Ústav počítačových systémů

Browse

Now showing 1 - 5 of 9

Efficient Low-Resource Compression of HIFU Data
(2018-06-26) Klepárník, Petr; Bařina, David; Zemčík, Pavel; Jaroš, Jiří
Large-scale numerical simulations of high-intensity focused ultrasound (HIFU), importantfor model-based treatment planning, generate large amounts of data. Typically, it is necessary to savehundreds of gigabytes during simulation. We propose a novel algorithm for time-varying simulationdata compression specialised for HIFU. Our approach is particularly focused on on-the-fly paralleldata compression during simulations. The algorithm is able to compress 3D pressure time seriesof linear and non-linear simulations with very acceptable compression ratios and errors (over 80%of the space can be saved with an acceptable error). The proposed compression enables significantreduction of resources, such as storage space, network bandwidth, CPU time, and so forth, enablingbetter treatment planning using fast volume data visualisations. The paper describes the proposedmethod, its experimental evaluation, and comparisons to the state of the arts.
Accurate simulation of transcranial ultrasound propagation for ultrasonic neuromodulation and stimulation
(2017-03-13) Robertson, James; Cox, Ben; Jaroš, Jiří; Treeby, Bradley
Non-invasive, focal neurostimulation with ultrasound is a potentially powerful neuroscientific tool that requires effective transcranial focusing of ultrasound to develop. Time-reversal (TR) focusing using numerical simulations of transcranial ultrasound propagation can correct for the effect of the skull, but relies on accurate simulations. Here, focusing requirements for ultrasonic neurostimulation are established through a review of previously employed ultrasonic parameters, and consideration of deep brain targets. The specific limitations of finite-difference time domain (FDTD) and k-space corrected pseudospectral time domain (PSTD) schemes are tested numerically to establish the spatial points per wavelength and temporal points per period needed to achieve the desired accuracy while minimizing the computational burden. These criteria are confirmed through convergence testing of a fully simulated TR protocol using a virtual skull. The k-space PSTD scheme performed as well as, or better than, the widely used FDTD scheme across all individual error tests and in the convergence of large scale models, recommending it for use in simulated TR. Staircasing was shown to be the most serious source of error. Convergence testing indicated that higher sampling is required to achieve fine control of the pressure amplitude at the target than is needed for accurate spatial targeting.
Effective EEG Feature Selection for Interpretable MDD (Major Depressive Disorder) Classification
(Association for Computing Machinery, 2023-04-14) Mrázek, Vojtěch; Jawed, Soyiba; Arif, Muhammad; Malik, Aamir Saeed
In this paper, we propose an interpretable electroencephalogram (EEG)-based solution for the diagnostics of major depressive disorder (MDD). The acquisition of EEG experimental data involved 32 MDD patients and 29 healthy controls. A feature matrix is constructed involving frequency decomposition of EEG data based on power spectrum density (PSD) using the Welch method. Those PSD features were selected, which were statistically significant. To improve interpretability, the best features are first selected from feature space via the non-dominated sorting genetic (NSGA-II) evolutionary algorithm. The best features are utilized for support vector machine (SVM), and k-nearest neighbors (k-NN) classifiers, and the results are then correlated with features to improve the interpretability. The results show that the features (gamma bands) extracted from the left temporal brain regions can distinguish MDD patients from control significantly. The proposed best solution by NSGA-II gives an average sensitivity of 93.3%, specificity of 93.4% and accuracy of 93.5%. The complete framework is published as open-source at https://github.com/ehw-fit/eeg-mdd.
On the usage of the Sparse Fourier Transform in ultrasound propagation simulation
(Association for Computing Machinery, 2024-02-27) Olšák, Ondřej; Jaroš, Jiří
The Fourier transform is an algorithm for transforming the signal from the space/time domain into the frequency domain. This algorithm is essential for applications like image processing, communication, medicine, differential equations solvers, and many others. In some of these applications, most of the Fourier coefficients are small or equal to zero. This property of the signals is used by the Sparse Fourier transform which estimates significant coefficients of the signal with a lower time complexity than the Fourier transform. The goal of this paper is to evaluate available implementations of the Sparse Fourier transform on a set of benchmarks solving the ultrasound wave propagation in 1D, 2D, and 3D heterogeneous media. The results show that the fastest available implementation in 1D domains is MSFFT, however, it is not possible to use it in our implementation of the 2D Sparse Fourier transform. Thus the AAFFT 0.9 is selected for our implementation of the 2D Sparse Fourier transform as the most stable and acceptably fast implementation. The results on 3D simulation data show, that by using the SpFFT library it is possible to reduce the computation time of the Fourier transform in ultrasound wave propagation simulation.
Deep learning-based assessment model for Real-time identification of visual learners using Raw EEG
(2024-01-02) Jawed, Soyiba; Faye, Ibrahima; Malik, Aamir Saeed
Automatic identification of visual learning style in real time using raw electroencephalogram (EEG) is challenging. In this work, inspired by the powerful abilities of deep learning techniques, deep learning-based models are proposed to learn high-level feature representation for EEG visual learning identification. Existing computer-aided systems that use
electroencephalograms and machine learning can reasonably assess learning styles. Despite their potential, offline processing is often necessary to eliminate artifacts and extract features, making these methods unsuitable for real-time applications. The dataset was chosen with 34 healthy subjects to measure their EEG signals during resting states (eyes open and eyes closed) and while performing learning tasks. The subjects displayed no prior knowledge of the animated educational content presented in video format. The paper presents an analysis of EEG signals measured during a resting state with closed eyes using three deep learning techniques: Long-term, short-term memory (LSTM), Long-term, short-term memory-convolutional neural network (LSTM-CNN), and Long-term, short-term memory - Fully convolutional neural network (LSTM-FCNN). The chosen techniques were based on their suitability for real-time applications with varying data lengths and the need for less computational time. The optimization of hypertuning parameters has enabled the identification of visual learners through the implementation of three techniques. LSTM- CNN technique has the highest average accuracy of 94%, a sensitivity of 80%, a specificity of 92%, and an F1 score of 94% when identifying the visual learning style of the student out of all three techniques. This research has shown that the most effective method is the deep learning-based LSTM-CNN technique, which accurately identifies a student's visual learning style.

Browse

Recent Submissions