Article
Computer Science, Artificial Intelligence
G. Melendez-Melendez, Alicia Morales-Reyes, Rene Cumplido
Summary: Pixel Value Ordering technique based on Genetic Algorithms (PVO-GA) is a significant method for reversible data hiding, which optimizes the embedding process using flexible sized blocks and a genetic algorithm, achieving satisfactory distortion levels and reducing computational cost.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Drishti Saxena, Prabhat Patel
Summary: Information sharing mechanisms have become faster and more efficient with advancements in computer and internet technologies. Data protection is crucial when exchanging and communicating data. Digital image encryption has emerged as an efficient solution for ensuring data security. Data hiding technology can be applied in various fields like healthcare, copyright protection, and defense. It is important to encrypt hidden data before transmission and ensure the security of encrypted data over the transmission medium. This paper proposes a detailed mechanism for data hiding, encryption, and security. It introduces a multilayer data hiding scheme that considers pixel interpolation and histogram shifting for data embedding. The Arnold transform is used for image encryption, and blockchain is utilized for ensuring the security of encrypted data. The results demonstrate that the data embedding and encryption algorithms outperform recently published works.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Ahmad Shaik, V. Thanikaiselvan
Summary: This study explores the development of reversible data hiding algorithms in secure data communication using integer-to-integer wavelet transforms, which results in higher capacity and robustness. The performance of various integer wavelet transforms and other techniques in terms of embedding capacity and image quality is compared, leading to a better understanding of the relationship between embedding capacity and stego image quality.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Ngoc-Hung Nguyen, Van-At Pham
Summary: In this paper, an Improved Pixel Value Ordering (IPVO) reversible data hiding method is proposed. The method increases the number of pixel pairs and the capacity for embedding data to improve the efficiency. Compared to the IPVO method, the proposed method doubles the number of pixel pairs used and increases the embedding capacity by 1.5 to 1.9 times depending on the smoothness of the original images. Experimental results show that the proposed method has superior embedding capacity while maintaining good stego image quality.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Amishi Mahesh Kapadia, P. Nithyanandam
Summary: This research proposes a reversible data hiding technique using the recursive embedding method of Integer wavelet transform and Arnold transform, which results in a more efficient and secure system by increasing payload and protecting embedded information.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2023)
Article
Multidisciplinary Sciences
Fatuma Saeid Hassan, Adnan Gutub
Summary: This research aims to enhance reversible data hiding within images using an interpolation-based scheme, which increases embedding capacity while maintaining superior image quality.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Kai Gao, Ji-Hwei Horng, Chin-Chen Chang
Summary: This paper proposes a new high-capacity reversible data hiding scheme in encrypted images, utilizing block permutation and bitwise stream cipher processes for encryption. Experimental results demonstrate an embedding capacity that outperforms existing schemes, along with investigations into the security level and robustness of the proposed scheme.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2022)
Article
Computer Science, Artificial Intelligence
Jian Li, Xiaobo Zhang, Bin Ma, Chuan Qin, Chunpeng Wang
Summary: In this paper, a method of protecting a device from being identified through image capture is proposed. This method involves suppressing the device-related fingerprint, PRNU, in an image by modifying it in the domain of integer wavelet transform. The suppressed PRNU is then embedded into the image using reversible data hiding for perfect recovery of the original image. Extensive experiments on MICHE-I and VISION datasets demonstrate that this method addresses the shortcomings of existing techniques and exhibits strong scalability.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Xu Wang, Ching-Chun Chang, Chia-Chen Lin, Chin-Chen Chang
Summary: This paper presents an efficient reversible data hiding scheme for crypto-images, which utilizes block prediction and adaptive block mapping algorithm to achieve high-capacity data embedding while ensuring security, leading to a significant improvement in the average embedding rate.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2022)
Article
Computer Science, Information Systems
Fang Cao, Jing Chen, Fengyong Li
Summary: This paper proposes a multi-level block selection embedding mechanism to address the contradiction between embedding capacity and image visual quality in reversible data hiding in encrypted image (RDHEI). The scheme divides the original image into non-overlapping blocks, predicts the most significant bit (MSB) planes of the pixels, and generates a prediction error map for each block. The pixels are then divided into bit planes and XOR operation is performed to create room. The scheme selects the blocks with the highest PSNR values to embed data, thus improving the image visual quality.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Mohamed Lamine Benseddik, Khalil Zebbiche, Mohamed Salah Azzaz, Said Sadoudi
Summary: This paper proposes a novel reversible data hiding scheme for fingerprint images, which combines the advantages of image interpolation approaches and transform-based data hiding schemes. The scheme achieves reversibility by hiding secret data into transform coefficients and setting reference pixels back to their original values. Experimental results demonstrate that the proposed scheme outperforms recent state-of-the-art techniques in terms of embedding capacity and visual quality.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Lingzhuang Meng, Lianshan Liu, Xiaoli Wang, Gang Tian
Summary: This paper proposes a reversible data hiding algorithm for encrypted images based on integer wavelet transform and chaotic system. The algorithm achieves higher security, embedding rate, visual quality of decrypted images, and anti-attack performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Biomedical
Ningxiong Mao, Hongjie He, Fan Chen, Paolo Bellavista, Yaolin Yang
Summary: This paper proposes an RDH scheme for JPEG images based on DCT block sorting and segmented embedding, which achieves a better performance by optimizing the balance between embedding capacity and file growth while maintaining good visual quality.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Chemistry, Analytical
Mohamed Yamni, Achraf Daoui, Pawel Plawiak, Haokun Mao, Osama Alfarraj, Ahmed A. Abd El-Latif
Summary: In this study, an integer and reversible version of the Krawtchouk transform (IRKT) is proposed to avoid rounding errors in floating-point processing. Based on the IRKT, a reliable 3D reversible data hiding (RDH) algorithm is developed for secure storage and transmission of extensive medical data in medical images. The algorithm demonstrates high embedding capacity, imperceptibility, and resilience against statistical attacks in experimental evaluations. Incorporating this algorithm into the Internet of Medical Things (IoMT) sector enhances security measures for the storage and transmission of massive medical data, addressing the limitations of conventional 2D RDH algorithms in medical images.
Article
Chemistry, Multidisciplinary
Rui-Hua Liu, Quan Zhou
Summary: This work proposes a mixed multi-bit layer embedding strategy in encrypted images to improve the effectiveness of reversible data hiding. The experimental results show that the proposed scheme has superior embedding capacity and high decryption quality over the current state-of-the-art works.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Xiao Wang, Xiao-Xue Sun, Shu-Chuan Chu, Junzo Watada, Jeng-Shyang Pan
Summary: The electricity output is worth monitoring due to the increasing demand. This study proposes a combined algorithm, BOAPPE, which improves power output estimation and reduces excessive cost waste. When used with an SVR model, BOAPPE enhances prediction accuracy and avoids premature local optimization. The parallel strategy of BOAPPE improves convergence speed, while the random walk strategy prevents sliding into local optimization. The results demonstrate that the BOAPPE-SVR model outperforms other models in terms of performance metrics. Thus, it is a viable model for power load forecasting.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Shi-Jie Jiang, Shu-Chuan Chu, Fu-Min Zou, Jie Shan, Shi-Guang Zheng, Jeng-Shyang Pan
Summary: The Archimedes optimization algorithm (AOA) is a user-friendly and easy-to-implement metaheuristic algorithm, but it has some drawbacks. In this study, a new variant called TPAOA is proposed to address the drawbacks of AOA using parallel mechanism and Taguchi orthogonal combination. Experimental results show that TPAOA outperforms other algorithms in the CEC2017 test suite. Additionally, TPAOA successfully solves the parameter tuning problem of wind turbine variable pitch controller.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2023)
Article
Physics, Multidisciplinary
Jeng-Shyang Pan, Tao Liu, Bin Yan, Hong-Mei Yang, Shu-Chuan Chu
Summary: This paper proposes a method to enhance the secure transmission of QR codes using a visual cryptography scheme (VCS). By dividing the QR code into multiple areas and distributing them to different nodes, an error-free recovery is achieved. Experimental results show that the proposed scheme is relatively safe and can effectively restore error-free QR codes.
Article
Physics, Multidisciplinary
Jeng-Shyang Pan, Li-Gang Zhang, Shu-Chuan Chu, Chin-Shiuh Shieh, Junzo Watada
Summary: This paper proposes an efficient surrogate-assisted hybrid meta-heuristic algorithm, SAGD, which combines the surrogate-assisted model with GOA and DE algorithms to solve the problem of long solution time for fitness function in high-complexity problems.
Article
Computer Science, Information Systems
Jeng-Shyang Pan, Pei Hu, Tien-Szu Pan, Shu-Chuan Chu
Summary: This paper proposes a hybrid algorithm EO-GWO to train the parameters of LSTM model, which balances the abilities of exploration and exploitation. It utilizes GWO to further search the optimal solutions acquired by EO without adding extra evaluation of objective function. The LSTM and EO-GWO structure is adopted for short-term traffic flow prediction, and the hyper parameters of LSTM are optimized by EO-GWO to overcome the problems of backpropagation. Experimental results demonstrate that the algorithm achieves wonderful results in the accuracy and computation time of the three prediction models in the highway intersection.
JOURNAL OF DATABASE MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Xu Yuan, Jeng-Shyang Pan, Ai-Qing Tian, Shu-Chuan Chu
Summary: The sparrow search algorithm (SSA) is a novel intelligent optimization algorithm that simulates the foraging and anti-predation behavior of sparrows. In this paper, the binary sparrow search algorithm (BSSA) is proposed to solve binary optimization problems, such as feature selection. By improving the position update equation and introducing three new transfer functions, the performance of BSSA is enhanced. Comparative experiments with other algorithms on benchmark functions and statistical analysis confirm the effectiveness of BSSA. Feature selection is successfully implemented in the UCI data set using BSSA.
JOURNAL OF INTERNET TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Zi-Nan Liu, Tao Liu, Bin Yan, Jeng-Shyang Pan, Hong-Mei Yang
Summary: The current no-computation grayscale image visual cryptography (VC) can only achieve halftone reconstruction but cannot truly achieve multitone. To solve this problem, we propose the concept of phase periodicity of the 2/2 retarder film and calculate the optical axis angle set with phase periodicity. According to the phase periodicity, we propose a 2/2 retarder film phase periodicity visual cryptography (RPP-VC).
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)
Article
Multidisciplinary Sciences
Jeng-Shyang Pan, Ru-Yu Wang, Shu-Chuan Chu, Kuo-Kun Tseng, Fang Fan
Summary: In this paper, a TLR-QUATRE algorithm, improved by the Taguchi strategy, levy flight and the restart mechanism, is proposed. The algorithm selects a specific optimization route according to a certain probability, and the Taguchi strategy enhances local exploitation. The levy flight and restart mechanism help particles explore in different random steps, improving global exploration ability. Experimental results on CEC2017 suite show that the new algorithm has strong optimization ability, high-dimensional exploration ability, and convergence. It is also applied to fault detection in wireless sensor networks, combined with BPNN, and demonstrates robust adaptability.
Article
Multidisciplinary Sciences
Jeng-Shyang Pan, Hao-Jie Shi, Shu-Chuan Chu, Pei Hu, Hisham A. Shehadeh
Summary: The Rafflesia Optimization Algorithm (ROA) is a swarm intelligence optimization algorithm inspired by Rafflesia's biological laws. It is highly efficient, has fast convergence speed, and effectively avoids local optima. It has been successfully applied to logistics distribution center location problems. In this study, a binary version of ROA is developed and improved using transfer functions and a parallel strategy to enhance its performance.
Review
Neurosciences
Yu Cao, Hongzhi Kuai, Peipeng Liang, Jeng-Shyang Pan, Jianzhuo Yan, Ning Zhong
Summary: Recent advancements in AI, big data analytics, and MRI have revolutionized the study of Alzheimer's Disease. However, most AI models for neuroimaging classification have limitations in their learning strategies. To address this, we propose the BNLoop-GAN model, which combines conditional generation, patch-based discrimination, and Wasserstein gradient penalty to learn brain networks. We also introduce a multiple-loop-learning algorithm to improve evidence combination and ranking. Our approach shows improved classification performance for AD using multi-modal brain networks.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Mathematics
Tsu-Yang Wu, Ankang Shao, Jeng-Shyang Pan
Summary: Metaheuristic algorithms are important in the field of artificial intelligence, and the tumbleweed optimization algorithm (TOA) is a new algorithm that mimics the growth and reproduction of tumbleweeds. Chaotic maps have been proven to be an improved method for optimization algorithms, and this paper presents a chaotic-based TOA (CTOA) that incorporates chaotic maps into the optimization process. The CTOA aims to improve population diversity, global exploration, and prevent falling into local optima. The performance of CTOA is tested using 28 benchmark functions, and the circle map is found to be the most effective in improving accuracy and convergence speed, especially in 50D.
Article
Computer Science, Artificial Intelligence
Zhongjie Zhuang, Jeng-Shyang Pan, Junbao Li, Shu-Chuan Chu
Summary: Arithmetic Optimization Algorithm (AOA) is a simple and easy to implement algorithm with few parameters. It utilizes the distribution behavior of arithmetic operators in mathematics. In this manuscript, AOA algorithm is converted into binary form with improved exploration using Multiplication Mathematical Optimizer Operator (MOO). Four families of transfer functions are used in the binary AOA (BAOA). Parallel mechanism is introduced to further enhance performance and proposed the Parallel Binary AOA (PBAOA) algorithm. Experimental results show that the proposed BAOA and PBAOA algorithms outperform classical and state-of-the-art algorithms in feature selection problems on low-dimensional and high-dimensional datasets.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Weimin Zheng, Mingchao Si, Xiao Sui, Shuchuan Chu, Jengshyang Pan
Summary: This paper proposes a new adaptive parameter strategy and a parallel communication strategy to improve the Cuckoo Search (CS) algorithm, which greatly enhances the convergence speed and accuracy of the algorithm and strengthens its ability to escape local optima.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2023)
Article
Physics, Multidisciplinary
Jin-Liang Yao, Hong-Mei Yang, Dong-Huan Jiang, Bin Yan, Jeng-Shyang Pan, Meng-Xi Wang
Summary: This paper proposes a novel quantum image steganography algorithm, which utilizes the Arnold scrambling method to scramble the information image and expands it to the same size as the carrier image using the quantum expansion method. The double-layer Gray code rule is applied to the carrier pixels to reduce the change rate of LSB. A key image is generated to enhance the algorithm's security. Compared to the classical Gray code algorithm, the proposed algorithm only needs to change 25% of the LSB bits of the carrier pixels during embedding. The algorithm achieves a higher PSNR value of around 54dB and exhibits better robustness in experiments.
INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS
(2023)
Article
Computer Science, Information Systems
Liya Yue, Pei Hu, Shu-Chuan Chu, Jeng-Shyang Pan
Summary: Feature selection is crucial for speech emotion recognition, and this paper proposes a hybrid filter-wrapper feature selection method based on a genetic algorithm, which shows promising results in high-dimensional speech emotion recognition.