Financial losses and sensitive data breaches are the most popular risks of credit card fraud in this modern society. Advanced deep learning algorithms have shown outstanding performance regarding fraud detection in this field. However, the proposed models still suffer from the imbalance class problem and the high rate of false positives and negatives. To overcome these challenges, we introduce in this paper a new approach based on TabNet-based feature selection and sequential hybridization of Random Forest and optimized deep learning algorithm. This model outperformed its rivals in detecting complex fraudulent patterns with confidence while minimizing false negatives. Our powerful performance is achieved by combining TabNet feature selection, outlier removal using Z -score and IQR, and strong classification of Random Forest-Deep Learning. The imbalance issue was handled using random oversampling. The results of the experiment demonstrated that our model achieved 100% accuracy, 100% precision, and 1.00 recall regardless of the dataset used which proved its generalization.

With the rise of different types of cyber threats, an efficient intrusion detection system (IDS) becomes very crucial for the network security. In this paper, we aim to enhance the performance of the intrusion detection by involving different Feature Selection (FS) algorithms that identify relevant features from high-dimensional datasets, reduce complexity, and improve the model accuracy. We aspire also to prove the importance of the use of large and balanced datasets in enhancing the intrusion detection performances. To do that, we use different recent datasets taken individually or combined with each other. After the preprocessing of the datasets, we apply diverse FS algorithms, and train the machine learning models. The performance evaluation is performed using metrics like accuracy, precision, recall, and F1-score, with an emphasis on analyzing computational efficiency. The obtained results were conclusive and prove the importance of either a balanced dataset or the use of well chosen FS algorithms in improving the intrusion detection.

Facial expressions are a crucial aspect of nonverbal human communication. Recent advancements in 3D facial expression recognition have allowed for accurate analysis and interpretation of these expressions using three-dimensional facial data. In this work, we present a novel approach for dynamic facial expression recognition using sequences of 3D meshes. Unlike existing state-of-the-art methods that either rely on hand-designed feature descriptors or project the faces to 2D domain, our proposed method directly extracts spatio-temporal information from the 3D meshes in a fully learned manner. This is achieved by feeding input meshes from the sequence individually to a spatial auto-encoder, that uses spiral convolutions to extract spatial embedding. Then, the sequence of embeddings is processed by a temporal transformer to capture temporal context and perform expression classification. We evaluate the proposed method on two facial expression benchmarks: MUG database and BU-4DFE database. Our preliminary experimental results demonstrate the effectiveness of the proposed approach in facial expression recognition. However, we acknowledge that the quality of pre-processing and mesh registration significantly impacts the obtained results. Further investigation and refinement in these areas are crucial for achieving a more accurate and robust performance.

In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image. We propose to exploit the face geometry by modeling the facial landmarks motion as curves encoded as points on a hypersphere. By proposing a conditional version of manifold-valued Wasserstein generative adversarial network (GAN) for motion generation on the hypersphere, we learn the distribution of facial expression dynamics of different classes, from which we synthesize new facial expression motions. The resulting motions can be transformed to sequences of landmarks and then to images sequences by editing the texture information using another conditional Generative Adversarial Network. To the best of our knowledge, this is the first work that explores manifold-valued representations with GAN to address the problem of dynamic facial expression generation. We evaluate our proposed approach both quantitatively and qualitatively on two public datasets; Oulu-CASIA and MUG Facial Expression. Our experimental results demonstrate the effectiveness of our approach in generating realistic videos with continuous motion, realistic appearance and identity preservation. We also show the efficiency of our framework for dynamic facial expressions generation, dynamic facial expression transfer and data augmentation for training improved emotion recognition models.

In this article, we propose a new approach for facial expression recognition (FER) using deep covariance descriptors. The solution is based on the idea of encoding local and global deep convolutional neural network (DCNN) features extracted from still images, in compact local and global covariance descriptors. The space geometry of the covariance matrices is that of symmetric positive definite (SPD) matrices. By conducting the classification of static facial expressions using a support vector machine (SVM) with a valid Gaussian kernel on the SPD manifold, we show that deep covariance descriptors are more effective than the standard classification with fully connected layers and softmax. Besides, we propose a completely new and original solution to model the temporal dynamic of facial expressions as deep trajectories on the SPD manifold. As an extension of the classification pipeline of covariance descriptors, we apply SVM with valid positive definite kernels derived from global alignment for deep covariance trajectories classification. By performing extensive experiments on the Oulu-CASIA, CK+, static facial expression in the wild (SFEW), and acted facial expressions in the wild (AFEW) data sets, we show that both the proposed static and dynamic approaches achieve the state-of-the-art performance for FER outperforming many recent approaches.

Recently, underwater video analysis are more used by marine ecologists to study fish populations as this technique is non-destructively, generates huge amount of visual data and does not perturb underwater environment. Automated methods for processing the recorded data are required because visual processing can be time consuming, subjective and costly. However, the underwater environment poses great challenges due to changes in luminosity, complex backgrounds and free movement of fish. In this paper, we present a convolutional neural network that was trained with transfer learning framework for fish species recognition. First, we use the original AlexNet model to extract fish features from images on the available underwater dataset. Then, to improve the performance, we fine-tune the model on the dataset. Finally, we re-extract features after that AlexNet has been fine-tuned. We use a linear SVM classifier for species classification. The proposed approach reach an accuracy of more than 99% that demonstrates its effectiveness.

There is a significantly increasing demand for monitoring systems for elderly people in the health‐care sector. As the aging population increases, patient privacy violations and the cost of elderly assistance have driven the research community toward computer vision and image processing to design and deploy new systems for monitoring the elderly in the authors’ society and turning their living houses into smart environments. By exploiting recent advances and the low cost of three‐dimensional (3D) depth sensors such as Microsoft Kinect, the authors propose a new skeleton‐based approach to describe the spatio‐temporal aspects of a human activity sequence, using the Minkowski and cosine distances between the 3D joints. We trained and validated their approach on the Microsoft MSR 3D Action and MSR Daily Activity 3D datasets using the Extremely Randomised Trees algorithm. The results are very promising, demonstrating that the trained model can be used to build a monitoring system for the elderly using open‐source libraries and a low‐cost depth sensor.

With the success of emerging RGB-D cameras such as the Kinect sensor, combining the shape (depth) and texture information to improve the quality of recognition became a trend among computer vision researchers. In this work, we address the problem of face classification in the context of RGB images and depth data. Inspired by the psychological results for human face perception, this article focuses on (i) finding out which facial parts are most effective at making the difference for some social aspects of face perception (gender, ethnicity, and emotional state), (ii) determining the optimal decision by combining the decision rendered by the individual parts, and (iii) extracting the promising features from RGB-D faces to exploit all the potential that this data provide. Experimental results on EurecomKinect Face and CurtinFaces databases show that the proposed approach improves the recognition quality in many use cases.

In this paper, we present a new approach for human action recognition using [Formula: see text] skeleton joints recovered from RGB-D cameras. We propose a descriptor based on differences of skeleton joints. This descriptor combines two characteristics including static posture and overall dynamics that encode spatial and temporal aspects. Then, we apply the mean function on these characteristics in order to form the feature vector, used as an input to Random Forest classifier for action classification. The experimental results on both datasets: MSR Action 3D dataset and MSR Daily Activity 3D dataset demonstrate that our approach is efficient and gives promising results compared to state-of-the-art approaches.

Automatic gender recognition, from face images, plays an important role in various biometric applications. This task has attracted the interest of not only computer vision researchers, but also of many psychologists. Inspired by the psychological results for human gender perception. There are two main purposes for this work. First; it aims at finding out which facial parts are most effective at making the difference between men and women. Second; it tries to combine the decisions of these parts using a voting system to improve the recognition quality. Recently, with the appearance of depth sensing technology; especially the low cost devices such as the Microsoft kinect; high quality images containing color and depth information can easily be acquired. This gives us the opportunity to combine depth information with standard vision systems in order to offer a better recognition quality. In this paper, we propose an approach for classifying gender using RGB-D data based on the separation of facial parts. The experimental results show that the proposed approach improves the recognition accuracy for gender classification.

A key features of the second generation for video broadcasting (DVB-S2) is the adoption of Adaptive Coding and Modulation (ACM) technology and Generic Stream Encapsulation (GSE) standards. In order to increase the system performance up to the Shannon limit a suitable resource management (RRM) exploiting this key features is a needed. Packet scheduling mechanisms particularly play a fundamental role to guarantee a better RRM, because they are responsible for choosing, with a fine time how to distribute the satellite resources among different terrestrial stations, taking into account channel condition and the quality-of-service requirements. This goal should be accomplish by providing, at the same time, an optimal trade-off between spectral efficiency, given the limited resources on satellite systems, while granting the requirements for quality-of-service. In this context, this paper provides an overview on the key issues that arise with the use of ACM technology and GSE encapsulation in the design of a scheduler to allocate satellite resources. Moreover, a survey on the most recent scheduling techniques is reported, including a comparison between different approaches presented in literature.

We utilize ideas from two growing but disparate ideas in computer vision-shape analysis using tools from differential geometry and feature selection using machine learning-to select and highlight salient geometrical facial features that contribute most in 3-D face recognition and gender classification. First, a large set of geometries curve features are extracted using level sets (circular curves) and streamlines (radial curves) of the Euclidean distance functions of the facial surface; together they approximate facial surfaces with arbitrarily high accuracy. Then, we use the well-known Adaboost algorithm for feature selection from this large set and derive a composite classifier that achieves high performance with a minimal set of features. This greatly reduced set, consisting of some level curves on the nose and some radial curves in the forehead and cheeks regions, provides a very compact signature of a 3-D face and a fast classification algorithm for face recognition and gender selection. It is also efficient in terms of data storage and transmission costs. Experimental results, carried out using the FRGCv2 dataset, yield a rank-1 face recognition rate of 98% and a gender classification rate of 86% rate.

We propose a pattern theoretic approach for studying variability in shapes of facial surfaces. Our idea is to impose a specific, yet natural, coordinate system, called a curvilinear coordinate system, on facial surfaces. In this system, one coordinate xi1measures the distance of a point from the tip of the nose and its level curves are called the facial curves. The other coordinate xi2measures distances along these curves; level curves of this coordinate are orthogonal to the facial curves. To compare two facial surfaces we use elastic deformations that use stretching, shrinking, and bending to optimally register points across two surfaces. We will demonstrate this idea on Florida State University (FSU) 3D face database.