Novel ECG classification method using deep time-frequency representation and progressive decision fusion.
problem Challenges in classifying abnormal ECG rhythms due to broad taxonomy, noises, and lack of annotated data.
method Transform ECG signal into time-frequency domain, train scale-specific deep CNNs, and fuse decisions progressively.
result Effective and efficient ECG classification method validated on synthetic and real-world datasets.
MCLNN improves music genre classification by learning frequency bands.
problem Classifying music genres using neural networks adapted from image recognition.
method MCLNN learns frequency bands, reducing susceptibility to frequency shifts and enabling concurrent exploration of feature combinations.
result MCLNN outperforms state-of-the-art Convolutional Neural Networks on the Ballroom music dataset.
Convolutional neural networks learn phase-dependent frequency representations.
problem Capturing phase dependence in frequency representations for better signal analysis.
method Convolutional neural networks learn filters with different phases, which rectify to phase-dependent descriptors.
result Phase harmonics correlations can compressively represent signals with sparse wavelet coefficients.
NFM models time-series data directly in the Fourier domain, achieving state-of-the-art performance.
problem Traditional time-series analysis focuses on the time domain, limiting flexibility.
method NFM models time-series data in the Fourier domain, using frequency extrapolation and interpolation.
result NFM achieves state-of-the-art performance on various time-series tasks.
End-to-end sound event detection uses learned time-frequency representations.
problem Sound event detection using standard features like mel spectrogram.
method End-to-end approach with a feedforward layer block and convolutional recurrent network.
result The learned time-frequency representations improve performance over fixed features.
Tensor-based methods improve mid-price prediction in high-frequency financial data.
problem Predicting price changes in high-frequency financial data.
method Multilinear tensor-based learning algorithms for mid-price prediction.
result Tensor-based models outperform vector-based approaches in mid-price prediction.
SRMD uses random features for efficient time-frequency analysis.
problem Efficiently analyzing time-series data with low computational cost.
method Sparse Random Mode Decomposition (SRMD) constructs a sparse approximation to the spectrogram.
result SRMD outperforms other methods in signal representation, outlier removal, and mode decomposition.
Bayesian model reconstructs time and frequency data robustly.
problem Missing observations and noise in time/frequency data.
method Probabilistic model, Bayesian update, joint reconstruction.
result Effective joint time/frequency reconstruction with missing data.
Improves speech separation by integrating time and frequency domains.
problem Speech separation using deep learning techniques.
method Proposes a framework that combines time and frequency domain features, using an embedding network and clustering.
result Obtained state-of-the-art results on WSJ0-2mix dataset.
Unified probabilistic models improve audio signal processing efficiency and interpretability.
problem High computational cost and difficulty in interpreting probabilistic models in time-frequency analysis.
method Equivalence to Spectral Mixture Gaussian processes, state space representation, Kalman smoothing, efficient parameter learning.
result Unified models make it easier to interpret and modify model assumptions.
MelNet generates high-fidelity audio with long-range structure.
problem Capturing long-range dependencies in audio waveforms.
method Generative model in frequency domain, leveraging spectrograms.
result Improves audio generation in various tasks.
FreSh shifts model's initial frequency spectrum to match target signal, improving neural representation performance.
problem MLPs' low-frequency bias limits capturing high-frequency details accurately.
method FreSh selects embedding hyperparameters to align model's initial output spectrum with target signal's spectrum.
result FreSh improves performance across various neural representation methods and tasks with minimal computational overhead.
Unified framework for nuclear reactor perturbation analysis using CNN and LSTM.
problem Monitoring reactor cores for safety and perturbation identification.
method 3D-CNN and LSTM networks for frequency and time domain analysis, respectively.
result High accuracy in recognising perturbation type and precise source localisation in frequency domain.
Paper proposes a unified time series forecasting model with adaptive transfer.
problem General forecasting models for diverse time series data.
method Unified representations through Decomposed Frequency Learning and adaptive domain-specific features via Time Series Register.
result State-of-the-art forecasting performance on seven real-world benchmarks.
CNNs show sensitivity to low-frequency signals due to image frequency distribution.
problem Understanding why CNNs are sensitive to low-frequency signals.
method Theoretical analysis of CNN representations in frequency space.
result CNNs sensitivity to low-frequency signals is due to the frequency distribution of natural images.
New layers estimate complex time-frequency masks without phase wrapping issues.
problem Lack of phase estimation in deep learning-based speech enhancement and source separation.
method Proposes magbook, phasebook, and combook layers for complex mask estimation.
result Match state-of-the-art performance on speaker separation datasets.
CNNs use a bottleneck structure to focus on a few frequencies, affecting function representation.
problem Understanding how CNNs focus on specific frequencies in their feature learning.
method Defined Convolution Bottleneck (CBN) structure, measured CBN rank, and analyzed parameter norms.
result Parameter norm scales with depth and CBN rank, and networks with optimal parameters exhibit this structure.
Continuous time Bayesian networks are investigated with a special focus on their ability to express causality. A framework is presented for doing inference in these networks. The central contributions are a representation of the intensity matrices for the networks and the introduction of a causality measure. A new mode…
We propose a new framework for measuring connectedness among financial variables that arises due to heterogeneous frequency responses to shocks. To estimate connectedness in short-, medium-, and long-term financial cycles, we introduce a framework based on the spectral representation of variance decompositions. In an e…
MCLNN improves music genre classification with automated feature exploration.
problem Music genre classification using neural networks.
method MCLNN uses a mask to enforce sparseness and learn time-frequency representations.
result MCLNN achieves competitive accuracy compared to state-of-the-art methods.
Power quality (PQ) analysis describes the non-pure electric signals that are usually present in electric power systems. The automatic recognition of PQ disturbances can be seen as a pattern recognition problem, in which different types of waveform distortion are differentiated based on their features. Similar to other …
Generative model improves audio synthesis from TF features.
problem Challenges in generating high-quality audio from TF features.
method Used a GAN to generate invertible TF features from short-time Fourier transforms.
result Generated TF features from GAN outperformed direct waveform generation.
Improved speech emotion recognition using pitch-synchronous single frequency filtering spectrogram.
problem Uncertainty principles in STFT spectrogram limit time and frequency resolutions.
method Modified SFF spectrogram by averaging amplitudes between GCI locations, named pitch-synchronous SFF spectrogram.
result Improved SER accuracy (63.95% to 70.4%) on IEMOCAP dataset.
End-to-end probabilistic inference improves audio signal processing.
problem Efficiently processing large audio signals with varying characteristics.
method Formulated a spectral mixture Gaussian process model with nonstationary priors, enabling infinite-horizon Gaussian process regression.
result The method outperforms standard techniques in processing audio signals with hundreds of thousands of data points.
A new neural network improves frequency estimation from noisy signals.
problem Estimating frequencies of sinusoidal components in noisy signals.
method A novel neural network architecture combined with a module to detect the number of frequencies.
result Significantly more accurate frequency estimation at medium-to-high noise levels.
MCLNN improves sound recognition by learning frequency bands.
problem Efficiently recognizing acoustic events from audio signals.
method MCLNN uses a binary mask to force sparseness in network weights, focusing on frequency bands.
result MCLNN achieves competitive performance in sound recognition compared to state-of-the-art methods.
TimbreTron transfers musical timbre using CQT and WaveNet.
problem Transfer musical timbre while preserving pitch, rhythm, and loudness.
method Apply image domain style transfer to CQT representation, then generate high-quality waveform with WaveNet.
result TimbreTron recognizably transfers timbre while preserving musical content.
VDA improves disentanglement of latent representations in complex signals.
problem Learning disentangled and interpretable representations in nonstationary, high-dimensional time-evolving signals.
method Variational decomposition autoencoding (VDA) framework, incorporating signal decomposition, contrastive self-supervised task, and variational prior approximation.
result DecVAEs surpass state-of-the-art VAE-based methods in disentanglement quality and generalization.
New model-independent compact representations of imaginary-time data are presented in terms of the intermediate representation (IR) of analytical continuation. This is motivated by a recent numerical finding by the authors [J. Otsuki et al., arXiv:1702.03056]. We demonstrate the efficiency of the IR through continuous-…
Proposes a deep multi-scale neural network for EEG signal representation learning.
problem Capturing multi-frequency properties in EEG signals for better brain-computer interface.
method A novel deep multi-scale neural network that discovers feature representations in multiple frequency/time ranges and extracts spatial relationships.
result Improved performance in various active/passive BCI datasets compared to state-of-the-art methods.
Deep learning reveals ubiquitous predictability in high-frequency returns.
problem Predicting returns in order book markets at high frequencies.
method Volume representation of the order book, deep learning models, model confidence sets.
result Predictability in mid-price returns is ubiquitous at high frequencies.
HyFAD improves time series imputation by combining time and frequency diffusion.
problem Improve time series imputation by handling frequency-sensitive denoising and balancing global and local dynamics.
method HyFAD is a hybrid time-frequency diffusion model with frequency-aware embedding, built on DDPM paradigm.
result HyFAD achieves state-of-the-art performance in time series imputation.
We introduce a trade strategy representation theorem for performance measurement and portable alpha in high frequency trading, by embedding a robust trading algorithm that describe portfolio manager market timing behavior, in a canonical multifactor asset pricing model. First, we present a spectral test for market timi…
Study non-parametric frequency-domain system identification from finite samples.
problem Frequency-domain system identification from limited data.
method Empirical Transfer Function Estimate (ETFE) under sub-Gaussian colored noise and stability assumptions.
result ETFE estimates are concentrated around true values with a finite-sample rate of Ntot−1/3 for all frequencies in the H∞ norm. Managing the prediction of metrics in high-frequency financial markets is a challenging task. An efficient way is by monitoring the dynamics of a limit order book to identify the information edge. This paper describes the first publicly available benchmark dataset of high-frequency limit order markets for mid-price pre…
Fusion framework improves time series classification across different datasets.
problem Kernel-based methods like Rocket perform inconsistently across datasets.
method Fusion-3 framework that adaptively fuses three representations (Rocket, SAX, SFA) based on dataset properties.
result Fusion-3 framework yields small but consistent average improvements over Rocket on 113 UCR datasets.
Deep learning detects arrhythmias from ECGs using multidimensional representations.
problem Detecting arrhythmias from ECGs using traditional methods.
method Convert 1-D ECG data into 2-D images, then use deep learning for classification.
result Deep learning outperforms existing methods in arrhythmia detection.
New algorithms improve time series classification accuracy and efficiency while enhancing interpretability.
problem Lack of interpretability in time series classification algorithms.
method Combining multiple resolutions and domains, using SEQL with greedy feature selection.
result SAX-SFA-SEQL achieves similar accuracy to state-of-the-art methods but with lower computational time.
Textual data predicts electricity consumption and weather.
problem Lack of textual data in time series prediction models.
method Used TF-IDF and neural word embeddings to predict time series from text.
result Textual data can predict time series with sufficient accuracy.
We present a sparse and invariant representation with low asymptotic complexity for robust unsupervised transient and onset zone detection in noisy environments. This unsupervised approach is based on wavelet transforms and leverages the scattering network from Mallat et al. by deriving frequency invariance. This frequ…
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
problem Improving acoustic scene classification accuracy.
method Harmonic and percussive source separation, two-stream CNN architecture, bilinear pooling.
result Improved accuracy on DCASE 2019 sub task 1a dataset.
This study applies EMD to MSCI World index and converts IMFs into graphs for GNN modeling.
problem Modeling financial time series with GNNs.
method EMD, CEEMDAN, graph transformations (natural visibility, horizontal visibility, recurrence, transition graphs), topological analysis.
result High-frequency IMFs yield dense, highly connected small-world graphs; low-frequency IMFs produce sparser networks.
Developed a diffusion model on spherical data, addressing geometric and stochastic challenges.
problem Diffusion models on spherical data face unique geometric and stochastic issues.
method Extended spectral diffusion to spherical harmonics, introducing modified stochastic differential equations.
result Introduced a geometry-dependent inductive bias in spectral diffusion models.
Autoencoder detects subtle changes in time series data.
problem Detect abrupt changes in time series data with high accuracy.
method Autoencoder with time-invariant representation and postprocessing.
result Outperforms baseline methods on various data sets.
FRAGE learns word embeddings without frequency bias, improving performance across NLP tasks.
problem Word embeddings are biased towards word frequency, affecting performance for rare words.
method Adversarial training to learn Frequency-Agnostic word Embedding (FRAGE).
result FRAGE achieves higher performance than baselines in all four NLP tasks.
A new FFT-based method simplifies causal structure recovery for linear dynamical systems.
problem Efficiently identifying dynamic causal effects from time-series data.
method FFT-based approach to reduce computational complexity to O(Tn3logN). result Significant computational advantage for graph reconstruction.
MCLNN improves sound event recognition with fewer parameters.
problem Improving sound event recognition with deep neural networks.
method Developed MCLNN to enforce sparseness and frequency shift invariance.
result MCLNN achieved competitive performance with 12% fewer parameters.
WaveLSFormer learns profitable trading policies from financial time series data.
problem Challenges in learning profitable intraday trading policies from financial time series data.
method WaveLSFormer uses a learnable wavelet-based long-short Transformer to jointly perform multi-scale decomposition and return-oriented decision learning.
result WaveLSFormer consistently outperforms MLP, LSTM, and Transformer backbones in trading performance.