Results 61 to 70 of about 1,698,574 (297)

Nonnegative Matrix Factorization with Transform Learning [PDF]

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Traditional NMF-based signal decomposition relies on the factorization of spectral data, which is typically computed by means of short-time frequency transform. In this paper we propose to relax the choice of a pre-fixed transform and learn a short-time orthogonal transform together with the factorization.
Dylan Fagot, Herwig Wendt, Cédric Févotte   +2 more
openaire   +3 more sources

Partial Identifiability for Nonnegative Matrix Factorization

SIAM Journal on Matrix Analysis and Applications, 2023
Abstract. Given a nonnegative matrix factorization, [Formula: see text], and a factorization rank, [Formula: see text], exact nonnegative matrix factorization (exact NMF) decomposes [Formula: see text] as the product of two nonnegative matrices, [Formula: see text] and [Formula: see text] with [Formula: see text] columns, such as ...
Nicolas Gillis, Róbert Rajkó
openaire   +5 more sources

STRIDE: A Sequencing Depth Robust Metric for Sparse Chromosome Conformation Capture Data Comparison

Advanced Science, EarlyView.
A mean first passage time (MFPT)‐based representation transforms sparse Hi‐C contact maps into robust topological representations, preserving biologically meaningful chromatin features and facilitating robust analysis of TADs, chromatin loops, differential chromatin contacts, and sparse single‐cell Hi‐C data.
Bingxiang Xu, Xiaomeng Gao, Weichu Tao, Zhihua Zhang, Feifei Li   +4 more
wiley   +1 more source

Stress‐Regulated Li Plating in Hybrid Ag–Carbon/Carbon Nanofiber Anodes for Durable All‐Solid‐State Batteries

Advanced Energy Materials, EarlyView.
Hybrid Ag–C/CNF anodes enable stress‐regulated operation of high‐loading solid‐state batteries by coupling uniform Li nucleation with mechanically compliant Li accommodation. The Ag–C interlayer homogenizes deposition, while the porous CNF framework buffers volumetric strain.
Junhee Kang, Tae Young Lee, Jeongvin Park, Hong Rim Shin, Dong Seok Kim, Jieun Lee, Hun‐Gi Jung, Jeong‐Hee Choi, Jong‐Won Lee   +8 more
wiley   +1 more source

Speech Enhancement Control Design Algorithm for Dual-Microphone Systems Using β-NMF in a Complex Environment

Complexity, 2018
Single-microphone speech enhancement algorithms by using nonnegative matrix factorization can only utilize the temporal and spectral diversity of the received signal, making the performance of the noise suppression degrade rapidly in a complex ...
Dong-xia Wang, Mao-song Jiang, Fang-lin Niu, Yu-dong Cao, Cheng-xu Zhou   +4 more
doaj   +1 more source

Boolean Matrix Factorization via Nonnegative Auxiliary Optimization

IEEE Access, 2021
A novel approach to Boolean matrix factorization (BMF) is presented. Instead of solving the BMF problem directly, this approach solves a nonnegative optimization problem with an additional constraint over an auxiliary matrix whose Boolean structure is ...
Duc P. Truong, Erik Skau, Derek Desantis, Boian Alexandrov   +3 more
doaj   +1 more source

A computational study of Ising‐based solvers for discrete landscape exploration in process optimization

AIChE Journal, EarlyView.
ABSTRACT Conceptual process design combines discrete configuration choices with continuous operating decisions, often yielding difficult mixed‐integer nonlinear or simulation‐based optimization problems. This work presents an exploratory computational assessment of Ising‐based solvers, simulated annealing, quantum annealing, and entropy computing, as ...
Yirang Park, David E. Bernal Neira
wiley   +1 more source

MetaPaCS: A Novel Meta‐Learning Framework for Pancreatic Cancer Subtype Identification

Advanced Intelligent Systems, EarlyView.
We have developed MetaPaCS, an ensemble meta‐learning framework for reliable prediction of pancreatic cancer subtypes with high accuracy. MetaPaCS is capable of capturing subtype‐specific distinct gene expression patterns and drug‐disease associations for pancreatic cancer.
Nick B. Peterson, Mengtao Sun, Xinchao Wu, Jieqiong Wang, Shibiao Wan   +4 more
wiley   +1 more source

Fuzzy Approximate Solution of Positive Fully Fuzzy Linear Matrix Equations

Journal of Applied Mathematics, 2013
The fuzzy matrix equations A~⊗X~⊗B~=C~ in which A~, B~, and C~ are m×m, n×n, and m×n nonnegative LR fuzzy numbers matrices, respectively, are investigated.
Xiaobin Guo, Dequan Shang
doaj   +1 more source

Beyond the Camera: Epidermal Sensor Platforms for Intelligent Facial Expression Recognition and Interactive Human Monitoring

Advanced Intelligent Systems, EarlyView.
Skin‐conformal epidermal sensors enable camera‐free intelligent facial monitoring by converting facial deformation and muscle activity into electrical signals through piezoresistive, capacitive, electrophysiologic, and self‐powered mechanisms. Coupled with artificial intelligence (AI), these platforms support facial expression recognition, human ...
Jeehyun Joung, Manchi Nagaraju, Jun‐Gyu Choi, Jaeil Park, Sungjun Park, Daegun Kim   +5 more
wiley   +1 more source