The popularity of Unmanned Aerial Vehicles (UAVs) in recent years has accelerated the demand for robust image security to secure communication and authenticate images or videos from usage by unauthorized parties who m...
详细信息
ISBN:
(数字)9798331541064
ISBN:
(纸本)9798331541071
The popularity of Unmanned Aerial Vehicles (UAVs) in recent years has accelerated the demand for robust image security to secure communication and authenticate images or videos from usage by unauthorized parties who may seek access to sensitive information. Having unauthorized and deceptive communication, from interference in signals to data manipulation, will be a challenge. This paper presents a novel approach to integrating GPS positioning with secure image capture and decentralized coordination for UAVs. Using EI-Gamal encryption and Magic Number Fragmentation, GPS coordinates are securely encrypted, and GPS data into captured images through a hybrid Discrete wavelet Transform-Discrete Cosine Transform (DWT-DCT) watermarking technique. A consensus mechanism ensures decentralized and privacy-preserving computation of secure meeting points for UAV s. Moreover, the system maintains high image quality, with superior PSNR and SSIM values, while demonstrating resilience against signalprocessing and geometric attacks. These findings affirm the method's ability to extract encrypted GPS coordinates reliably, enhancing UAV network security.
A powerful area that seeks to minimize the amount of space of signals that are compressible or sparse in a specific base representation that uses compressed recognizing in video streaming applications. A sparse signal...
详细信息
ISBN:
(数字)9798350368949
ISBN:
(纸本)9798350368956
A powerful area that seeks to minimize the amount of space of signals that are compressible or sparse in a specific base representation that uses compressed recognizing in video streaming applications. A sparse signal provides a good approximation of the signal since the representation is sparse and the amplitude of the coefficient’s decays according to the power law. The process of projecting signals into a space with low dimensions results in measurement vectors. A sparse signal may be accurately reconstructed using the measurement vector. Imprecise or noisy data that may nevertheless be compressed and used for approximation purposes. images in the frequency or wavelet domain are suitable for Compressed Sensing because they are inherently compressible. Reconstructed images are of higher quality, and the compression ratio—the ratio of an image's pixel count to its measurement vector—has been reduced, enabling more precise reconstruction. Taylor SFO based CS is a two-stage optimization technique for picture compression and recovery that aims to enhance the quality of models with high correlation and low redundancy. An image that uses self-replication and 3D change to compress itself is first processed in the early phase. In the last step, the CS uses SSIM to recover pictures using an ensemble sparseness estimate and Taylor SFO parameters.
The integration of infrared and visible images has become increasingly relevant in the field of remote sensing technologies and imageprocessingapplications. This technique has proven beneficial in scenarios such as ...
The integration of infrared and visible images has become increasingly relevant in the field of remote sensing technologies and imageprocessingapplications. This technique has proven beneficial in scenarios such as thermal source monitoring and anomaly detection for industrial machines. The fusion of these two images allows for the creation of a compound image that contains important information from both sources, resulting in an enhanced image with rich background details and clear targets. This paper presents a model for image fusion and probabilistic generation of infrared and visible images. The variational Bayesian approximation method is utilized to fuse the information from both images. The proposed method also introduces a hierarchical prior model using wavelet transform and a variational Bayesian inference algorithm to achieve information fusion. The proposed method provides a feasible and effective solution for health monitoring applications of high-speed direct-drive blowers in industrial scenarios.
In real world, data understanding involves finding relationship between dependent and independents events, and usually this data is embedded in the form of images, audio, videos, speech, text and much more and to extr...
详细信息
ISBN:
(数字)9798350309249
ISBN:
(纸本)9798350309256
In real world, data understanding involves finding relationship between dependent and independents events, and usually this data is embedded in the form of images, audio, videos, speech, text and much more and to extract useful and representative information, feature extraction and representation is a front-end step. For machine learning algorithms, feature extraction is a preprocessing technique that helps in finding the relationship between different variables. In biomedical signal analysis such as cerebral emboli signal detection, feature extraction from samples constitutes an important step. In this paper, we performed two step feature extraction procedure. First we extracted Mel Frequency Cepstral Coefficients (MFCC) and biologically inspired Gamma-tone Cepstral Coefficients from Doppler signals. Second we extracted kurtosis and skewness parameters from all the Mel-frequency cepstral coefficients and Gamma-tone Cepstral Coefficients coefficients. To gain the understanding of extracted features from Doppler signals, we trained some machine learning algorithms such as k-nearest neighbors, support vector machines and logistic regression. GTCC based kurtosis and skewness features show better classification between emboli, artifact signals and Doppler speckle signals. We present evaluation results using confusion matrix for classification between emboli signals (ES), Doppler speckle (DS) and artifact signals (AS).
Decomposing an image through Fourier, DCT or wavelet transforms is still a common approach in digital imageprocessing, in number of applications such as denoising. In this context, data-driven dictionaries and in par...
详细信息
ISBN:
(纸本)9781665441155
Decomposing an image through Fourier, DCT or wavelet transforms is still a common approach in digital imageprocessing, in number of applications such as denoising. In this context, data-driven dictionaries and in particular exploiting the redundancy withing patches extracted from one or several images allowed important improvements. This paper proposes an original idea of constructing such an image-dependent basis inspired by the principles of quantum many-body physics. The similarity between two image patches is introduced in the formalism through a term akin to interaction terms in quantum mechanics. The main contribution of the paper is thus to introduce this original way of exploiting quantum many-body ideas in imageprocessing, which opens interesting perspectives in image denoising. The potential of the proposed adaptive decomposition is illustrated through image denoising in presence of additive white Gaussian noise, but the method can be used for other types of noise such as image-dependent noise as well. Finally, the results show that our method achieves comparable or slightly better results than existing approaches.
The rapid evolution of technology and computer networks has brought about a paradigm shift in data transmission within the medical field, facilitating the utilization of wireless networks for seamless communication. H...
The rapid evolution of technology and computer networks has brought about a paradigm shift in data transmission within the medical field, facilitating the utilization of wireless networks for seamless communication. However, this convenience also introduces various challenges, including copyright infringement, data theft, and the imperative need for robust ownership identification during data transmission across open networks. Addressing these concerns, watermarking emerges as a practical solution by discreetly embedding confidential personal information within other data. This paper introduces a watermarking technique designed to enhance the security of medical images, utilizing a fusion of the Dual-Tree Complex wavelet Transform and spread spectrum (DTCWT-SS) methods. The watermark image undergoes a pre-processing stage involving a spread spectrum modulation technique employing a random pseudo-noise code. Subsequently, the watermark series is meticulously embedded into the DTCWT-based host image, resulting in the creation of a watermarked image. At the receiving end, the watermarked image undergoes processing by DTCWT, and the optimal subband is carefully selected to extract the original watermark with high fidelity. The proposed scheme achieves an impressive peak signal-to-noise ratio of over 50 dB for each medical image modality, underscoring the preservation of image quality despite watermarking. Moreover, the watermark retrieval process demonstrates exceptional performance, achieving a normalized correlation of 1 and a bit error rate of 0 under no-attack conditions, ensuring accurate and reliable watermark extraction. Notably, the proposed model exhibits robustness against signalprocessing attacks and noise addition, confirming its efficacy in various scenarios and resilience against potential threats.
In this paper, an intelligent tire algorithm based on back propagation neural network was proposed to identify the type of road peak adhesion coefficient. In the drum test, eight different vehicle conditions were take...
In this paper, an intelligent tire algorithm based on back propagation neural network was proposed to identify the type of road peak adhesion coefficient. In the drum test, eight different vehicle conditions were taken into account for each of three simulated road conditions. Tire pressure of 900 or 1000 kPa, speed of 30 or 40 km/h, and load of 500 or 1000 kg were the parameters for the vehicle conditions. The corresponding tire x-acceleration signal was obtained using the tire acceleration sensor. Then, the original signal data was denoised using wavelet transform. The signal data was grouped by tire rotation period and the anomalous data was eliminated using the isolated forest algorithm. Following that, wavelet transform was used once more to extract the time domain and frequency domain characteristics from each batch of data, producing 45-dimensional feature parameters. Principal components analysis was applied to reduce the dimension of feature parameters to obtain 8-dimensional principal components. Finally, to identify the type of road peak adhesion coefficient, the normalized principal components and vehicle condition parameters (tire pressure, speed, load) were used as input to build a four-layer back propagation neural network, while the adam algorithm was used to optimize the learning rate. 10-fold cross validation was used to examine the model effect. The prediction results show that the model has a high identification accuracy for three types of road, with an average accuracy of 99.53%. The prediction accuracy of the models developed in 10-fold cross-validation fluctuates between ±0.2%. Under different vehicle conditions, the proposed road identification perception algorithm establishes the direct correlation between tire x-axis acceleration and road adhesion coefficient. With its high dependability and real-time capabilities, this algorithm has a wide range of possible applications in the areas of automated driving and intelligent tires.
An overview of the brain-computer interface is given in this publication and the variety of deep learning architectures for the acquisition of brain signals we have discussed the EEG signals that are used in BCI appli...
详细信息
ISBN:
(数字)9798350368949
ISBN:
(纸本)9798350368956
An overview of the brain-computer interface is given in this publication and the variety of deep learning architectures for the acquisition of brain signals we have discussed the EEG signals that are used in BCI applications. Time-frequency localization is frequently poor in EEG signals. As a result, BCI systems frequently have low task detection accuracy and high error rates. It also exhibits extremely quasi qualities and has a lot of trans variances. Additionally, we have discussed noise removal techniques given by different researchers from EEG signals and BCI applications, and the comparison is given further than we have discussed regarding the EEG signal's image retrieval and different deep learning techniques for EEG learning commons. From the analysis of the results of different approaches, it’s been noticed that non-stationary EEG signals are more contributing to BCI applications. Whereas, in pre-processing steps, SWT-ICA, DWT, and CSP algorithms are most efficient for noise removal. For feature extraction sliding window spatial and temporal methods and deep learning methods contributed the most. Finally, for feature learning and classification, transfer learning and fine-tuned model performance were analyzed. It was observed from the analytical review that the fine-tuned transfer learning model outperforms better.
To address the problem of low accuracy and poor stability of bearing diagnostic models under strong background noise, a bearing fault image recognition method is proposed that reduces the randomness of the model by av...
详细信息
ISBN:
(数字)9798350360240
ISBN:
(纸本)9798350384161
To address the problem of low accuracy and poor stability of bearing diagnostic models under strong background noise, a bearing fault image recognition method is proposed that reduces the randomness of the model by avoiding the need for artificial parameterization, which can introduce random factors. This method is based on hyperparameter optimization of the GoogLeNet convolutional neural network model and decision fusion. First of all, two-dimensional wavelet time-frequency variation of the original signal of the bearing vibration to construct an image dataset, one-dimensional classification is into a two-dimensional image problem; Secondly, three lightweight convolutional neural network architectures are selected for the noise immunity test, to get the best noise-resistant network architecture GoogLeNet; Finally, hyper-parameter optimization is performed for the network, comparing the mesh method, the progressive mesh method, and the group optimization algorithm, respectively, and getting The optimal parameters are then analyzed for decision fusion and visualization of the network. To verify the method proposed in this paper, we used the open Case Western Reserve University bearing dataset. The experimental verification demonstrates that the proposed method achieves a correctness rate of 94.33% in decision fusion under noise, with good accuracy and stability.
The use of dental radiography techniques like XRay has increased the diagnosis efficiency, but the images contain impulse noise. Therefore, denoising is a very important factor in any subjective evaluation of the qual...
详细信息
暂无评论