Artemio Sotomayor-Olmedo

Modeling Key Parameters for Greenhouse Using Fuzzy Clustering Techniques

The clustering techniques are usually used in classification and pattern recognition. Moreover, fuzzy logic is used for system modeling when the information is scarce, inaccurate or its behavior is described using a complex mathematical model. As example of this type of system, a greenhouse is considered, where the variables are: in-house and out-house temperature, humidity for both inside and outside the greenhouse and wind direction. These variables show a dynamic and non-linear behavior; being the in-house temperature and internal humidity the variables of concern for the greenhouse control and modeling. In this project, the development and implementation of three clustering algorithms, being fuzzy K-means, Fuzzy C-means and fuzzy clustering subtractive, is presented. This project is used as the foundation for the design of fuzzy systems and its application in temperature and humidity modeling of a greenhouse used as a laboratory of biotronics at the Universidad Autonoma de Queretaro.

Comparison between Fuzzy C-means clustering and Fuzzy Clustering Subtractive in urban air pollution

Clustering is generally associated with classification problem. In this contribution, the implementation of cluster estimation method as a basis of a fuzzy model identification algorithm has been developed. A comparison between two different clustering techniques is presented, Fuzzy C-means clustering and Fuzzy Clustering Subtractive. Also, an application in modeling the relationship between temperature, humidity and PM10 concentration in urban air pollution in Liverpool at northwest of England is presented.

Performance assessment of fuzzy clustering models applied to urban airborne pollution

An application in modeling a non-lineal system between temperature, humidity and urban airborne air pollution is presented. In this contribution, the implementation of cluster estimation method as a basis of a fuzzy model identification algorithm has been developed. Fuzzy clustering allowed partitioning this complex non-linear system into many linear sub-systems. Finally, comparison of the performance between two different clustering techniques for this particular case study is presented: Fuzzy C-means Clustering and Fuzzy Subtractive Clustering.

A comparison between local and global phase unwrapping algorithms in a modified Fourier Transform Profilometry Method

This work present a modified Fourier Transform Profilometry method, in particular, the development of local and global phase unwrapping algorithms has been considered, because this is one of the major challenges when this method is applied. The basic idea is to project a sinusoidal fringe pattern with a known spatial frequency on the object to digitize, and then a vision system captures and processes the image to obtain the objects depth information. First, the fringe pattern is projected on a reference plane then an image is acquired, later the object to digitize is placed in front of the reference plane and then another image is acquired. The fringe pattern is distorted due to the objects irregular shape. One of the main difficulties to face is the high frequency content in the unwrapping process. This effect can be minimized by knowing the spatial frequency and its multiples. Here, we propose to implement global and local phase unwrapping algorithms to overcome the high frequency problems. These algorithms are part of the modified Fourier Transform Profilometry Method (FTP), where the resulting phase difference of the acquired and processed images have the information of the objects depth. Some tests with computer generated and real objects with different geometries are carried out to verify the proposed methodology, considering the factors that mostly affect the method.

A 3D Sensor Based on a Profilometrical Approach

An improved method which considers the use of Fourier and wavelet transform based analysis to infer and extract 3D information from an object by fringe projection on it is presented. This method requires a single image which contains a sinusoidal white light fringe pattern projected on it, and this pattern has a known spatial frequency and its information is used to avoid any discontinuities in the fringes with high frequency. Several computer simulations and experiments have been carried out to verify the analysis. The comparison between numerical simulations and experiments has proved the validity of this proposed method.

Evaluating trends of airborne contaminants by using support vector regression techniques

Monitoring, modeling and forecasting of air quality parameters are important topics in environmental and health research due to their impact caused by exposing to air pollutants in urban environments. The aim of this article is to show that forecast of daily airborne pollution using support vector machines (SVM) is feasible in regression mode. Results are presented using data measurements of Particulate Matter of aerodynamical size on the order of 10 and 2.5 micrograms (PMx) in London-Bloomsbury at south England.

Analysis of Key Features of Non-Linear Behaviour Using Recurrence Quantification. Case Study: Urban Airborne Pollution at Mexico City

The use of recurrence plots have been extensively used in various fields. In this work, recurrence plots investigate the changes in the non-linear behaviour of urban air pollution using large datasets of raw data (hourly). This analysis has not been used before to extract information from large datasets for this type of non-linear problem. Two different approaches have been used to tackle this problem. The first approach is to show results according to monitoring network. The second approach is to show the results by particle type. This analysis shows the feasibility of using recurrence analysis for pollution monitoring and control.