Contrast everything: A hierarchical contrastive framework for medical time-series
Y Wang, Y Han, H Wang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Contrastive representation learning is crucial in medical time series analysis as it alleviates
dependency on labor-intensive, domain-specific, and scarce expert annotations. However …
dependency on labor-intensive, domain-specific, and scarce expert annotations. However …
[HTML][HTML] Automated monitoring innovations for efficient and safe construction practices
As construction projects increase in complexity, there are growing challenges with
conventional monitoring methods in terms of efficiency, safety, and competitiveness …
conventional monitoring methods in terms of efficiency, safety, and competitiveness …
Memory shapelet learning for early classification of streaming time series
X Wan, L Cen, X Chen, Y Xie… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Early classification predicts the class of the incoming sequences before it is completely
observed. How to quickly classify streaming time series without losing interpretability …
observed. How to quickly classify streaming time series without losing interpretability …
[HTML][HTML] Applications of Entropy in Data Analysis and Machine Learning: A Review
SA Sepúlveda-Fontaine, JM Amigó - Entropy, 2024 - mdpi.com
Since its origin in the thermodynamics of the 19th century, the concept of entropy has also
permeated other fields of physics and mathematics, such as Classical and Quantum …
permeated other fields of physics and mathematics, such as Classical and Quantum …
Early Time Series Anomaly Prediction With Multi-Objective Optimization
Anomaly prediction, aiming to predict abnormal events before occurrence, plays a key role
in significantly reducing costs and minimizing potential threats to mechanical devices …
in significantly reducing costs and minimizing potential threats to mechanical devices …
POCKET: Pruning random convolution kernels for time series classification from a feature selection perspective
In recent years, two competitive time series classification models, namely, ROCKET and
MINIROCKET, have garnered considerable attention due to their low training cost and high …
MINIROCKET, have garnered considerable attention due to their low training cost and high …
Water source identification in mines combining LIF technology and ResNet
P Yan, Y Zhao, G Li, J Wang, W Wang - Journal of Mountain Science, 2023 - Springer
The problem of mine water source has always been an important hidden danger in mine
safety production. The water source under the mine working face may lead to geological …
safety production. The water source under the mine working face may lead to geological …
Combining machine learning, molecular dynamics, and free energy analysis for (5HT)-2A receptor modulator classification
X Yu, Y Eid, M Jama, D Pham, M Ahmed… - Journal of Molecular …, 2024 - Elsevier
Abstract The 5-Hydroxytryptamine (5HT)-2A receptor, a key target in psychoactive drug
development, presents significant challenges in the design of selective compounds. Here …
development, presents significant challenges in the design of selective compounds. Here …
Hierarchical Multimodal Graph Learning for Outfit Compatibility Modelling
Outfit compatibility modelling plays a significant role in e-commerce decision-making, but the
existing methods are restricted to modelling the visual and textual information and have …
existing methods are restricted to modelling the visual and textual information and have …
P-ROCKET: Pruning Random Convolution Kernels for Time Series Classification
In recent years, two time series classification models, ROCKET and MINIROCKET, have
attracted much attention for their low training cost and state-of-the-art accuracy. Utilizing …
attracted much attention for their low training cost and state-of-the-art accuracy. Utilizing …