|
|
Floor detection during elevator ride
Havelka, Martin ; Králík, Jan (referee) ; Krejsa, Jiří (advisor)
This diploma thesis deals with the detection of the current floor during elevator ride. This functionality is necessary for robot to move in multi-floor building. For this task, a fusion of accelerometric data during the ride of the elevator and image data obtained from the information display inside the elevator cabin is used. The research describes the already implemented solutions, data fusion methods and image classification options. Based on this part, suitable approaches for solving the problem were proposed. First, datasets from different types of elevator cabins were obtained. An algorithm for working with data from the accelerometric sensor was developed. A convolutional neural network, which was used to classify image data from displays, was selected and trained. Subsequently, the data fusion method was implemented. The individual parts were tested and evaluated. Based on their evaluation, integration into one functional system was performed. System was successfully verified and tested. Result of detection during the ride in different elevators was 97%.
|
|
| |
|
|
Data Monitoring for Production Process Modelling
Havelka, Martin ; Opletal, Tomáš (referee) ; Videcká, Zdeňka (advisor)
The abstrakt of this bachelor thesis is presenting of the simulation method with focus on data collection in company ALPS ELECTRIC CZECH, s.r.o. Thesis briefly introduces the questions of manufacture process simulations. It shows what data are required for making real models, in what way are these data capable of being measured and filed.
|
|
|
Design and testing of the system for localizing a sound source
Havelka, Martin ; Vechetová, Jana (referee) ; Najman, Jan (advisor)
This bachelor’s thesis deals with possibilities of sound source localization. There are generally mentioned possible hardware and software solutions at the beginning, from which two applicable methods and suitable components of test device are selected. Further there is a practical part of this work, where programmed algorithms are described. An essential part is testing. Accuracy is tested for the selected microphone array, depending on the change in the number and position of the sensors, the effect of ambient noise, and the location of the obstacle in the area. The output of the tests is the evaluation of functionality and accuracy for both methods used.
|
|
| |
|
|
Floor detection during elevator ride
Havelka, Martin ; Králík, Jan (referee) ; Krejsa, Jiří (advisor)
This diploma thesis deals with the detection of the current floor during elevator ride. This functionality is necessary for robot to move in multi-floor building. For this task, a fusion of accelerometric data during the ride of the elevator and image data obtained from the information display inside the elevator cabin is used. The research describes the already implemented solutions, data fusion methods and image classification options. Based on this part, suitable approaches for solving the problem were proposed. First, datasets from different types of elevator cabins were obtained. An algorithm for working with data from the accelerometric sensor was developed. A convolutional neural network, which was used to classify image data from displays, was selected and trained. Subsequently, the data fusion method was implemented. The individual parts were tested and evaluated. Based on their evaluation, integration into one functional system was performed. System was successfully verified and tested. Result of detection during the ride in different elevators was 97%.
|
|
|
Design and testing of the system for localizing a sound source
Havelka, Martin ; Vechetová, Jana (referee) ; Najman, Jan (advisor)
This bachelor’s thesis deals with possibilities of sound source localization. There are generally mentioned possible hardware and software solutions at the beginning, from which two applicable methods and suitable components of test device are selected. Further there is a practical part of this work, where programmed algorithms are described. An essential part is testing. Accuracy is tested for the selected microphone array, depending on the change in the number and position of the sensors, the effect of ambient noise, and the location of the obstacle in the area. The output of the tests is the evaluation of functionality and accuracy for both methods used.
|
|
|
Data Monitoring for Production Process Modelling
Havelka, Martin ; Opletal, Tomáš (referee) ; Videcká, Zdeňka (advisor)
The abstrakt of this bachelor thesis is presenting of the simulation method with focus on data collection in company ALPS ELECTRIC CZECH, s.r.o. Thesis briefly introduces the questions of manufacture process simulations. It shows what data are required for making real models, in what way are these data capable of being measured and filed.
|
|
| |
|
|
The selection process of an information system
Krejsa, Jiří ; Lorenc, Miroslav (advisor) ; Havelka, Martin (referee)
This diploma thesis focuses on the selection process of the enterprise information system in the enterprise. The general investment process and vendor selection process are described in the theoretical part. This part also includes the analysis of the specifics and differences of the selection process of the information system and recommended methodology for public tender. The optimized selection process of enterprise information system is designed on the basis of specialized literature and found deficiencies. The applicability of the proposed process in practice is assessed through comparison with a case study of a successful selection of an information system in the final part of the thesis. The design can be considered usable in practice according to the described transformation of the tender in the case study to the proposed process. The application of the thesis outputs brings reduction of the required effort and increases the success rate of the selection process of the enterprise information system.
|
guest ::
RSS feed.