Fakulta elektrotechniky a informatiky / Faculty of Electrical Engineering and Informatics
Stálý URI pro tuto komunituhttps://hdl.handle.net/10195/3847
Práce obhájené před rokem 2008 jsou uloženy pouze v kolekci Vysokoškolské kvalifikační práce
Procházet
3 výsledky
Search Results
Konferenční objektpeer-reviewedpostprint Otevřený přístup Development of Artificial Intelligence Based Module to Industrial Network Protection System(Springer Nature Switzerland AG, 2020) Holík, Filip; Doležel, Petr; Merta, Jan; Štursa, DominikThe paper deals with the software-defined networking concept applied to industrial networks. This innovative concept supports network programmability and dynamic implementation of customized features, including security related ones. In a previous work of the authors, the industrial network protection system (INPS) was designed and implemented. The INPS provides complex security features of various traditional and modern security solutions within a single system. In this paper, the AI module, which is one of the crucial parts of the INPS, is dealt with. In particular, a detailed report focused on the development of the AI module decision function is provided. As a result, an artificial neural network, used for the network traffic evaluation in the AI module, is developed and comprehensively tested.Konferenční objektpeer-reviewedpostprint Omezený přístup Neural Network for Smart Adjustment of Industrial Camera - Study of Deployed Application(Springer, 2018) Doležel, Petr; Honc, DanielSince machine vision is gaining more and more interest lately, it is necessary to deal with correct approaches to visual data acquisition in industry. As a particular part of this complex problematics, a technique for the industrial camera exposure time and image sensor gain tuning is presented in this contribution. In comparison to other approaches, a human expert photographer is used instead of explicitly defined cost function. His knowledge is transformed into an artificial expert system represented by a feedforward neural network. The expert system then provides the suitable exposure time and image sensor gain to gather sharp and balanced images.Článekpeer-reviewedpostprint Otevřený přístup Weight Initialization Possibilities for Feedforward Neural Network with Linear Saturated Activation Functions(Elsevier Science BV, 2016) Doležel, Petr; Škrabánek, Pavel; Gago, LumírInitial weight choice is an important aspect of the training mechanism for feedforward neural networks. This paper deals with a particular topology of a feedforward neural network, where symmetric linear saturated activation functions are used in a hidden layer. Training of such a topology is a tricky procedure, since the activation functions are not fully differentiable. Thus, a proper initialization method for that case is even more important, than dealing with neural networks with sigmoid activation functions. Therefore, several initialization possibilities are examined and tested here. As a result, particular initialization methods are recommended for application, according to the class of the task to be solved.