Breast cancer is the most commonly diagnosed cancer among women worldwide, with early detection playing an essential role in improving survival rates. Detection of breast abnormalities at an early stage is best performed using mammography. This paper presents a new approach integrating advanced preprocessing techniques based on Cellular Automaton. It was applied on the Mini-MIAS dataset, and its performance led to improvements in the preprocessing and segmentation phases. The inclusion of Cellular Automaton and Fuzzy Logic facilitated more precise classification of pixels associated with regions of interest. The experimental results show that the proposed method improves segmentation performance, achieving 99.56% accuracy and producing segmentation results that closely align with the ground truth.

Breast cancer is the most common type of cancer found in women. One of the most effiective methods for early identification of breast cancer is the mammogram. Numerous computer-aided systems for detecting breast cancer from mammograms have been introduced. In this paper, we present a new way for combining Cellular Automata with Fuzzy Logic, resulting in a so-called Fuzzy Cellular Automaton. The results obtained by testing our proposed approach on the mini-MIAS dataset are close to the ground truth, which is highly encouraging. The choice of using fuzzy logic provides a more flexible technique for categorizing the pixels of interest. The suggested method produces promising results for segmenting the mass region in mammograms with an accuracy of 98,66%, according to the experimental results.

Between 2015 and 2020, 7.8 million women were diagnosed with breast cancer. If the cancer is discovered early, it can be completely cured. Computer-aided detection and diagnosis systems are a helpful tool. We propose such a system: after pre-processing the mammography, the region of interest is identified using an unsupervised manner. Textural features are extracted from the Gray-Level Co-occurrence Matrix and used with the Linear Discriminant Analysis classifier, obtaining a diagnosis: benign or malignant. The proposed system is tested on the Mini-MIAS dataset, reaching an accuracy score of 95% and a precision and specificity of 100%.

Breast cancer causes numerous deaths worldwide; yet the numbers have decreased in the past years as a result of computer-aided diagnosis and proper treatment. The current paper is addressed to the base of such diagnosis system: pre-processing and segmentation. After a robust pre-processing, an unsupervised version of GrowCut is applied to define the location of the abnormality. We present a method to automatically define the foreground seeds used in GrowCut. For experiments, mammograms from mini-MIAS dataset are used and a precision of 93.63% for the foreground seeds masks is achieved, which leads to promising segmentation results.

The most common cancer type amongst women is the breast cancer with a large number of cases reported each year, many of them diagnosed in an advanced phase. In this paper our scope is to create a base for a support system that helps detecting breast cancer in an early stage. After defining the region of interest (ROI) and segmenting the result image (using k-means algorithm), Gray-Level Run-Length Matrices (GLRLM) features are extracted from both the ROI and from the segmented image in four directions (horizontal, vertical, first- and second diagonals). To reduce the dimensionality of the input data composed from the GLRLM features of the ROI and its segmentation for different combination of directions (removing redundant information, selecting just the most essential ones) two methods are used: Principal Component Analysis (PCA), and genetic algorithm (GA) feature selection. For classification, two methods are used and compared, namely Decision Trees (DT) and Random Forest (RF). For experiments we used the Mammographic Image Analysis Society (MIAS) dataset to train and to test the classifiers. The best performance is obtained for GLRLM features calculated for directions 45◦, and 90◦, using PCA feature selection and RF with a 100% training accuracy and 70% test accuracy.

Breast cancer is one of the most common types of cancer amongst women, but it is also one of the most frequently cured cancers. Because of this, early detection is crucial, and this can be done through mammography screening. With the increasing need of an automated interpretation system, a lot of methods have been proposed so far and, regardless of the algorithms, they all share a step: segmentation. That is, identifying the region of interest in order to further analyze and classify it either as benign or malignant. However, due to the different types of mammary tissues, mammography segmentation can prove to be a difficult task. Various techniques of mammography segmentation have been proposed so far. Yet, since obtaining the ground-truth for mam-mographic images might be problematic, recent literature leans towards unsupervised techniques. In this paper we present a segmentation approach based on the GrowCut algorithm. The original method starts with a number of seed points inside and outside the region of interest, selected by a human expert, and iterates over the pixels multiple times, until it reaches a stable state where all the pixels have been assigned to a class. Our proposal aims to reduce the human intervention by eliminating the need of selecting initial background seeds and, also, to reduce the computational time by limiting the process of parsing the entire image to a small, fixed number of iterations. The proposed approach was compared to the original method, using three variants: (1) automatically constructing the initial background seeds surrounding the foreground ones; (2) using mammograms’s background as initial background seeds; (3) not using initial background seeds. Experimental results obtained for the Mini-MIAS dataset show that, for the variations that use background seeds outside the breast and that do not use any background seeds, our approach yields much better results than the original method.

Edge detection is an important component in many computer vision tasks since edges convey information about the objects in an image. This paper presents a comparative analysis of the proposed edge detector with respect to one of the state-of-the-art methods, the Canny edge detector. Our edge detection model involves the supervised optimization of a cellular automaton rule with particle swarm optimization. Using this scheme we obtain transferable rules that can be applied on multiple images with similar properties. We test the two methods on clean and noisy images and the proposed method outperforms Canny on average on our data set containing a variety of edges.

Extensive research has been performed in image processing to find the best edge detector, from the gradient-based operators to evolved Cellular Automata (CA). Some of these detectors have weak points, such as disconnected edges, the incapacity of detecting the branching edges or the need of a ground truth that is not always available. To overcome these issues, we propose a CA-based edge detector adapted to the particularities of the image. The adaption means to identify the best CA rule, which is an optimization problem solved by a Genetic Algorithm (GA). The GA requires a fitness function and we propose to use an unsupervised fitness based on edge dissimilarity. The performed numerical experiments are meant to evaluate the proposed approach and to emphasize that some of the weak points of a well-known detector (Canny) can be overcome by our method.

Complex networks are data structures with great importance in representing real world interactions which surrounds us. While their structures might look chaotic at a first glance, the focus of most on-going studies in this field is in understanding how their topological properties influence the dynamics of a complex network’s structure in order to prove a possible order in the apparent chaos that they display. Based on the evidence found in our previous studies, which revealed a significant correlation between the existence of articulation points and meso-level components such as network motifs, this paper tries to extend this study by presenting analytical research between a consistent set of micro-level topological properties from Graph and Complex Networks Theory and the appearance of the motifs. The purpose of this study is to use network properties to provide a better understanding of how and why network motifs appear, a further step toward the goal of proposing a generator model for networks with specific concentrations of motifs.

The discovery and analysis of communities in networks is a topic of high interest in sociology, biology and computer science. Complex networks in nature and society range from the immune system and the brain to social, communication and transport networks. The key issue in the development of algorithms able to automatically detect communities in complex networks refers to a meaningful quality evaluation of a community structure. Given a certain grouping of nodes into communities, a good measure is needed to evaluate the quality of the community structure based on the definition that a strong community has dense intra-connections and sparse outside-community links. We propose a new fitness function for the assessment of community structures quality which is based on the number of nodes and their links inside a community versus the community size further reported to the size of the network. A novel aspect of the proposed fitness function refers to considering the way nodes connect to other nodes inside the same community making this second level of links contribute to the strength of the community. The introduced fitness function is tested inside a collaborative evolutionary algorithm specifically designed for the problem of community detection in complex networks. Computational experiments are performed for several real-world complex networks which have a known real community structure. This allows the direct verification of the quality of evolved communities via the proposed fitness function emphasizing extremely promising numerical results.

Resource-Constrained Project Scheduling is an NP-hard problem very attractive for researchers due to its large area of applications. This paper concentrates on the evolutionary approaches to Resource-Constrained Project Scheduling based on permutation encoded individuals. A new recombination operator is proposed and a comparative analysis of several recombination operators is presented based on computational experiments for several project instances. Numerical results emphasize a good performance of the proposed crossover scheme which takes into account information from the global best individual besides the genetic material from parents.

The discovery of community structures in complex networks is a challenging problem intensively studied in recent years. This paper investigates the performance of evolutionary algorithms for the task of detecting overlapping communities. This task is of great importance as the membership of a node to more than one group is naturally occuring in many real-world networks from fields such as sociology, biology and computer science. One of the major challenges in designing evolutionary algorithms for overlapping community detection is the efficient assessment of the quality of any particular division of nodes into groups. We test four different fitness functions in an evolutionary approach to the problem using the same chromosome representation and search scheme. The performance of the resulting algorithms is tested in a set of computational experiments for some real-world networks. We show that none of the fitness functions used are able to guide the search process towards good partitions based on a measure of the normalized mutual information.

A Geometric Collaborative Evolutionary (GCE) model is presented and studied. An asynchronous search process is facilitated through a gradual propagation of the fittest individuals' genetic material into the population. Recombination is guided by the geometrical structure of the population. The GCE model specifies three strategies for recombination corresponding to three subpopulations (societies of agents). Each individual in the population acts as an autonomous agent with the goal of optimizing its fitness being able to communicate and select a mate for recombination. Complex dynamics in the proposed system are investigated against the probability of dominance between agent societies. A significant emergent pattern and corresponding transition interval are emphasized in several experiments. Percolation-like behavior is also detected, suggesting the complete dominance of one agent society over the entire population under certain conditions. Furthermore, numerical results indicate a good performance of the proposed evolutionary asynchronous search model.

One of the most important decisions that influence the performance of evolutionary algorithms is the way individuals are selected for recombination. Two new selection operators that explore more promising regions of the search space are proposed in order to avoid the search becoming trapped into a local optimum. The first operator is a variant of the proportional selection and the second a variant of the tournament selection - both of them using information about the best ancestor of each individual within the population. In order to prove the efficiency of the proposed operators, several instances of the travelling salesman problem are considered. Experimental results show an acceleration of the search process when using the proposed selection schemes, compared to the most popular existing selection operators. While the first operator performs better only in the first stages of the algorithm, the second outperforms the other selection operators in all its stages.

A new evolutionary algorithm for problems having potential solutions encoded as permutations is proposed. The introduced algorithm is based on the collaboration between individuals that exchange information in order to accelerate the search process. Numerical experiments prove the efficiency of the proposed technique. Categories and Subject Descriptors

Modern companies dynamically change their departmental structure, type of activities and staff. Database management systems of such companies require adequate design and administration solutions. In such a system the initial estimations and predictions for performance characteristics are mandatory but not sufficient. The performance problems of data reallocation and query optimization in distributed database systems done by means of mobile agents and evolutionary algorithms are considered. These problems still present a challenge because of the dynamic changes in data amount, number of components and architectural complexity of nowadays system topologies. The distributed system is modeled as a graph structure on which is defined a dynamic cost vector. The cost vector remains consistent, relevant, by use of mobile agents performing cost statistics and vector updates. An evolutionary algorithm is proposed to solve this NP-complete problem. Experimental results prove the efficiency of the proposed technique