An Objective Performance Evaluation of the LSTM Networks in Time Series Classification

• URL: http://arxiv.org/abs/2605.19311v1
• Date: Tue, 19 May 2026 03:47:01 GMT
• Title: An Objective Performance Evaluation of the LSTM Networks in Time Series Classification
• Abstract summary: Long short-term memory (LSTM) networks have become a popular choice for time-series analysis.<n>This paper presents a performance evaluation framework comparing an LSTM classifier against a model-based expectation (EM) classifier for binary time-series classification.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid adoption of deep learning has increasingly led to data-driven models replacing classical model-based algorithms, even in domains governed by well-understood physical laws. While data-driven models, such as long short-term memory (LSTM) networks, have become a popular choice for time-series analysis, their performance relative to model-based approaches in structured environments is rarely evaluated objectively. This paper presents a performance evaluation framework comparing an LSTM classifier against a model-based expectation maximization (EM) classifier for binary time-series classification. The evaluation is conducted on two scalar linear Gaussian state space models differing only in their noise statistics, where the Kalman filter likelihood ratio test with true parameters serves as a reference for the best achievable classification performance.Through Monte Carlo simulations, the classifiers are evaluated across three axes: task difficulty, controlled by the separation in process or measurement noise between the two models; sequence length; and training dataset size. The results show that the EM classifier, which exploits the known model structure, performs strongly when the data conform to the assumed model class. The LSTM classifier requires a larger separation in noise statistics to achieve reliable classification, and its performance saturates below the reference classifier when the models differ only in measurement noise, regardless of sequence length or training dataset size.

Related papers

• Sleep-stage efficient classification using a lightweight self-supervised model [9.983526161001995]
  The mulEEG model, which learns electroencephalogram signal representations in a self-supervised manner, was simplified here.<n>The results showed that reducing the volume of data offered a better cost-benefit ratio compared to simplifying the model.
  arXiv  Detail & Related papers  (2026-05-25T19:37:54Z)
• Elastic Net Regularization and Gabor Dictionary for Classification of Heart Sound Signals using Deep Learning [1.8907108368038215]
  We evaluate the classification performance of deep learning networks in discriminating five heart valvular conditions.<n>A fitting model is obtained based on a heart sound signal and an overcomplete dictionary of Gabor atoms.<n>The best classification accuracy of $98.95%$ is achieved with the second architecture.
  arXiv  Detail & Related papers  (2026-04-14T09:09:30Z)
• TSFM in-context learning for time-series classification of bearing-health status [2.1569807291469454]
  This paper introduces a classification method using in-context learning in time-series foundation models (TSFM)<n>We show how data, which was not part of the TSFM training data corpus, can be classified without the need of finetuning the model.<n>We apply this method to vibration data for assessing the health state of a bearing within a servo-press motor.
  arXiv  Detail & Related papers  (2025-11-19T14:01:12Z)
• Area under the ROC Curve has the Most Consistent Evaluation for Binary Classification [3.1850615666574806]
  This study investigates how consistent different metrics are at evaluating models across data of different prevalence. I find that evaluation metrics that are less influenced by prevalence offer more consistent evaluation of individual models and more consistent ranking of a set of models.
  arXiv  Detail & Related papers  (2024-08-19T17:52:38Z)
• LETS-C: Leveraging Text Embedding for Time Series Classification [15.520883566827608]
  We propose an alternative approach to leveraging the success of language modeling in the time series domain.<n>We utilize a text embedding model to embed time series and then pair the embeddings with a simple classification head composed of convolutional neural networks (CNN) and multilayer perceptron (MLP)<n>Our findings suggest that leveraging text embedding models to encode time series data, combined with a simple yet effective classification head, offers a promising direction for achieving high-performance time series classification.
  arXiv  Detail & Related papers  (2024-07-09T04:07:57Z)
• Latent Semantic Consensus For Deterministic Geometric Model Fitting [109.44565542031384]
  We propose an effective method called Latent Semantic Consensus (LSC) LSC formulates the model fitting problem into two latent semantic spaces based on data points and model hypotheses. LSC is able to provide consistent and reliable solutions within only a few milliseconds for general multi-structural model fitting.
  arXiv  Detail & Related papers  (2024-03-11T05:35:38Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Dynamically-Scaled Deep Canonical Correlation Analysis [77.34726150561087]
  Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. We introduce a novel dynamic scaling method for training an input-dependent canonical correlation model.
  arXiv  Detail & Related papers  (2022-03-23T12:52:49Z)
• Locate This, Not That: Class-Conditioned Sound Event DOA Estimation [50.74947937253836]
  We propose an alternative class-conditioned SELD model for situations where we may not be interested in all classes all of the time. This class-conditioned SELD model takes as input the spatial and spectral features from the sound file, and also a one-hot vector indicating the class we are currently interested in localizing.
  arXiv  Detail & Related papers  (2022-03-08T16:49:15Z)
• Training Experimentally Robust and Interpretable Binarized Regression Models Using Mixed-Integer Programming [3.179831861897336]
  We present a model-based approach to training robust and interpretable binarized regression models for multiclass classification tasks. Our MIP model balances the optimization of prediction margin and model size by using a weighted objective. We show the effectiveness of training robust and interpretable binarized regression models using MIP.
  arXiv  Detail & Related papers  (2021-12-01T11:53:08Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.