Search results for "Convolution"
showing 10 items of 334 documents
One Dimensional Convolutional Neural Networks for Seizure Onset Detection Using Long-term Scalp and Intracranial EEG
2021
Epileptic seizure detection using scalp electroencephalogram (sEEG) and intracranial electroencephalogram (iEEG) has attracted widespread attention in recent two decades. The accurate and rapid detection of seizures not only reflects the efficiency of the algorithm, but also greatly reduces the burden of manual detection during long-term electroencephalogram (EEG) recording. In this work, a stacked one-dimensional convolutional neural network (1D-CNN) model combined with a random selection and data augmentation (RS-DA) strategy is proposed for seizure onset detection. Firstly, we segmented the long-term EEG signals using 2-sec sliding windows. Then, the 2-sec interictal and ictal segments w…
The ion-optical design of the MARA recoil separator and absolute transmission measurements of the RITU gas-filled recoil separator
2011
In this thesis work, the use of two complementary recoil separators for studies of nuclear structure via fusion-evaporation reactions are discussed. The design and the main ion-optical properties of the vacuum-mode recoil-mass separator MARA, intended for studies of nuclei with N Z close to the proton drip-line, are presented. MARA (Mass Analysing Recoil Apparatus) consists of a magnetic quadrupole triplet followed by an electrostatic de ector and a magnetic dipole. The working principle of MARA is discussed and the reasons for the choice of the optical parameters of the elements are given. The performance of MARA for di erent kind of fusion reactions has been studied with Monte Carlo simul…
Approaching electrical tomography
2009
A general approach to electrical tomography is here described, based on the distribution of the experimental data to the set of voxels in which the subsoil has been divided. This approach utilizes the sensitivity coefficients as factors of the convolution procedure to execute the back projection of the data, to obtain the 3D pictures of the subsoil. A subsequent probabilistic filtering technique is described to improve the pictures in view of sharp boundary models. Some models are finally presented, mostly regarding cubic buried anomalies as well as pipe-shaped and L-shaped anomalies.
A Novel Fast Volumetric Light Sheet Microscopy
2016
Fast noninvasive three-dimensional (3D) imaging is crucial for the quantitative understanding of highly dynamic biological processes. Over the last decades, several fluorescence microscopy techniques have been developed in order to provide a faster and deeper imaging of thick biological samples [1]. Within this framework, Light Sheet Fluorescence Microscopy (LSFM) has emerged as a powerful imaging tool for 3D imaging of thick samples ranging from single cells to entire animals [2,3].However, to obtain a 3D reconstruction either sample or microscope parts usually need to be moved limiting the acquisition speed and inducing possible interferences in volume recording. To solve this problem, he…
Perceived differences between natural and convolution reverberation types in 5.0 surround sound
2011
This Graduate Thesis investigates the perceived differences between natural and convolution reverberation in surround sound. Two spaces with distinct reverberation times were used for this study. Initially three musical excerpts from three instruments (Cello, Oboe, and Piano) were recorded in a dry studio environment. Then the Impulse Response (IR) of the spaces was captured using two methods: balloon burst and sine sweep. The dry excerpts were then recorded in the spaces to capture the natural reverberation pattern while the IRs were convolved with them to create the artificial reverberation excerpts. A listening test was then conducted using six perceptual scales to rate these 18 excerpts…
Automatic image‐based identification and biomass estimation of invertebrates
2020
Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming sorting and expert-based identification of taxa pose strong limitations on how many insect samples can be processed. In turn, this affects the scale of efforts to map and monitor invertebrate diversity altogether. Given recent advances in computer vision, we propose to enhance the standard human expert-based identification approach involving manual sorting and identification with an automatic image-based technology. We describe a robot-enabled image-based identificat…
The Truth is Out There : Focusing on Smaller to Guess Bigger in Image Classification
2023
In Artificial Intelligence (AI) in general and in Machine Learning (ML) in particular, which are important and integral components of modern Industry 4.0, we often deal with uncertainty, e.g., lack of complete information about the objects we are classifying, recognizing, diagnosing, etc. Traditionally, uncertainty is considered to be a problem especially in the responsible use of AI and ML tools in the smart manufacturing domain. However, in this study, we aim not to fight with but rather to benefit from the uncertainty to improve the classification performance in supervised ML. Our objective is a kind of uncertainty-driven technique to improve the performance of Convolutional Neural Netwo…
Performance Evaluation of EEG Based Mental Stress Assessment Approaches for Wearable Devices
2021
Mental stress has been identified as the root cause of various physical and psychological disorders. Therefore, it is crucial to conduct timely diagnosis and assessment considering the severe effects of mental stress. In contrast to other health-related wearable devices, wearable or portable devices for stress assessment have not been developed yet. A major requirement for the development of such a device is a time-efficient algorithm. This study investigates the performance of computer-aided approaches for mental stress assessment. Machine learning (ML) approaches are compared in terms of the time required for feature extraction and classification. After conducting tests on data for real-t…
Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance
2022
Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolut…
Classification of Schizophrenia Patients and Healthy Controls Using ICA of Complex-Valued fMRI Data and Convolutional Neural Networks
2019
Deep learning has contributed greatly to functional magnetic resonance imaging (fMRI) analysis, however, spatial maps derived from fMRI data by independent component analysis (ICA), as promising biomarkers, have rarely been directly used to perform individualized diagnosis. As such, this study proposes a novel framework combining ICA and convolutional neural network (CNN) for classifying schizophrenia patients (SZs) and healthy controls (HCs). ICA is first used to obtain components of interest which have been previously implicated in schizophrenia. Functionally informative slices of these components are then selected and labelled. CNN is finally employed to learn hierarchical diagnostic fea…