|
Neural network utilization for etwork traffic predictions
Pavela, Radek ; Mačák, Jaromír (referee) ; Kacálek, Jan (advisor)
In this master’s thesis are discussed static properties of network traffic trace. There are also addressed the possibility of a predication with a focus on neural networks. Specifically, therefore recurrent neural networks. Training data were downloaded from freely accessible on the internet link. This is the captured packej of traffic of LAN network in 2001. They are not the most actual, but it is possible to use them to achieve the objective results of the work. Input data needed to be processed into acceptable form. In the Visual Studio 2005 was created program to aggregate the intensities of these data. The best combining appeared after 100 ms. This was achieved by the input vector, which was divided according to the needs of network training and testing part. The various types of networks operate with the same input data, thereby to make more objective results. In practical terms, it was necessary to verify the two principles. Principle of training and the principle of generalization. The first of the nominated designs require stoking training and verification training by using gradient and mean square error. The second one represents unknown designs application on neural network. It was monitored the response of network to these input data. It can be said that the best model seemed the Layer recurrent neural network (LRN). So, it was a solution developed in this direction, followed by searching the appropriate option of recurrent network and optimal configuration. Found a variant of topology is 10-10-1. It was used the Matlab 7.6, with an extension of Neural Network toolbox 6. The results are processed in the form of graphs and the final appreciation. All successful models and network topologies are on the enclosed CD. However, Neural Network toolbox reported some problems when importing networks. In creating this work wasn’t import of network functions practically used. The network can be imported, but the majority appear to be non-trannin. Unsuccessful models of networks are not presented in this master’s thesis, because it would be make a deterioration of clarity and orientation.
|
| |
| |
|
Neural network utilization for etwork traffic predictions
Pavela, Radek ; Mačák, Jaromír (referee) ; Kacálek, Jan (advisor)
In this master’s thesis are discussed static properties of network traffic trace. There are also addressed the possibility of a predication with a focus on neural networks. Specifically, therefore recurrent neural networks. Training data were downloaded from freely accessible on the internet link. This is the captured packej of traffic of LAN network in 2001. They are not the most actual, but it is possible to use them to achieve the objective results of the work. Input data needed to be processed into acceptable form. In the Visual Studio 2005 was created program to aggregate the intensities of these data. The best combining appeared after 100 ms. This was achieved by the input vector, which was divided according to the needs of network training and testing part. The various types of networks operate with the same input data, thereby to make more objective results. In practical terms, it was necessary to verify the two principles. Principle of training and the principle of generalization. The first of the nominated designs require stoking training and verification training by using gradient and mean square error. The second one represents unknown designs application on neural network. It was monitored the response of network to these input data. It can be said that the best model seemed the Layer recurrent neural network (LRN). So, it was a solution developed in this direction, followed by searching the appropriate option of recurrent network and optimal configuration. Found a variant of topology is 10-10-1. It was used the Matlab 7.6, with an extension of Neural Network toolbox 6. The results are processed in the form of graphs and the final appreciation. All successful models and network topologies are on the enclosed CD. However, Neural Network toolbox reported some problems when importing networks. In creating this work wasn’t import of network functions practically used. The network can be imported, but the majority appear to be non-trannin. Unsuccessful models of networks are not presented in this master’s thesis, because it would be make a deterioration of clarity and orientation.
|
|
Extraction Kinetics and Insecticidal Activity of Volatile Components Isolatedfrom rue by Supercritical CO2.
Sajfrtová, Marie ; Karban, Jindřich ; Sovová, Helena ; Pavela, R.
The aim of the work was to describe the SFE of volatile components from rue and to analyse their insecticidal effects. The objectives consisted in: (a) optimizing the SFE condition (pressure, temperature, extraction time, use of additional separator and concentration of modifier in CO2),investigating their effect on the yield, concentration volatiles in extract and the insecticidal activity, determination of the SFE kinetics of major components in the rue extracts and comparing the SFE with hydrodistillation and maceration.
Fulltext: content.csg - PDF Plný tet: SKMBT_C22014090110391 - PDF
|
| |
| |
|
Supercritical Fluid Extraction and Insecticidal Activity of Lamiaceae Plants
Sajfrtová, Marie ; Pavela, R. ; Karban, Jindřich ; Sovová, Helena
Natural insecticides based on bioactive extracts from plants represent a new trend in plant protection. Supercritical extraction (SFE) using CO2 is a modern extraction technique able to isolate high-added value compounds from plant without any thermal degradation, which allows to obtain extracts with high biological activity. In this work, insecticidal activity of SFE extracts from plant of mint family (Lamiaceae) has been studied and compared to activity of isolates obtained by conventional extraction techniques (hydrodistillation, organic solvent extraction). As a result of variation in extraction pressure, three types of extract were obtained: extract rich in volatile compounds (at 12 MPa), extract rich in oleoresins (at 28 MPa) and in polar compounds (5% of acetone used as modifier). Chemical composition and biological activity (LD50, antifeedant activity) of all isolates were evaluated and compared.
|
|
Utilization of Supercritical Fluid Extraction for Botanical Insecticide Isolation
Sajfrtová, Marie ; Sovová, Helena ; Karban, Jindřich ; Pavela, R.
The aim of this study was to compare the insecticidal activity of extracts obtained by SFE and traditional extraction methods from 20 plants. Three types of extracts were prepared using the benefit of variable solvent power of supercritical carbon dioxide. The extracts rich in essential oil or oleoresin were obtained at 50 °C and 12 or 28 MPa, respectively. The extract enriched with polar components was extracted at pressure of 28 MPa with ethanol added to CO2 as modifier. Essential oils were isolated from the herbs by hydrodistillation and oleoresins were obtained using Soxhlet extraction with liquid solvents. The biological activity of extracts was measured on different kinds of insect by means of contact toxicity test (LD50, LD90) and antifeedant activity. The insecticidal activity of the SFE products was compared with conventional extracts.
|
| |