Artem Lensky

Wenbo Ge, Pooia Lalbakhsh, Leigh Isai et al.

This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data. The paper evaluates a range of models, starting from simpler and shallower ones and progressing to deeper and more complex architectures. Additionally, the performance of these models is compared against naive predictions and variations of classical GARCH models. The prediction of volatility for five assets, namely S&P500, NASDAQ100, gold, silver, and oil, is specifically addressed using GARCH models, Multi-Layer Perceptrons, Recurrent Neural Networks, Temporal Convolutional Networks, and the Temporal Fusion Transformer. In the majority of cases, the Temporal Fusion Transformer, followed by variants of the Temporal Convolutional Network, outperformed classical approaches and shallow networks. These experiments were repeated, and the differences observed between the competing models were found to be statistically significant, thus providing strong encouragement for their practical application.

Artem Lensky, Mingyu Hao

Introduction: The paper addresses the challenging problem of predicting the short-term realized volatility of the Bitcoin price using order flow information. The inherent stochastic nature and anti-persistence of price pose difficulties in accurate prediction. Methods: To address this, we propose a method that transforms order flow data over a fixed time interval (snapshots) into images. The order flow includes trade sizes, trade directions, and limit order book, and is mapped into image colour channels. These images are then used to train both a simple 3-layer Convolutional Neural Network (CNN) and more advanced ResNet-18 and ConvMixer, with additionally supplementing them with hand-crafted features. The models are evaluated against classical GARCH, Multilayer Perceptron trained on raw data, and a naive guess method that considers current volatility as a prediction. Results: The experiments are conducted using price data from January 2021 and evaluate model performance in terms of root mean square error (RMSPE). The results show that our order flow representation with a CNN as a predictive model achieves the best performance, with an RMSPE of 0.85+/-1.1 for the model with aggregated features and 1.0+/-1.4 for the model without feature supplementation. ConvMixer with feature supplementation follows closely. In comparison, the RMSPE for the naive guess method was 1.4+/-3.0.

Muhammad S. Battikh, Artem Lensky

Batch effects in high-dimensional Cytometry by Time-of-Flight (CyTOF) data pose a challenge for comparative analysis across different experimental conditions or time points. Traditional batch normalization methods may fail to preserve the complex topological structures inherent in cellular populations. In this paper, we present a residual neural network-based method for point set registration specifically tailored to address batch normalization in CyTOF data while preserving the topological structure of cellular populations. By viewing the alignment problem as the movement of cells sampled from a target distribution along a regularized displacement vector field, similar to coherent point drift (CPD), our approach introduces a Jacobian-based cost function and geometry-aware statistical distances to ensure local topology preservation. We provide justification for the k-Nearest Neighbour (kNN) graph preservation of the target data when the Jacobian cost is applied, which is crucial for maintaining biological relationships between cells. Furthermore, we introduce a stochastic approximation for high-dimensional registration, making alignment feasible for the high-dimensional space of CyTOF data. Our method is demonstrated on high-dimensional CyTOF dataset, effectively aligning distributions of cells while preserving the kNN-graph structure. This enables accurate batch normalization, facilitating reliable comparative analysis in biomedical research.

Andrea Papaluca, Daniel Krefl, Sergio Mendez Rodriguez et al.

In this work, we tested the Triplet Extraction (TE) capabilities of a variety of Large Language Models (LLMs) of different sizes in the Zero- and Few-Shots settings. In detail, we proposed a pipeline that dynamically gathers contextual information from a Knowledge Base (KB), both in the form of context triplets and of (sentence, triplets) pairs as examples, and provides it to the LLM through a prompt. The additional context allowed the LLMs to be competitive with all the older fully trained baselines based on the Bidirectional Long Short-Term Memory (BiLSTM) Network architecture. We further conducted a detailed analysis of the quality of the gathered KB context, finding it to be strongly correlated with the final TE performance of the model. In contrast, the size of the model appeared to only logarithmically improve the TE capabilities of the LLMs.

Artem Lensky

This study investigates EEG as a potential early biomarker by applying deep learning techniques to resting-state EEG recordings from 31 subjects (15 with PD and 16 healthy controls). EEG signals underwent preprocessing to remove tremor artifacts before classification with CNNs using wavelet-based electrode triplet images. Our analysis across different brain regions and frequency bands showed distinct spatial-spectral patterns of PD-related neural oscillations. We identified high classification accuracy (76%) using central electrodes (C3, Cz, C4) with full-spectrum 0.4-62.4 Hz analysis and 74% accuracy in right parietal regions (P8, CP6, P4) with 10-second windows. Bilateral centro-parietal regions showed strong performance (67%) in the theta band (4.0-7.79 Hz), while multiple areas demonstrated some sensitivity (65%) in the alpha band (7.8-15.59 Hz). We also observed a distinctive topographical pattern of gamma band (40-62.4 Hz) alterations specifically localized to central-parietal regions, which remained consistent across different temporal windows. In particular, we observed pronounced right-hemisphere involvement across several frequency bands. Unlike previous studies that achieved higher accuracies by potentially including tremor artifacts, our approach isolates genuine neurophysiological alterations in cortical activity. These findings suggest that specific EEG-based oscillatory patterns, especially in central and parietal regions and across multiple frequency bands, may provide diagnostic information for PD, potentially before the onset of motor symptoms.

Artem Lensky, Yiding Qiu

Blinks in electroencephalography (EEG) are often treated as unwanted artifacts. However, recent studies have demonstrated that blink rate and its variability are important physiological markers to monitor cognitive load, attention, and potential neurological disorders. This paper addresses the critical task of accurate blink detection by evaluating various deep learning models for segmenting EEG signals into involuntary blinks and non-blinks. We present a pipeline for blink detection using 1, 3, or 5 frontal EEG electrodes. The problem is formulated as a sequence-to-sequence task and tested on various deep learning architectures including standard recurrent neural networks, convolutional neural networks (both standard and depth-wise), temporal convolutional networks (TCN), transformer-based models, and hybrid architectures. The models were trained on raw EEG signals with minimal pre-processing. Training and testing was carried out on a public dataset of 31 subjects collected at UCSD. This dataset consisted of 15 healthy participants and 16 patients with Parkinson's disease allowing us to verify the model's robustness to tremor. Out of all models, CNN-RNN hybrid model consistently outperformed other models and achieved the best blink detection accuracy of 93.8%, 95.4% and 95.8% with 1, 3, and 5 channels in the healthy cohort and correspondingly 73.8%, 75.4% and 75.8% in patients with PD. The paper compares neural networks for the task of segmenting EEG recordings to involuntary blinks and no blinks allowing for computing blink rate and other statistics.