In this article a possibility of application of the ultrasonic non-contact method for assessing the quality of yogurt was researched. A prediction assessment was made by an ultrasound based on four parameters – pH, conductivity, fat content, and viscosity. An ultrasonic device was developed to determine the parameters of yoghurt by modified ultrasound sensor available commercially. In order to obtain data for post-processing, a software application was designed for recognizing the ultrasonic signal through the image processing and analysis techniques.<br>The developed algorithms and procedures were applied to determine the distance between the object and the sensor, whereby basic physico-chemical parameters of yogurt could be predicted with the lowest relative error. The working distance was 35 cm for the considered system. The survey results show that the parameters fat content, pH, conductivity, and viscosity of yogurt could be predicted by the proposed system for contactless measurement with accuracy of 94-97%.<br><br>

Motors are the most important driving components of industrial and consumer products. Therefore improving the energy efficiency of their work is an important environmental and economic problem. Systematic review of laboratory equipment for training in energy efficiency is made for the integrated influence between curricular practical training and current requirements of the industry. The application of various training tools opens up new possibilities for adapting the teaching methods in universities to the learning style of today's students. The presented system is improved with application of additional software and hardware components from other manufacturers.

Predicting student performance is important for universities. Thus, they can identify students who need support and take measures to improve educational outcomes. The paper presents analyze of the results of a study conducted at the Trakia University of Stara Zagora. The study aims to identify the most significant features that affect student performance and to select the most efficient machine-learning algorithm to predict their performance. The efficiency of four classification algorithms was compared-BayesNet (BN), Multilayer Perceptron (MLP), Sequential minimal optimization (SMO) and Decision tree (J48). For comparison, the indicators TP Rate, Precision, F-Measure, Accuracy and error measures-MAE, RMSE, RAE, and RRSE were used. The processing is done with Weka open-source software. The obtained results show that the MLP algorithm is the best for the used data. The obtained accuracy is sufficient to create an effective forecast model. 12 attributes have been identified that have the greatest impact on student performance.

Many students in Bulgarian universities drop out of the university before completing their studies. Identifying students at risk of dropping out allows timely taking measures for their retention. The paper presents the results of a study conducted among students of engineering programs at Trakia University - Stara Zagora. The collected data are subjected to processing, which aims to find the most important attributes that determine the risk of dropping out of university. The processing is done with Weka open source software. Different algorithms for selecting attributes with different search methods are applied. The most appropriate attribute selection algorithm was selected after applying the BayesNet classifier to the results obtained. The indicators TP rate, Precision and F-measure were compared. When applying InfoGainAttributeEval, the highest results are obtained for the accuracy of the classification. At the next stage, it is planned to expand the study among a larger number of students from different programs and create an effective forecasting model.

No abstract

This article presents results of a study of the opinion of former and current students on issues related to the evaluation with e-tests. The experience of lecturers conducting assessment in technical and computer disciplines with tests in e-learning environment Moodle from Faculty of Technics and Technologies of Yambol is also analyzed. Analyzes and research carried out show that the progress of the technologies and their entry into education leads to one negative effect. Some of the students use digital technologies to access exam test questions and learn only these questions rather than the teaching content. Conclusions are made on the minimum number of questions from which the tests should be formed. Measures have been proposed for easy and fast automated raising of the total number of questions in the bank by developing Plugins in Moodle, allowing the creation of new types of test questions.

No abstract

The article presents the results of wind potential research in the area . Measurements were made in the period from 01. 06.2017 to 27.11.2017. For both seasons -summer and autumn the average wind speed and wind speed distribution are determined. The wind roses, which give a visual idea of the distribution of wind potential in different directions are build. Conclusions for the possibility of using the wind potential for extracting electricity are made.