TCN
PulseAugur coverage of TCN — every cluster mentioning TCN across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New CPDA Framework Enhances Unsupervised Time-Series Domain Adaptation
Researchers have introduced Class-Conditional Path Distribution Alignment (CPDA), a novel framework for unsupervised time-series domain adaptation. Unlike existing methods that align marginal feature distributions, CPDA…
-
Time-series forecasting benchmarks may inflate AI model performance, study finds
A recent paper questions the evaluation methods for time-series forecasting models, arguing that current benchmarks often favor models adept at learning repetitive patterns. The authors suggest that these benchmarks may…
-
Deep TCNs with Label-Wise Attention Boost Medical Coding Accuracy
Researchers have developed a novel deep neural network model designed to improve the accuracy of medical coding. This model, which combines multi-layer Temporal Convolutional Networks (TCNs) with a label-wise attention …
-
Temporal Convolutional Networks for Trajectory Inpainting
Researchers have developed a Temporal Convolutional Network (TCN) designed to reconstruct missing segments in trajectory data. This model utilizes symmetric dilation, allowing it to consider both past and future observa…
-
New CruiseBench benchmark standardizes aircraft engine RUL prediction
Researchers have introduced CruiseBench, a new benchmark designed to standardize the evaluation of remaining useful life (RUL) prediction models for aircraft engines. This benchmark is derived from the N-CMAPSS dataset,…
-
Deep learning model predicts adhesive forces in soft robotics
Researchers have developed a deep learning model capable of rapidly predicting adhesive forces in viscoelastic materials, a task that previously required computationally intensive simulations. The model, utilizing a seq…
-
New AI framework boosts fault prediction accuracy for complex systems
Researchers have developed a novel prognostic framework integrating Spatiotemporal Permutation Entropy (STPE) with Boosted Enhanced Quantile Regression Neural Networks (B-EQRNNs) for long-horizon fault prediction in com…
-
New AI framework uses LLM and time-series model for autonomous cyber defense
A new research paper introduces a neuro-agentic control framework that combines a Large Language Model (LLM) planner, like Gemini 2.5 Flash-Lite, with a time-series foundation model (TimesFM). This framework aims to aut…
-
New AI framework uses LLMs and physics models for industrial security
Researchers have developed a novel neuro-agentic control framework that combines a Large Language Model (LLM) planner, like Gemini 2.5 Flash-Lite, with a Time-Series Foundation Model (TimesFM) to enhance security in ind…
-
Study Compares AI Architectures for Mobile Health Forecasting
A new study compares six deep learning architectures, two Foundation Models (FM), and statistical baselines for multi-horizon behavioral forecasting using mobile health data. The research found that no single architectu…
-
New method improves zero-shot human activity recognition
Researchers have developed a new method to improve zero-shot learning for human activity recognition using inertial measurement unit (IMU) data. Their approach focuses on bridging the gap between sensor data and semanti…
-
AI models leverage WiFi signals for privacy-preserving human activity recognition
Researchers have developed new deep learning frameworks for human activity recognition using WiFi signals, offering a privacy-preserving alternative to camera-based systems. One approach, WISE-HAR, utilizes an ensemble …
-
New TCMP model achieves SOTA multi-object tracking with high efficiency
Researchers have developed a new Temporal Convolutional Motion Predictor (TCMP) for multi-object tracking that challenges the trend of using overly complex generative models. TCMP utilizes a modified Temporal Convolutio…
-
Deep learning models show promise in pavement, aero-engine, and affect recognition tasks
Researchers are exploring deep learning models for predictive maintenance and performance analysis across various domains. One study utilizes CNN and LSTM networks with extensive pavement condition data from Texas to mo…