Search

Real-world data mining problems require feature selection to improve efficiency and accuracy. Due to not considering characteristics of the FS problem itself, traditional mechanisms limit their performance on dealing with high-dimensional FS problems. Focused on it, this paper proposes a novel feature selection algorithm based on binary transient search optimization (TSO) with chaotic maps. Due to their pseudo-random behavior, chaotic systems can mimic randomness, which is essential for addressing complex problems through feature selection. In this methodology, the logistic equation is employed to generate periodic sequences of varying lengths within the TSO evolutionary algorithm. Experimental evaluations are conducted on 12 datasets from the UCI repository. On average, modified TSO improves classification accuracy by 15% over traditional methods across the datasets tested. Experimental results demonstrate that the proposed method has improved classification accuracy, diversity, and convergence, while removing redundancy. [ABSTRACT FROM AUTHOR]

In recent years, many chaotic image encryption algorithms have been cracked by chosen plaintext attack. Therefore, the method of associating the key with the plaintext to resist the cryptanalysis has received extensive attention from designers. This paper proposes a new method of cryptanalysis for image encryption algorithms with a key associated with plaintext. We broke an image encryption scheme using chaos and DNA encoding. Through our comprehensive security analysis, we found a security vulnerability in the mechanism of the association between the key and plaintext and proposed a breaking scheme. The experimental results show that the chosen plaintext attack can recover the cipher image to the plain image. The cryptanalysis scheme proposed in this paper can provide new ideas for subsequent cryptanalysis work and also provide some meaningful references for designers to improve the security of encryption algorithms when designing them. In addition, we also propose an improved logistic chaotic map with random bit-position scrambling. The improved chaotic map has a wider parameter range and a larger Lyapunov exponent. In the end, some suggestions are given to improve the original algorithm to resist such attacks. [ABSTRACT FROM AUTHOR]

Francis turbines, essential for stability in diverse operating conditions and variable-speed scenarios, encounter efficiency-compromising vortex rope formations in the draft tube, leading to substantial pressure fluctuations. This research delves into the analysis of energy loss and pressure fluctuations associated with these vortex ropes. Employing the local entropy generation rate (LEGR) method and chaos theory, we scrutinize the behaviour of vortex ropes and their resultant pressure fluctuations. Notably, vortex ropes exhibit maximum LEGR near the runner cone, with secondary vortices escalating instability downstream. In the elbow section, the collision of vortex ropes with the outer elbow amplifies LEGR, primarily driven by fluctuating velocities (approximately 90%). Leveraging the GWO-VMD algorithm, non-stationary signals are decomposed, unveiling a significant 1.6 Hz vortex rope frequency under partial load (PL) conditions and isolating external noise frequencies, such as the prominent 300 Hz. Following decomposition, chaos theory tools, including phase space reconstruction and phase trajectory graphs, unveil the chaotic nature of PL conditions attributed to spiral vortex ropes, resulting in profound pressure fluctuations. This study enhances our understanding of such systems and provides methodologies for improved noise reduction and optimization of turbine performance. [ABSTRACT FROM AUTHOR]

This paper presents a hardware-based audio encryption system using a 2D chaotic map and dynamic S-box design implemented on an Artix-7 FPGA platform. Three distinct chaotic maps—logistic–fraction (2D-LF), logistic–sine (2D-LS), and fraction–sine (2D-FS)—were investigated and implemented on an FPGA. The 2D-LF map was employed in the encryption system for its throughput and power efficiency performance. The proposed encryption system benefits from the randomness of chaotic sequences for block permutation and S-box substitution to enhance the diffusion and confusion properties of the encrypted speech signal. The system's encryption strength is validated through performance evaluations, using the mean squared error (MSE), signal-to-noise ratio (SNR), correlation coefficients, and NIST randomness tests, which confirm the unpredictability of the encrypted speech signal. The hardware implementation results show a throughput of 2880 Mbps and power consumption of 0.13 W. [ABSTRACT FROM AUTHOR]

The internet and technological advancements have facilitated faster communication and information sharing. However, cybercrime, including malware, phishing, and ransomware, remains a severe problem despite technical progress. Detecting the intrusion via Intrusion Detection System IDS in network communication and wireless networks WSN is a big challenge that grown with the rapid development of the technologies. The detection accuracy of the IDS mainly depends on the relevant features of the incoming data from the internet. Selecting the most relevant features within the optimal attributes is one of the primary stage of the machine learning and pattern recognition modules. Finding the feature subset from the present or existing features that will improve the algorithms' learning performance in terms of accuracy and learning time is the main goal of feature selection. Therefore, this paper proposes an accurate approach for intrusion detection in the network and WSN using machine learning methods include Chaotic Maps, Nomadic People Optimizer (NPO), and SVM. The proposed approach has five main stages which are: data collection, pre-processing, feature selection, classification, and evaluation. An improved version of NPO based on chaotic map called CNPO is proposed. The proposed CNPO uses chaotic maps to initialize the population and solution distribution. Besides, a proposed fitness function for CNPO based on SVM is proposed. The CNPO is employed for feature selection task by selecting only the most relevant features from the input dataset. The proposed approach evaluated using two datasets and achieve accuracy 99.96% and 99.98 for NSL-KDD, and WSN-DS respectively. [ABSTRACT FROM AUTHOR]

The elementary cellular automata (ECAs) under the chaotic rule possess long periodicity and are widely used in pseudo-random number generators. However, their period is limited, related to the rule and the number of cells. Meanwhile, the Boolean functions of some ECAs are linear and vulnerable to linear analysis. Thus, the ECA cannot be directly implemented in the stream cipher. In this paper, a hybrid ECA (HECA) with dynamic mask (HECA-M) is designed. The HECA-M consists of two parts: the driving and mask parts. The driving part based on a HECA is used in generating the keystream, and the mask part based on a chaotic ECA is utilized to determine the iterative rule of the driving part. Subsequently, a stream cipher based on the HECA-M and SHA-512 is proposed. The statistic and secure analyses indicate that the proposed stream cipher possesses good randomness and can resist stream cipher analyses, such as exhaustive search, Berlekamp–Massey synthesis, guess and determine attack, time–memory–data tradeoff attack, etc. Hence, the proposed scheme can meet security requirements. Moreover, the time and space consumption of the proposed stream cipher is qualified. [ABSTRACT FROM AUTHOR]

Optical communications and their security have been got a great attention. In this work, a simple, low cost and secure optical system integrating orthogonal frequency division multiplexing-based passive optical network (OFDM-PON) and chaotic theory is proposed. In the proposed system, a novel scheme of quadrature amplitude modulation (QAM) encryption method is adopted. For privacy of image and video encryption, the process of encryption consists of two processes and a 3D chaotic system is employed. The chaotic system is used to generate the encryption sequences. In the first stage, the first generated chaotic sequence is XORed with the incoming data. While in the second stage, the QAM symbol is remapped using the other two generated chaotic sequences. Generally, the proposed system is designed to provide secure data, videos, and images transmission. The proposed system is simulated and evaluated with a transmission of a 10 Gb/s along 50 km single-mode fiber (SMF). The performance of the proposed system showed that there is a performance enhancement in terms of Peak to average power ratio (PAPR) and bit error rate (BER). The BER of unauthorized user is around 0.6147, while the PAPR is reduced to approximately half. The proposed system is simple and doesn't require complex computations. It requires simple analog multiplexers for its implementation. [ABSTRACT FROM AUTHOR]

Deviant behaviours are often classified as errors in the education received by the individual within the family. Children act according to the model seen at home, being a mirror of the environment where they develop their personality. The imprint that the family leaves on them will have effects throughout their life, influencing their later lifestyle. In this paper I intended to study one of the family personalities analysed by David Field and to observe the influence it has in the child's life. I chose to analyse the chaotic family personality, because it is one of the factors that most often determines the appearance of problematic behaviour in a child. The objectives I forward are 1) Analysing the way in which the child from the chaotic family understands the concept of family and 2) The link between the relationship between family members and the child's relationship with society. We shall study how the child is affected by the chaotic interaction in the family, and we will analyse the effects that the family environment has on the child's behaviour by studying the literature. Through the paper, we want to identify how the problems of the chaotic family environment affect the child's behaviour and relationships in interactions with other children, the school environment and society. [ABSTRACT FROM AUTHOR]

The increasingly complex electromagnetic environment of modern warfare and the proliferation of intelligent jamming threaten to reduce the survival rate of radio fuzes on the battlefield. Radio frequency (RF) stealth technology can fundamentally improve the anti-interception and reconnaissance capabilities of radio fuzes, thereby lessening the probability of them being intercepted, recognized, and jammed by the enemy. In this paper, an RF stealth waveform based on chaotic pulse-position modulation is proposed for ultra-wideband (UWB) radio fuzes. Adding a perturbation signal based on the Tent map ensures that the chaotic sequences have sufficiently long periods despite hardware byte limitations. Measuring the approximate entropy and sequence period shows that the Tent map with the addition of perturbation signals can maintain good randomness under byte constraints, closely approximating the Tent map with ideal precision. Simulations verify that the proposed chaotic mapping used to modulate the pulse position of an ultra-wideband radio fuze signal results in superior detection, anti-interception, and anti-jamming performance. [ABSTRACT FROM AUTHOR]

The INCOSE Complex Systems Working Group Heuristics Team has selected 67 Principles and Heuristics that are considered to be particularly relevant to Complex Systems. These have been incorporated into a Difficulty Assessment Tool that prioritizes the list of Principles and Heuristics based on scoring of a matrix of four Difficulty Elements and six System Elements (to characterize the nature of the complexity). The purpose of this paper is to describe an initial assessment of the effectiveness and usefulness of the Difficulty Assessment Tool. The Tool has been used to assess eight Case Studies by five assessment teams — one with three people working together, one with two people and the remaining three with individual assessments. The results of these assessments have been compared using four different correlation methods, using the total weighted Heuristic score, the maximum weighted Heuristic score, a Match / Mismatch analysis of the top fifteen and bottom seven Heuristics, and a difference ranking between pairs of assessors of all 67 Principles and Heuristics. The last two assessment methods are shown to be more insightful. The assessment teams then reviewed the relevance of the highest and lowest‐ranked Principles and Heuristics to the full Case Study definitions (Problem and Outcome). There is good agreement of relevance for the highest‐ranking Principles and Heuristics, less so for the lowest‐ranking ones. Based on this initial assessment, the DAT shows promise to help people develop complex systems. The paper concludes with recommendations for further assessment of the Difficulty Assessment Tool. [ABSTRACT FROM AUTHOR]

Based on the chaotic polarization system of optically injected cascaded vertical-cavity surface-emitting lasers (VCSELs), we propose a novel implementation scheme for high-speed optical chaotic data selection logic operations. Under the condition where the slave VCSEL (S-VCSEL) outputs a chaotic laser signal, we calculate the range of the applied electric field and the optical injection amplitude. We also investigate the evolution of the correlation characteristics between the polarized light output from the periodic poled LiNbO3 (PPLN) and the S-VCSEL as a function of the optical injection amplitude under different applied electric fields. Furthermore, we analyze the polarization bistability of the polarized light from the PPLN and S-VCSEL. Based on these results, we modulate the optical injection amplitude as the logic input and the applied electric field as the control logic signal. Using a mean comparison mechanism, we demodulate the polarized light from the PPLN and S-VCSEL to obtain two identical logic outputs, achieving optical chaotic data selection logic operations with an operation speed of approximately 114 Gb/s. Finally, we investigate the influence of noise on the logic outputs and find that both logic outputs do not show any error symbols under the noise strength as high as 180 dBw. The anti-noise performance of logic output O1 is superior to that of optical chaotic logic output O2. For noise strengths up to 185 dBw, error symbols in O2 can be detected and corrected by comparison with O1. [ABSTRACT FROM AUTHOR]

Data encryption is an important part of the communication system. The Chaos essential properties, make it a crucial candidate for encryption applications. There is a compromise between complexity and security in previous studies. In this study, high security was achieved with low complexity. This paper proposed a 3D chaotic map and S-Box has been cascaded to get a high efficiency as complex algorithms or multi-iteration schemes. The first stage is ciphering using 3D cat-map, the second stage is S-box based on 3D henon map, while the third stage is another ciphering stage using 3D henon map. In this study, various encryption techniques, including cipher algorithms and substitution box, are combined with the OFDM system to establish a secure image transmission over a Rayleigh fading channel. QPSK modulation is used to ensure the simplicity of the proposed system. Six gray images are used, Lena, the cameraman, Barbara, Baboon, pepper and Elaine for testing and comparing with previous works. Security analysis is performed to evaluate the quality and security of the encryption process, the entropy value reach 7.99, correlation coefficient is around zero and the histogram is uniform. In addition, the key size is 2630. For image transmission evaluation, the PSNR and BER are utilized and it reached 10-5 for BER. According to the statistical results, the proposed image encryption scheme is secure and efficient.

The area of DNA cryptography is an interdisciplinary field that has emerged recently, focusing on the possible applications of DNA (deoxyribonucleic acid) molecules for secure encryption and data storage. It uses DNA sequences to create methods for encoding, encrypting, and decoding data by fusing concepts from cryptography and molecular biology. This paper presents various works proposed in DNA encoding. [ABSTRACT FROM AUTHOR]

Aiming at the problems of small chaotic space and weak chaotic ability of existing chaotic mapping models, a new two-dimensional chaotic mapping model was designed by coupling two-dimensional Henon chaotic mapping model and Sine chaotic mapping model. A new one-dimensional chaotic mapping model was designed by coupling Sine chaotic mapping model and Logistic chaotic mapping model. To solve the problem of low security when using single scrambling method for image encryption, a randomly selected scrambling algorithm was designed by using Lorenz mapping. A color image encryption scheme was proposed using two designed chaotic mapping and scrambling selection methods. The experimental results show that the proposed method has a large scrambling range, high security, good image encryption effect, strong resistance to common attacks, and it is easy to implement. [ABSTRACT FROM AUTHOR]

Let G be an abelian semigroup of matrices on K n ( K = C or R ). We show that if G is hypercyclic, then it has no non-zero finite orbit. This result fails if we drop the assumption that G is abelian. As a consequence, if G is abelian, it is not chaotic. On the other hand, we show that G is not minimal for n ≥ 3 , but it can be minimal for n = 1 ; for K = R , the critical number is n = 2 . [ABSTRACT FROM AUTHOR]

A proposed algorithm for digital image encryption is presented in this paper. It combines permutation and substitution techniques. Logistic map which is a chaos function is used in both techniques. Before encrypting, the keystream is generated first from the logistics map. Then, the plain image's pixel positions are shuffled with perfect shuffle permutation based on ascending keystream order, thereby executing the permutation process. Next, the pixel values are substituted using the XOR operation with a keystream which is also generated from the logistic map. Pixels are operated in cipher block chain mode. This research aim is to develop an image encryption algorithm, especially in the permutation process, that has high resistance to attacks by crackers. The attack types observed in this research include statistical attacks, permutation matrix attacks, differential attacks, as well as brute force attacks. From the experimental results and analysis of the proposed algorithm indicate that it has high resistance from all those attacks. [ABSTRACT FROM AUTHOR]

The study of extreme events (EEs) in photonics has expanded significantly due to straightforward implementation conditions. EEs have not been discussed systematically, to the best of our knowledge, in the chaotic dynamics of a Fabry–Perot laser with optical feedback, so we address this in the current contribution. Herein, we not only find EEs in all modes but also divide the EEs in total output into two categories for further discussion. The two types of EEs have similar statistical features to conventional rogue waves. The occurrence probability of EEs undergoes a saturation effect as the feedback strength increases. Additionally, we analyze the influence of feedback strength, feedback delay, and pump current on the probability of EEs defined by two criteria of EEs and find similar trends. We hope that this work contributes to a deep understanding and serves as inspiration for further research into various multimode semiconductor laser systems. [ABSTRACT FROM AUTHOR]

This paper proposes a lossless compression and encryption algorithm for sequence images based on adaptive inter-frames coding. This method can use the correlation in the time dimension to reduce redundant information. To increase the complexity of chaotic systems, this paper proposes a novel two-dimensional coupled and transformed Chebyshev cubic map (2D-CTCCM). Compared with existing chaotic systems, 2D-CTCCM exhibits better randomness and complexity. Moreover, this paper employs the Chinese remainder theorem in the process of lossless compression to obtain better compression performance. We extend the fractal sorting matrix to multi-dimensional space and apply it to the process of permutation. This paper proposes an improved semi-tensor product (STP) diffusion method to solve the problem that existing STP diffusion methods cannot resist chosen-plaintext attacks. Experimental results show that the performance of our algorithm is better than other lossless compression algorithms. It has strong key sensitivity and plaintext sensitivity and can resist brute-force attacks, statistical attacks, known-plaintext and chosen-plaintext attacks. [ABSTRACT FROM AUTHOR]

Aiming at the problems of small chaotic space and weak chaotic ability of existing chaotic mapping models, a new three-dimensional chaotic mapping model is designed by coupling two-dimensional Henon chaotic mapping model and Sine chaotic mapping model. Aiming at the problem that the security of encryption system will be reduced if the key is reused, this paper designs a new key generation method using Chebyshev mapping and plaintext image. Using the 3D chaotic mapping and key generation method designed in this paper, a color image encryption method is proposed. The results show that the method can encrypt images safely and effectively and protect the security of image information. [ABSTRACT FROM AUTHOR]

It has been reported by World Health Organization (WHO) that the Covid-19 epidemic due to the Sar Cov-2 virus, which started in China and affected the whole world, caused the death of approximately six million people over three years. Global disasters such as pandemics not only cause deaths but also bring other global catastrophic problems. Therefore, governments need to perform very serious strategic operations to prevent both infection and death. It is accepted that even if there are vaccines developed against the virus, it will never be possible to predict very complex spread dynamics and reach a spread pattern due to new variants and other parameters. In the present study, four countries: Türkiye, Germany, Italy, and the United Kingdom have been selected since they exhibit similar characteristics in terms of the pandemic’s onset date, wave patterns, measures taken against the outbreak, and the vaccines used. Additionally, they are all located on the same continent. For these reasons, the three-year Covid-19 data of these countries were analyzed. Detailed chaotic attractors analyses were performed for each country and Lyapunov exponents were obtained. We showed that the three-year times series is chaotic for the chosen countries. In this sense, our results are compatible with the results of the Covid-19 analysis results in the literature. However, unlike previous Covid-19 studies, we also found out that there are chaotic, periodic, or quasi-periodic sub-series within these chaotic time series. The obtained results are of great importance in terms of revealing the details of the dynamics of the pandemic.

Data security is vital if transferred over a wireless network or stored on a personal computer. The essential properties of chaos, such as initial state sensitivity and unpredictability, make it a crucial candidate for encryption applications. This paper proposes a 3D chaotic map and a cascaded S-Box that can be combined to get a high-efficiency and complex cryptographic algorithm. The first stage is ciphering using a 3D cat map, the second stage is an S-box based on a 3D Henon map, and the third stage is another ciphering stage using a 3D Henon map. This study combines various encryption techniques, including cipher algorithms and substitution boxes, with the OFDM system to establish a secure image transmission over a Rayleigh fading channel. BPSK modulation is used to ensure the simplicity of the proposed system. Three grey images are used, Lena, the camera-man, and Pepper, for testing and comparing with previous works. Security analysis is performed to evaluate the quality and security of the encryption process. For image transmission evaluation, the PSNR and BER are utilized. According to the statistical results, the proposed image encryption scheme is secure and efficient. The comparison with the previous studies shows that this system is competitive with previous works.

The elementary cellular automata (ECAs) under the chaotic rule possess long periodicity and are widely used in pseudo-random number generators. However, their period is limited, related to the rule and the number of cells. Meanwhile, the Boolean functions of some ECAs are linear and vulnerable to linear analysis. Thus, the ECA cannot be directly implemented in the stream cipher. In this paper, a hybrid ECA (HECA) with dynamic mask (HECA-M) is designed. The HECA-M consists of two parts: the driving and mask parts. The driving part based on a HECA is used in generating the keystream, and the mask part based on a chaotic ECA is utilized to determine the iterative rule of the driving part. Subsequently, a stream cipher based on the HECA-M and SHA-512 is proposed. The statistic and secure analyses indicate that the proposed stream cipher possesses good randomness and can resist stream cipher analyses, such as exhaustive search, Berlekamp–Massey synthesis, guess and determine attack, time–memory–data tradeoff attack, etc. Hence, the proposed scheme can meet security requirements. Moreover, the time and space consumption of the proposed stream cipher is qualified.

This study presents new simulations of chaotic behavior by combining the Chua circuit with other circuits. The Chua circuit serves as an ideal subject for exploring complex dynamics. Through meticulous simulations, we scrutinize the circuit's response under various input conditions, unveiling complex patterns and behaviors characteristic of chaos. Our results contribute to a deeper understanding of the chaotic properties inherent in electronic systems, potentially paving the way for applications in various fields. Additionally, integrating the Chua circuit with other components and treating it as a Sierpinski triangle in simulation studies provides valuable insights into the captivating realm of chaos. Furthermore, our observations include many cases of convergence and stability in chaotic systems. [ABSTRACT FROM AUTHOR]

It has been reported by World Health Organization (WHO) that the Covid-19 epidemic due to the Sar-Cov-2 virus, which started in China and affected the whole world, caused the death of approximately six million people over three years. Global disasters such as pandemics not only cause deaths but also bring other global catastrophic problems. Therefore, governments need to perform very serious strategic operations to prevent both infection and death. It is accepted that even if there are vaccines developed against the virus, it will never be possible to predict very complex spread dynamics and reach a spread pattern due to new variants and other parameters. In the present study, four countries: Türkiye, Germany, Italy, and the United Kingdom have been selected since they exhibit similar characteristics in terms of the pandemic's onset date, wave patterns, measures taken against the outbreak, and the vaccines used. Additionally, they are all located on the same continent. For these reasons, the three-year Covid-19 data of these countries were analyzed. Detailed chaotic attractors analyses were performed for each country and Lyapunov exponents were obtained. We showed that the three-year times series is chaotic for the chosen countries. In this sense, our results are compatible with the results of the Covid-19 analysis results in the literature. However, unlike previous Covid-19 studies, we also found out that there are chaotic, periodic, or quasi-periodic sub-series within these chaotic time series. The obtained results are of great importance in terms of revealing the details of the dynamics of the pandemic. [ABSTRACT FROM AUTHOR]

Transformerless grid-connected inverters for photovoltaic (PV) applications provide several advantages such as reduced cost and volume as well as an increased efficiency. However, the removal of the transformer gives rise to several problems related to leakage currents and electromagnetic interferences (EMI). This paper presents different chaotic unipolar sine-pulse width modulation (C-USPWM) techniques for a transformerless grid-connected PV inverter based on parameter selection. The main objective behind this proposed chaotic modulation technique is to reduce the conducted EMI without worsening the power quality and the common-mode voltage (CMV). The method is validated through numerical simulations and experimental tests carried out on laboratory prototype of an optimized H5 inverter (oH5). The obtained results showed its superiority to the conventional unipolar sine-pulse width modulation (USPWM). We showed also that the appropriate parameter selection of the C-UPSWM could advantageously combine an improved EMI performance and an efficient control, making it possible to deliver a significant reduction of the peaks' amplitudes in the frequency spectrum of the common-mode (CM) voltage. [ABSTRACT FROM AUTHOR]

Dublin, 1904 Trieste, 1914. The time period during which James Joyce wrote the novel is the same period that produced revolutionary developments in science and arts. This revolutionized knowledge became the ultimate foundation for modern arts. The art forms had begun to show a progressive inclination towards a certain preciosity in ways of exhibition, representation and innovations. In Literature, the novel writings showed new ways of rendering how people experienced the world around them. The novelists inward turned to the everyday complexities of human lives, the self-conscious perseverance, the attempted efforts to capture the chaotic order and in such collective ways, authentically established the modernist intelligence and ways of writing the 'modernist novel'. [ABSTRACT FROM AUTHOR]

In this study, encrypted image transmission was carried out with a secure communication application using reversible chaotic image encryption with the synchronization of two identical chaotic systems. Encryption and decryption of the image can be done with the same algorithm using the same chaotic signal. The image can be encrypted using the same chaotic signal on the sending side and decoded with the encryption algorithm and chaotic signal on the receiving side. Experimental results show that the proposed encryption algorithm can securely encrypt and transfer images in 24-bit RGB and 8-bit grayscale images. In the study, histogram, histogram variance, salt & pepper, speckle, NPCR and UACI, four classical types of attacks, NIST, key sensitive and crop visual and statistical attacks were made on encrypted images and the robustness of the encryption method was tested. In addition, PSNR, SSIM, UIQ, BER and NCC image quality criteria were used and the results of attacks on chaotic encrypted images were measured. As a result of visual and statistical attacks, it has been seen that the proposed chaotic encryption algorithm is resistant to attacks. The NPCR and UACI analysis results of the proposed method were compared with the results of similar studies in the literature. According to similar chaotic image coding studies in the literature, the NPCR and UACI values of the proposed method gave better results than most. As a result of the tests, with the secure communication application of the proposed method, image encryption and decryption can be performed by using a common chaotic signal on the sender and receiver sides. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shenzhen University Science & Engineering is the property of Editorial Department of Journal of Shenzhen University Science & Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Recently, medical technologies have developed, and the diagnosis of diseases through medical images has become very important. Medical images often pass through the branches of the network from one end to the other. Hence, high‐level security is required. Problems arise due to unauthorized use of data in the image. One of the methods used to secure data in the image is encryption, which is one of the most effective techniques in this field. Confusion and diffusion are the two main steps addressed here. The contribution here is the adaptation of the deep neural network by the weight that has the highest impact on the output, whether it is an intermediate output or a semi‐final output in additional to a chaotic system that is not detectable using deep neural network algorithm. The colour and grayscale images were used in the proposed method by dividing the images according to the Region of Interest by the deep neural network algorithm. The algorithm was then used to generate random numbers to randomly create a chaotic system based on the replacement of columns and rows, and randomly distribute the pixels on the designated area. The proposed algorithm evaluated in several ways, and compared with the existing methods to prove the worth of the proposed method.