Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In

Portable devices such as smartphones, tablet PCs, and PDAs are a useful combination of hardware and software turned toward the mobile workers. While they present the ability to review documents, communicate via electronic mail,  appointments management, meetings, etc. They usually lack a variety of essential security features. To address the security concerns of sensitive data, many individuals and organizations, knowing the associated threats mitigate them through improving authentication of users, encryption of content, protection from malware, firewalls,  intrusion prevention, etc. However, no standards have been developed yet to determine whether such mobile data management systems adequately provide the fu

Abstract 

For sparse system identification,recent suggested algorithms are  -norm Least Mean Square (  -LMS), Zero-Attracting LMS (ZA-LMS), Reweighted Zero-Attracting LMS (RZA-LMS), and p-norm LMS (p-LMS) algorithms, that have modified the cost function of the conventional LMS algorithm by adding a constraint of coefficients sparsity. And so, the proposed algorithms are named  -ZA-LMS, 

In this study, the performance of the adaptive optics (AO) system was analyzed through a numerical computer simulation implemented in MATLAB. Making a phase screen involved turning computer-generated random numbers into two-dimensional arrays of phase values on a sample point grid with matching statistics. Von Karman turbulence was created depending on the power spectral density. Several simulated point spread functions (PSFs) and modulation transfer functions (MTFs) for different values of the Fried coherent diameter (r_o) were used to show how rough the atmosphere was. To evaluate the effectiveness of the optical system (telescope), the Strehl ratio (S) was computed. The compensation procedure for an AO syst

Researchers are increasingly using multimodal biometrics to strengthen the security of biometric applications. In this study, a strong multimodal human identification model was developed to address the growing problem of spoofing attacks in biometric security systems. Through the use of metaheuristic optimization methods, such as the Genetic Algorithm(GA), Ant Colony Optimization(ACO), and Particle Swarm Optimization (PSO) for feature selection, this unique model incorporates three biometric modalities: face, iris, and fingerprint. Image pre-processing, feature extraction, critical image feature selection, and multibiometric recognition are the four main steps in the workflow of the system. To determine its performance, the model wa

A QR code is a type of barcode that can hold more information than the familiar kind scanned at checkouts around the world. The “QR” stands for “Quick Response”, a reference to the speed at which the large amounts of information they contain can be decoded by scanners. They are being widely used for advertising campaigns, linking to company websites, contest sign-up pages and online menus. In this paper, we propose an efficient module to extract QR code from background and solve problem of rotation in case of inaccurate image taken from mobile camera.

Activity recognition (AR) is a new interesting and challenging research area with many applications (e.g. healthcare, security, and event detection). Basically, activity recognition (e.g. identifying user’s physical activity) is more likely to be considered as a classification problem. In this paper, a combination of 7 classification methods is employed and experimented on accelerometer data collected via smartphones, and compared for best performance. The dataset is collected from 59 individuals who performed 6 different activities (i.e. walk, jog, sit, stand, upstairs, and downstairs). The total number of dataset instances is 5418 with 46 labeled features. The results show that the proposed method of ensemble boost-based classif