirect.com/science/article/pii/S0952197624004949?via%3Dihub},

year  = {2024},

date = {2024-07-01},

journal = {Engineering Applications Of Artificial Intelligence},

volume = {133},

number = {Part D},

pages = {108336},

abstract = {Automatic classification methods widely used for diagnosing and analyzing COVID-19 cases. These methods assume known labels and rely on a single view of the dataset. Given the prevalence of COVID-19 cases and the extensive volume of patient records lacking labels, this communication underscores our unique approach?conducting the first study on COVID-19 case diagnosis in an unsupervised manner. Our work operates under the assumption of prior knowledge regarding the number of classes, such as COVID-19, pneumonia, and normal, in a case study.



By adopting an unsupervised learning paradigm, we leverage the wealth of unlabeled data, reducing dependence on human experts for annotating numerous images. This paper introduces an enhanced version of a recent direct method where non-negative cluster indices and spectral embeddings are jointly estimated. Beyond the inherent advantages of this method, our proposed model introduces improvements through two additional types of constraints: (i) ensuring consistent smoothing of cluster labels across all views and (ii) imposing an orthogonality constraint on the matrix of cluster assignments. The efficacy of the proposed method is demonstrated using the public COVIDx dataset with three classes, showcasing promising results in categorizing radiographs. The proposed approach is tested on other public image datasets to assess its effectiveness.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}