Predrag Pecev

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.

A system for deductive prediction and analysis of movement of basketball referees

This paper presents us with an automatic prediction and analysis of basketball referees movement which is useful for educational software. Such software would be very beneficial in training the young basketball referees. The paper proposes that the movement prediction of basketball referees can be achieved with a multilayered perceptron neural network. Network will reason on the basis of a ball movement during a play action. Proposed neural network will be trained with a modified Back Propagation algorithm which essentially presents a special algorithm for a multiple dependent Time Series prediction. In this paper, we will also describe initial designs of a neural network structure that, we believe, would better suit the nature of a multiple dependent Time Series prediction problems. The aforementioned educational software is capable of determining whether a referee was moving properly in a certain situation or not. Determination is possible on the basis of numerical values that are calculated by simulating the human visual field. The referee’s horizontal field of view simulation is based on the standard set by the American Optometric Association. It is implemented through a modified Sweep and Prune algorithm which is also discussed in this paper.

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.

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.

An ontology driven credit risk scoring model

In this paper, the authors propose a model for credit risk management. Two main aspects of credit risk management are analyzed. The first aspect of this paper discusses techniques for reducing the risk of investments using standard commercial bank methods for client scoring. The second aspect deals with social, political and development components of investment. In this paper, ontology is used to enable the implementation of domain knowledge to support decision-making and client scoring in government development funds. Authors propose an integrated ontological model for evaluating client applications, which incorporates both: the default risk of investment and the development component of the investment.

Modeling of an ontology of the administrative task

Administrative tasks are a crucial part of the business process in Public Administration. Ontologies, generated from the workflow of administrative processes, can provide significant improvements and reduce the time of modelling, testing and integration in the process of building an information system of the Public Administration (PA). In this paper, the authors propose an approach for building an ontological model of the administrative task (OMAT) of the Public Administration. The annotation of the proposed ontology with elements of user interface components and presented algorithm for a direct transformation of the semantic description of the administrative task in the user interface components, contribute to the improvement of information systems modeling techniques. The proposed approach, with standardized formalism in the method of creating an ontology of the administrative process (task), can be applied to any administrative process.

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.