Cyberbullying, which manifests in various forms, is a growing challenge on social media, mainly when it involves threats of violence through images, especially those featuring weapons. This study introduces computational framework to identify such content using convolutional neural networks weapon-related images. By integrating artificial intelligence techniques with image analysis, our model detects visual patterns associated violent threats, creating safer digital environments. The...

In this paper, an improved harmony search (ImHS) algorithm is presented. HS a simple but efficient metaheuristic method explored in recent literature, that simulates the process of musical improvisation. Two modifications for parameter tuning are proposed to enhance performance solution constrained numerical optimization problems, maintaining simplicity its original design. Metaheuristics methods solving and based two processes: exploration (diversification) exploitation (intensification)....

There are problems that difficult to solve through mathematical programming or by classical methods. These called hard due their high complexity dimension. On the other hand, mataheuristics intends seek a better solution problem. The Improvement Harmony Search algorithm is proposed under modification of bandwidth parameter increasing quality exploitation solutions. That why within state art, mentioned several versions harmonic search. art supports fact belongs category those who make...

Today, there is a great necessity for security systems in banks, laboratories, etc.; specially those that have restricted areas or expensive equipment. Most of the time people use magnetic cards similar technologies. However, these kinds devices can be vulnerable, because might used by intruders case misplaced device. More advanced technologies iris voice detection, potentially increasing level against intruders. This work focused on latter group. paper proposes hybrid method, speech...

In this paper we present a fuzzy reasoning model and designed system for Recognition of Facial Expressions, which can measure recognize the intensity basic or non-prototypical emotions. The proposed operates with encoded facial deformations described in terms either Ekmans Action Units (AUs) Animation Parameters (FAPs) MPEG-4 standard provides recognition expression using knowledge base implemented on acquisition ontology editor Protege. It allows modeling features obtained from geometric...

Resumen.En este trabajo se presenta la síntesis de un mecanismo cuatro barras para seguimiento una trayectoria lineal seis puntos.Para resolver

Memetic algorithms (MA), explored in recent literature, are hybrid metaheuristics formed by the synergistic combination of a population-based global search technique with one or more local algorithms, which turn can be exact stochastic methods. Different versions MAs have been developed, and although their use was focused originally on combinatorial optimization, nowadays there memetic developments to solve wide selection numerical type problems: without constraints, mono multi objective,...

The need for content-based image retrieval is staggering given the information explosion. advantage of systems their effectiveness to find relevant images when searching in large collections. We believe that an improved technique can be achieved by combining techniques. So, we approach problem two stages: organization and phase, employing different techniques each. First phase classifies based on a preliminary feature extraction progress. This gathers set statistical parameters. After...

This paper address the multilevel image segmentation by merging Gaussian mixtures models (GMM) and Differential Evolution (DE) with constraints handling. Since estimation of parameters associated to GMM is a complex task, DE used estimate them. Afterwards, these are for obtaining optimal thresholds achieve segmentation. The tests include use 83 images parasite named Trypanosoma. experiments were done using original equalized images. results show better performance latter. We conclude that...

In this paper we propose a vision algorithm to object recognition during mobile robot's journey in controlled environment. Furthermore, another was used drawing the path of robot, which is based on evaluation provide results. The first uses color processing techniques achieve an image thresholding and Harris corner detector recognize objects scene. A graphical user interface has been developed perform analysis path-drawing real time. These algorithms, working together, provided 97% as rate.

Computer vision imply several morphological and mathematical process. Image compression requires methods which involves algorithms image processing techniques. AHBE system (Algorithm of Huffman combined with Bit Extraction method) provides a novel method to when high quantity light is present. Preprocessing images useful in robotics applications avoid noised data providing relevant information normalized vector data. Hoffman algorithm greedy technique that improves bright contrast for...

Practitioner engineers in both academic and industrial areas, are often faced with the challenge of identifying model a given system or process order to setup controller extract some useful information. Among existing identification algorithms, those being numerically simple stable more attractive for practitioners. This paper deals state-space models, i.e., state space matrices A, B, C D multivariable dynamic systems directly from test data (data-driven). In guarantee numerical reliability...

When it is necessary to analyze a personpsilas face, whether for recognizing pathologies, emotions, or states of mind, becomes obtain maximum information the facial characteristics that especially reflect these aspects. These are principally, mouth, eyes and eyebrows. The start analytic process, once face feature be analyzed have been divided into segments, consists in applying an algorithm said detection its edges. most used edges algorithms are; SUSAN, Canny, Sobel, Roberts, among others....

The use of virtual tools in a university level results series benefits. A world allows the students to interact with modern technology, learn different tools, etc. This project was developed be used Interaction Computer-Human and Computer Graphics courses, due manipulations kind, combination 3D graphics sound, at Bachelor Engineering Autonomous University Tlaxcala. Specifically, this paper focuses on behavior sound combining: "Navigation, objects sound", worlds. Our building environment...

Stellar classification inside astrophysics, is not a trivial task, because huge data amount of stellar objects in the sky. Telescopes earth or atmosphere allows to provide this about bodies. Data availability overwhelming some cases and automatized processes can fast despite redundancy improve relevance sets. Nature data, features may be irrelevant pulsar classification, star, constellation, galaxy cluster nebula. samples must have noise elimination. Electromagnetic spectre considered order...

Visual Information retrieval is an area where the analysis and recognition helpful to generate obtain data from image samples.In this research samples are obtained of electrophoresis that captures protein profiles in tissues.The provides a sample proteins computed know their molecular weight.The digital processing takes images wavelet transform applied can be fractioned emphasize weights at first sight not identified.Therefore, with transform, it possible compute corresponding...