Since many real-world problems are related to the satisfaction of at least one goal, several optimization techniques have been proposed in past. However, traditional computationally expensive and normally highly susceptible some characteristics such as high dimensionality, non-differentiability, non-linearity, function calculation, among others. Evolutionary algorithms bio-inspired meta-heuristics that shown flexibility, adaptability good performance when solving these sort problems. In...

In recent years, the development of selection mechanisms based on performance indicators has become an important trend in algorithmic design. Hereof, hypervolume been most popular choice. Multi-objective evolutionary algorithms (MOEAs) this indicator seem to be a good choice for dealing with many-objective optimization problems. However, their main drawback is that such are typically computationally expensive. This motivated some research which use other explored. Here, we propose efficient...

The use of the Web has increased creation digital information in an accelerated way and about multiple subjects. Text classification is widely used to filter emails, classify pages, organize results retrieved by browsers. In this paper, we propose raise problem automatic scientific texts as optimization problem, which will allow obtaining groups from a data set. evolutionary algorithms solve problems been recurrent approach. However, there are few approaches solved, where attributes be...

We propose to couple the<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mi>R</mml:mi><mml:mn fontstyle="italic">2</mml:mn></mml:math>performance measure and Particle Swarm Optimization in order handle multi/many-objective problems. Our proposal shows that through a well-designed interaction process we could maintain the metaheuristic almost inalterable id="M3"><mml:mi>R</mml:mi><mml:mn did not use neither an external archive nor Pareto dominance guide search. The...

The use of sensors to detect or measure ripening changes in fruit is a growing area interest the scientific community. Colorimeters are commonly employed for color and shade identification; however, their usage parameters rinds based on image analysis can be expensive. This article presents non-invasive low-cost optoelectronic system detecting oranges predict stage. utilises 1 W white LED as light source, an RGB photodiode array, two plastic optical fibres bundled parallel form head...

Citrus fruits are the second most important crop worldwide. One of tasks is sorting, which involves manually separating fruit based on its degree maturity, and in many cases, a task carried out by human operators. A machine vision-based citrus sorting system can replace labor work for inspection sorting. This article proposes vision implemented dedicated efficient Field Programmable Gate Array (FPGA) hardware architecture coupled with mechanical machine, where FPGA performs segmentation...

Distance transform (DT) and Voronoi diagrams (VDs) have found many applications in image analysis. Euclidean distance (EDT) can generate forms that do not vary with the rotation, because it is radially symmetrical, which a desirable characteristic applications. Recently, parallel architectures been very accessible and, particularly, GPU-based are promising due to their high performance, low power consumption affordable prices. In this paper, new algorithm proposed for computation of map...

Nowadays, in a knowledge-driven economy, the organizations, public or private, require to make an appropriate managing knowledge assets sustain competitive edge global markets governmental services. Advances Information and Communications Technologies have supported innovations Knowledge Management (KM). Since KM has been recognized as one of critical factors for obtaining organizational competitiveness. is among promising areas application Semantic Web. In this paper we propose approach...

In this paper, a smartphone-based learning monitoring system is presented. During pandemics, most of the parents are not used to simultaneously deal with their home office activities and school children. Therefore, allowing parent, teacher or tutor assign task its corresponding execution time children, could be helpful in situation. work, mobile application academic tasks child, measure time, monitor child's attention, proposed. The children users application, hosted on smartphone tablet...

To ensure appropriate quality control during marketing, accurate assessment of sugar content in citrus fruits is essential. Additionally, it important to limit intake people with medical conditions. In this study, we present a simplified and approach for measuring sucrose Valencia oranges by using low-cost optoelectronic system that designed fabricated. The proposed comprises plastic optical fiber (POF) integrated multispectral sensor obtaining the visible spectrum juices. This integration...

Abstract The color of oranges originates from carotenoids, which are natural pigments ranging yellow to red and is indicative the sugar level degree ripeness. During degreening process, fruit quality can deteriorate, manifested as insufficient ripeness (sucrose) content. Therefore, in this study, we have designed a low-cost, easy-to-use optoelectronic system measure content orange lemon juice. consists U-shaped plastic optical fiber (POF) visible multispectral sensor. device identifies...

This study aimed at estimating the macro- and micronutrient concentrations in leaves of Valencia oranges (Citrus sinensis [L.] Osbeck) through multiple regression analysis using multispectral images vegetation indices (VIs) selected stepwise method. The data were collected a commercial orchard El Barretal, Tamaulipas, Mexico. leaf samples analysed laboratory to determine N, P, K, Ca, Mg, Cu, Fe, Mn, Zn traditional chemical methods; relative chlorophyll values obtained metre (SPAD502 Plus)....

Brain–computer interfaces (BCI) have been focused on improving people’s lifestyles with motor or communication disabilities. However, the utilization of this technology has found news applications, such as increasing human capacities. Nowadays, several researchers are working probing capabilities to control robotic devices simultaneously. The design BCI is an intricate work that needs a long time its implementation. For reason, architecture and implement different types BCIs presented in...

In recent years, Evolutionary Algorithms (EAs) have been widely used to solve difficult optimization problems. However, when these problems are expensive (computationally speaking), they can remain intractable even by approaches. The EA community has effectively surrogate models approximate the response of some with aim replace it objective function calls. in order good results, is important an accurate approach. this regard, most existing approaches try whole problem (the so-called global...

In recent years, the development of hybrid approaches to solve multiobjective optimization problems has become an important trend in evolutionary computation community. Despite mathematical programming techniques with algorithms are not very popular, when both fields successfully coupled, results impressive. However, main objective this sort hybridization relays on needing several executions approach order obtain a sample Pareto front, raising this, number fitness function evaluations. use...

A practical solution to the problems caused by water, air, and soil pollution produced large volumes of waste is recycling. Plastic glass bottle recycling a but sometimes unfeasible in underdeveloped countries. In this paper, we propose high-performance real-time hardware architecture for classification, that process input image bottles generate color as output. The proposed was implemented on Spartan-6 Field Programmable Gate Array, using Hardware Description Language. system tested several...

Brain-computer interfaces are systems capable of mapping brain activity to specific commands, which enables remotely automate different types processes in hardware devices or software applications. However, the development brain-computer has been limited by several factors that affect their performance, such as characterization events signals and excessive processing load generated high volume data. In this paper, we propose a method based on computational intelligence techniques handle...