scholarly journals The secure steganography for hiding images via GAN

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Zhangjie Fu ◽  
Fan Wang ◽  
Xu Cheng
Keyword(s):  
Deep Learning ◽  
Color Image ◽  
Visual Quality ◽  
Learning Networks ◽  
Secret Data ◽  
Rapid Improvement ◽  
Proposed Model ◽  
Adversarial Training ◽  
Human Eyes

Abstract Steganography is one of the important methods in the field of information hiding, which is the technique of hiding secret data within an ordinary file or message in order to avoid the detection of steganalysis models and human eyes. In recent years, many scholars have applied various deep learning networks to the field of steganalysis to improve the accuracy of detection. The rapid improvement of the accuracy of steganalysis models has caused a huge threat to the security of steganography. In addition, another important factor that limits the security of steganography is capacity. The larger the capacity, the worse and more unnatural the visual quality of carrier images after embedded. Therefore, this paper proposes a steganography model—HIGAN, which constructs the encoding network composed of residual blocks to hide the color secret image into another color image of the same size to output a lower distortion and higher visual quality steganographic image. Moreover, it utilizes the adversarial training between the encoder-decoder network and the steganalysis model to improve the ability to resist the detection of steganalysis models based on deep learning. The experimental results show that our proposed model is achievable and effective. Compared with the previous steganography model for hiding color images based on deep learning, the steganography model in this article could achieve steganographic images with higher visual quality and stronger security.

scholarly journals Multimedia Quality Integration Using Piecewise Function

2011 ◽  
Vol 1 ◽  
pp. 375-380
Author(s):  
Shu Ai Wan ◽  
Kai Fang Yang ◽  
Hai Yong Zhou
Keyword(s):  
Visual Quality ◽  
Experimental Results ◽  
Integration Model ◽  
Quality Performance ◽  
Piecewise Function ◽  
Proposed Model ◽  
Constant Coefficients ◽  
Theoretical Analyses ◽  
Different Levels

In this paper the important issue of multimedia quality evaluation is concerned, given the unimodal quality of audio and video. Firstly, the quality integration model recommended in G.1070 is evaluated using experimental results. Theoretical analyses aide empirical observations suggest that the constant coefficients used in the G.1070 model should actually be piecewise adjusted for different levels of audio and visual quality. Then a piecewise function is proposed to perform multimedia quality integration under different levels of the audio and visual quality. Performance gain observed from experimental results substantiates the effectiveness of the proposed model.

scholarly journals Deep Learning-Based Optimal Smart Shoes Sensor Selection for Energy Expenditure and Heart Rate Estimation

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7058
Author(s):  
Heesang Eom ◽  
Jongryun Roh ◽  
Yuli Sun Hariyani ◽  
Suwhan Baek ◽  
Sukho Lee ◽  
...  
Keyword(s):  
Heart Rate ◽  
Deep Learning ◽  
Energy Expenditure ◽  
Mean Squared Error ◽  
Pressure Sensors ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Proposed Model ◽  
Point Pressure

Wearable technologies are known to improve our quality of life. Among the various wearable devices, shoes are non-intrusive, lightweight, and can be used for outdoor activities. In this study, we estimated the energy consumption and heart rate in an environment (i.e., running on a treadmill) using smart shoes equipped with triaxial acceleration, triaxial gyroscope, and four-point pressure sensors. The proposed model uses the latest deep learning architecture which does not require any separate preprocessing. Moreover, it is possible to select the optimal sensor using a channel-wise attention mechanism to weigh the sensors depending on their contributions to the estimation of energy expenditure (EE) and heart rate (HR). The performance of the proposed model was evaluated using the root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Moreover, the RMSE was 1.05 ± 0.15, MAE 0.83 ± 0.12 and R2 0.922 ± 0.005 in EE estimation. On the other hand, and RMSE was 7.87 ± 1.12, MAE 6.21 ± 0.86, and R2 0.897 ± 0.017 in HR estimation. In both estimations, the most effective sensor was the z axis of the accelerometer and gyroscope sensors. Through these results, it is demonstrated that the proposed model could contribute to the improvement of the performance of both EE and HR estimations by effectively selecting the optimal sensors during the active movements of participants.

scholarly journals Logistic Regression for Employability Prediction

2020 ◽  
Vol 9 (3) ◽  
pp. 2471-2478
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Deep Learning ◽  
Weather Forecasting ◽  
Previous Knowledge ◽  
Recruitment Process ◽  
Proposed Model ◽  
Unknown Event ◽  
The Right

Prediction is a conjecture about something which may happen. Prediction need not be based upon the previous knowledge or experience on the unknown event of interest in the future. But it is a necessity for mankind to foresee and make the right decisions to live better. Every person does predictions but the quality of the predictions differs and that differentiates successful persons and unsuccessful persons. In order to automate the prediction process and to make quality predictions available to every person, machines are trained to make predictions and such field comes under machine learning and later on deep learning algorithms. Various fields such as health care, weather forecasting, natural calamities, and crime prediction are some of the applications of prediction. The researchers have applied the field of prediction to see whether a model can predict the employability of a candidate in a recruitment process. Organizations use human expertise to identify a skilled candidate for employment based on various factors and now these organizations are trying to migrate to automated systems by harnessing the benefits of the exponential growth in the area of machine learning and deep learning. This investigation presents the development of a model to predict the employability by using Logistic Regression. A set of candidates was tested in the proposed model and results are discussed in this paper.

scholarly journals Data-driven prediction of unsteady flow over a circular cylinder using deep learning

2019 ◽  
Vol 879 ◽  
pp. 217-254 ◽  
Author(s):  
Sangseung Lee ◽  
Donghyun You
Keyword(s):  
Deep Learning ◽  
Circular Cylinder ◽  
Unsteady Flow ◽  
Conservation Laws ◽  
Flow Fields ◽  
Loss Functions ◽  
Generative Adversarial Networks ◽  
Learning Networks ◽  
Adversarial Networks ◽  
Adversarial Training

Unsteady flow fields over a circular cylinder are used for training and then prediction using four different deep learning networks: generative adversarial networks with and without consideration of conservation laws; and convolutional neural networks with and without consideration of conservation laws. Flow fields at future occasions are predicted based on information on flow fields at previous occasions. Predictions of deep learning networks are made for flow fields at Reynolds numbers that were not used during training. Physical loss functions are proposed to explicitly provide information on conservation of mass and momentum to deep learning networks. An adversarial training is applied to extract features of flow dynamics in an unsupervised manner. Effects of the proposed physical loss functions and adversarial training on predicted results are analysed. Captured and missed flow physics from predictions are also analysed. Predicted flow fields using deep learning networks are in good agreement with flow fields computed by numerical simulations.

Modeling Deep Learning Neural Networks With Denotational Mathematics in UbiHealth Environment

2020 ◽  
Vol 12 (3) ◽  
pp. 14-27 ◽  
Author(s):  
John Sarivougioukas ◽  
Aristides Vagelatos
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Ubiquitous Computing ◽  
Medical Decision Making ◽  
Medical Decision ◽  
Learning Networks ◽  
Healthcare Applications ◽  
Medical Diagnoses ◽  
The Given

Ubiquitous computing environments that are involved in healthcare applications are typically characterized by dynamically changing contexts. The contextual information must be efficiently processed in order to support medical decision making. The ubiquitous computing healthcare ecosystem must be capable of extracting medically valuable characteristics, making precise decisions, and taking medically appropriate actions. In this framework, deep learning networks can be used for data fusion of large and complex sets of information in order to make the appropriate medical diagnoses. The quality of decisions depends on the selection of appropriate network weights, which define a transformation of the given input into a diagnosis. Denotational mathematics provide a promising framework for modeling deep learning networks and adjusting their behavior by adapting their weights for the given input. Furthermore, the fidelity of the network's output can be controlled by applying a regulator to the weights values. The authors show that Denotational Mathematics can serve as a rigorous framework for modeling and controlling deep learning networks, thereby enhancing the quality of medical decision making.

Performance Analysis of GAN Architecture for Effective Facial Expression Synthesis

2021 ◽  
pp. 290-316
Author(s):  
Karthik R. ◽  
Nandana B. ◽  
Mayuri Patil ◽  
Chandreyee Basu ◽  
Vijayarajan R.
Keyword(s):  
Deep Learning ◽  
Performance Analysis ◽  
Facial Expressions ◽  
Data Distribution ◽  
Loss Functions ◽  
Human Beings ◽  
Learning Networks ◽  
Open Mouth ◽  
Important Means

Facial expressions are an important means of communication among human beings, as they convey different meanings in a variety of contexts. All human facial expressions, whether voluntary or involuntary, are formed as a result of movement of different facial muscles. Despite their variety and complexity, certain expressions are universally recognized as representing specific emotions - for instance, raised eyebrows in combination with an open mouth are associated with surprise, whereas a smiling face is generally interpreted as happy. Deep learning-based implementations of expression synthesis have demonstrated their ability to preserve essential features of input images, which is desirable. However, one limitation of using deep learning networks is that their dependence on data distribution and the quality of images used for training purposes. The variation in performance can be studied by changing the optimizer and loss functions, and their effectiveness is analysed based on the quality of output images obtained.

scholarly journals High-Capacity Image Steganography with Minimum Modified Bits Based on Data Mapping and LSB Substitution

2018 ◽  
Vol 8 (11) ◽  
pp. 2199 ◽  
Author(s):  
Abdul Zakaria ◽  
Mehdi Hussain ◽  
Ainuddin Wahab ◽  
Mohd Idris ◽  
Norli Abdullah ◽  
...  
Keyword(s):  
Signal To Noise Ratio ◽  
High Capacity ◽  
Visual Quality ◽  
Data Mapping ◽  
Embedding Capacity ◽  
Secret Data ◽  
Stego Image ◽  
Mapping Strategy ◽  
Lsb Substitution

Steganography is the art and practice of communication using hidden messages. The least significant bits (LSB) based method is the well-known type of steganography in the spatial domain. Usually, achieving the larger embedding capacity in LSB-based methods requires a large number of LSB bits modification which indirectly reduces the visual quality of stego-image and increases the risk of steganalysis detection attacks. In this study, we propose a novel steganography method with data mapping strategy which can reduce the number of bits modification per pixel. In the proposed method, four secret data bits are mapped with the four most significant bits of a cover pixel. Furthermore, the only two LSBs of a pixel are modified to indicate the mapping strategy. Experimental results show that the proposed method is able to achieve 3.48% larger embedding capacity while enhancing the visual quality (i.e., peak signal to noise ratio (PSNR) 3.73 dB) and reducing the modification of 0.76 bits per pixel. Moreover, the proposed method provides security against basic Regular and Singular groups (RS) steganalysis and histogram steganalysis detection attacks.

Block-Based High Capacity Multilevel Image Steganography

2016 ◽  
Vol 25 (08) ◽  
pp. 1650091 ◽  
Author(s):  
Geeta Kasana ◽  
Kulbir Singh ◽  
Satvinder Singh Bhatia
Keyword(s):  
Digital Images ◽  
High Capacity ◽  
Block Size ◽  
Visual Quality ◽  
Cover Image ◽  
Embedding Capacity ◽  
Secret Data ◽  
Block Based ◽  
High Embedding Capacity

This paper proposes a block-based high capacity steganography technique for digital images. The cover image is decomposed into blocks of equal size and the largest pixel of each block is found to embed the secret data bits and also the smallest pixel of each block is used for embedding to enhance the capacity. Embedding of secret data is performed using the concept that the pixel of a cover image has only two states — even and odd. Multilevel approach is also combined in the proposed technique to achieve high embedding capacity. In order to make the proposed technique more secure, a key is generated using embedding levels, block size, pixel embedding way, encryption parameters, and starting blocks of each embedding levels. Embedding capacity and visual quality of stego images generated by the proposed steganography technique are higher than the existing techniques. Steganalysis tests have been performed to show the un-detectability and imperceptibility of the proposed technique.

scholarly journals Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Chin-Fu Liu ◽  
Johnny Hsu ◽  
Xin Xu ◽  
Sandhya Ramachandran ◽  
Victor Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
False Positive Rate ◽  
Learning Networks ◽  
Large Dataset ◽  
Lower False Positive Rate ◽  
Proposed Model ◽  
Positive Rate ◽  
Total Agreement ◽  
Clinical And Translational Research

Abstract Background Accessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities. Methods We developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external dataset (STIR). Results Our proposed model outperforms generic networks and DeepMedic, particularly in small lesions, with lower false positive rate, balanced precision and sensitivity, and robustness to data perturbs (e.g., artefacts, low resolution, technical heterogeneity). The agreement with human delineation rivals the inter-evaluator agreement; the automated lesion quantification of volume and contrast has virtually total agreement with human quantification. Conclusion Our tool is fast, public, accessible to non-experts, with minimal computational requirements, to detect and segment lesions via a single command line. Therefore, it fulfills the conditions to perform large scale, reliable and reproducible clinical and translational research.

scholarly journals Real-Time Color Image Classification Based On Deep Learning Network

2019 ◽  
Vol 54 (5) ◽  
Author(s):  
Mohammed Hamzah Abed ◽  
Atheer Hadi Issa Al-Rammahi ◽  
Mustafa Jawad Radif
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Real Time ◽  
Color Image ◽  
Input Image ◽  
Proposed Model ◽  
Real Time Image ◽  
Deep Learning Network ◽  
Fully Connected ◽  
Time Image

Real-time image classification is one of the most challenging issues in understanding images and computer vision domain. Deep learning methods, especially Convolutional Neural Network (CNN), has increased and improved the performance of image processing and understanding. The performance of real-time image classification based on deep learning achieves good results because the training style, and features that are used and extracted from the input image. This work proposes an interesting model for real-time image classification architecture based on deep learning with fully connected layers to extract proper features. The classification is based on the hybrid GoogleNet pre-trained model. The datasets that are used in this work are 15 scene and UC Merced Land-Use datasets, used to test the proposed model. The proposed model achieved 92.4 and 98.8 as a higher accuracy.

Sign in / Sign up

Export Citation Format

Share Document