|
|
Quantitative Digital Holographic Microscopy using machine learning
Duša, Martin ; Kolář, Radim (referee) ; Vičar, Tomáš (advisor)
This thesis presents machine learning methods for determining the parameters of micro and nano particles from digital holographic microscopy images. In the theoretical part the principles of hologram imaging, holographic microscopy and the similarity between Mie theory and hologram are presented. The second part of the theoretical review is devoted to machine learning methods used in determining the quantitative information of particles. The practical part is focused on the design of a procedure for determining the position, refractive index and radius using the U-Net architecture implemented in PyTorch and DeepTrack 2.1. The results of the proposed methodologies are discussed at the end of the paper.
|
|
|
Flow measurement in microfluidic systems with recording and sharing of measured values
Duša, Martin ; Harabiš, Vratislav (referee) ; Čmiel, Vratislav (advisor)
This paper is focused on flow measurement, microfluidic systems and realization system, which is able to flow measure and share with the possibility of their visualization via web interface. The first part of the work is devoted to the theoretical research, which briefly deals with the theory of flow and other concepts that belong to the flow There are also mentioned principles of flowmeter and their advantages or applications. The second part is devoted to microfluidic system. This section describes the elements that make up the microfluidic system, their capabilities and applications. The last part is devoted to the realization of the measuring system. The implementation includes a design of the measuring system, where the selection of microcotroler and sensor is given. The software solution includes used platforms and examples of algorithmization. At the end, the physical implementation of the whole system and calibration is described.
|
|
|
Quantitative Digital Holographic Microscopy using machine learning
Duša, Martin ; Kolář, Radim (referee) ; Vičar, Tomáš (advisor)
This thesis presents machine learning methods for determining the parameters of micro and nano particles from digital holographic microscopy images. In the theoretical part the principles of hologram imaging, holographic microscopy and the similarity between Mie theory and hologram are presented. The second part of the theoretical review is devoted to machine learning methods used in determining the quantitative information of particles. The practical part is focused on the design of a procedure for determining the position, refractive index and radius using the U-Net architecture implemented in PyTorch and DeepTrack 2.1. The results of the proposed methodologies are discussed at the end of the paper.
|
|
|
Flow measurement in microfluidic systems with recording and sharing of measured values
Duša, Martin ; Harabiš, Vratislav (referee) ; Čmiel, Vratislav (advisor)
This paper is focused on flow measurement, microfluidic systems and realization system, which is able to flow measure and share with the possibility of their visualization via web interface. The first part of the work is devoted to the theoretical research, which briefly deals with the theory of flow and other concepts that belong to the flow There are also mentioned principles of flowmeter and their advantages or applications. The second part is devoted to microfluidic system. This section describes the elements that make up the microfluidic system, their capabilities and applications. The last part is devoted to the realization of the measuring system. The implementation includes a design of the measuring system, where the selection of microcotroler and sensor is given. The software solution includes used platforms and examples of algorithmization. At the end, the physical implementation of the whole system and calibration is described.
|
guest ::
