Diseases significantly impact plant growth, and one reliable way of detecting illnesses is to observe changes in the leaves. Plant diseases are caused by a number of pests that eat on the leaves, stems, bases, and entire plant. Therefore, it’s critical to detect and eradicate the illness before it harms plants. Identifying and treating plant diseases manually is becoming more and more challenging. Advancements in deep learning, particularly deep clustering algorithms, have significantly contributed to the discovery and diagnosis of plant diseases. For this purpose, we explore the effectiveness of a deep clustering model based on Dynamic Autoencoder to improve plant disease detection. This approach aims to tackle challenges such as feature drift and randomness, while also adapting to the evolving nature of the data and enhancing disease detection accuracy. Results from an experimental study using PlantVillage datasets were compared with current methods, demonstrating the model’s superiority and performance.

Zero-shot guided unsupervised image segmentation enables dense scene understanding without relying on target-domain annotations, making it particularly valuable in domains where labeled data is scarce. However, most existing approaches struggle to reconcile global semantic coherence with fine-grained boundary precision. This paper introduces DynaGuide, an adaptive segmentation framework that addresses this challenge through a novel dual-guidance strategy and dynamic loss optimization. Building on our prior work, DynaSeg, DynaGuide integrates global pseudo-labels with local boundary refinement via a lightweight CNN trained from scratch. Crucially, the global pseudo-labels can originate either from a fully unsupervised source, such as DiffSeg, or from a supervised-pretrained model such as SegFormer. In both cases, these models act only as frozen priors on unseen data, ensuring that DynaGuide itself trains entirely without ground-truth labels in the target domain. Training is driven by a multi-component loss that dynamically balances feature similarity, Huber-smoothed spatial continuity (including diagonal relationships), and semantic alignment with the global pseudo-labels. Extensive experiments on BSD500, PASCAL VOC2012, and COCO demonstrate that DynaGuide achieves state-of-the-art performance, improving mIoU by 17.5% on BSD500, 3.1% on PASCAL VOC2012, and 11.66% on COCO. With its modular design, strong generalization, and minimal computational footprint, DynaGuide offers a scalable and practical solution for zero-shot guided unsupervised segmentation in real-world settings. • Proposes DynaGuide: a dual-guidance framework for zero-shot unsupervised segmentation. • Combines static global pseudo-labels with dynamic local CNN refinement. • Introduces adaptive multi-loss: feature similarity, diagonal Huber continuity, and global guidance. • Trains fully label-free using DiffSeg or SegFormer pseudo-labels without fine-tuning. • Outperforms recent SOTA on BSD500, PASCAL VOC2012, and COCO with fewer parameters and FLOPs.

We introduce a cutting-edge approach for matching a pair of images by using a multi-dimension graph which is constructed from the images and processed using graph attention neural networks. Our method is detector-free, and in contrast to the state-of-the-art, it uses the hierarchical mechanism, a novel approach to establish image correspondence. Our framework consists of three key components: 1) a convolution neural network to compute the embedding of the hierarchical grid cell of the image, 2) a graph attention neural network that establishes correspondences between regions at each hierarchical level, and 3) a neural network model used to establish pixel-level correspondence. All three components are trained jointly to ensure optimal performance. By using the hierarchical mechanism, our model is shown to be competitive with the state-of-the-art methods and even provides performance overhead on various datasets using similar relevant metrics.

The effective management of services based on Quality of Experience (QoE) is crucial for the successful deployment of multimedia services in advanced networks like 5G/6G. This necessitates the use of appropriate tools for monitoring, predicting, and managing quality, with Machine Learning (ML) playing a pivotal role. However, predicting the QoE of multimedia streams poses a challenge due to its dependence on numerous influencing factors, and it must adapt to dynamic environments with large-scale data. Machine learning approaches provide a method to quantify the complex relationships between these influencing factors and QoE. In this paper, we propose an innovative improved mixture of classification for assessing the QoE of video streaming. Our approach combines the predictive capabilities of ensemble learning models rather than single models, as experts. Also, we have employed a robust gating network trained by minimizing an improved error function that combines the Classification Loss and the gating loss. We assess our method through a comprehensive simulation model encompassing diverse wireless network environments and various video sequences. The experimental results reveal substantial enhancements in QoE, ensuring users have stable, high-quality video streaming sessions.

The dependence on smart city applications has expanded in recent years. Consequently, the number of cyberattack attempts to exploit smart application vulnerabilities significantly increases. Therefore, improving smart application security during the software development process is mandatory to ensure sustainable smart cities. But the challenge is how to adopt security practices in the software development process. There are Several established and mature security testing frameworks exist that consider security requirements and testing during Several already established and mature security testing frameworks exist that consider security requirements and testing during Software Development Life Cycle (SDLC), but there is a unique challenges posed by smart city applications and the need for a comprehensive approach to address the evolving threat landscape in this context. This paper proposed a framework that adopts security testing practices in all phases of the software development process. The proposed framework identifies several security activities and steps that can be applied in each phase of the software development process.

Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits scalability. We introduce DynaSeg, an innovative unsupervised image segmentation approach that overcomes the challenge of balancing feature similarity and spatial continuity without relying on extensive hyperparameter tuning. Unlike traditional methods, DynaSeg employs a dynamic weighting scheme that automates parameter tuning, adapts flexibly to image characteristics, and facilitates easy integration with other segmentation networks. By incorporating a Silhouette Score Phase, DynaSeg prevents undersegmentation failures where the number of predicted clusters might converge to one. DynaSeg uses CNN-based and pre-trained ResNet feature extraction, making it computationally efficient and more straightforward than other complex models. Experimental results showcase state-of-the-art performance, achieving a 12.2% and 14.12% mIOU improvement over current unsupervised segmentation approaches on COCO-All and COCO-Stuff datasets, respectively. We provide qualitative and quantitative results on five benchmark datasets, demonstrating the efficacy of the proposed approach. Code available at \url{https://github.com/RyersonMultimediaLab/DynaSeg}

Deep clustering models are trained based on self-supervision and pseudo-supervision. However, applying these techniques can cause Feature Randomness and Feature Drift. On one hand, Feature Randomness takes place when a considerable portion of the pseudo-labels do not match the true ones. On the other hand, Feature Drift takes place when there is a strong con-flict between the self-supervision and pseudo-supervision tasks. We propose ADEC (Adversarial Deep Embedded Clustering) a novel autoencoder-based clustering model, which relies on a discriminator network to reduce random features while avoiding the drifting effect. Experimental results validate that our model alleviates these problems and outperforms existing methods.

Recent graph clustering methods have resorted to Graph Auto-Encoders (GAEs). However, two important issues have been overlooked. First, the accumulative error, inflicted by learning from noisy clustering assignments, degrades the model’s effectiveness. This problem is called Feature Randomness (FR). Second, reconstructing the adjacency matrix sets the model to learn irrelevant similarities for the clustering task. This problem is called Feature Drift (FD). To address these issues, we first propose a sampling operator that triggers a protection mechanism against FR. second, we propose an operator Υ that triggers a correction mechanism against FD by transforming the reconstructed graph. Experimental results validate that our operators alleviate these problems and bring significant clustering improvement.

Breast cancer is a prevalent and life-threatening disease affecting many women worldwide. Early diagnosis plays a crucial role in improving survival rates and allowing effective treatment. Mammography is recognized as the most effective imaging modality for breast cancer diagnosis. To achieve early diagnosis, researchers have developed intelligent systems based on Deep Learning (DL) models, specifically Convolutional Neural Networks (CNNs), which are well-suited for analyzing medical images. Training deep CNN models for breast cancer diagnosis poses challenges, mainly due to the limited size of publicly available mammography datasets commonly used by researchers. This scarcity of data can lead to overfitting issues. Obtaining a large-scale breast mammogram dataset is a time-consuming and expensive process in clinical practice. Researchers have successfully employed Transfer Learning (TL) to overcome this issue. In this scenario, models are initially trained on large datasets from other domains, generating pre-trained models that capture general image representations. These models are then fine-tuned on a breast cancer image dataset. This approach leverages the learned knowledge from the first dataset to improve the performance of DL models in the breast cancer diagnosis task. This survey aims to present the latest research findings in the realm of TL architectures applied to breast cancer diagnosis using limited mammography datasets. It covers the following areas: (i) The structure of CNNs, (ii) Essential background knowledge on TL, (iii) Diverse strategies for implementing TL, (iv) Commonly employed pre-trained CNN architectures, (v) Well-known publicly available mammography datasets along with their key characteristics and strengths, and (vi) A summary of the current state-of-the-art pretrained CNNs specifically applied to breast cancer diagnosis. The survey focuses on the performance and key findings of these models, showcasing their effectiveness in enhancing diagnostic accuracy. This survey seeks to summarize the current trends in TL for breast cancer diagnosis using mammography images, intending to inspire researchers to actively contribute to the progress of transfer learning in the mammogram image analysis field.

Variational Graph Auto-Encoders (VGAEs) have achieved promising performance in several applications. Some recent models incorporate the clustering inductive bias by imposing non-Gaussian prior distributions. However, the regularization term is practically insufficient to learn the clustering structures due to the mismatch between the target and the learned distributions. Thus, we formulate a new variational lower bound that incorporates an explicit clustering objective function. The introduction of a clustering objective leads to two problems. First, the latent information destroyed by the clustering process is critical for generating the between-cluster edges. Second, the noisy and sparse input graph does not benefit from the information learned during the clustering process. To address the first problem, we identify a new term overlooked by existing Evidence Lower BOunds (ELBOs). This term accounts for the difference between the variational posterior used for the clustering task and the variational posterior associated with the generation task. Furthermore, we find that the new term increases resistance to posterior collapse. Theoretically, we demonstrate that our lower bound is a tighter approximation of the log-likelihood function. To address the second problem, we propose a graph update algorithm that reduces the over-segmentation and under-segmentation problems. We conduct several experiments to validate the merits of our approach. Our results show that the proposed method considerably improves the clustering quality compared to state-of-the-art VGAE models.

When building a performing one-class classifier, the low variance direction of the training data set might provide important information. The low variance direction of the training data set improves the Covariance-guided One-Class Support Vector Machine (COSVM), resulting in better accuracy. However, this classifier does not use data dispersion in the one class. It explicitly does not make use of target class subclass information. As a solution, we propose Scatter Covariance-guided One-Class Support Vector Machine, a novel variation of the COSVM classifier (SC-OSVM). In the kernel space, our approach makes use of subclass information to jointly decrease dispersion. Our algorithm technique is even based on a convex optimization problem that can be efficiently solved using standard numerical methods. A comparison of artificial and real-world data sets shows that SC-OSVM provides more efficient and robust solutions than normal COSVM and other contemporary one-class classifiers.

Despite the significant benefits that the Internet of Healthcare Things (IoHT) offered to the medical sector, there are concerns and risks regarding these systems which can delay their wide deployment as they handle sensitive and often life-critical medical information. In addition to the IoHT concerns and risks, there are security constraints which include hardware, software, and network constraints that pose a security challenge to these systems. Therefore, security measures need to be deployed that can overcome the concerns, mitigate the risks, and meet the constraints of the IoHT. For these reasons, a subclasses intrusion detection system for the IoHT is proposed in this research work based on a novel variation of the standard one-class support vector machine (OSVM), namely, deep subclass dispersion OSVM (Deep SDOSVM), which considers subclasses in the target class, i.e., normal class, in order to minimize the data dispersion within and between subclasses, thereby improving the discriminative power and classification performance of the intrusion detection system. A deep clustering model is used for subclasses generation in the proposed Deep SDOSVM approach, namely, the dynamic autoencoder model (DynAE), to overcome the drawbacks of the classical clustering algorithms and further enhance the classification performance of the intrusion detection system. The proposed deep clustering subclasses intrusion detection system was evaluated on the real-world TON_IoT data set and compared to other state-of-the-art one-class classifiers. Experimentation results have shown that the proposed approach outperformed the other relevant one-class classifiers for network intrusion detection.

Most recent graph clustering methods have resorted to Graph Auto-Encoders (GAEs) to perform joint clustering and embedding learning. However, two critical issues have been overlooked. First, the accumulative error, inflicted by learning from noisy clustering assignments, degrades the effectiveness of the clustering model. This problem is called Feature Randomness. Second, reconstructing the adjacency matrix sets the model to learn irrelevant similarities for the clustering task. This problem is called Feature Drift. Furthermore, the theoretical relation between the aforementioned problems has not yet been investigated. We study these issues from two aspects: (1) there is a trade-off between Feature Randomness and Feature Drift when clustering and reconstruction are performed at the same level, and (2) the problem of Feature Drift is more pronounced for GAE models, compared with vanilla auto-encoder models. Thus, we reformulate the GAE-based clustering methodology. Our solution is two-fold. First, we propose a sampling operator$\Xi$that triggers a protection mechanism against Feature Randomness. Second, we propose an operator$\Upsilon$that triggers a correction mechanism against Feature Drift by gradually transforming the reconstructed graph into a clustering-oriented one. As principal advantages, our solution grants a considerable improvement in clustering effectiveness and can be easily tailored to GAE models.

We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previous approaches built a scene-dependent model that explicitly or implicitly embeds the structure of the scene. They use convolution neural networks or decision trees to establish 2D/3D-3D correspondences. Such a mapping overfits the target scene and does not generalize well to dynamic changes in the environment. Our work introduces a novel approach to solve the camera relocalization problem by using the available triangle mesh. Our 3D-3D matching framework consists of three blocks: (1) a graph neural network to compute the embedding of mesh vertices, (2) a convolution neural network to compute the embedding of grid cells defined on the RGB-D image, and (3) a neural network model to establish the correspondence between the two embeddings. These three components are trained end-to-end. To predict the final pose, we run the RANSAC algorithm to generate camera pose hypotheses, and we refine the prediction using the point-cloud representation. Our approach significantly improves the camera pose accuracy of the state-of-the-art method from 0.358 to 0.506 on the RIO10 benchmark for dynamic indoor camera relocalization.

Most recent graph clustering methods rely on pretraining graph auto-encoders using self-supervision techniques (pretext task) and finetuning based on pseudo-supervision (main task). However, the transition from self-supervision to pseudo-supervision has never been studied from a geometric perspective. Herein, we establish the first systematic exploration of the latent manifolds' geometry under the deep clustering paradigm; we study the evolution of their intrinsic dimension and linear intrinsic dimension. We find that the embedded manifolds undergo coarse geometric transformations under the transition regime: from curved low-dimensional to flattened higher-dimensional. Moreover, we find that this inappropriate flattening leads to clustering deterioration by twisting the curved structures. To address this problem, which we call Feature Twist, we propose a variational graph auto-encoder that can smooth the local curves before gradually flattening the global structures. Our results show a notable improvement over multiple state-of-the-art approaches by escaping Feature Twist.

To overcome the absence of concrete supervisory signals, deep clustering models construct their own labels based on self-supervision and pseudo-supervision. However, applying these techniques can cause Feature Randomness and Feature Drift. In this paper, we formally characterize these two new concepts. On one hand, Feature Randomness takes place when a considerable portion of the pseudo-labels is deemed to be random. In this regard, the trained model can learn non-representative features. On the other hand, Feature Drift takes place when the pseudo-supervised and the reconstruction losses are jointly minimized. While penalizing the reconstruction loss aims to preserve all the inherent data information, optimizing the embedded-clustering objective drops the latent between-cluster variances. Due to this compromise, the clustering-friendly representations can be easily drifted. In this context, we propose ADEC (Adversarial Deep Embedded Clustering) a novel autoencoder-based clustering model, which relies on a discriminator network to reduce random features while avoiding the drifting effect. Our new metrics$\Delta _{FR}$and$\Delta _{FD}$allows to, respectively, assess the level of Feature Randomness and Feature Drift. We empirically demonstrate the suitability of our model on handling these problems using benchmark real datasets. Experimental results validate that our model outperforms state-of-the-art autoencoder-based clustering methods.

Satisfying the user it's a primary goal to reach by telecom operators. Therefore, Quality of Experience (QoE), which is the measure of the user-perceived quality of a received service, has become a pivotal topic in the academic research. Generally, an efficient QoE model should be able to handle dynamic environments with large scale data, in order to continuously acquire feedback from the user, and then provide a real-time and accurate description of his perception. This paper proposes a novel online QoE estimation model, which is able to classify user perception toward video streaming service, using incremental multiclass SVM (multiclass-iSVM). The proposed online QoE model investigates the effectiveness of incremental learning, in order to handle large scale dynamic data and to improve prediction accuracy of QoE. In fact, it uses the mathematical properties of SVM and updates its unknown weights, as well as, the classification results incrementally, as new observations are considered. Comparative evaluation of the proposed multiclass iSVM-based QoE model is performed to show its superiority over relevant batch learning based models, in terms of QoE prediction accuracy and computational complexity. In particular, this model has achieved the highest classification rate of 89%, starting with only 10% of the dataset at the beginning of the incremental process.

The main telecom operator goal is to build end user loyalty towards offered services. Computing the perceived quality, known, Quality of Experience (QoE) has become a crucial topic for investigation. Machine learning algorithms provide a solution to tease out the complex relationships between several influencing factors and QoE. This paper proposes a novel QoE estimation model for video service, namely, Boosting Support Vector Regression (BSVR) based QoE model. The purpose of this model is to investigate the effectiveness of combining multiple learners instead of classical individual learner, in order to improve prediction accuracy of the QoE. The BSVR is based on a combination of two principal techniques: Boosting algorithm and Support Vector Regression (SVR). More precisely, multiple SVR models were trained in an iterative boosting algorithm to create a powerful predictive model. In fact, the use of SVRs as weak learners has several advantages. First, the SVR is based on a convex optimization problem, where a global optimal solution exploits a limited number of support vectors, which results in improved prediction accuracy, while maintaining low computational complexity. Second, each SVR uses flexible Radial Basis Function (RBF) kernel function to model QoE data efficiently. Comparative evaluation of our proposed BSVR-based QoE model is performed to show its superiority over relevant ensemble learning methods and regression models based on single learner, in terms of prediction accuracy and computational complexity.

Transfer function (TF) generation is a fundamental problem in direct volume rendering (DVR). A TF maps voxels to color and opacity values to reveal inner structures. Existing TF tools are complex and unintuitive for the users who are more likely to be medical professionals than computer scientists. In this article, we propose a novel image-centric method for TF generation where instead of complex tools, the user directly manipulates volume data to generate DVR. The user’s work is further simplified by presenting only the most informative volume slices for selection. Based on the selected parts, the voxels are classified using our novel sparse nonparametric support vector machine classifier, which combines both local and near-global distributional information of the training data. The voxel classes are mapped to aesthetically pleasing and distinguishable color and opacity values using harmonic colors. Experimental results on several benchmark datasets and a detailed user survey show the effectiveness of the proposed method.

Ground Penetrating Radar (GPR) is used for subsurface exploration across different applications like landmines detection. It can detect and deliver the response of any buried kinds of object, however it cannot discriminate between landmines and false alarms. In this paper, we propose a detection method based on support vector machine (SVM) using one-dimensional GPR delivered data called Ascans. Each Ascan data is considered as a feature input for the proposed SVM classifier based on RBF Kernel. This method is tested on MACADAM database. Used data includes responses of different kind of landmines (targets) and responses of other objects (outliers) like alusquare, wood stick, pine, sodacan and stone buried in different types of soils. In order to evaluate the performance of our detection method, we have used three evaluation measures which are the Receiver Operating Characteristic (ROC) curves, the Area Under the Curve for the ROCs (AUC) and the running time. We have obtained 94.71% as AUC and 1.028s as running time. So, experimental results prove that the proposed method can successfully detect landmines and discriminate between targets and outliers.

In Direct Volume Rendering (DVR), the Transfer Function (TF) to map voxel values to color and opacity values is difficult to obtain. Existing TF design tools are complex and non-intuitive for the end user, who is more likely to be a medical professional than an expert in image processing. In this paper, we propose a volume visualization method where the user directly works on the volume data to simply select the parts he/she would like to visualize. The user's work is further simplified by presenting only the most informative volume slices for selection. Based on the selected parts, all the voxels are classified using our Sparse Nonparametric Support Vector Machine (SN-SVM) classifier, which combines both local and near-global distributional information of the training data to obtain accurate results. The voxel classes are then mapped to color and opacity values using the concept of harmonic colors, which provides easily distinguishable and aesthetically pleasing results. Experimental results on several benchmark datasets show the effectiveness of the proposed method.

Unlike multi-class problems, the low variance directions in the training data are important for one-class classification. However, projecting in these directions before classification will result in loss of important data properties. This paper introduces a Covariance-guided One-Class Support Vector Machine (COSVM) classification method which emphasizes the low variance projectional directions of the training data without compromising any important characteristics. COSVM combines the global information from the covariance matrix of the training data with the local information of Support Vectors. Our proposed method is a convex optimization problem resulting in one global solution, which can be found efficiently with the help of existing numerical methods. The method also keeps the principal structure of the OSVM method intact, and can be implemented easily with the existing OSVM applications. Comparative experimental results with contemporary one-class classifiers on numerous benchmark datasets verify that our method results in significantly better performance.

In this paper, we investigate the effectiveness of a Bayesian logistic regression model to compute the weights of a pseudo-metric, in order to improve its discriminatory capacity and thereby increase image retrieval accuracy. In the proposed Bayesian model, the prior knowledge of the observations is incorporated and the posterior distribution is approximated by a tractable Gaussian form using variational transformation and Jensen's inequality, which allow a fast and straightforward computation of the weights. The pseudo-metric makes use of the compressed and quantized versions of wavelet decomposed feature vectors, and in our previous work, the weights were adjusted by classical logistic regression model. A comparative evaluation of the Bayesian and classical logistic regression models is performed for content-based image retrieval as well as for other classification tasks, in a decontextualized evaluation framework. In this same framework, we compare the Bayesian logistic regression model to some relevant state-of-the-art classification algorithms. Experimental results show that the Bayesian logistic regression model outperforms these linear classification algorithms, and is a significantly better tool than the classical logistic regression model to compute the pseudo-metric weights and improve retrieval and classification performance. Finally, we perform a comparison with results obtained by other retrieval methods.