Corina Savulescu

A recognition system of components from a production line using neuronal networks

We developed and implemented a system for real time automatic recognition of components from a production line using neuronal networks. The capture device (Web camera) is placed over the production line and the system can identify the type of component even if this is not in the correct position or centered. The device sends the information to a recognition system (software) which identifies the type of component and its parts. Once all parts of the component are identified by the system, the operator is informed about the type of component and this is recorded in the fabrications report. When a manufacturing defect is observed, the system alerts the operator and the component is recorded as inappropriate. This system can be used for real time recognition of the components. In addition, if the component is an electrical board for example, the system can also decide if all components are present in the correct position.

Aspects of learning techniques in power system

This paper aims at describing the problems encountered during the learning process of the functioning of a power energy system and some solutions applied to this experience. For a better training of future electromechanical engineers, it is necessary to gain practical skills using specialized equipment during practical sessions. Using high voltage electrical equipment in the lab is not available. Therefore it is necessary to develop computer assisted learning processes. In this way students can simulate or assist maneuvers taking place in the real system. In this way, they can learn the hazards and damages that may occur as a result of wrong maneuvers. These procedures will enhance the quality of learning and teaching engineering.

Approximation of current-voltage curve from experimental data, using Bézier functions

In this paper it is analyzed a method for presentation of current - voltage curve, when it is known only experimental data, for example: a specified input - measured output. We started from classical method of estimation for a trace (the method of least squares) and we implemented a method for recursive computed of trend of input - output curve. By using linear interpolation, the overall trend might be compromised. A better solution is to use a cubic interpolation, but this method implies complex calculus and either it increases the time between the moment of measurement and the moment of display, or it requires more expensive equipment (like faster computers, better acquisition boards, and so on). The Bezier method is a good method for interpolation that uses less calculus than the cubic interpolation, but is more appropriate than linear interpolation. This method is also used in computer graphics for displaying complex surfaces in games, animations or simulations of different processes from physics, chemistry, electronics and mechanics. The final goal of this research is to use this method, in real time, for a general image about how does the analyzed device works. Even if there are some errors in the measurement process, they are overcome by the method, because there are used all the data points once, and the percent of bad data is smaller.

An approach for systems identification using artificial inteligence

In this paper we presented an approach for systems identification using artificial intelligence. To demonstrate its practical applicability, we tested it in the medical field in the interpretation of electrophoresis tests, but this application can be implemented in different areas of interest e.g. in business, management, advertising, etc. Extensive research has been performed exploiting the robust properties of genetic algorithms and demonstrating their capabilities across a large range of problems. We can use this application in many activities areas (medical, business, etc.) The resulting recommendations may constitute the basis of future work in the use of genetic algorithms in business area.

Mobile solutions in small and medium enterprises

The paper concerns the problem of using and implementing mobile solutions in SMEs (Small and Medium Enterprises). Some of the existing examples of mobile solutions are analyzed and characterized. A significant part of the paper is a presentation of the research on mobile solutions which can be used to manage the business activities in SMEs. The role and methods of testing the mobile systems have been presented. A significant part of paper concerns the research on using mobile solutions in SMEs. Additionally, the article contains information related to the direction of development of mobile solutions in SMEs in particular: mobile Business Intelligence, business tourism. The work ends with short conclusions.

Grid based routing in cognitive radio networks for concurrent communication

Cognitive Radio Network (CRN) exploits the spectrum hole in licensed bands by allowing co located cognitive users to communicate among themselves when licensed users are idle. In such opportunistic communication, the cognitive users need to vacate the channel as and when the licensed user becomes active. Most of the time such sudden termination of ongoing sessions of cognitive devices leads to unacceptable overhead and degrades service quality. So, in this paper a new routing protocol is proposed which emphasizes on concurrent communication of cognitive users rather than opportunistic communication. In concurrent communication cognitive devices are allowed to communicate even in the presence of licensed users activity by controlling the transmission power of cognitive devices such that they do not interfere with the ongoing conversation of licensed users. The algorithm is based on the full location information with the assumption that each of the cognitive device can detect the location information of its own and any other cognitive device in the network. All cognitive devices are arranged into grid cells and every grid selects a grid Head (gH) based on some predefined criteria who takes care of routing. Further, the protocol also suggests a routing zone and forwarding region based on the location of the destination in order to reduce routing overhead and faster route establishment. The simulated results of the protocol is compared with CAODV protocol and observed an improvement in packet delivery ratio and routing overhead.

An approach to signaling cost reduction in Proxy MIPv6 for mobility management

Proxy Mobile IPv6 (PMIPv6)is gaining popularity asa Network based mobility management scheme in the recent years. It manages mobility of nodes through Local Mobility Anchor(LMA) that works in co-operation with Mobile Anchor Gateways (MAGs). The original PMIPv6 suggests to collocate MAG with Access Router (AR) in the PMIPv6 architecture. However, this architecture leads to generation of large signaling cost for mobility management. Because, for movement of mobile host (MH) (or mobile node (MN)) even to nearby cells mobility management signals need to traverse to LMA. In this paper, we propose an enhancement to PMIPv6 by re-arranging AR and MAG and allowing single MAG to cover multiple ARs. Further, the protocol tunnels leftover packet of MH directlyfrom old to new MAGA to reduce packet delivery cost. A mathematical analysis is carried out to realize the benefits of the proposed scheme. We analyze signaling cost of the proposed model and compare with PMIPv6 basic version and Dynamic Mobility Anchoring (DMA) scheme. The impact of few input parameters on the signaling cost are investigated. The result reveals that proposed scheme outperforms both PMIPv6 basic and DMA.

The Online and Computer Aided Assessment

This paper briefly describes the Online and Computer Aided Assessment (OCAA) from the perspective of the security of the online evaluation process. Significant aspects of online evaluation have been discussed. The evaluation is considered to be a critical item in determining the Key Performance Indicators (KPI). This study contains a short description of offered online evaluation systems in particularly from a security perspective. Moreover, the article indicates methods dedicated to online evaluation systems which can be used to secure them. The most important part of the article is a presentation of the security model of Online and Computer Aided Assessment. Findings suggest that online evaluations may be a suitable alternative to the traditional paper-based approach.