Search

Image segmentation is a fundamental process in image processing, aiming to transform the image into a more comprehensible or simplified representation. This process groups pixels under common characteristics, facilitating the unique identification of regions or elements of interest. The quality of segmentation is crucial as it significantly influences the subsequent stages of image processing. Image segmentation plays a vital role in various advanced applications, including computer vision and the analysis of medical, topographical, and astronomical images. Given that there is no universal segmentation method guaranteeing optimal performance for all cases, selecting an appropriate technique for a specific type of image or application represents a complex and demanding challenge. In this work, we propose the use of Multi-Objective Evolutionary Algorithms (MOEAs) as a training tool that integrates operations representative of the usual techniques and strategies in image segmentation. This allows for the generation of operation sequences adapted to specific applications or types of images. The objective functions used to guide the evolutionary process are the maximization of sensitivity (TPR) and specificity (TNR), fundamental components of ROC analysis. Experiments were conducted with multiple images sharing common characteristics from image databases, specifically: i ) benign and malignant melanoma images, ii ) ophthalmoscopic retinal images, and iii ) binary cell form images. We compared the segmentation generated by our proposed algorithm with the ideal segmentation. The results are quite promising and demonstrate the feasibility of using MOEAs to generate sequences of segmentation operations valid for specific applications.

Internet energy consumption has increased rapidly, and energy conservation has become a significant issue that requires focused research efforts. The most promising solution is to identify the minimum power subsets within the network and shut down unnecessary network devices and links to satisfy traffic loads. Due to their distributed network control, implementing a centralized and coordinated strategy in traditional networks is challenging. Software-Defined Networking (SDN) is an emerging technology with dynamic, manageable, cost-effective, and adaptable solutions. SDN decouples network control and forwarding functions, allowing network control to be directly programmable, centralizing control with a global network view to manage power states. Nevertheless, it is crucial to develop efficient algorithms that leverage the centralized control of SDN to achieve maximum energy savings and consider peak traffic times. Traffic demand usually cannot be satisfied, even when all network devices are active. This work jointly addresses the routing of traffic flows and the assignment of SDN devices to these flows, called the Routing and Device Assignment (RDA) problem. It simultaneously seeks to minimize the network’s energy consumption and blocked traffic flows. For this approach, we develop an exact solution based on Mixed-Integer Linear Programming (MILP) as well as a metaheuristic based on a Genetic Algorithm (GA) that seeks to optimize both criteria by routing flows efficiently and suspending devices not used by the flows. Conducted simulations on traffic environment scenarios show up to 34% savings in overall energy consumption for the MILP and 33% savings achieved by the GA. These values are better than those obtained using competitive state-of-the-art strategies.

This paper addresses serialized approaches of the routing, modulation level, and spectrum assignment (RMLSA) problem in elastic optical networks, using multiple sequential sub-sets of requests, under Integer Linear Programming (ILP). The literature has reported two-stage serial optimization methods referred to as RML+SA, which retain computational efficiency when the problem grows, compared to the classical one-stage RMLSA optimization approach. However, there still remain numerous issues in terms of the spectrum used that can be improved when compared to the RMLSA solution. Consequently, this paper proposes RML+SA solutions considering multiple sequential sub-sets of requests, split traffic flow, as well as path-oriented and link-oriented routing models. Simulation results on different test scenarios determine that: (a) the multiple sequential sub-sets of request-based models improve computation time without worsening the spectrum usage when compared to just one set of requests optimization approaches, (b) divisible traffic flow approaches show promise in cases where the number of request sub-sets is low compared to the non-divisible counterpart, and (c) path-oriented routing succeeds in improving the used spectrum by increasing the number of candidate routes compared to link-oriented routing.

This paper presents a data set with information on meteorological data and electricity consumption in the department of Alto Paraná, Paraguay. The meteorological data were registered every three hours at the Aeropuerto Guarani, Department of Alto Paraná, which belongs to the Dirección Nacional de Aeronáutica Civil of Paraguay. The final data consists of a total of 22.445 records of temperature, relative humidity, wind speed and atmospheric pressure. On the other hand, the electrical energy consumption data set contains a total of 1.848.947 records, all of them coming from the one hundred and fifteen feeders located throughout the Alto Paraná region of Paraguay. Electrical energy consumption data was provided by Administración Nacional de Electricidad (ANDE). The analysis of this data can yield insights regarding the energy consumption in the area.

Protein structure prediction is one of the most important problems in Computational Biology; and consists of determining the 3D structure of a protein given its amino acid sequence. A key component that has allowed considerable improvements in recent decades is the prediction of contacts in a protein, since it provides fundamental information about its three-dimensional structure. In the 13th edition of the CASP (Critical Assessment of protein Structure Prediction), a notable progress has been evidenced for both problems with the use of deep learning algorithms. For the contact prediction category, the best methods in CASP13 achieved an average precision of 70%. In the present work, the performance of these methods is analyzed using a larger data set, with 483 proteins from four families according to the structural classication of the SCOP database (Structural Classication of Proteins). The selected methods were evaluated using the CASP metrics, and their results indicate an average contact prediction precision greater than 90%. SPOT-Contact was the method with the best overall performance, and one of the methods with the best performance for each SCOP class. The set of proteins used for the experiments and the implementations made for the analysis are publicly available.

This research is conducted to analyze the shopping basket by using association rules in the retail area, more specically in a home goods sales company such as appliances, computer items, furniture, and sporting goods, among others. With the rise of globalization and the advancement of technology, retail companies are constantly struggling to maintain and raise their prots, as well ordering the products and services that the customer wants to obtain. In this sense, they need a new approach to identify different objectives in order to be more competitive and successful, looking for new decision-making strategies. To achieve this goal, and to obtain clear and efficient strategies, by providing large amounts of data collected in business transactions, the need arises to intelligently analyze such data in order to extract useful knowledge that will support decision-making and, an understanding of the association patterns that occur in sales-customer behavior. Predicting which product will make the most prot, products that are sold together, this type of information is of great value for storing products in inventory. Knowing when a product is out of fashion can support inventory management effectively. In this sense, this work presents the rules of association of products obtained by analyzing the data with the FPGrowth algorithm using the Orange tool.

This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR).

In binary image segmentation, the choice of the order of the operation sequence may yield to suboptimal results. In this work, we propose to tackle the associated optimization problem via multi-objective approach. Given the original image, in combination with a list of morphological, logical and stacking operations, the goal is to obtain the ideal output at the lowest computational cost. We compared the performance of two Multi-objective Evolutionary Algorithms (MOEAs): the Non-dominated Sorting Genetic Algorithm (NSGA-II) and the Strength Pareto Evolutionary Algorithm 2 (SPEA2). NSGA-II has better results in most cases, but the difference does not reach statistical significance. The results show that the similarity measure and the computational cost are objective functions in conflict, while the number of operations available and type of input images impact on the quality of Pareto set.

In feature selection, redundancy is one of the major concerns since the removal of redundancy in data is connected with dimensionality reduction. Despite the evidence of such a connection, few works present theoretical studies regarding redundancy. In this work, we analyze the effect of redundant features on the performance of classification models. We can summarize the contribution of this work as follows: (i) develop a theoretical framework to analyze feature construction and selection, (ii) show that certain properly defined features are redundant but make the data linearly separable, and (iii) propose a formal criterion to validate feature construction methods. The results of experiments suggest that a large number of redundant features can reduce the classification error. The results imply that it is not enough to analyze features solely using criteria that measure the amount of information provided by such features.

Skin dermoscopy images frequently lack contrast caused by varying light conditions. Indeed, often low contrast is seen in dermoscopy images of melanoma, causing the lesion to blend in with the surrounding skin. In addition, the low contrast prevents certain details from being seen in the image. Therefore, it is necessary to design an approach that can enhance the contrast and details of dermoscopic images. In this work, we propose a multi-scale morphological approach to reduce the impacts of lack of contrast and to enhance the quality of the images. By top-hat reconstruction, the local bright and dark features are extracted from the image. The local bright features are added and the dark features are subtracted from the image. In this way, images with higher contrast and detail are obtained. The proposed approach was applied to a database of 236 color images of benign and malignant melanocytic lesions. The results show that the multi-scale morphological approach by reconstruction is a competitive algorithm since it achieved a very satisfactory level of contrast enhancement and detail enhancement in dermoscopy images.

The superformula generates curves called Gielis curves, which depend on a small number of input parameters. Recovering parameters generating a curve that adapts to a set of points is a non-trivial task, thus methods to accomplish it are still being developed. These curves can represent a great variety of forms, such as living organisms, objects and geometric shapes. In this work we propose a method that uses a genetic algorithm to minimize a combination of three objectives functions: Euclidean distances from the sample points to the curve, from the curve to the sample points and the curve length. Curves generated with the parameters obtained by this method adjust better to real curves in relation to the state of art, according to observational and numeric comparisons.

Discrete entropy is used to measure the content of an image, where a higher value indicates an image with richer details. Infrared images are capable of revealing important hidden targets. The disadvantage of this type of image is that their low contrast and level of detail are not consistent with human visual perception. These problems can be caused by variations of the environment or by limitations of the cameras that capture the images. In this work we propose a method that improves the details of infrared images, increasing their entropy, preserving their natural appearance, and enhancing contrast. The proposed method extracts multiple features of brightness and darkness from the infrared image. This is done by means of the multiscale top-hat transform. To improve the infrared image, multiple scales are added to the bright areas and multiple areas of darkness are subtracted. The method was tested with 450 infrared thermal images from a public database. Evaluation of the experimental results shows that the proposed method improves the details of the image by increasing entropy, also preserving natural appearance and enhancing the contrast of infrared thermal images.