752 publications from this institution
No abstract is provided for this article.
No abstract is provided for this article.
Medical image registration represents a pivotal element in the field of disease image analysis, acting as the essential precursor for a multitude of sophisticated analytical tasks. In recent years, traditional methodologies have encountered significant challenges in meeting the evolving demands of clinical practice. In contrast, deep learning-based strategies have emerged as powerful alternatives, showcasing their ability to facilitate more rapid and accurate registration processes, thereby exerting a profound impact on clinical applications. Within the specialized domain of medical imaging, the intricate level of expertise required for domain knowledge imposes rigorous standards on annotators, which in turn leads to increased annotation costs. As a result, the efficacy of supervised learning approaches compared to unsupervised learning methodologies can exhibit substantial variability in real-world applications. This paper systematically utilizes a diverse array of medical imaging datasets to rigorously assess the performance outcomes of both supervised and unsupervised learning techniques, specifically in relation to their practical applications in the medical imaging landscape.
Nature-inspired algorithms are among the most powerful algorithms for optimization. This paper intends to provide a detailed description of a new Firefly Algorithm (FA) for multimodal optimization applications. We will compare the proposed firefly algorithm with other metaheuristic algorithms such as particle swarm optimization (PSO). Simulations and results indicate that the proposed firefly algorithm is superior to existing metaheuristic algorithms. Finally we will discuss its applications and implications for further research.
The stability of discrete time-varying bilinear systems is studied. The control u(t) in the bilinear systems is considered as output feedback functions with time delay, i.e. u(t)=f(y(t), y(t-1),. . .,y(t-r+1)), which is an important case and is absent in the literature. Also, the authors assumed that the feedback function f is of larger classes than the classes given by current literature. The sufficient conditions derived in theorems in the paper depend only on the coefficient matrices of the bilinear systems, so that these results are convenient to check and to apply in engineering problems.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Bat algorithm (BA) is a recent metaheuristic optimization algorithm proposed by Yang. In the present study, we have introduced chaos into BA so as to increase its global search mobility for robust global optimization. Detailed studies have been carried out on benchmark problems with different chaotic maps. Here, four different variants of chaotic BA are introduced and thirteen different chaotic maps are utilized for validating each of these four variants. The results show that some variants of chaotic BAs can clearly outperform the standard BA for these benchmarks.
No abstract is provided for this article.
Nature-inspired metaheuristic algorithms have become powerful and popular in computational intelligence and many applications. There are some important developments in recent years, and this special issue aims to provide a timely review of such developments, including ant colony optimization, bat algorithm, cuckoo search, particle swarm optimization, genetic algorithms, support vector machine, neural networks, and others. In addition, these algorithms have been applied in a diverse range of applications, and some of these latest applications are also summarized here. Computational intelligence and metaheuristic algorithms have become increasingly popular in computer science, artificial intelligence, machine learning, engineering design, data mining, image processing, and data-intensive applications. Most algorithms in computational intelligence and optimization are based on swarm intelligence (SI) [1, 2]. For example, both particle swarm optimization [1] and cuckoo search [3] have attracted much attention in science and engineering. They both can effectively deal with continuous problems [2] and combinatorial problems [4]. These algorithms are very different from the conventional evolutionary algorithms such as genetic algorithms and simulated annealing [5, 6] and other heuristics [7]. Many new optimization algorithms are based on the so-called swarm intelligence (SI) with diverse characteristics in mimicking natural systems [1, 2]. Consequently, different algorithms may have different features and thus may behave differently, even with different efficiencies. However, It still lacks in-depth understanding why these algorithms work well and exactly under what conditions, though there were some good studies that may provide insight into algorithms [2, 8]. This special issue focuses on the recent developments of SI-based metaheuristic algorithms and their diverse applications as well as theoretical studies. Therefore, this paper is organized as follows. Section 2 provides an introduction and comparison of the so-called infinite monkey theorem and metaheuristics, followed by the brief review of computational intelligence and metaheuristics in Section 3. Then, Section 4 touches briefly the state-of-the-art developments, and finally, Section 5 provides some open problems about some key issues concerning computational intelligence and metaheuristics.
This technical note reports the results of a set of tests of software toolboxes for optimisation and uncertainty evaluation using finite element models.
No abstract is provided for this article.
Although K-means clustering algorithm is simple and popular, it has a fundamental drawback of falling into local optima that depend on the randomly generated initial centroid values. Optimization algorithms are well known for their ability to guide iterative computation in searching for global optima. They also speed up the clustering process by achieving early convergence. Contemporary optimization algorithms inspired by biology, including the Wolf, Firefly, Cuckoo, Bat and Ant algorithms, simulate swarm behavior in which peers are attracted while steering towards a global objective. It is found that these bio-inspired algorithms have their own virtues and could be logically integrated into K-means clustering to avoid local optima during iteration to convergence. In this paper, the constructs of the integration of bio-inspired optimization methods into K-means clustering are presented. The extended versions of clustering algorithms integrated with bio-inspired optimization methods produce improved results. Experiments are conducted to validate the benefits of the proposed approach.
Percussive drilling is gaining interest for both shallow and deep applications due to its potential for higher drilling rates in hard rocks. Therefore, for efficient rock breaking, the development of advanced percussive drilling simulation tools has the potential to be transformative. Such tools must accurately capture the rock’s response to enable an effective analysis of the fragmentation process. Traditional continuum numerical methods, such as the finite element method (FEM), do not simulate discrete cracks or the contact interaction between rock fragments. The finite-discrete element method (FDEM) is a three-dimensional hybrid method that combines FEM with the discrete element method (DEM) that addresses these limitations. New FDEM simulation results of impacts on Kuru Grey granite show good agreement with published experimental data. The interpretation focuses on two significant processes in percussive drilling: crack propagation and chipping generation. FDEM successfully simulates the evolution of cracks, including radial, side, and inclined cracks, as well as crushed and cracked zones. The simulation also reproduces the coalescence of adjacent craters to generate more chippings. Additionally, the stress state, velocity field and discrete fractures simulated by FDEM provide detailed insights into the different fracture patterns for Kuru Grey granite, enhancing understanding of the fundamental underlying mechanisms.
