M
Matous Cejnek
Researcher at Czech Technical University in Prague
Publications - 21
Citations - 124
Matous Cejnek is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: Novelty detection & Artificial neural network. The author has an hindex of 5, co-authored 19 publications receiving 93 citations.
Papers
More filters
Journal ArticleDOI
A Fast Neural Network Approach to Predict Lung Tumor Motion during Respiration for Radiation Therapy Applications
Ivo Bukovsky,Noriyasu Homma,Kei Ichiji,Matous Cejnek,Matous Slama,Peter Mark Benes,Jiri Bila +6 more
TL;DR: This work has investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency.
Journal ArticleDOI
Concept drift robust adaptive novelty detection for data streams
Matous Cejnek,Ivo Bukovsky +1 more
TL;DR: The results show that both newly studied NDMs are superior to the merely use of the plain error of adaptive model and also to the sample entropy based detection while they are robust against the concept drift occurrence.
Proceedings ArticleDOI
Learning entropy for novelty detection a cognitive approach for adaptive filters
TL;DR: Principal Component Analysis and Kernel PCA for HONU is discussed as a potential method to suppress detection of data-measurement perturbations and to enforce LG for system-perturbation novelties.
Journal ArticleDOI
Novelty detection-based approach for Alzheimer’s disease and mild cognitive impairment diagnosis from EEG
TL;DR: In this article, a new approach for detecting Alzheimer's disease and potentially mild cognitive impairment according to the measured EEG records is presented, which evaluates the amount of novelty in the EEG signal as a feature for EEG record classification.
Proceedings ArticleDOI
Adaptive classification of EEG for dementia diagnosis
TL;DR: The proposed method evaluates EEG signal according to included novelty using prediction error and increment of adaptive weights obtained during adaptive prediction of individual EEG channels using linear dynamic neuron as a predictor with gradient descent adaptation.