Darwin Alulema

Signature Recognition: Human Performance Analysis vs. Automatic System and Feature Extraction via Crowdsourcing

This paper presents discriminative features as a result of comparing the authenticity of signatures, between standardized responses from a group of people with no experience in signature recognition through a manual system based on crowdsourcing, as well as the performance of the human vs. an automatic system with two classifiers. For which an experimental protocol is implemented through interfaces programmed in HTML and published on the platform Amazon Mechanical Turk. This platform allows obtaining responses from 500 workers on the veracity of signatures shown to them. By normalizing the responses, several general features which serve for the extraction of discriminative features are obtained in signature recognition. The comparison analysis in terms of False Acceptance Rate and False Rejection Rate founds the presented features, which will serve as a future study of performance analysis in the implementation of automatic and semiautomatic signature recognition systems that will support financial, legal and security applications.

Development and implementation of an application that translates the alphabet and the numbers from 1 to 10 from sign language to text to help hearing impaired by Android mobile devices

This article is based on the design and implementation of an application for mobile devices with Android operating system, which allows the interrelation of people with hearing impairment. The application is able to learn and recognize a letter or number sign language with no movement by applying artificial neural networks. The application indicates whether the captured image is part of the letter to be recognized, if the image does not belong to the corresponding letter, the application displays an error message.

Analysis of attack and protection systems in Wi-Fi wireless networks under the Linux operating system

This article describes the preparation of a Wi-Fi wireless network in production system, with intrusion detection systems Snort and Kismet; for subsequent evaluation under attack. Through Penetration Testing with Backtrack 5 R3 using Fern WiFi Cracker and Ettercap to monitor response reaction of IDSs. Once the attacks are completed, the results are analyzed, in terms of the captured traffic by the system using Wireshark, and the attack description, in order to determine the response characteristics of Snort and Kismet. In addition, minimum safety recommendations are deducted, targeting both network administrators and clients; to avoid problems with the attackers.

Design and construction of an anthropomorphic robotic arm of seven degrees of freedom with kinematic and dynamic analysis based on genetic algorithms

This article describes the design and construction of an anthropomorphic robotic arm capable of performing activities difficult or avoid collisions within your workspace, which is controlled by a computer program where the user indicates the target position and orientation to be achieved by the robot TCP. The software programmed in Matlab is developed, it calculates the angular displacements of the actuators using Genetic Algorithms (GA) considered as restricting the minimum and maximum angular displacement of each motor. The program has a graphical interface that displays a 3D robot animation, displays graphs of torque, velocity and acceleration at each joint also allows you to generate trajectories based on programmed points. The robot is connected to the computer using an USB connection and has an USB2Dynamixel device through which communication with computer controllers and servomotors Dynamixel is managed.

Design and implementation of a control of position system for the quadricopter AR. Drone 2.0 by Parrot

This article describes experimental develop of control position without considerate trajectory that realize the quadricopter, realizing the essays in different highs about above sea level. Using parametric identification to obtain the model, its designed a PID control with positions “x” and “y” by using Routh Hurwitz method to determinate the parameters. Finally it simulates the control in Matlab which presents the test and results of real system.

State of the art: Humans performance contributions in signature recognition via crowdsourcing and manual annotation

This work visualizes a state - of - the - art study of researches in the biometry specially in signature recognition, to show the potential of collaborative tools such as crowdsourcing and a tool for human - assisted schemes to improve automatic signature recognition systems. We present an analysis of experiments of evaluation of signatures made through crowdsourcing and labeling of attributes inspired by the FDE analysis. These experiments allow us to establish human performance in signature recognition tasks, the same ones that they use, an HTML interface through the Mturk platform, a public BiosecureID database, and an interface developed in Matlab for manual annotation. The results of these studies demonstrate how human intervention can help improve the performance of automatic signature recognition systems and be able to propose a semi-automatic system schema.

System for monitoring natural disasters using natural language processing in the social network Twitter

This paper presents the design and implementation of an automated system that allows monitoring the social network Twitter, making a connection to the API, to filter content according to four categories (volcanic, telluric, fires and climatological) which affect Ecuador because of its geographical location, taking into account that these cannot be easily predicted, and stores all tweets in a database for analysis. The filtering process is performed by using the NLTK tool with which the frequency of a word is determined within a tweet, to be classified later in one of the proposed categories. The results for each category are displayed on a web page that contains real-time statistics of the database. This work provides access to information on natural disasters because they are classified.

Feasibility study for the implementation of a collaborative learning virtual environment training company

Training through virtual learning environments is widely used in academics; however it also has the capacity to give major benefits to business sectors. The present project features a feasibility study relative to the implementation of a company that offers virtual courses, LMS (Learning Management System) and knowledge management services to telecommunications companies located in the north center of the Quito Metropolitan District. Through market research, the existing supply and demand of previously stated services is defined and with the obtained data, making use of a business plan, it is determined that the company is profitable. In other words, the company is able to recover its investment and generate profit within the first five working years with indicators such as NPV (Net Present Value), IRR (Internal Rate of Return) and equilibrium point.