Search Results

You are looking at 1 - 5 of 5 items for

  • Author or Editor: Zsolt Ercsey x
  • Refine by Access: All Content x
Clear All Modify Search

The current work focuses on a Hungarian clothing manufacturer’s problem. First the industrial problem is presented; its corresponding critical pass method graph is depicted. To answer all emerging questions with respect to alternative possibilities, a large number of critical pass method problems have to be solved cumbersomely. Instead, first this graph is transformed into a process network. Alternatives specified by mainly financial necessities as well as human resource constraints can now be easily managed, namely where specific activities can be performed in different ways by various employee having different qualifications, requiring different durations and obviously respective costs can be considered within this model. These separate cases can commonly be handled within the resultant sole process network and the corresponding mathematical programming model.

Open access

Abstract

Streaming services spread rapidly. Among these services there are the linear TV, video library or program review system, while the online platform offering these contents is called mobile TV. A recommendation system may not only keep existing clients, but may also generate further turnover, should it introduce new content to the users. In this paper a recommendation system based on the Élő point calculation method is addressed. It is detailed how the programs should be grouped into different dimensions and what type of categories should be considered. Further, the idea of punch cards is introduced. Besides, the user profiles are set. The match system introduced by Élő is applied to the present situation. The system is introduced at a local mobile TV provider with 20,000 users.

Open access

Abstract

Visual identification of objects is an important challenge today. Main target of frequently applied methods is to identify or classify complex objects. These methods are far less effective when objects are small and less complex, and thus less descriptor features are on hand. The main reason for this is that these features can significantly change on object occlusion or appearance of noise.

The presented solution performs identification of simple, small (size is 17 × 13 pixels) objects with elliptical shape. High pass filtered normalized cross correlation is used for region of interest detection and a simple deep neural network is used for classification of selected regions. The proposed method detected objects on a noisy image with accuracy of 96.2%.

Open access
Pollack Periodica
Authors:
Nándor Vincze
,
Kristóf Roland Horváth
,
István Kistelegdi
,
Tamás Storcz
, and
Zsolt Ercsey

Abstract

As part of the energy design synthesis method, complex dynamic building simulation database was created with IDA ICE code for all family house building configurations for a considered problem. In this paper, the annual heat energy demand output parameter is considered to serve as basis of a building energy design investigation. The sensitivity analysis performed by Morris' elementary effect method was used. As the result of the sensitivity analysis of the output parameter, the most important input parameters can be identified, that influence the buildings' energy efficiency, that can support further building designs.

Open access

This paper corresponds to the solution of some problems realized during ragweed identification experiments, namely the samples collected on the field by botanical experts did not match the initial conditions expected. Reflections and shadows appeared on the image, which made the segmentation more difficult, therefore also the classification was not efficient in previous study. In this work, unlike those solutions, which try to remove the shadow by restoring the illumination of image parts, the focus is on separating leaf and background points based on chromatic information, basically by examining the histograms of the full image and the border. This proposed solution filters these noises in the subspaces of hue, saturation and value space and their combination. It also describes a qualitative technique to select the appropriate values from the filtered outputs. With this method, the results of segmentation improved a lot.

Restricted access