Search

This paper presents an image Steganography algorithm that can work for cover images of multiple formats. Having a single algorithm for multiple image types provides several advantages. For example, we can apply uniform security policies across all image formats, we can adaptively select the most suitable cover image based on data length, network bandwidth and allowable distortions, etc. We present our algorithm based on the abstract concept of image components that can be adapted for JPEG, Bitmap, TIFF and PNG cover images. To the best of our knowledge, the proposed algorithm is the first Steganography algorithm that can work for multiple cover image formats. In addition, we have utilized concepts like capacity pre-estimation, adaptive partition schemes and data spreading to embed secret data with enhanced security. The proposed method is tested for robustness against Steganalysis with favorable results. Moreover, comparative results for the proposed algorithm are very promising for three different cover image formats.

Problems of designing circuits including being sensitive to parasitic elements, inaccurate design equations, complicated manual calculations, requiring a large number of trials and errors and lack of accurate passive integrated element model have motivated engineers to look for computer-aided design (CAD) methods. In this paper, a CAD tool is presented through linking Hspice and grasshopper optimization algorithm aiming to design a double-tail comparator optimally. This tool employs accurate model of transistors and considers all parasitic elements, to obtain results which are close to reality. The proposed tool minimizes multiple objectives simultaneously and presents a set of optimal solutions as a Pareto front. The designer can select any configuration and extract circuit parameters considering the specific application and understanding the relationship between objective functions. Finally, the designer evaluates the final solutions by verifying the design at PVT corners.

Speaker recognition is one of the most common and user-friendly methods for biological signals based people identification. Nowadays, Speaker verification based on factor analysis and i-vector space has a great impact on the performance improvement of these systems. In this paper, a method is proposed for weighting the model and test vectors, which utilizes the statistical characteristics of target training vectors. The effect of the use of weighted vectors on the accuracy of scoring and the performance of the entire speaker verification system was evaluated for Mel-frequency cepstral coefficients (MFCC) and power-normalized cepstral coefficients (PNCC) feature vectors, and two scoring methods, i.e., the cosine distance and probabilistic linear discriminant analysis (PLDA). TIMIT database has been used in the evaluation of the system. The test results indicate that the use of proposed weighted vectors reduces the error rate of the speaker verification system significantly.

The efficiency of heuristic optimization methods has led researchers to considerably use these methods to solve complex engineering problems. Inclined planes system optimization (IPO) is a relatively new heuristic algorithm that is inspired by the dynamic movement of objects on inclined planes without friction. This paper presents a simplified and effective version of IPO (called SIPO) with the aim of simplifying the main IPO equations, creating a powerful trade-off between the concepts of exploitation and exploration, and modifying the complexity of their structural parameters. The performance of the proposed algorithm is measured on 10 benchmark functions. The results clearly demonstrate the improved performance and superiority of SIPO compared to the standard version of the IPO and its improved versions.

Low-Noise Amplifier (LNA) is the first critical component and an important part of the analog integrated systems and wireless communication technology. LNA plays a key role in the design of Radio Frequency (RF) circuits. High voltage gain, low power consumption, high bandwidth and low Noise Figure (NF) are among the most prominent characteristics of LNAs. In this paper, in order to establish an appropriate tradeoff between circuit contradictory objectives and overcoming the design problem of an efficient LNA, the approach is focused on utilizing metaheuristic optimization methods for elements intelligent sizing and circuit automatic design. For this purpose, the Computer-Aided Design (CAD) tool based on the new and powerful version of Multi-Objective Gray Wolf Optimization (MOGWO) has been used. Implementation of algorithms in Matlab and circuit simulations in Hspice has done. Simulation results, in contrast to other research, not only meet the design specifications, but also provide a variety of solutions under the "Pareto-optimality", which allows designers to have more design options. Also, the evaluations indicate the close competition between the proposed method and other commonly used methods.

So far, many methods have been proposed for speaker verification which provide good results, but their performances reduce in actual noisy environments. A common approach to partially alleviate this problem is the fusion of several methods. In this paper, four systems based on different speech features, i.e., MFCC, IMFCC, LFCC, and PNCC were combined in score-level to improve verification accuracy under clean and noisy speech conditions. The features pairwise and foursome fusion in a speaker verification system based on speaker modeling through the Gaussian mixture model (GMM) were evaluated. TIMIT and NOISEX92 databases were used to implement as the speech and noise datasets, respectively. The experimental results show that the score-level fusion of different feature vectors enhances the accuracy of speaker verification system and this reduces the equal error rates is in some cases up to 44%.

This paper presents a comparative study and evaluation of the performances of four speech feature vectors, i.e., MFCC, IMFCC, LFCC, and PNCC in a speaker verification system based on speaker modeling through the Gaussian mixture model (GMM) under clean and noisy speech conditions. The TIMIT and NOISEX92 dataset were used in implementing the tests for speech signal and noise, respectively. The evaluation results show that IMFCC and PNCC provide superior performance in the presence of noise. In order to enhance the performance of the system under noisy conditions, the application of spectral subtraction algorithm as a pre-processing stage was investigated. It only improved the performance for the speech signal contaminated with white noise.

Proper recognition of microscopic sperm cells in video images is an important step in diagnosis and treatment of male infertility. The small sizes of the sperm cells make their segmentation and detection an important stage in the microscopic images analysis. Histogram-based thresholding schemes are one of the common approaches for this purpose. This paper proposes a non-linear amplitude compression transform method applied as a pre-processing stage for histogram-based thresholding algorithms. The results of conducted experiments verify the higher performance of the proposed scheme when used with Kittler method compared to its utilization with the other competitive algorithms in most cases for this application.

This paper presents a novel video descriptor based on substantial derivative, an important concept in fluid mechanics, that captures the rate of change of a fluid property as it travels through a velocity field. Unlike standard approaches that only use temporal motion information, our descriptor exploits the spatio-temporal characteristic of substantial derivative. In particular, the spatial and temporal motion patterns are captured by respectively the convective and local accelerations. After estimating the convective and local field from the optic flow, we followed the standard bag-of-word procedure for each motion pattern separately, and we concatenated the two resulting histograms to form the final descriptor. We extensively evaluated the effectiveness of the proposed method on five benchmarks, including three standard datasets (Violence in Movies, Violence In Crowd, and BEHAVE), and two new video-survelliance sequences downloaded from Youtube. Our experiments show how the proposed approach sets the new state-of-the-art on all benchmarks and how the structural information captured by convective acceleration is essential to detect violent episodes in crowded scenarios.

Detecting abnormal events in video sequences is a challenging task that has been broadly investigated over the last decade. The main challenges come from the lack of a clear definition of abnormality and from the scarcity, often absence, of abnormal training samples. To address these two shortages, the computer vision community made use of generative models to learn normal behavioral patterns in videos. Then, for each test observation, a (crowd) commotion measure is computed quantifying the deviation from the normal model. In this paper, we evaluated two different families of generative models, namely topic models, representing the standard choice, and the most recent Counting Grids which have never been considered for this task. Moreover, we also extended the 2D Counting Grid, introduced for the analysis of images, to three dimensions, making the model able to capture the spatial-temporal relationships of the videos. In the experimental section, we compared all the approaches on five challenging sequences showing the superiority of the 3-D counting grid.

In intensity modulated radiation therapy (IMRT) a treatment plan is a high dimensionality optimization problem with the goal to give the prescribed radiation dose to the Planning Target Volume (PTV) while sparing critical organs. A clinically acceptable plan is usually generated by a numerical optimization process in pursuit of attaining the above mentioned goal. Incorporation of dose volume constraints (DVCs) for the OARs introduce an additional degree of impediment to the optimization task. Heuristic algorithms have been ascertained in the past as a powerful tool for various problems in radiation therapy, such as beam angle optimization (BAO) and IMRT treatment planning. Simulated Annealing (SA) algorithm has the capability to find global minima for bound-constrained optimization problems. However, its performance depends on the penalty method which is utilized for the constraints. In the current study we investigate the performance of three penalty methods for IMRT treatment planning for five prostate cases with dose volume constraints. In addition, sensitivity analysis was performed in order to study the effect of the penalty variables on the treatment plan. Finally the merits and demerits of each method have been discussed.

This paper presents a novel video descriptor, referred to as Histogram of Oriented Track lets, for recognizing abnormal situation in crowded scenes. Unlike standard approaches that use optical flow, which estimates motion vectors only from two successive frames, we built our descriptor over long-range motion trajectories which is called track lets in the literature. Following the standard procedure, we divided video sequences in spatio-temporal cuboids within which we collected statistics on the track lets passing through them. In particular, we quantized orientation and magnitude in a 2-dimensional histogram which encodes the motion patterns expected in each cuboid. We classify frames as normal and abnormal by using Latent Dirichlet Allocation and Support Vector Machines. We evaluated the effectiveness of the proposed descriptors on three datasets: UCSD, Violence in Crowds and UMN. The experiments demonstrated (i) very promising results in abnormality detection, (ii) setting new state-of-the-art on two of them, and (iii) outperforming former descriptors based on the optical flow, dense trajectories and the social force model.

The determination of sensor node's position is one of the important issues in sensor networks. Several methods have been presented in order to determine the position of nodes in these networks. Among them, the "Data Fusion" method, due to the combinational utilization of TDOA and RSS has been able to calculate the distance between nodes more accurately. In the method presented in this paper, by using a series of rules, clustering and Prioritizing in choosing reference nodes the precision of localization of "Data Fusion" Method has been increased, particularly in those locations where the density of reference nodes is little in the network or those places in which the network has holes. Meanwhile, we were able to avoid Error dissemination in network, by applying clustering. The simulation results show that, in a similar environment, the suggested method is more accurate comparing to the existing localization methods. It also has appropriate reliability as well.

Gaussian selection is a technique applied in the GMM-UBM framework to accelerate score calculation. We have recently introduced a novel Gaussian selection method known as sorted GMM (SGMM). SGMM uses scalar-indexing of the universal background model mean vectors to achieve fast search of the top-scoring Gaussians. In the present work we extend this method by using 2-dimensional indexing, which leads to simultaneous frame and Gaussian selection. Our results on the NIST 2002 speaker recognition evaluation corpus indicate that both the 1- and 2- dimensional SGMMs outperform frame decimation and temporal tracking of top-scoring Gaussians by a wide margin (in terms of Gaussian computations relative to GMM-UBM as baseline).

In an Ad-hoc network, mobile nodes disconnected intermittently. One of the biggest challenges in such network is design of routing protocols that tolerate the nodes disconnection. In this paper, we present a novel schema to perform fault tolerant location management named FTLM. With location management scheme, each source node in the network trusts a small subset of nodes, namely its location servers, and updates them with its new geographic location. Fault tolerance in our approach achieved by redundancy in number of location servers that store node's positions. Same the Octopus[1] we employ synchronized aggregation technique to decreasing location management overhead. In this technique the location of many nodes updated at many other nodes with only a single packet. Simulation results show that FTLM is more scalable than Octopus and some other location management methods, moreover it is highly fault tolerant in failure prone environments.

Partial discharge (PD) detection and measurement system is one of the important equipment in high power systems. It is possible to measure partial discharge of different components such as capacitors, transformers, insulators, cables, electrical machines an etc. with PD-meter system. In this article, design and implementation principles of PD system are presented. High frequency pulses of PD are filtered out by a quadripole and then sent to the PD-meter via the measurement cable in this system. Partial discharge process and detection computer system consists of an A/D card, a software code in Visual C++ for PD signal processing, an external calibrator and an external synchronization system. Rectifying and filtering of PD signal and also the display with capabilities of creating window for a more convenient measurement are included in the software code. At the end, measurement and analysis results of PD which are obtained by using the implemented system for the new resonance generator are presented.

In this paper, we propose a hierarchical mixture clustering method and investigate its application for complexity reduction of a GMM based speaker identification system. We show that by using GMM-HMC one can cluster speakers more accurately than that of a sorted GMM with the same acceleration rate. The system was tested on a universal background model-Gaussian mixture model with KL-divergence as the distance measure. While the proposed systempsilas performance is slightly inferior to the baseline system, its comparatively smaller computational load provides the potential to develop systems with higher performance.

One of the biggest challenges in MANETs is the design of scalable routing protocols. With the development and application of position devices, location-based routing has received growing attention. An important component of these protocols is the management of the location information at network nodes, this work is done by location services. In this paper, we present one such scheme called aggregated location service (ALS) which scales well in large mobile ad-hoc networks. Simulation results show that under a specific environment the overhead cost of ALS is asymptotically lower than common methods that had been proposed for MANETs, while its reliability is reasonable.

In this paper we propose a new segmentation algorithm called delta MFCC based speech segmentation (DMFCC-SS), with application to speaker recognition systems. We show that DMFCC-SS can separate the regions of speech that result from similar likelihood scores using models such as a Gaussian mixture model (GMM), and can therefore be used to identify the regions of speech between two transitional states in a speech signal. By combining this segmentation algorithm with the discriminative power of transient frames in speaker recognition, we can investigate the tradeoff in speed-up rates that result from DMFCC-SS, with speaker verification equal error rates that result from representatives of each segment. We use a universal background model Gaussian mixture model (UBM-GMM) as a baseline system. The proposed speed-up algorithm, working in the pre-processing stage, performs well while having no computational load compared to the main GMM system. Experimental results show the superior performance of this pre-processing method in comparison with other algorithms working in the pre-processing stage of a UBM-GMM system.

In this paper a new inter-frame fast scoring scheme is proposed for Gaussian mixture model universal background model (GMM-UBM) speaker verification systems. It is combined with a recently introduced intra-frame efficient scoring method called the sorted Gaussian mixture model (SGMM) classifier which itself uses a sorted UBM known as the sorted background model (SBM). To enhance the performance of the system a GMM identifier is applied as a post-processing block. Experimental results show that the performance of this combined method compares favorably with the baseline GMM-UBM system, while the computational load of the proposed system is greatly less than that of the baseline system.

In this work we study an enhanced sorting function for the recently developed sorted GMM, which is computationally efficient method for implementing the Gaussian mixture model universal background model (GMM-UBM) scheme. The sorted GMM employ partial search and thus has lower computational complexity and relaxed memory requirements when compared to the well-known tree-structured GMM of the same model order. Experimental evaluation of the sorted GMM and its enhanced version was performed on two databases: (1) clean speech in Farsi recorded from TV broadcasts, and (2) telephone quality speech in english (NIST 2002 SRE one-speaker detection data). The enhanced sorting scheme outperformed the original one, primarily for cases where very high acceleration rates were targeted, in scenarios where there was match between training and testing conditions. However, in mismatched train-test conditions the original sorted GMM performed better. Finally, the sorted GMM proved 14 times faster than the baseline system at the cost of only 0.43 increase in equal error rate.

In this paper the application of Gaussian mixture model (GMM) classifier is investigated as an efficient post-processing method to enhance the performance of GMM-based speaker identification systems; such as Gaussian mixture model universal background model (GMM-UBM) scheme. The proposed classifier presents outstanding performance while its computational complexity is almost negligible compared to the main GMM system. Moreover, the effects of the model order of GMM classifier is studied using experimental method. Experimental results verify the superior performance of applying GMM post-processor while the proper selection of model order for this GMM has a great impact on the overall performance of the system.

In this paper a Gaussian mixture model (GMM) classifier, called GMM identifier, is proposed as an efficient post-processing method to enhance the performance of a CMM-based speaker verification system; such as Gaussian mixture model universal background model (GMM-UBM) and structural Gaussian mixture models with structural background model (SGMM-SBM) speaker verification schemes. The proposed classifier shows good performance while its computational load is almost negligible compared to the main GMM system. Experimental results show the superior performance of this post-processing method in comparison with a neural-network post-processor for such applications.

Line spectral frequencies (LSFs) are the most popular parameters for spectrum quantization in speech coders using linear prediction. A new method for the quantization of the LSFs is proposed in this paper. This method is a scalar quantization scheme based on a nonlinear two-dimensional prediction in the index domain, and hereafter will be referred to as predictive delta adaptive scalar quantization (PDASQ). It is shown that it can be implemented efficiently with negligible computational overhead and memory requirements compared to the simple scalar quantization method. Although PDASQ needs lower bit rates, its quantization distortion is of the same order as that of the conventional scalar quantization. Satisfactory performance of the new method is verified through experimental tests using computer simulation.

Sorted codebook vector quantization (SCVQ) is shown to be a very efficient vector quantization method. Generalization of SCVQ is suggested and its application to the spectral coding of speech using the quantization of line spectral frequencies (LSF), which are the most popular parameters to represent the linear prediction model for spectrum quantization in speech coders, is described. Computer simulations are conducted to evaluate the performance of the new method. We demonstrate that the new method achieves superior quality and has low implementation costs.

A new vector quantization method, namely sorted codebook vector quantization (SCVQ) is presented in this article. The paper explains the principles of this method, including training and optimization of the associated codebook. It is shown that this quantizer can be implemented efficiently with almost similar computational complexity to tree-searched vector quantization (TSVQ) and the storage cost of that is the same as unstructured VQ (i.e less than TSVQ). Application of SCVQ to quantization of Line Spectral Frequencies (LSFs), which are the most popular parameters for spectrum quantization in speech coders using linear prediction model, is described. Superior performance of the new method is verified through experimental simulations.

In low rate speech coders based on the linear prediction method, the quality of synthesized speech can be improved by enhancement of the short-term spectrum quantization stage. In this study, we propose two new efficient methods for coding the spectral parameters, namely sorted codebook vector quantization (SCVQ) and fine-coarse vector quantization (FCVQ). The principles of these methods are presented along with the methods of training and optimizing the related codebooks. The performance of the new schemes is compared experimentally with other efficient methods, such as tree-searched vector quantization (TSVQ) and multi-stage vector quantization (MSVQ). We demonstrate that the new methods offer significant cost reduction whilst achieving superior quality.