N. Karthika

Bio: N. Karthika is an academic researcher from National Institute of Technology, Tiruchirappalli. The author has contributed to research in topics: Deep learning & Confusion and diffusion. The author has an hindex of 1, co-authored 3 publications receiving 5 citations.

Image Encryption and Decryption using Chaotic System

Abstract: The age of digital information uses images in fields like military and medical applications, but the security of those transacted images is still a question mark. To overcome this challenge, an efficient encryption system has to be developed which should accomplish confidentiality, integrity, security and it should also prevent the access of images by unauthorized users. Such an image encryption system has to be developed which provides enhanced security for images. This system uses two important techniques which is based on chaos theory namely: Confusion and Diffusion. Confusion part uses block scrambling and modified zigzag transformation while the Diffusion part uses 3D logistic map and key generation followed by additive cipher. This system also protects from statistical and differential attacks. The experimental results such as Entropy, Histogram analysis, Mean Absolute Error, Number of Pixels Change Rate (NPCR), Unified Average Changing Intensity (UACI) proves that the security of the images has been preserved at a higher level and also prevents the unauthorized access to the sensitive information.

Clustering Performance Analysis

Abstract: Clustering plays a significant role in identifying the intrinsic structure of data. In this paper, various clustering algorithms are compared on real, numerical, categorical datasets around the cluster size. From the analysis, it is inferred that the repetition of KMeans many times does not bring better significant iterations since it starts randomly. It purely depends on the initial choice of the centroid of clusters. The sum of squared error decreases with increasing cluster size. The Expectation–Maximization (EM) is time-consuming than KMeans.

Deep convolutional network for urbansound classification

Abstract: The efficiency of Convolutional Neural Networks in classifying terse audio snippets of UrbanSounds is evaluated. A deep neural model contains two convolutional layers coupled with Maxpooling plus three fully interconnected (dense) layers. The deep neural model is being trained upon low level description of various urban sound clips with deltas. The efficiency of the neural network is examined on urban recordings and compared with different contemporary approaches. The model obtained 76% validation accuracy that is better than other conventional models which relied only on Mel Frequency Cepstral Coefficients.

SSLnDO-Based Deep Residual Network and RV-Coefficient Integrated Deep Fuzzy Clustering for Cotton Crop Classification

Abstract: The excellent classification accuracy of remote sensory images has led to a major expansion of their use in agricultural field surveillance in recent years. The accurate classification of crop is very significant for agricultural management and food security. There are diverse varieties of crops are available. Among them, each possesses same spectral curves. Due to increasing number of remote sensing information, a major limitation arises in the domain of crop classification is how to determine significant data from huge volume of information to maintain categorization accuracy and implementation time. Consequently, one of the main obstacles in the agricultural industry is the precise classification of crops. Deep Residual Network (ResNet)-based Social Sea Lion Driver Optimization (SSLnDO)-based Deep Fuzzy Clustering (DFC), where the distance is calculated using RV coefficient, are used to develop an effective method for classifying cotton crops. Finally, classification of the cotton crop is successfully accomplished using Deep ResNet, and the network classifier is trained by inserting produced SSLnDO. The vegetation index is generated for each color band independently. Combining the Social Ski Driver (SSD) optimization and the Sea Lion Optimization (SLnO) method yields the newly developed SSLnDO. A maximum testing accuracy of 0.940, a sensitivity of 0.931, and a specificity of 0.926 have been achieved by the designed model. When comparing the accuracy value produced by the proposed method for image-2 to the existing approaches, namely WLI-Fuzzy + BS-Lion NN, OSVM-OCNN, GAN, Hybrid CNN-RF, Deep learning, and Deep ResNet, they are 15.21%, 11.06%, 15.21%, 9.04%, 4.36%, and 2.3% higher.

A VOHE System for Underwater Communications

Abstract: This paper presents a new method for encrypting holographic information based on optical and acoustic signals called a Virtual Optical Holographic Encryption (VOHE) system for underwater communications that can be applicable for communications between deep submergence research vehicles. The transmission medium is composed of a combination of optical signals and acoustic signals together to form the VOHE system for transmitting system information. The optical encryption system provides essential parameters for constructing secure communications such as the propagation wavelength (λ) and focal length (f) of the Fourier lens, which are considered as keys for implementing encryption and decryption processes. An expanded RSA (ERSA) algorithm using a complex function sends system information (λ, f) as a message to a receiver. To determine accuracy of the information retrieved by the proposed technique, the minimum mean square error (MSE) was conducted to evaluate the accuracy of the received signal. The VOHE system employs virtual optical encryption system was simulated based on COMSOL Multiphysics simulation software. Finally, the National Institute of Standards and Technology (NIST) method and Pollard’s rho method were separately applied to evaluate the proposed ERSA algorithm. Obtained results showed that ERSA is able to achieve a more significant security level than RSA.

A Virtual Optical Holographic Encryption System Using Expanded Diffie-Hellman Algorithm

Abstract: This paper presents a new method for encrypting information over a Virtual Optical Holographic Encryption (VOHE) system which employs a virtual optical system based on digital holography and Fourier lens The VOHE system provides parameters such as propagation wavelength ( $\lambda$ ) and focal length (f) of the Fourier lens which are keys that are used for encryption and decryption processes The encrypted holographic information is based on an expanded Diffie-Hellman (EDH) algorithm The method of expansion is presented based on a two-dimension complex function EDH-C Furthermore, an expanded Pollard’s Rho method was applied to evaluate the security of the proposed EDH-C algorithm To determine the accuracy of the information retrieved by a receiver site, the mean absolute error (MAE) was calculated between the original code and retrieved code Finally, the randomness of the transmitted message for both methods was evaluated using NIST tests and the results show that the message that was encrypted by the proposed EDH-C algorithm had higher security than DH in view of the unpredictability and complexity of the transmitted message over an insecure channel

Image Encryption and Decryption System through a Hybrid Approach Using the Jigsaw Transform and Langton’s Ant Applied to Retinal Fundus Images

Abstract: In this work, a new medical image encryption/decryption algorithm was proposed. It is based on three main parts: the Jigsaw transform, Langton’s ant, and a novel way to add deterministic noise. The Jigsaw transform was used to hide visual information effectively, whereas Langton’s ant and the deterministic noise algorithm give a reliable and secure approach. As a case study, the proposal was applied to high-resolution retinal fundus images, where a zero mean square error was obtained between the original and decrypted image. The method performance has been proven through several testing methods, such as statistical analysis (histograms and correlation distributions), entropy computation, keyspace assessment, robustness to differential attack, and key sensitivity analysis, showing in each one a high security level. In addition, the method was compared against other works showing a competitive performance and highlighting with a large keyspace (>1×101,134,190.38). Besides, the method has demonstrated adequate handling of high-resolution images, obtaining entropy values between 7.999988 and 7.999989, an average Number of Pixel Change Rate (NPCR) of 99.5796%±0.000674, and a mean Uniform Average Change Intensity (UACI) of 33.4469%±0.00229. In addition, when there is a small change in the key, the method does not give additional information to decrypt the image.

Novel Pehlivan-Uyarŏglu Chaotic System Variants and their CFOA Based Realization

Abstract: In this paper, four variants of Pehlivan–Uyarŏglu chaotic system (PUCS) have been proposed. The properties of the proposed PUCSs are examined through numerical simulations and the parameter values are obtained by observing the bifurcation diagrams for state variables. Further, the convergence/divergence of nearby orbits is investigated by noticing the evolution of Lyapunov exponents with time. It is found that the values of Lyapunov exponents are negative, zero and positive for all proposed variants thus confirming the chaoticity of the proposals. The strangeness of the proposed variants is also studied. The stability of PUCS and its proposed variants is examined using Jacobi stability analysis. A current feedback operational amplifier (CFOA) based circuit is put forward that can realize the existing PUCS and its proposed variants, by simply adjusting the component values. The proposed realization is compact (23% saving in overall component count) in comparison to its operational amplifier (OpAmp) based counterpart. The behavior of the proposed variants in time domain, frequency domain and phase space have been examined through simulations in LTspice design environment. Furthermore, the feasibility of the proposed variants is also discussed through presenting the electronic circuit implementation of two of the variants and the results obtained are in good agreement with the LTspice simulations. Monte Carlo (MC) simulations are also included to show the robustness of the proposed circuit against parameter variations.