An intelligent audio watermarking based on KNN learning algorithm

Latifpour, Hadi; Mosleh, Mohammad; Kheyrandish, Mohammad

doi:10.1007/s10772-015-9318-0

Cited by 9 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KNN works as the density evaluator to distribute the training data. Based on the extracted features, which are also considered as training patterns, the data can be classified by applying KNN [ 21 ]. By Euclidean distance formula, this distance can be determined; the formula of Euclidean distance is shown below in Eq.…”

Section: Methodsmentioning

confidence: 99%

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG)

Mohamed

Uçan

Bayat

et al. 2020

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

An electroencephalogram (EEG) is a significant source of diagnosing brain issues. It is also a mediator between the external world and the brain, especially in the case of any mental illness; however, it has been widely used to monitor the dynamics of the brain in healthy subjects. This paper discusses the resting state of the brain with eyes open (EO) and eyes closed (EC) by using sixteen channels by the use of conventional frequency bands and entropy of the EEG signal. The Fast Fourier Transform (FFT) and sample entropy (SE) of each sensor are computed as methods of feature extraction. Six classifiers, including logistic regression (LR), K-Nearest Neighbors (KNN), linear discriminant (LD), decision tree (DT), support vector machine (SVM), and Gaussian Naive Bayes (GNB) are used to discriminate the resting states of the brain based on the extracted features. EEG data were epoched with one-second-length windows, and they were used to compute the features to classify EO and EC conditions. Results showed that the LR and SVM classifiers had the highest average classification accuracy (97%). Accuracies of LD, KNN, and DT were 95%, 93%, and 92%, respectively. GNB gained the least accuracy (86%) when conventional frequency bands were used. On the other hand, when SE was used, the average accuracies of SVM, LD, LR, GNB, KNN, and DT algorithms were 92% 90%, 89%, 89%, 86%, and 86%, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG)

Mohamed

Uçan

Bayat

et al. 2020

Applied Bionics and Biomechanics

View full text Add to dashboard Cite

show abstract

“…We will use this sequence later in the extraction phase to train the machine learning classifiers. This sequence is represented with T. In references like [2,12] who have used a sequence to train the classifier, this sequence is generated as pseudo-random and without a regular basis, and the whole training sequence is available to the receiver (at the extraction stage) which makes the proposed system of these references semi-blind.…”

Section: Watermark Embeddingmentioning

confidence: 99%

“…Because watermark detection in audio files is easier than image files, therefore, audio watermarking is more challenging than other areas of watermarking. Since it has been proven that the human hearing system has more sensitivity than the human vision system [2], (several valid tests have been carried out on the auditory nerve [3]), therefore protection of imperceptibility in audio watermarking is more difficult than image watermarking (like references [4,5]). Because of the high capability of audio in watermarking data, many researchers have focused on this topic today.…”

Section: Introductionmentioning

confidence: 99%

“…An intelligent KNN learning machine is trained to capture the correlation between modified frequency coefficients, in wavelet domain, and the watermark sequence. The detection method in this system is semi-blind and has problems for implementation in industrial applications [2]. Jeyhoon et al have embedded watermark by modifying the mean DCT coefficients.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel audio watermarking scheme using ensemble-based watermark detector and discrete wavelet transform

Pourhashemi

Mosleh

Erfani

2020

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Most existing extraction techniques in audio watermarking use conventional techniques in which some sets of special rules based on reverse embedding rules are used for watermark extraction and have many weaknesses, like very low robustness to destructive attacks. To overcome this problem, the use of machine learning-based methods has increased in recent years in this field. The disadvantage of these methods is the high reliance on a unique classifier and lack of proper efficiency when achieving high capacity, which is a major challenge in audio watermarking. The main purpose of this paper is to present a method that covers the weak points of conventional methods and simple intelligent methods and improves system performance using a synergistic combination of discrete wavelet transform (DWT) and ensemble-intelligent extraction approach by proposed combination of trained machine learning classifiers. For the embedding operation in the proposed method, the DWT and the difference in energy levels obtained through DWT coefficients are used. In the extraction section, three methods are used in parallel: (a) the trained support vector machine (SVM) classifier with RBF kernel, (b) trained SVM classifier with quadratic kernel and (c) the trained K-nearest neighbor classifier; finally, the majority function is used to vote and make a final decision to create an intelligent-based watermark detector. A training set is required to train the classifiers, whose bit sequence is generated by a proposed 5-bit linear-feedback shift register. The results of various experiments indicate that this ensemble method has achieved the appropriate imperceptibility and high capacity, along with higher robustness compared to conventional techniques and individual learning classifiers.

show abstract

“…Two standard methods, namely encryption and watermarking, are currently used to achieve this aim (Latifpour et al 2015). In encryption methods, an encryption algorithm is used to encode information, and a receiver at the opposite site recovers the information with a known decoding key.…”

Section: Introductionmentioning

confidence: 99%

Ownership protection of outsourced biomedical time series data based on optimal watermarking scheme in data mining

Pham

Tran

2017

AJIS

View full text Add to dashboard Cite

In the biomedical and healthcare fields, the ownership protection of the outsourced data is becoming a challenging issue in sharing the data between data owners and data mining experts to extract hidden knowledge and patterns. Watermarking has been proved as a rightprotection mechanism that provides detectable evidence for the legal ownership of a shared dataset, without compromising its usability under a wide range of data mining for digital data in different formats such as audio, video, image, relational database, text and software. Time series biomedical data such as Electroencephalography (EEG) or Electrocardiography (ECG) is valuable and costly in healthcare, which need to have owner protection when sharing or transmission in data mining application. However, this issue related to kind of data has only been investigated in little previous research as its characteristics and requirements. This paper proposes an optimized watermarking scheme to protect ownership for biomedical and healthcare systems in data mining. To achieve the highest possible robustness without losing watermark transparency, Particle Swarm Optimization (PSO) technique is used to optimize quantization steps to find a suitable one. Experimental results on EEG data show that the proposed scheme provides good imperceptibility and more robust against various signal processing techniques and common attacks such as noise addition, low-pass filtering, and resampling.

show abstract

An intelligent audio watermarking based on KNN learning algorithm

Cited by 9 publications

References 17 publications

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG)

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG)

A novel audio watermarking scheme using ensemble-based watermark detector and discrete wavelet transform

Ownership protection of outsourced biomedical time series data based on optimal watermarking scheme in data mining

Contact Info

Product

Resources

About