- Advanced Steganography and Watermarking Techniques
- Video Coding and Compression Technologies
- Digital Media Forensic Detection
- Chaos-based Image/Signal Encryption
- Image and Video Quality Assessment
- Neural Networks and Applications
- Nonlinear Dynamics and Pattern Formation
- Advanced Image Fusion Techniques
- Advanced Data Compression Techniques
- Cooperative Communication and Network Coding
- EEG and Brain-Computer Interfaces
- Visual Attention and Saliency Detection
- Fault Detection and Control Systems
- Advanced MIMO Systems Optimization
- ECG Monitoring and Analysis
- Blind Source Separation Techniques
- Optical Imaging and Spectroscopy Techniques
- Cardiac electrophysiology and arrhythmias
- Metaheuristic Optimization Algorithms Research
- Photoacoustic and Ultrasonic Imaging
- Network Traffic and Congestion Control
- Neural dynamics and brain function
- Robotic Path Planning Algorithms
- stochastic dynamics and bifurcation
- Chaos control and synchronization
Ferdowsi University of Mashhad
2011-2022
University of Wollongong
2002
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses feedback structure similar to Hopfield-type networks and competitive training algorithm Kohonen-type self-organizing maps (K-SOMs). Consequently, composed of constructive part, which grows tour an optimizer part optimize it. algorithm, initial created first...
Abstract Despite all its irrefutable benefits, the development of steganography methods has sparked ever-increasing concerns over abuse in recent decades. To prevent inimical usage steganography, steganalysis approaches have been introduced. Since motion vector manipulation leads to random and indirect changes statistics videos, MV-based video center attention years. In this paper, we propose a 54-dimentional feature set exploiting spatio-temporal features vectors blindly detect stego...
In this paper a novel approach for cardiac arrhythmias detection is proposed. The proposed method based on using independent component analysis (ICA) and wavelet transform to extract important features. Using the extracted features different machine learning classification schemas, MLP RBF neural networks K-nearest neighbor, are used classify 274 instance signals from MIT-BIH database. Simulations show that multilayer with Levenberg-Marquardt (LM) back propagation algorithm provide optimal...
Spread spectrum audio watermarking (SSW) is one of the most secure techniques watermarking. SSW hides information by spreading their which called watermark and adding to a host signal as watermarked signal. Spreading done pseudo-noise (PN) sequence. In conventional approaches, receiver must know PN sequence used at transmitter location in for detecting hidden information. It contributed high feature this method since any unauthorized user who doesn't access couldn't detect paper novel...
Objective video quality assessment plays an important role in a variety of processing applications such as compression, transmission, visualization, and display. This paper proposes no-reference model based on visual memory understanding. Inspired by the findings neuroscience researchers, who argue there is large overlap between active human brain area when performing saliency detection tasks, maps are employed here to assist assessment. To this end, we first generate using CLBP (Complete...
Abstract Steganography is the art and science of data hiding. This article proposes an adaptive steganographic algorithm that embeds secret in a compressed video stream using temporal spatial features signal human visual system characteristics. Qualified‐DCT coefficients I‐VOP motion vectors P‐VOP B‐VOP are used for video, respectively. Embedded‐data extracted without original there no need full decompression. Experimental results demonstrate proposed has high imperceptibility capacity....
In this paper, phase synchronization and the frequency of two synchronized van der Pol oscillators with delay coupling are studied. The dynamics such a system obtained using describing function method, necessary conditions for also achieved. Finding vicinity is major advantage method over other traditional methods. equations based on justify phenomenon coupled either higher, between, or lower than highest, in lowest natural aggregate oscillators. Several numerical examples simulate different...
Many variants of fuzzy c-means (FCM) clustering method are applied to crisp numbers but only a few them extended non-crisp numbers, mainly due the fact that latter needs complicated equations and exhausting calculations. Vector form
This paper proposes an exact and robust genetic algorithm-based method for the calibration of soccer camera. According to FIFA official field layout we defined a model court. Camera is done through finding homography transform between input frame which followed with DLT decomposition. The intersection lines in form feature points by means algorithm, found correspondence those points. Our algorithm was applied couple video frames achieved results demonstrate its robustness, accuracy high performance.
In this paper a new method based on artificial neural networks (ANN), is introduced for identifying pathogenic antibodies in Systemic Lupus Erythmatosus (SLE). dsDNA binding have been implicated the pathogenesis of autoimmune disease. order to identify these antibodies, protein sequences 42 and 608 non-dsDNA were extracted from Kabat database encoded using physicochemical property their amino acids namely Hydrophilicity. Encoded used as training patterns general regression network (GRNN)....
Spread spectrum watermarking (SSW) is one of the most widespread methods. In this paper, characterization SSW from information theoretic point view performed. Previous works on channel capacity analysis systems are reviewed. Since method designed so that host signal unknown to embedding encoder, Costa's results for not directly applicable. and detection modeled as a transmits in presence noise model derived reliable transmission rate hidden obtained. addition, case additive watermark...
Summary Pilot contamination is a major limitation in estimating the uplink channel state massive MIMO systems using time division duplex communication method. This has huge impediment to harnessing main advantages of such as spectral and energy efficiencies. In this article, new low‐complexity subspace‐based method proposed for eliminating pilot estimation, which exploits virtual modeling combined with problem formulation technique. On contrary most existing approaches availability...
In this paper, a smart pilot sequence assignment method is proposed to minimize inter-cell interference generated in massive multi-input multi-output (MIMO) system due contamination uplink TDD (Time Division Duplex) mode. The employs zero-one integer linear programming as the algorithm. amount of intercell imposed on target cell users considered assigning cost. introduced cost composed steering vectors desired cell, and sum channel correlation matrices adjacent cells. By exploiting virtual...