Optimization of Reverse Engineering Data for Regeneration of Triangular Mesh

Surface reconstruction of 3D reverse engineering data through the application of a triangulated mesh is a popular method. This thesis proposes a new simple genetic algorithm, an artificial intelligence method, to optimize triangular mesh generation which reduces the number of data points required to depict an object without sacrificing the details and accuracy.

Optimization of Reverse Engineering Data for Regeneration of Triangular Mesh

Surface reconstruction of 3D reverse engineering data through the application of a triangulated mesh is a popular method. This thesis proposes a new simple genetic algorithm, an artificial intelligence method, to optimize triangular mesh generation which reduces the number of data points required to depict an object without sacrificing the details and accuracy.

A Multiple Sieve Approach Based on Artificial Intelligent Techniques and Correlation Power Analysis

Side-channel analysis achieves key recovery by analyzing physical signals generated during the operation of cryptographic devices. Power consumption is one kind of these signals and can be regarded as a multimedia form. In recent years, many artificial intelligence technologies have been combined with classical side-channel analysis methods to improve the efficiency and accuracy. A simple genetic algorithm was employed in Correlation Power Analysis (CPA) when apply to cryptographic algorithms implemented in parallel. However, premature convergence caused failure in recovering the whole key, especially when plenty of large S-boxes were employed in the target primitive, such as in the case of AES. In this article, we investigate the reason of premature convergence and propose a Multiple Sieve Method (MS-CPA), which overcomes this problem and reduces the number of traces required in correlation power analysis. Our method can be adjusted to combine with key enumeration algorithms and further improves the efficiency. Simulation experimental results depict that our method reduces the required number of traces by and , compared to classic CPA and the Simple-Genetic-Algorithm-based CPA (SGA-CPA), respectively, when the success rate is fixed to . Real experiments performed on SAKURA-G confirm that the number of traces required for recovering the correct key in our method is almost equal to the minimum number that makes the correlation coefficients of correct keys stand out from the wrong ones and is much less than the numbers of traces required in CPA and SGA-CPA. When combining with key enumeration algorithms, our method has better performance. For the traces number being 200 (noise standard deviation ), the attacks success rate of our method is , which is much higher than the classic CPA with key enumeration ( success rate). Moreover, we adjust our method to work on that DPA contest v1 dataset and achieve a better result (40.04 traces) than the winning proposal (42.42 traces).

A Multiple Mitosis Genetic Algorithm

<p>Genetic algorithm is a well-known metaheuristic method to solve optimization problem mimic the natural process of cell reproduction. Having great advantages on solving optimization problem makes this method popular among researchers to improve the performance of simple Genetic Algorithm and apply it in many areas. However, Genetic Algorithm has its own weakness of less diversity which cause premature convergence where the potential answer trapped in its local optimum. This paper proposed a method Multiple Mitosis Genetic Algorithm to improve the performance of simple Genetic Algorithm to promote high diversity of high-quality individuals by having 3 different steps which are set multiplying factor before the crossover process, conduct multiple mitosis crossover and introduce mini loop in each generation. Results shows that the percentage of great quality individuals improve until 90 percent of total population to find the global optimum.</p>

Realisation of Optimal Parameters of PEM Fuel Cell Using Simple Genetic Algorithm (SGA) and Simulink Modeling

A methodology to solve parameter extraction of PEM Fuel cell by an optimisation process using simple genetic algorithm and Simulink is proposed. The results are validated using the traditional curve fitting method where in the initial values are compared with the existing curve for its convergence and exactitude. In this work the modelling and extensive simulation of the PEM Fuel cell has been undertaken using MATLAB-SIMULINK. The steps have been elaborated further in order to explain the incorporation and efficacy of Genetic algorithm codes in FC model. Simple Genetic Algorithm (SGA) is a reliable methodology towards optimisation of fuel cell parameters. It is inferred from the simulated results that the process is precise and absolute error is generated to showcase the subtleness of the algorithm. The proposed model can be utilised to study and develop steady state performances of PEMFC stacks

REDBLUE: UM CLUSTER PARA SIMULAÇÕES COMPUTACIONAIS

Computational simulations are widely used in scientific research. However, they may require a lot of computational resources. This can be solved by distributing the application between multiple computers. In this way, this work presents the RedBlue platform that allows users with less knowledge in distributed programming to adopt this strategy in computer labs. The platform uses common computers as clusters. To demonstrate the feasibility of the platform, tests were performed with 60 machines, and it was possible to reduce the execution time by 98% for a neural network and 99.3% for a simple genetic algorithm.