|
|
Smartphone-based fall detection
Strejček, Jakub ; Smital, Lukáš (referee) ; Němcová, Andrea (advisor)
This bachelor thesis deals with basic processing of data from accelerometer in smartphone, which is used for fall detection of people. By right detection we could prevent many serious injuries caused by delayed help to people, who were unable to call for help. This paper focuses on the mechanisms of falls and their characteristics and also on hardware used for fall detection. Furthermore, already created Android applications from Google Play and their functionality are studied. In addition to that there were collected data about people falls and an algorithm for detection of fall was created in Matlab. Android smartphone application was developed and tested in this work.
|
|
|
Removing noise in images using deep learning methods
Strejček, Jakub ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
This thesis focuses on comparing methods of denoising by deep learning and their implementation. In the last few years, it has become clear that it is not necessary to have paired data, as for noisy and clean pictures, to train convolution neural networks but it is sufficient to have only noisy pictures for denoising in particular cases. By using methods described in this thesis it is possible to effectively remove i.e. additive Gaussian noise and what more, it is possible to achieve better results than by using statistic methods, which are being used for denoising these days.
|
|
|
Removing noise in images using deep learning methods
Strejček, Jakub ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
This thesis focuses on comparing methods of denoising by deep learning and their implementation. In the last few years, it has become clear that it is not necessary to have paired data, as for noisy and clean pictures, to train convolution neural networks but it is sufficient to have only noisy pictures for denoising in particular cases. By using methods described in this thesis it is possible to effectively remove i.e. additive Gaussian noise and what more, it is possible to achieve better results than by using statistic methods, which are being used for denoising these days.
|
|
|
Efektivnost podnikových procesů a jejich řízení v malých a středních podnicích působících v sektoru výroba ostatních strojů a zařízení pro všeobecné účely
Strejček, Jakub
Strejček, J. Efficiency of enterprise processes and their management in small and medium enterprises in sector production of other machinery and general-purpose machinery. Diploma thesis. Brno: Mendel University, 2019. The aim of this diploma thesis is to identify options of the automation of management in terms of efficiency in small and medium enterprise processes in the sector of production of machinery devices or other machinery for general purposes. The thesis is divided into two parts. The first part contains literary survey that gives the fundamentals of in terms of theory and methodology for the second part. The second part presents financial and non-financial indicators for ERP enterprise systems in the sector. The results are verified by the particular company in the sector. The conclusion contains suggestions and recommendations that could improve potential efficiency of the enterprise processes using the indicators of ERP systems.
|
|
|
Smartphone-based fall detection
Strejček, Jakub ; Smital, Lukáš (referee) ; Němcová, Andrea (advisor)
This bachelor thesis deals with basic processing of data from accelerometer in smartphone, which is used for fall detection of people. By right detection we could prevent many serious injuries caused by delayed help to people, who were unable to call for help. This paper focuses on the mechanisms of falls and their characteristics and also on hardware used for fall detection. Furthermore, already created Android applications from Google Play and their functionality are studied. In addition to that there were collected data about people falls and an algorithm for detection of fall was created in Matlab. Android smartphone application was developed and tested in this work.
|
guest ::
RSS feed.