Related papers: Identifying Stochasticity in Time-Series with Auto…
In remote healthcare monitoring, time series representation learning reveals critical patient behavior patterns from high-frequency data. This study analyzes home activity data from individuals living with dementia by proposing a two-stage,…
Effective modeling of electronic health records presents many challenges as they contain large amounts of irregularity most of which are due to the varying procedures and diagnosis a patient may have. Despite the recent progress in machine…
Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to…
We explore the possibility of retrieving cosmological information from 21-cm tomographic data at intermediate redshift. The first step in our approach consists of training an encoder, composed of several three dimensional convolutional…
Optimizing molecular design and discovering novel chemical structures to meet certain objectives, such as quantitative estimates of the drug-likeness score (QEDs), is NP-hard due to the vast combinatorial design space of discrete molecular…
This work presents a non-intrusive surrogate modeling scheme based on machine learning technology for predictive modeling of complex systems, described by parametrized time-dependent PDEs. For these problems, typical finite element…
This paper introduces a novel learning-based Stochastic Hybrid System (LSHS) approach for detecting and classifying various contingencies in modern power systems. Specifically, the proposed method is capable of identifying hidden…
Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many…
Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical…
Most existing time series classification methods adopt a discriminative paradigm that maps input sequences directly to one-hot encoded class labels. While effective, this paradigm struggles to incorporate contextual features and fails to…
Event cameras are activity-driven bio-inspired vision sensors, thereby resulting in advantages such as sparsity,high temporal resolution, low latency, and power consumption. Given the different sensing modality of event camera and high…
To analyze high-dimensional and complex data in the real world, deep generative models, such as variational autoencoder (VAE) embed data in a low-dimensional space (latent space) and learn a probabilistic model in the latent space. However,…
Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…
In recent years, there has been renewed interest in developing methods for skeleton-based human action recognition. A skeleton sequence can be naturally represented as a high-order tensor time series. In this paper, we model and analyze…
Climate change has increased the vulnerability of forests to insect-related damage, resulting in widespread forest loss in Central Europe and highlighting the need for effective, continuous monitoring systems. Remote sensing based forest…
Accurate behavior prediction for vehicles is essential but challenging for autonomous driving. Most existing studies show satisfying performance under regular scenarios, but most neglected safety-critical scenarios. In this study, a…
We analyze the training of a two-layer autoencoder used to parameterize a flow-based generative model for sampling from a high-dimensional Gaussian mixture. Previous work shows that the phase where the relative probability between the modes…
An electrocardiogram (ECG) is a time-series signal that is represented by one-dimensional (1-D) data. Higher dimensional representation contains more information that is accessible for feature extraction. Hidden variables such as frequency…
Autoencoders have been extensively used in the development of recent anomaly detection techniques. The premise of their application is based on the notion that after training the autoencoder on normal training data, anomalous inputs will…
Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…