arXiv research

Paper extends SI method for detecting CPs in complex systems' frequency domain.

This paper analyzes the multi-armed bandit problem using frequency-domain methods.

FreDF improves forecasting by learning in the frequency domain.

SPGD improves adversarial training efficiency and accuracy.

Method improves clarity in forecasting spatio-temporal data.

FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.

In this paper, we take the first steps towards a novel unified framework for the analysis of perturbations in both the Time and Frequency domains. The identification of type and source of such perturbations is fundamental for monitoring reactor cores and guarantee safety while running at nominal conditions. A 3D Convol…

CMC method detects causal relationships in time series data.

Transforms game optimization dynamics into frequency domain for precise hyperparameter analysis.

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for speech signals. It is highly correlated to the phonetic structure of speech, or "how…

A two-layer classifier improves smartphone transportation mode recognition.

Study non-parametric frequency-domain system identification from finite samples.

Previous research has shown that computation of convolution in the frequency domain provides a significant speedup versus traditional convolution network implementations. However, this performance increase comes at the expense of repeatedly computing the transform and its inverse in order to apply other network operati…

In this study an Artificial Neural Network was trained to classify musical instruments, using audio samples transformed to the frequency domain. Different features of the sound, in both time and frequency domain, were analyzed and compared in relation to how much information that could be derived from that limited data…

FredNormer improves time series forecasting by adapting to frequency domain patterns.

Sparse graph learning for dependent time series using ADMM.

Tactile enhanced multimedia is generated by synchronizing traditional multimedia clips, to generate hot and cold air effect, with an electric heater and a fan. This objective is to give viewers a more realistic and immersing feel of the multimedia content. The response to this enhanced multimedia content (mulsemedia) i…

In this paper, we contribute to the literature on energy market co-movement by studying its dynamics in the time-frequency domain. The novelty of our approach lies in the application of wavelet tools to commodity market data. A major part of economic time series analysis is done in the time or frequency domain separate…

FreST Loss decorrelates spatio-temporal dependencies in graph signals.

TimeVQVAE-AD detects anomalies in time series data with high accuracy and provides explainable results.

Bayesian model reconstructs time and frequency data robustly.

FAST selects coresets more efficiently by matching distributions in the frequency domain.

DecoR estimates causal effects in confounded time series data.

The paper introduces a method for interpretable principal component analysis of high-dimensional time series.

In this paper, a genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to …

This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different patterns of an image, we are inspired by a method called "PCANet" in "PCANet: A Simple …

FreDN separates trends and periodicities in non-stationary time series forecasts.

The paper introduces a frequency-domain estimator for low-order systems from noisy data.

We propose a new framework for manifold denoising based on processing in the graph Fourier frequency domain, derived from the spectral decomposition of the discrete graph Laplacian. Our approach uses the Spectral Graph Wavelet transform in order to per- form non-iterative denoising directly in the graph frequency domai…

Improves Gaussian process factor models for multi-population recordings.

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only partly successful and is able to better capture the underlying clean signal than th…

This paper contributes to the literature on international stock market comovements and contagion. The novelty of our approach lies in application of wavelet tools to high-frequency financial market data, which allows us to understand the relationship between stock markets in a time-frequency domain. While major part of…

New method constrains CNN filter frequencies to improve robustness.

We examine the performance of six estimators of the power-law cross-correlations -- the detrended cross-correlation analysis, the detrending moving-average cross-correlation analysis, the height cross-correlation analysis, the averaged periodogram estimator, the cross-periodogram estimator and the local cross-Whittle e…

I propose a frequency domain adaptation of the Expectation Maximization (EM) algorithm to group a family of time series in classes of similar dynamic structure. It does this by viewing the magnitude of the discrete Fourier transform (DFT) of each signal (or power spectrum) as a probability density/mass function (pdf/pm…

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…

DOPPLER optimizes DP training with low-pass filtering, improving model accuracy.

This work studies learning dynamics in SSMs, linking them to deep linear networks.

Developed a diffusion model on spherical data, addressing geometric and stochastic challenges.

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is oft…

Wavelet analysis reveals non-linear dynamics in cryptocurrency prices.

We show that gradient descent on full-width linear convolutional networks of depth $L$ converges to a linear predictor related to the $\ell_{2/L}$ bridge penalty in the frequency domain. This is in contrast to linearly fully connected networks, where gradient descent converges to the hard margin linear support vector m…

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is cru…

Enhances uncertainty estimation in medical image segmentation.

The log-periodic power law (LPPL) is a model of asset prices during endogenous bubbles. A major open issue is to verify the presence of LPPL in price sequences and to estimate the LPPL parameters. Estimation is complicated by the fact that daily LPPL returns are typically orders of magnitude smaller than measured price…

There are three equivalent ways of representing two jointly observed real-valued signals: as a bivariate vector signal, as a single complex-valued signal, or as two analytic signals known as the rotary components. Each representation has unique advantages depending on the system of interest and the application goals. I…

Study examines grain futures connectedness during Russia-Ukraine conflict.

This paper investigates the effect of leak in spiking neural networks.