Contains all the articles of the site

We continue with the series about posture recognition with the Microsoft Kinect sensor. This time I will comment the classes responsible of posture normalization of the body in the way commented in the first article, so that we obtain a series of data that constitute a simplified version of the skeleton most appropriate for analysis using pattern recognition techniques.

[Read More...]

This article closes the series on posture recognition using the Microsoft Kinect sensor. To finish, I will simply show you the implementation of a basic form that uses the class libraries explained in the previous articles.

[Read More...]

One of the most popular algorithms for training multilayer artificial neural networks is the back propagation algorithm, or retro-propagation algorithm. In this article I will try to explain its fundamentals, through a simplified implementation of a neural network that allows testing with different configurations of the network.

[Read More...]

When we try to apply a neural network to a given problem, finding the most suitable topology for it can be a tedious trial and error task, as well as end up producing a poorly optimized network. To automate this process, we can draw on evolutionary algorithms, inspired in the natural selection of living organisms, which can greatly facilitate our job.

[Read More...]

In this second article on the application of evolutionary algorithms to the optimization of the design of neural networks, I am going to provide a small sample application that allows you to build and train networks, in addition to using this type of algorithms to find the best configuration for a given data set. The application allows generating artificial test data, and I provide the source code for you to be able to modify it, as you want.

[Read More...]

With this article I conclude the series dedicated to the application of genetic algorithms to the design of neural networks. I will explain the most relevant code of the sample application given with these articles, mainly the classes dedicated to the genes management and the selection process. You can find more information in the previous articles of the series.

[Read More...]

When we try to learn how to work with time series, it is very useful to have good data sets, and much better if they contain real data. It is difficult to obtain long series, or series presenting interesting and well located and identified patterns, with which we can perform practices. An excellent source of complex time series is our own organism, and everything we can learn by working with them can be extrapolated to any other context.

[Read More...]

In some other articles in this blog, I have already written about complex time series, recurrence quantification analysis (RQA) and neural networks. In this series of articles, I will discuss some points to take into account when combining the use of these two tools to identify patterns in complex series, such as detecting anomalies in electrocardiograms or electroencephalograms.

[Read More...]

In this second article in the series on combining recurrence quantification analysis (RQA) and neural networks to work with complex time series, we will examine some ideas about possible processing that you can apply to the data and the selection of parameters. We will work using electrocardiographic signals, as mentioned in the previous article.

[Read More...]

In this series of articles, I will present an application to manage a chess match database, ChesPosDb. It is not a program that plays chess; it only stores matches, but it allows queries with a large number of options: searching for games in which a series of moves occur, either one after another or separated by several moves, and even look for partially defined positions, no matter in which place on the board the pieces are located.

[Read More...]

In this series of articles, I will comment on a chess game database manager, ChesPosDb. In the first article in this series, I explained how to load chess games in the database using PGN files, which you can download from many Internet sites. In this article and the following ones, I will show the different filter types that you can build to search chess matches in the database.

[Read More...]

This post is the third of the series of articles about the ChessPosDB database manager application. Here you also have a link to the first article in this series, in case you want to start reading from the beginning. In the present article, I will continue commenting on the rest of the movement and position filters that can be applied to find chess games in the database. As you may recall from the previous article, we can combine these filters in multiple ways to build virtually any query that you can think of.

[Read More...]

This article is the fourth of a series of articles dedicated to the ChessPosDB application, a chess game database manager with a powerful search engine. Here, I will finish the section about the search filters by showing the chess match filters. Those filters can include several movement or position filters, which we have already seen in previous posts.

[Read More...]

This post is the fifth in a series of articles about the ChessPosDB application, which allows you to store many chess games in different professional database engines and search for them with a wide variety of options. Here, I will show how to query the database with the filters explained in the previous ones. We will also see the chess match editing options, which allow adding comments and new tags.

[Read More...]

I finish the series dedicated to the ChessPosDB chess match database manager with this article. In this post, I will explain how to install and configure the database server used with the application, which can be Oracle, MySQL, or SQL Server. Whichever database server you choose, you can install it on the same computer as the application or on another more powerful computer that you can access through your local network.

[Read More...]

I will show in this series of articles how to build a self-defence and martial arts training robot. I have named Octopussy to the invention since you can put several limbs to simulate different types of punches and kicks directed to all of the body parts. It is controlled by a computer, an Arduino board, and an application. I also provide the application source code for you to make modifications as you want.

[Read More...]

This article is the second one on the Octopussy training sparring robot for self-defence and martial arts. Here, I will explain how to build the electronics of the invention. The task consists of little more than connecting a few wires, although a tin soldering iron would also be convenient to have at hand to finish the job better.

[Read More...]

This article is the last in the series dedicated to building the Octopussy martial arts and self-defence training sparring robot. Here, I will explain the use of the software to control the device, which allows you to design a virtually unlimited range of training routines within the robot's features.

[Read More...]

All massive data processing applications can benefit from the ever-increasing processing capacity of modern computers, which is now affordable for anyone's pocket. I will show in this article a basic performance comparison among various CPU / GPU platforms, based on the well-known Mandelbrot set and its surprising graphical representation.

[Read More...]