Temporal Convolutional Network
PulseAugur coverage of Temporal Convolutional Network — every cluster mentioning Temporal Convolutional Network across labs, papers, and developer communities, ranked by signal.
-
New TEMPEST model offers scalable driver identification with high accuracy
Researchers have developed TEMPEST, a new Temporal Convolutional Network embedding model that uses an additive angular margin loss (ArcFace) for scalable driver identification. This model maps 60-second multimodal drivi…
-
Quantum-inspired QiKAN model leads in neutron monitor time series forecasting
A new research paper explores various models for forecasting time series data from the Lomnicky Stit neutron monitor. The study compares simple seasonal baselines with advanced deep learning architectures like LSTM, TCN…
-
New TCN-Transformer Model Predicts Satellite Collision Risk
Researchers have developed a novel hybrid Temporal Convolutional Network (TCN)-Transformer model to predict satellite collision probabilities more effectively. This model aims to improve the analysis of Conjunction Data…
-
New framework enhances online signature verification with path signatures and T-Mamba
Researchers have developed a new framework for online signature verification that combines the augmented path signature (APS) descriptor with a T-Mamba model. The APS descriptor captures geometric structures and nonline…
-
AI model predicts ICU organ dysfunction with 74% accuracy
Researchers have developed a Temporal Convolutional Network (TCN) to predict future organ dysfunction in ICU patients using data from MIMIC-IV. The model achieved an R2 score of 0.740 and an MAE of 1.431, outperforming …
-
New research advances Visual Inertial Odometry for robotics
Two new research papers explore advancements in Visual Inertial Odometry (VIO) for robotics. The first paper introduces a minimalist approach using only four visual sensors and an Inertial Measurement Unit (IMU) to achi…
-
NanoSleep: Efficient AI for Sleep Stage Classification on Wearables
Researchers have developed NanoSleep, a compact hybrid temporal convolutional network designed for efficient sleep stage classification from single-channel EEG data. This model addresses the challenge of deploying accur…
-
Deep learning models enhance H-IoT cybersecurity with lightweight detection
Researchers have developed new deep learning models, Temporal Convolutional Network (TCN) and Residual TCN (Res-TCN), to enhance cybersecurity for healthcare Internet of Things (H-IoT) systems. These lightweight models …
-
New AI models enhance handwriting trajectory reconstruction from sensor data · 3 sources tracked
Researchers have developed new methods for reconstructing handwriting trajectories using digital pens equipped with IMU sensors. One approach utilizes a Mixture-of-Experts (MOE) model, with separate experts for pen-touc…
-
New framework uses self-supervised learning for early sepsis prediction
Researchers have developed a new framework for predicting sepsis using self-supervised learning techniques, specifically Joint Embedding Predictive Architecture (JEPA) and Variance-Invariance-Covariance Regularization (…
-
In-vehicle Digital Twin framework detects Sybil attacks, improves collision warnings
Researchers have developed a new collision warning framework for connected vehicles that incorporates a Digital Twin (DT) and Sybil attack detection. This framework utilizes a Temporal Convolutional Network (TCN) and Hi…
-
New Sensor Fusion Framework Enhances Robot Interaction
Researchers have developed a new framework for tactile-proprioceptive sensor fusion to enhance physical human-robot interaction. This method combines tactile data from pneumatic skin pads with motor-current-based propri…
-
Minimalist VIO system uses photodiodes for robot navigation
Researchers have developed a minimalist approach to visual-inertial odometry (VIO) for differential-drive robots, utilizing only four visual measurements and an IMU for robust motion estimation. This system employs down…
-
Minimalist VIO system uses photodiodes for robot navigation
Researchers have developed a minimalist visual-inertial odometry system for differential-drive robots that uses only four photodiodes and an IMU. This approach bypasses the need for resource-intensive cameras by employi…
-
Google AI uses smartwatches for advanced gait analysis
Google AI researchers have developed a deep learning model capable of accurately estimating advanced walking metrics using data from smartwatches. This model, built on a temporal convolutional network (TCN) architecture…