Autoencoder
Dotaz
Zobrazit nápovědu
BACKGROUND: This study aims to evaluate the feasibility of generating pseudo-normal single photon emission computed tomography (SPECT) data from potentially abnormal images. These pseudo-normal images are primarily intended for use in an on-the-fly data harmonization technique. MATERIAL AND METHODS: The methodology was tested on brain SPECT with [123I]Ioflupane. The proposed model for generating a pseudo-normal image was based on a variational autoencoder (VAE) designed to process 2D sinograms of the brain [123I]-FP-CIT SPECT, potentially exhibiting abnormal uptake. The model aimed to predict SPECT sinograms with corresponding normal uptake. Training, validation, and testing datasets were created by SPECT simulator from 45 brain masks segmented from real patient's magnetic resonance (MR) scans, using various uptake levels. The training and validation datasets each comprised 612 and 360 samples, respectively, drawn from 36 brain masks. The testing dataset contained 153 samples based on 9 brain masks. VAE performance was evaluated through brain dimensions, Dice similarity coefficient (DSC) and specific binding ratio. RESULTS: Mean DSC was 80% for left basal ganglia and 84% for right basal ganglia. The proposed VAE demonstrated excellent consistency in predicting basal ganglia shape, with a coefficient of variation of DSC being less than 1.1%. CONCLUSIONS: The study demonstrates that VAE can effectively estimate an individualized pseudo-normal distribution of the radiotracer [123I]-FP-CIT SPECT from abnormal SPECT images. The main limitations of this preliminary research are the limited availability of real brain MR data, used as input for the SPECT data simulator, and the simplified simulation setup employed to create the synthetic dataset.
- Klíčová slova
- SPECT, [123I]-FP-CIT, harmonization, variational autoencoder,
- MeSH
- autoenkodér * MeSH
- jednofotonová emisní výpočetní tomografie * MeSH
- lidé MeSH
- mozek diagnostické zobrazování MeSH
- počítačové zpracování obrazu * metody MeSH
- tropany MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- Názvy látek
- 2-carbomethoxy-8-(3-fluoropropyl)-3-(4-iodophenyl)tropane MeSH Prohlížeč
- tropany MeSH
Electroencephalography (EEG) experiments typically generate vast amounts of data due to the high sampling rates and the use of multiple electrodes to capture brain activity. Consequently, storing and transmitting these large datasets is challenging, necessitating the creation of specialized compression techniques tailored to this data type. This study proposes one such method, which at its core uses an artificial neural network (specifically a convolutional autoencoder) to learn the latent representations of modelled EEG signals to perform lossy compression, which gets further improved with lossless corrections based on the user-defined threshold for the maximum tolerable amplitude loss, resulting in a flexible near-lossless compression scheme. To test the viability of our approach, a case study was performed on the 256-channel binocular rivalry dataset, which also describes mostly data-specific statistical analyses and preprocessing steps. Compression results, evaluation metrics, and comparisons with baseline general compression methods suggest that the proposed method can achieve substantial compression results and speed, making it one of the potential research topics for follow-up studies.
- Klíčová slova
- Artificial neural networks, Data compression, Electroencephalography, Machine learning, Neuroinformatics,
- MeSH
- autoenkodér MeSH
- elektroencefalografie * metody MeSH
- komprese dat * metody MeSH
- lidé MeSH
- neuronové sítě * MeSH
- počítačové zpracování signálu * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- dataset MeSH
Manual visual review, annotation and categorization of electroencephalography (EEG) is a time-consuming task that is often associated with human bias and requires trained electrophysiology experts with specific domain knowledge. This challenge is now compounded by development of measurement technologies and devices allowing large-scale heterogeneous, multi-channel recordings spanning multiple brain regions over days, weeks. Currently, supervised deep-learning techniques were shown to be an effective tool for analyzing big data sets, including EEG. However, the most significant caveat in training the supervised deep-learning models in a clinical research setting is the lack of adequate gold-standard annotations created by electrophysiology experts. Here, we propose a semi-supervised machine learning technique that utilizes deep-learning methods with a minimal amount of gold-standard labels. The method utilizes a temporal autoencoder for dimensionality reduction and a small number of the expert-provided gold-standard labels used for kernel density estimating (KDE) maps. We used data from electrophysiological intracranial EEG (iEEG) recordings acquired in two hospitals with different recording systems across 39 patients to validate the method. The method achieved iEEG classification (Pathologic vs. Normal vs. Artifacts) results with an area under the receiver operating characteristic (AUROC) scores of 0.862 ± 0.037, 0.879 ± 0.042, and area under the precision-recall curve (AUPRC) scores of 0.740 ± 0.740, 0.714 ± 0.042. This demonstrates that semi-supervised methods can provide acceptable results while requiring only 100 gold-standard data samples in each classification category. Subsequently, we deployed the technique to 12 novel patients in a pseudo-prospective framework for detecting Interictal epileptiform discharges (IEDs). We show that the proposed temporal autoencoder was able to generalize to novel patients while achieving AUROC of 0.877 ± 0.067 and AUPRC of 0.705 ± 0.154.
Enzymes play a crucial role in sustainable industrial applications, with their optimization posing a formidable challenge due to the intricate interplay among residues. Computational methodologies predominantly rely on evolutionary insights of homologous sequences. However, deciphering the evolutionary variability and complex dependencies among residues presents substantial hurdles. Here, we present a new machine-learning method based on variational autoencoders and evolutionary sampling strategy to address those limitations. We customized our method to generate novel sequences of model enzymes, haloalkane dehalogenases. Three design-build-test cycles improved the solubility of variants from 11% to 75%. Thorough experimental validation including the microfluidic device MicroPEX resulted in 20 multiple-point variants. Nine of them, sharing as little as 67% sequence similarity with the template, showed a melting temperature increase of up to 9 °C and an average improvement of 3 °C. The most stable variant demonstrated a 3.5-fold increase in activity compared to the template. High-quality experimental data collected with 20 variants represent a valuable data set for the critical validation of novel protein design approaches. Python scripts, jupyter notebooks, and data sets are available on GitHub (https://github.com/loschmidt/vae-dehalogenases), and interactive calculations will be possible via https://loschmidt.chemi.muni.cz/fireprotasr/.
- Publikační typ
- časopisecké články MeSH
The current population worldwide extensively uses social media to share thoughts, societal issues, and personal concerns. Social media can be viewed as an intelligent platform that can be augmented with a capability to analyze and predict various issues such as business needs, environmental needs, election trends (polls), governmental needs, etc. This has motivated us to initiate a comprehensive search of the COVID-19 pandemic-related views and opinions amongst the population on Twitter. The basic training data have been collected from Twitter posts. On this basis, we have developed research involving ensemble deep learning techniques to reach a better prediction of the future evolutions of views in Twitter when compared to previous works that do the same. First, feature extraction is performed through an N-gram stacked autoencoder supervised learning algorithm. The extracted features are then involved in a classification and prediction involving an ensemble fusion scheme of selected machine learning techniques such as decision tree (DT), support vector machine (SVM), random forest (RF), and K-nearest neighbour (KNN). all individual results are combined/fused for a better prediction by using both mean and mode techniques. Our proposed scheme of an N-gram stacked encoder integrated in an ensemble machine learning scheme outperforms all the other existing competing techniques such unigram autoencoder, bigram autoencoder, etc. Our experimental results have been obtained from a comprehensive evaluation involving a dataset extracted from open-source data available from Twitter that were filtered by using the keywords "covid", "covid19", "coronavirus", "covid-19", "sarscov2", and "covid_19".
- Klíčová slova
- COVID-19, N-gram feature extraction, data prediction, ensemble machine learning, twitter data,
- MeSH
- COVID-19 * MeSH
- lidé MeSH
- pandemie MeSH
- SARS-CoV-2 MeSH
- sociální média * MeSH
- sociální sítě MeSH
- strojové učení MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
This paper presents a method for estimating the position of a target under jammed conditions using the Time Difference of Arrival (TDOA) method. The algorithm utilizes a deep neural network to overcome the challenges posed by the jammed conditions. The simulations and results indicate that the presented method is more accurate and efficient than the traditional TDOA methods.
- Klíčová slova
- TDOA, autoencoder, correlation method, deep neural network, jamming, neural network, radar,
- Publikační typ
- časopisecké články MeSH
Novel neural network training methods (commonly referred to as deep learning) have emerged in recent years. Using a combination of unsupervised pre-training and subsequent fine-tuning, deep neural networks have become one of the most reliable classification methods. Since deep neural networks are especially powerful for high-dimensional and non-linear feature vectors, electroencephalography (EEG) and event-related potentials (ERPs) are one of the promising applications. Furthermore, to the authors' best knowledge, there are very few papers that study deep neural networks for EEG/ERP data. The aim of the experiments subsequently presented was to verify if deep learning-based models can also perform well for single trial P300 classification with possible application to P300-based brain-computer interfaces. The P300 data used were recorded in the EEG/ERP laboratory at the Department of Computer Science and Engineering, University of West Bohemia, and are publicly available. Stacked autoencoders (SAEs) were implemented and compared with some of the currently most reliable state-of-the-art methods, such as LDA and multi-layer perceptron (MLP). The parameters of stacked autoencoders were optimized empirically. The layers were inserted one by one and at the end, the last layer was replaced by a supervised softmax classifier. Subsequently, fine-tuning using backpropagation was performed. The architecture of the neural network was 209-130-100-50-20-2. The classifiers were trained on a dataset merged from four subjects and subsequently tested on different 11 subjects without further training. The trained SAE achieved 69.2% accuracy that was higher (p < 0.01) than the accuracy of MLP (64.9%) and LDA (65.9%). The recall of 58.8% was slightly higher when compared with MLP (56.2%) and LDA (58.4%). Therefore, SAEs could be preferable to other state-of-the-art classifiers for high-dimensional event-related potential feature vectors.
- Klíčová slova
- P300, brain-computer interfaces, deep learning, event-related potentials, machine learning, stacked autoencoders,
- Publikační typ
- časopisecké články MeSH
We propose a novel approach for background subtraction in repeated gamma-ray spectrometric measurements. This entirely data-driven method eliminates the need for Monte Carlo detector simulation. To accomplish this, we utilized the framework of Latent Variable Modeling, incorporating various matrix factorization techniques and artificial neural networks. Subsequently, we applied this method to estimate radionuclide activity through spectrum unmixing. Significant improvements in sensitivity, surpassing traditional methods, were observed for the test case scenario of aerosol filter measurements.
- Klíčová slova
- Autoencoder, Cs-134, Cs-137, Deep learning, Gamma-ray spectrometry, I-131, Machine learning, PCR, PLSR, SVD,
- Publikační typ
- časopisecké články MeSH
The estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three sensors at the shoe, shin, and thigh. We show that existing general-purpose architectures outperform classical feature-based approaches and propose a novel architecture tailored for this task. The proposed architecture is based on a semi-supervised variational auto-encoder structure with innovated decoder in the form of a dense layer with a sinusoidal activation function. The proposed architecture achieved the lowest average error on the test data. Analysis of sensor placement reveals that the best location for the sensor is the shoe. Significant accuracy gain was observed when all three sensors were available. All data acquired in this experiment and the code of the estimation methods are available for download.
- Klíčová slova
- autoencoder architecture, deep learning, inertial measurement unit, motion speed estimation, walking speed,
- MeSH
- bérec MeSH
- chodci * MeSH
- deep learning * MeSH
- lidé MeSH
- nositelná elektronika * MeSH
- pohyb těles MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
In gait stability analysis, patients suffering from dysfunction problems are impacted by shifts in their dynamic balance. Monitoring the patients' progress is important for allowing physicians and patients to observe the rehabilitation process accurately. In this study, we designed a new methodology for classifying gait disorders to quantify patients' progress. The dataset in this study includes 84 measurements of 37 patients based on a physician's opinion. In this study, the system, which includes a Kinect camera to observe and store the frames of patients walking down a hallway, a key-point detector to detect the skeletal key points, and an encoder transformer classifier network integrated with generator-discriminator networks (ET-GD), is designed to evaluate the classification of gait dysfunction. The detector extracts the skeletal key points of patients. After feature engineering, the selected high-level features are fed into the proposed neural network to analyse patient movement and perform the final evaluation of gait dysfunction. The proposed network is inspired by the 1D encoder transformer, which is integrated with two main networks: a network for classification and a network to generate fake output data similar to the input data. Furthermore, we used a discriminator structure to distinguish between the actual data (input) and fake data (generated data). Due to the multi-structural networks in the proposed method, multi-loss functions need to be optimised; this increases the accuracy of the encoder transformer classifier.
- Klíčová slova
- Autoencoder, Classification, Deep learning, Discriminator, Gait disorders, Vision transformer,
- MeSH
- analýza chůze MeSH
- chůze (způsob) * MeSH
- chůze MeSH
- lidé MeSH
- neuronové sítě MeSH
- pohybové poruchy * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
