Abel C. H. Chen

Abel C. H. Chen

In recent years, several swarm intelligence optimization algorithms have been proposed to be applied for solving a variety of optimization problems. However, the values of several hyperparameters should be determined. For instance, although Particle Swarm Optimization (PSO) has been applied for several applications with higher optimization performance, the weights of inertial velocity, the particle's best known position and the swarm's best known position should be determined. Therefore, this study proposes an analytic framework to analyze the optimized average-fitness-function-value (AFFV) based on mathematical models for a variety of fitness functions. Furthermore, the optimized hyperparameter values could be determined with a lower AFFV for minimum cases. Experimental results show that the hyperparameter values from the proposed method can obtain higher efficiency convergences and lower AFFVs.

Abel C. H. Chen

In the recent years, various gradient descent algorithms including the methods of gradient descent, gradient descent with momentum, adaptive gradient (AdaGrad), root-mean-square propagation (RMSProp) and adaptive moment estimation (Adam) have been applied to the parameter optimization of several deep learning models with higher accuracies or lower errors. These optimization algorithms may need to set the values of several hyperparameters which include a learning rate, momentum coefficients, etc. Furthermore, the convergence speed and solution accuracy may be influenced by the values of hyperparameters. Therefore, this study proposes an analytical framework to use mathematical models for analyzing the mean error of each objective function based on various gradient descent algorithms. Moreover, the suitable value of each hyperparameter could be determined by minimizing the mean error. The principles of hyperparameter value setting have been generalized based on analysis results for model optimization. The experimental results show that higher efficiency convergences and lower errors can be obtained by the proposed method.

Abel C. H. Chen

With the maturity of web services, containers, and cloud computing technologies, large services in traditional systems (e.g. the computation services of machine learning and artificial intelligence) are gradually being broken down into many microservices to increase service reusability and flexibility. Therefore, this study proposes an efficiency analysis framework based on queuing models to analyze the efficiency difference of breaking down traditional large services into n microservices. For generalization, this study considers different service time distributions (e.g. exponential distribution of service time and fixed service time) and explores the system efficiency in the worst-case and best-case scenarios through queuing models (i.e. M/M/1 queuing model and M/D/1 queuing model). In each experiment, it was shown that the total time required for the original large service was higher than that required for breaking it down into multiple microservices, so breaking it down into multiple microservices can improve system efficiency. It can also be observed that in the best-case scenario, the improvement effect becomes more significant with an increase in arrival rate. However, in the worst-case scenario, only slight improvement was achieved. This study found that breaking down into multiple microservices can effectively improve system efficiency and proved that when the computation time of the large service is evenly distributed among multiple microservices, the best improvement effect can be achieved. Therefore, this study's findings can serve as a reference guide for future development of microservice architecture.

Abel C. H. Chen

The Elliptic Curve Integrated Encryption Scheme (ECIES) is widely regarded as a practical method and has been adopted by multiple standards. However, the advancement of quantum computing technologies poses potential security risks to ECIES. Therefore, this study proposes a Key Encapsulation Mechanism-Based Integrated Encryption Scheme (KEM-IES), which enhances resistance to quantum attacks by incorporating a Post-Quantum Cryptography (PQC)-based Key Encapsulation Mechanism (KEM). Furthermore, the study integrates the Ascon algorithm, released by the National Institute of Standards and Technology (NIST) in August 2025, to further improve computational efficiency and enable applicability to embedded systems. The proposed KEM-IES and its Ascon-based variant are implemented on a Raspberry Pi 4, and evaluations are conducted to compare the performance of ECIES and KEM-IES.

Abel C. H. Chen, James W. H. Tung, Austin B. Y. Lin et al.

This study aims to enhance the bidirectional authentication capability of ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism) by proposing the post-quantum cryptography-based (PQC-based) bidirectional authentication key exchange protocol. Furthermore, it introduces dual-usage certificates combining PQC-based DSA (Digital Signature Algorithm) and PQC-based KEM, which include composite schemes, catalyst schemes, and chameleon schemes. These dual-usage certificates utilize the PQC-based DSA public key and PQC-based KEM public key within the certificate to meet the requirements for bidirectional authentication and encryption, enabling the negotiation of a shared secret key. During the experimental phase, the study validates and compares key exchange message lengths and computation times under different certificate configurations. Finally, instant messaging is presented as an industry application to demonstrate the practical implementation of the proposed protocol.

Abel C. H. Chen

In recent years, quantum computers and Shor quantum algorithm have posed a threat to current mainstream asymmetric cryptography methods (e.g. RSA and Elliptic Curve Cryptography (ECC)). Therefore, it is necessary to construct a Post-Quantum Cryptography (PQC) method to resist quantum computing attacks. Therefore, this study proposes a PQC-based neural network that maps a code-based PQC method to a neural network structure and enhances the security of ciphertexts with non-linear activation functions, random perturbation of ciphertexts, and uniform distribution of ciphertexts. In practical experiments, this study uses cellular network signals as a case study to demonstrate that encryption and decryption can be performed by the proposed PQC-based neural network with the uniform distribution of ciphertexts. In the future, the proposed PQC-based neural network could be applied to various applications.

Abel C. H. Chen

With the maturation of quantum computing technology, many cryptographic methods are gradually facing threats from quantum computing. Although the Grover algorithm can accelerate search speeds, current research indicates that the Advanced Encryption Standard (AES) method can still enhance security by increasing the length of the secret key. However, the AES method involves multiple modes in implementation, and not all modes are secure. Therefore, this study proposes a normalized Gini impurity (NGI) to verify the security of each mode, using encrypted images as a case study for empirical analysis. Furthermore, this study primarily compares the Electronic Codebook (ECB) mode, Cipher Block Chaining (CBC) mode, Counter (CTR) mode, Counter with CBC-Message Authentication Code (MAC) (CCM) mode, and Galois Counter Mode (GCM).

Abel C. H. Chen

With the maturation of quantum computing technology, research has gradually shifted towards exploring its applications. Alongside the rise of artificial intelligence, various machine learning methods have been developed into quantum circuits and algorithms. Among them, Quantum Neural Networks (QNNs) can map inputs to quantum circuits through Feature Maps (FMs) and adjust parameter values via variational models, making them applicable in regression and classification tasks. However, designing a FM that is suitable for a given application problem is a significant challenge. In light of this, this study proposes an Enhanced Quantum Neural Network (EQNN), which includes an Enhanced Feature Map (EFM) designed in this research. This EFM effectively maps input variables to a value range more suitable for quantum computing, serving as the input to the variational model to improve accuracy. In the experimental environment, this study uses mobile data usage prediction as a case study, recommending appropriate rate plans based on users' mobile data usage. The proposed EQNN is compared with current mainstream QNNs, and experimental results show that the EQNN achieves higher accuracy with fewer quantum logic gates and converges to the optimal solution faster under different optimization algorithms.

Abel C. H. Chen

In recent years, numerous incidents involving the leakage of website accounts and text passwords (referred to as passwords) have raised significant concerns regarding the potential exposure of personal information. These events underscore the critical importance of both information security and password protection. While many of these breaches are attributable to vulnerabilities within website infrastructure, the strength and security of the passwords themselves also play a crucial role. Consequently, the creation of secure passwords constitutes a fundamental aspect of enhancing overall system security and protecting personal data. In response to these challenges, this study presents a secure password generation approach utilizing a cryptographically secure Pseudo-Random Number Generator (PRNG). The generator is implemented using a range of Message Authentication Code (MAC) algorithms, including the Keyed-Hash Message Authentication Code (HMAC), Cipher-based Message Authentication Code (CMAC), and KECCAK Message Authentication Code (KMAC), to produce robust random values suitable for password generation. To evaluate the proposed method, empirical assessments were conducted in accordance with the guidelines provided in the National Institute of Standards and Technology (NIST) Special Publication (SP) 800-90B. The evaluation focused on two primary aspects: entropy estimation and verification of independent and identically distributed (IID) properties. Experimental results indicate that the proposed method satisfies both entropy and IID requirements, thereby demonstrating its ability to generate passwords with a high degree of randomness and security.