Wyniki wyszukiwania - BazTech

1

FPGA-based secure and noiseless image transmission using lea and optimized bilateral filter

Hebbale Sunil B., Akula V.S. Giridhar, Baraki Parashuram

Computer Science

|

2022

|

T. 23 (4)

451--466

EN

In today’s world, the transmission of secured and noiseless images is a difficult task. Therefore, effective strategies are important for securing data or secret images from attackers. Besides, denoising approaches are important for obtaining noise-free images. For this, an effective crypto-steganography method that is based on a lightweight encryption algorithm (LEA) and the modified least significant bit (MLSB) method for secured transmission is proposed. Moreover, a bilateral filter-based whale optimization algorithm (WOA) is used for image denoising. Before the image transmission, a secret image is encrypted by the LEA algorithm and embedded into the cover image using discrete wavelet transform (DWT) and MLSB techniques. After the image transmission, an extraction process is performed in order to recover the secret image. Finally, a bilateral WOA filter is used to remove the noise from the secret image. The Verilog code for the proposed model is designed and simulated in Xilinx software. Finally, the simulation results show that the proposed filtering technique results in performance that is superior to conventional bilateral and Gaussian filters in terms of the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

2

Optimal tuning procedure for FOPID controller of integrated industrial processes with deadtime

Anuja R., Sivarani T. S., Germin Nisha M.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 1

art. no. e139954

EN

Industrial processes such as batch distillation columns, supply chain, level control etc. integrate dead times in the wake of the transportation times associated with energy, mass and information. The dead time, the cause for the rise in loop variability, also results from the process time and accumulation of time lags. These delays make the system control poor in its asymptotic stability, i.e. its lack of self-regulating savvy. The haste of the controller’s reaction to disturbances and congruence with the design specifications are largely influenced by the dead time; hence it exhorts a heed. This article is aimed at answering the following question: “How can a fractional order proportional integral derivative controller (FOPIDC) be tuned to become a perfect dead time compensator apposite to the dead time integrated industrial process?” The traditional feedback controllers and their tuning methods do not offer adequate resiliency for the controller to combat out the dead time. The whale optimization algorithm (WOA), which is a nascent (2016 developed) swarm-based meta-heuristic algorithm impersonating the hunting maneuver of a humpback whale, is employed in this paper for tuning the FOPIDC. A comprehensive study is performed and the design is corroborated in the MATLAB/Simulink platform using the FOMCON toolbox. The triumph of the WOA tuning is demonstrated through the critical result comparison of WOA tuning with Bat and particle swarm optimization (PSO) algorithm-based tuning methods. Bode plot based stability analysis and the time domain specification based transient analysis are the main study methodologies used.

3

Aspect-based sentiment classification model employing whale-optimized adaptive neural network

Balaganesh Nallathambi, Muneeswaran K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e137271

EN

Nowadays in e-commerce applications, aspect-based sentiment analysis has become vital, and every consumer started focusing on various aspects of the product before making the purchasing decision on online portals like Amazon, Walmart, Alibaba, etc. Hence, the enhancement of sentiment classification considering every aspect of products and services is in the limelight. In this proposed research, an aspect-based sentiment classification model has been developed employing sentiment whale-optimized adaptive neural network (SWOANN) for classifying the sentiment for key aspects of products and services. The accuracy of sentiment classification of the product and services has been improved by the optimal selection of weights of neurons in the proposed model. The promising results are obtained by analyzing the mobile phone review dataset when compared with other existing sentiment classification approaches such as support vector machine (SVM) and artificial neural network (ANN). The proposed work uses key features such as the positive opinion score, negative opinion score, and term frequency-inverse document frequency (TF-IDF) for representing each aspect of products and services, which further improves the overall effectiveness of the classifier. The proposed model can be compatible with any sentiment classification problem of products and services.

4

WOANet: Whale optimized deep neural network for the classification of COVID-19 from radiography images

Murugan R., Goel Tripti, Mirjalili Seyedali, Chakrabartty Deba Kumar

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1702--1718

EN

Coronavirus Diseases (COVID-19) is a new disease that will be declared a global pandemic in 2020. It is characterized by a constellation of traits like fever, dry cough, dyspnea, fatigue, chest pain, etc. Clinical findings have shown that the human chest Computed Tomography (CT) images can diagnose lung infection in most COVID-19 patients. Visual changes in CT scan due to COVID-19 is subjective and evaluated by radiologists for diagnosis purpose. Deep Learning (DL) can provide an automatic diagnosis tool to relieve radiologists’ burden for quantitative analysis of CT scan images in patients. However, DL techniques face different training problems like mode collapse and instability. Deciding on training hyper-parameters to adjust the weight and biases of DL by a given CT image dataset is crucial for achieving the best accuracy. This paper combines the backpropagation algorithm and Whale Optimization Algorithm (WOA) to optimize such DL networks. Experimental results for the diagnosis of COVID-19 patients from a comprehensive COVID-CT scan dataset show the best performance compared to other recent methods. The proposed network architecture results were validated with the existing pre-trained network to prove the efficiency of the network.