Steganalysis of Quantization Index Modulation Steganography in G.723.1 Codec

Steganalysis is used for preventing the illegal use of steganography to ensure the security of network communication through detecting whether or not secret information is hidden in the carrier. This paper presents an approach to detect the quantization index modulation (QIM) of steganography in G.723.1 based on the analysis of the probability of occurrence of index values before and after steganography and studying the influence of adjacent index values in voice over internet protocol (VoIP). According to the change of index value distribution characteristics, this approach extracts the distribution probability matrix and the transition probability matrix as feature vectors, and uses principal component analysis (PCA) to reduce the dimensionality. Through a large amount of sample training, the support vector machine (SVM) is designed as a classifier to detect the QIM steganography. The speech samples with different embedding rates and different durations were tested to verify their impact on the accuracy of the steganalysis. The experimental results show that the proposed approach improves the accuracy and reliability of the steganalysis.

Download Full-text

UNRAVELING MARKOV PROCESSES IN MOVEMENT PATTERNS OF INDICATOR SPECIES IN RESPONSE TO CHEMICAL STRESSORS

Modern Physics Letters B ◽

10.1142/s0217984911026851 ◽

2011 ◽

Vol 25 (12n13) ◽

pp. 1143-1149 ◽

Cited By ~ 8

Author(s):

TUYEN VAN NGUYEN ◽

YUEDAN LIU ◽

IL-HYO JUNG ◽

TAE-SOO CHON ◽

SANG-HEE LEE

Keyword(s):

Markov Processes ◽

Transition Probability ◽

Movement Patterns ◽

Critical Issue ◽

Transition Probability Matrix ◽

Behavioral Changes ◽

Environmental Stressors ◽

Biological Responses ◽

Low Concentrations ◽

Before And After

Revealing biological responses of organisms in responding to environmental stressors is the critical issue in contemporary ecological sciences. Markov processes in behavioral data were unraveled by utilizing the hidden Markov model (HMM). Individual organisms of daphnia (Daphnia magna) and zebrafish (Danio rerio) were exposed to diazinon at low concentrations. The transition probability matrix (TPM) and the emission probability matrix (EPM) were accordingly estimated by training with the HMM and were verified before and after the treatments with 10-6 tolerance in 103 iterations. Structured property in behavioral changes was accordingly revealed to characterize dynamic processes in movement patterns. Parameters and sequences produced through the HMM training could be a suitable means of monitoring toxic chemicals in environment.

Download Full-text

SCADA Data Analysis Methods for Diagnosis of Electrical Faults to Wind Turbine Generators

Applied Sciences ◽

10.3390/app11083307 ◽

2021 ◽

Vol 11 (8) ◽

pp. 3307

Author(s):

Francesco Castellani ◽

Davide Astolfi ◽

Francesco Natili

Keyword(s):

Fault Diagnosis ◽

Wind Turbine ◽

Wind Turbines ◽

Principal Component ◽

Support Vector ◽

General Context ◽

Test Case ◽

Electric Generator ◽

Before And After ◽

Electrical Faults

The electric generator is estimated to be among the top three contributors to the failure rates and downtime of wind turbines. For this reason, in the general context of increasing interest towards effective wind turbine condition monitoring techniques, fault diagnosis of electric generators is particularly important. The objective of this study is contributing to the techniques for wind turbine generator fault diagnosis through a supervisory control and data acquisition (SCADA) analysis method. The work is organized as a real-world test-case discussion, involving electric damage to the generator of a Vestas V52 wind turbine sited in southern Italy. SCADA data before and after the generator damage have been analyzed for the target wind turbine and for reference healthy wind turbines from the same site. By doing this, it has been possible to formulate a normal behavior model, based on principal component analysis and support vector regression, for the power and for the voltages and currents of the wind turbine. It is shown that the incipience of the fault can be individuated as a change in the behavior of the residuals between model estimates and measurements. This phenomenon was clearly visible approximately two weeks before the fault. Considering the fast evolution of electrical damage, this result is promising as regards the perspectives of exploiting SCADA data for individuating electric damage with an advance that can be useful for applications in wind energy practice.

Download Full-text

Higher Order Statistics Based Blind Steg analysis using Deep Learning

Journal of Ravishankar University (Part-B) ◽

10.52228/jrub.2021-34-1-3 ◽

2021 ◽

Vol 34 (1) ◽

pp. 19-28

Author(s):

S. Bera ◽

K. Thakur ◽

P. Vyas ◽

M. Thakur ◽

A. Shrivastava

Keyword(s):

Transition Probability ◽

Principal Component ◽

Transition Probability Matrix ◽

Higher Order ◽

Gradient Boosting ◽

Detection Accuracy ◽

Stego Image ◽

Markov Transition ◽

Extreme Gradient Boosting ◽

Relationship Of

Universal isteganalysis of grey level JPEG images is addressed by modelling the neighbourhood relationship of the image coefficients using the higher order statistical method developed by two-step Markov Transition Probability Matrix (TPM). The implementation of TPM together with the neighbouring pixel relationship provides a better and comparable detection results. The detection accuracy is evaluated on the stego image database using eXtreme Gradient Boosting (XGBoost) with Principal Component Analysis (PCA) on nsF5 and JUNIWARD hiding techniques. Execution time is also compared for all the classifiers. The images are taken from Green spun library and Google website- eXtreme Gradient Boosting.

Download Full-text

Prediction of Displacement Time Series Based on Support Vector Machines-Markov Chain

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.580-583.436 ◽

2014 ◽

Vol 580-583 ◽

pp. 436-439 ◽

Cited By ~ 2

Author(s):

Fei Xu ◽

Wen Xiong Xu ◽

Ke Wang

Keyword(s):

Time Series ◽

Markov Chain ◽

Support Vector Machines ◽

Transition Probability ◽

Absolute Error ◽

Transition Probability Matrix ◽

Support Vector ◽

State Transition Probability ◽

Vector Machines ◽

Measured Displacement

A new displacement time series predicting model was proposed by combining the Support Vector Machines and the Markov Chain, which was named as Support Vector Machines and Markov Chain (SVM-MC) model. Through studying the measured displacement, SVM optimized by particle swarm optimization (PSO) was used to forecast the trend of macro development in roll. Markov chain was applied to compute State Transition Probability Matrix. By classifying system state and calculating absolute error and relative error between measured value and SVM fitting value, the predicting results are improved. The model was used on predicting displacement time series of a high slope of a permanent lock. The engineering case studies indicated that the model was scientific and reliable, and there was engineering practical value for displacement time series forecasting.

Download Full-text

Adaptive Video Watermarking against Scaling Attacks Based on Quantization Index Modulation

Electronics ◽

10.3390/electronics10141655 ◽

2021 ◽

Vol 10 (14) ◽

pp. 1655

Author(s):

Zhongze Lv ◽

Ying Huang ◽

Hu Guan ◽

Jie Liu ◽

Shuwu Zhang ◽

...

Keyword(s):

Computational Cost ◽

Vital Role ◽

Video Watermarking ◽

Modulation Method ◽

Quantization Index Modulation ◽

Adaptive Video ◽

Before And After ◽

Blind Extraction ◽

Dc Coefficient ◽

Index Modulation

Video watermarking plays a vital role in protecting the video copyright. The quantization-based methods are widely used in the existing watermarking algorithms, owing to their low computational complexity and completely blind extraction. However, most of them work poorly in resisting scaling attacks, by which the quantization value may fall outside the original quantization interval. For addressing this issue, an adaptive quantization index modulation method is proposed. The property that is associated with the ratio of the DC coefficient before and after scaling the video resolution motivates us to select the DC coefficient as the quantization value and set the size of the quantization interval by the video resolution to maintain the synchronization between them before and after scaling. Moreover, a strategy taking advantage of the high decoding reliability of the QRCode is proposed to terminate the extraction in advance, and both the embedding and the extracting process are performed in the spatial domain, which all contribute to further enhance the execution efficiency. The experimental results show that our algorithm outperforms the state-of-the-art method in terms of imperceptibility, robustness, and computational cost.

Download Full-text

Compressive Sensing Audio Watermarking dengan Metode LWT dan QIM

ELKOMIKA Jurnal Teknik Energi Elektrik Teknik Telekomunikasi & Teknik Elektronika ◽

10.26760/elkomika.v6i3.405 ◽

2018 ◽

Vol 6 (3) ◽

pp. 405

Author(s):

IRMA SAFITRI ◽

NUR IBRAHIM ◽

HERLAMBANG YOGASWARA

Keyword(s):

Wavelet Transform ◽

Compressive Sensing ◽

Audio Watermarking ◽

Quantization Index Modulation ◽

Computationally Efficient ◽

Black And White ◽

Additional Information ◽

Audio Files ◽

Index Modulation ◽

Mp3 Compression

ABSTRAKPenelitian ini mengembangkan teknik Compressive Sensing (CS) untuk audio watermarking dengan metode Lifting Wavelet Transform (LWT) dan Quantization Index Modulation (QIM). LWT adalah salah satu teknik mendekomposisi sinyal menjadi 2 sub-band, yaitu sub-band low dan high. QIM adalah suatu metode yang efisien secara komputasi atau perhitungan watermarking dengan menggunakan informasi tambahan. Audio watermarking dilakukan menggunakan file audio dengan format *.wav berdurasi 10 detik dan menggunakan 4 genre musik, yaitu pop, classic, rock, dan metal. Watermark yang disisipkan berupa citra hitam putih dengan format *.bmp yang masing-masing berukuran 32x32 dan 64x64 pixel. Pengujian dilakukan dengan mengukur nilai SNR, ODG, BER, dan PSNR. Audio yang telah disisipkan watermark, diuji ketahanannya dengan diberikan 7 macam serangan berupa LPF, BPF, HPF, MP3 compression, noise, dan echo. Penelitian ini memiliki hasil optimal dengan nilai SNR 85,32 dB, ODG -8,34x10-11, BER 0, dan PSNR ∞.Kata kunci: Audio watermarking, QIM, LWT, Compressive Sensing. ABSTRACTThis research developed Compressive Sensing (CS) technique for audio watermarking using Wavelet Transform (LWT) and Quantization Index Modulation (QIM) methods. LWT is one technique to decompose the signal into 2 sub-bands, namely sub-band low and high. QIM is a computationally efficient method or watermarking calculation using additional information. Audio watermarking was done using audio files with *.wav format duration of 10 seconds and used 4 genres of music, namely pop, classic, rock, and metal. Watermark was inserted in the form of black and white image with *.bmp format each measuring 32x32 and 64x64 pixels. The test was done by measuring the value of SNR, ODG, BER, and PSNR. Audio that had been inserted watermark was tested its durability with given 7 kinds of attacks such as LPF, BPF, HPF, MP3 Compression, Noise, and Echo. This research had optimal result with SNR value of 85.32 dB, ODG value of -8.34x10-11, BER value of 0, and PSNR value of ∞.Keywords: Audio watermarking, QIM, LWT, Compressive Sensing.

Download Full-text

QSAR Study of PARP Inhibitors by GA-MLR, GA-SVM and GA-ANN Approaches

Current Analytical Chemistry ◽

10.2174/1573411016999200518083359 ◽

2020 ◽

Vol 16 (8) ◽

pp. 1088-1105

Author(s):

Nafiseh Vahedi ◽

Majid Mohammadhosseini ◽

Mehdi Nekoei

Keyword(s):

Present Report ◽

Principal Component ◽

Parp Inhibitors ◽

Support Vector ◽

Ann Model ◽

Statistical Parameters ◽

Qsar Study ◽

Data Set ◽

Test Set ◽

Non Linear

Background: The poly(ADP-ribose) polymerases (PARP) is a nuclear enzyme superfamily present in eukaryotes. Methods: In the present report, some efficient linear and non-linear methods including multiple linear regression (MLR), support vector machine (SVM) and artificial neural networks (ANN) were successfully used to develop and establish quantitative structure-activity relationship (QSAR) models capable of predicting pEC50 values of tetrahydropyridopyridazinone derivatives as effective PARP inhibitors. Principal component analysis (PCA) was used to a rational division of the whole data set and selection of the training and test sets. A genetic algorithm (GA) variable selection method was employed to select the optimal subset of descriptors that have the most significant contributions to the overall inhibitory activity from the large pool of calculated descriptors. Results: The accuracy and predictability of the proposed models were further confirmed using crossvalidation, validation through an external test set and Y-randomization (chance correlations) approaches. Moreover, an exhaustive statistical comparison was performed on the outputs of the proposed models. The results revealed that non-linear modeling approaches, including SVM and ANN could provide much more prediction capabilities. Conclusion: Among the constructed models and in terms of root mean square error of predictions (RMSEP), cross-validation coefficients (Q2 LOO and Q2 LGO), as well as R2 and F-statistical value for the training set, the predictive power of the GA-SVM approach was better. However, compared with MLR and SVM, the statistical parameters for the test set were more proper using the GA-ANN model.

Download Full-text

Application of Machine Learning in Animal Disease Analysis and Prediction

Current Bioinformatics ◽

10.2174/1574893615999200728195613 ◽

2020 ◽

Vol 15 ◽

Author(s):

Shuwen Zhang ◽

Qiang Su ◽

Qin Chen

Keyword(s):

Machine Learning ◽

Unsupervised Learning ◽

Supervised Learning ◽

Clustering Algorithm ◽

Principal Component ◽

Support Vector ◽

Animal Disease ◽

Human Beings ◽

Animal Diseases ◽

Disease Analysis

Abstract: Major animal diseases pose a great threat to animal husbandry and human beings. With the deepening of globalization and the abundance of data resources, the prediction and analysis of animal diseases by using big data are becoming more and more important. The focus of machine learning is to make computers learn how to learn from data and use the learned experience to analyze and predict. Firstly, this paper introduces the animal epidemic situation and machine learning. Then it briefly introduces the application of machine learning in animal disease analysis and prediction. Machine learning is mainly divided into supervised learning and unsupervised learning. Supervised learning includes support vector machines, naive bayes, decision trees, random forests, logistic regression, artificial neural networks, deep learning, and AdaBoost. Unsupervised learning has maximum expectation algorithm, principal component analysis hierarchical clustering algorithm and maxent. Through the discussion of this paper, people have a clearer concept of machine learning and understand its application prospect in animal diseases.

Download Full-text