Zdravko Ivankovic

Analysis of basketball games using neural networks

Data mining is a technology in data analysis with rising application in sports. Basketball is one of most popular sports. Due to its dynamics, a large number of events happen during a game. Basketball statisticians have task to note as many of these events as possible, in order to provide their analysis. In this paper, we used data from the First B basketball league for men in Serbia, for seasons 2005/06, 2006/07, 2007/08, 2008/09 and 2009/2010. During these five seasons, total of 890 games were played. Data were collected for individual players, so it was necessary to adapt these in order to show statistics for a whole team. These data were analyzed using feedforward technique in neural networks, which is the most often used technique in analyzing nonlinear sports data. As a final result, we concluded that the most important elements in basketball are two-point shots under the hoop and defensive rebound, i.e. game “in paint”.

Appliance of neural networks in Basketball - Basketball board for Basketball Referees

What is presented in this paper is a solution that bears large applicable values depending on implementation and realization. The paper describes the methods and the developed software which, based on the action and the movement of the ball, using the neural network, determines the movement of a basketball referee on the court, in order to gain the best view of the action. The solution is developed in Microsoft Visual Studio 2010, written in the programming language C#, reffering to AForge .NET Framework for the support in the aspects of configuring, training and usage of neural networks. AForge .NET Framework is published with LGPL v3 licence.

Guidelines on accessible web portal design

WWW (World Wide Web) as a basic internet service has an important role in almost every aspect of life. The goal of the message sent from one Web page is to attract temporary and future clients i.e. visitors, and to inform them about products, services and to stimulate them to buy and use them. Therefore, the authors of Web pages have to consider different abilities possibilities and conditions of using. Each attempt which makes accessibility easier is useful for people with disabilities. The authors of these paper present guidelines which should be considered in web portals design, in order to make them accessible to people with disabilities. The problem of adjustment of web pages to people with disabilities is analyzed in more details

Making muJava more accessible

This paper describes an effort that has been made to make muJava more accessible. muJava is a Mutation testing tool, built on Java platform for Java programs. In order to make muJava more accessible, a Java stand alone application has been made, to act as a main menu for muJava tool. muJava Menu requires muJava in order to work properly and developed menu represents a third party nonprofit add-on for muJava that should simplify the usage of muJava Mutation system. muJava is not embeded into muJava Menu. Developed application is platform independent, and works on any operating system. Prime goal was to make an application that would lessen configuration efforts regarding muJava tool from the aspects of muJava path location, JDK location, and constant CLASSPATH changes that are needed to generate, and then run muJava mutants. Also, for Windows users, whos operating system version is greater or equal to 5 (Microsoft Windows XP and above), a custom BATCH menu script has been made that is much faster then the previously mentioned muJava wrapper menu.

Optimization of bulk operation performances within Oracle database

The Oracle database enables use of bulk operation in order to reduce time needed for commands execution over a large amount of data. Operations are called using PL/SQL programming language. Advantage of these operations is that they transfer a large amount of data in a single step to SQL engine where they are executed. Bulk operation may also be used with a limitation to maximal number of lines transferred in a single step between PL/SQL engine and SQL engine. This limitation is specified by the LIMIT parameter. In this paper, performances of inquiry are compared to different values of LIMIT parameter. In this way, we have shown which amount of data is optimal for transfer in a single step, and how further increase influences performances. It is also described what influences optimal amount of data that may be transferred in a single step. Different configurations of memory structures were tested within the Oracle itself (SGA and PGA areas) as well as how their changes influence performances. Influence of data types on optimal amount of data was compared, as well as a role of a processor. The method used for verification of optimal values was arithmetical means of execution times for certain inquiries over database. Measurements were done on the same data in several occasions in order to obtain highly precise value and to eliminate possible background processes that are executed in the computer.

Separation of Players in Teams during Basketball Matches

This paper represents a framework for automatic player separation in teams during basketball matches. Separation is made in images broadcasted via television stations. In them, we have view from only single camera in particular point of time. This makes detection of players and their separation much more difficult. The player detection is based on mixture of non-oriented pictorial structures. After detection we extract image parts that represent player’s jersey. Over that area we calculate histogram on S value from HSV color system. According to top five picks, we cluster players in teams. This approach give us accuracy of 92.38%. Its main advantages are robustness and applicability on the large number of footages from different basketball games without need for additional training and algorithm changes.

Implementation of embedded assistive device for disabled people

In this paper we present an embedded assistive device for disabled people that is intended to be used as both keyboard and mouse replacement. Assistive device consists of two main parts: an Arduino compatible board, preferably an Arduino UNO R3 as used in this paper, or an Arduino Leonardo, and a simple analog thumb-stick joystick. Presented device is connected to a computer trough a USB port trough which it sends its input data. Special software collects the received input data and triggers various events in order to execute various actions. Primary goal of presented assistive device is to simulate mouse movements and a single mouse click and in that manner replace majority of moue functions thus enabling users to perform various mouse based tasks such as navigating through menus, drag and drop actions etc., as well as to enable an input and control over a virtual onscreen keyboard thus enabling users to type.

Using Neural Networks in Preparing and Analysis of Basketball Scouting

Basketball is the one of most popular sports, in Serbia and in the world. It is a team sport. Actors of a basketball game are the players from two opposing teams, their team officials with coaches, assistant coaches, doctors and officials (commissioner, referees, table officials, statisticians). Every team, depending on a league or competition, may have no more than 12 or 10 players per game, and of those 5 are actively engaged in the game [1]. Basketball game would not start without 5 players from each game on the court. In Europe, regular basketball game is divided into 4 quarters of 10 minutes each, while in NBA every quarter is 2 minutes longer. If a result is draw, after regular time additional time of 5 minutes is played, as many times as necessary to decide a winner of a game.

Features and security aspects of FASS subsystem

This paper describes fundamental goals and features which one open source, free modular Administrator subsystem should provide. Main goal of entire project was to develop stand-alone administrator subsystem, with complete modular access control and strong data encryption of critical data. FASS (Free Administrator Subsystem) is a downgrade version of Administrator subsystem HEFES 2.0, and contains only its basic features. Features and security aspects of Administrator Subsystem HEFES version 1.0 where published in paper [8], while a paper describing full features of Administrator subsystem HEFES 2.0 will be published in the near future. This paper also describes technologies which were used while developing the administrator system. Data encryption is provided by SHA256 algorithm and TSL security standard. FASS subsystem relies on Java Servlet technology which provides full control over response which is sent from server to a client. Since FASS subsystem also relies on MySQL database service, system security is brought to a new level by developing a set of classes which are designed to stop MySQL injection attacks on the system. Formed classes filter every input data and Query parameters which are transmitted while communicating with servlets. Interface of FASS subsystem was developed in a way so it provides simple and functional access to FASS subsystem, which makes job of a System Administrator much easier, especially in the areas of system maintenance and access rights management through developed ROLE system. Implemented ROLE system has a feature of role inheritance by which, access rules can be inherited from some role, and then modified. This concept was borrowed from Oracle type databases.

Mutation Testing: Object-Oriented Mutation and Testing Tools

Software testing represents activity in detecting software failures. Mutation testing represents a way to test a test. The basic idea of mutation testing is to seed lots of artificial defects into the program, test all defects individually, focus on those mutations that are not detected, and, finally, improve the test suite until it finds all mutations. Mutants can be created by mutating the grammar and then generating strings, or by mutating values during a production. Object-oriented (OO) programming features changed the requirements for mutation testing. Non object-oriented mutation systems make mutations of expressions, variables and statements, but do not mutate type and component declarations. OO programs are composed of user-defined data types (classes) and references to the user-defined types. It is very likely that user-defined components contain many defects such as mutual dependency between members/classes, inconsistencies or conflicts between the components developed by different programmers. Class Mutation is a mutation technique for OO programs which particularly targets plausible faults that are likely to occur due to features in OO programming. Mutation testing requires automated testing tools, which is not a trivial tool to make. Automated mutation tools must be able to parse the program and know its language. When the program is run, mutant can be killed by one of two possible scenarios: if a mutant crashes, or if the mutant goes into an infinite loop.