We propose an adaptive improved natural gradient algorithm for blind separation of independent sources. First, inspired by the well-known backpropagation algorithm, we incorporate a momentum term into the natural gradient learning process to accelerate the convergence rate and improve the stability. Then an estimation function for the adaptation of the separation model is obtained to adaptively control a step-size parameter and a momentum factor. The proposed natural gradient algorithm with variable step-size parameter and variable momentum factor is therefore particularly well suited to blind source separation in a time-varying environment, such as an abruptly changing mixing matrix or signal power. The expected improvement in the convergence speed, stability, and tracking ability of the proposed algorithm is demonstrated by extensive simulation results in both time-invariant and time-varying environments. The ability of the proposed algorithm to separate extremely weak or badly scaled sources is also verified. In addition, simulation results show that the proposed algorithm is suitable for separating mixtures of many sources (e.g., the number of sources is 10) in the complete case.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1162/neco.2008.07-07-562 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Vegetation Types Shift Physiological and Phenological Controls on Carbon Sink Strength in a Coastal Zone.
Glob Chang Biol
January 2025
Key Laboratory of Coastal Zone Environmental Processes and Ecological Remediation, Yantai Institute of Coastal Zone Research, Chinese Academy of Sciences, Yantai, Shandong, China.
The carbon sink function performed by the different vegetation types along the environmental gradient in coastal zones plays a vital role in mitigating climate change. However, inadequate understanding of its spatiotemporal variations across different vegetation types and associated regulatory mechanisms hampers determining its potential shifts in a changing climate. Here, we present long-term (2011-2022) eddy covariance measurements of the net ecosystem exchange (NEE) of CO at three sites with different vegetation types (tidal wetland, nontidal wetland, and cropland) in a coastal zone to examine the role of vegetation type on annual carbon sink strength.
View Article and Find Full Text PDFThe Interactive Role of Climatic Transfer Distance and Overstory Retention on Douglas-Fir Seedling Survival and Height Growth in Interior British Columbia.
Glob Chang Biol
January 2025
Faculty of Forestry, Forest Sciences Centre, The University of British Columbia, Vancouver, British Columbia, Canada.
The future climatic niche of interior Douglas-fir (Pseudotsuga menziesii var. glauca [Mirb.] Franco) is expected to have little spatial overlap with its current range due to climate change.
View Article and Find Full Text PDFAnalysis of the genetic basis of fiber-related traits and flowering time in upland cotton using machine learning.
Theor Appl Genet
January 2025
State Key Laboratory of Cotton Bio-Breeding and Integrated Utilization, Institute of Cotton Research of Chinese Academy of Agricultural Sciences, Anyang, 455000, Henan, China.
Cotton is an important crop for fiber production, but the genetic basis underlying key agronomic traits, such as fiber quality and flowering days, remains complex. While machine learning (ML) has shown great potential in uncovering the genetic architecture of complex traits in other crops, its application in cotton has been limited. Here, we applied five machine learning models-AdaBoost, Gradient Boosting Regressor, LightGBM, Random Forest, and XGBoost-to identify loci associated with fiber quality and flowering days in cotton.
View Article and Find Full Text PDFMid-Infrared High-Power InGaAsSb/AlGaInAsSb Multiple-Quantum-Well Laser Diodes Around 2.9 μm.
Nanomaterials (Basel)
January 2025
Key Laboratory of Optoelectronic Materials and Devices, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China.
Antimonide laser diodes, with their high performance above room temperature, exhibit significant potential for widespread applications in the mid-infrared spectral region. However, the laser's performance significantly degrades as the emission wavelength increases, primarily due to severe quantum-well hole leakage and significant non-radiative recombination. In this paper, we put up an active region with a high valence band offset and excellent crystalline quality with high luminescence to improve the laser's performance.
View Article and Find Full Text PDFEnhancement of Fracture Toughness of NiTi Alloy by Controlling Grain Size Gradient.
Nanomaterials (Basel)
January 2025
School of Civil Engineering, Wuhan University, Wuhan 430072, China.
Fracture toughness is a critical indicator for the application of NiTi alloys in medical fields. We propose to enhance the fracture toughness of NiTi alloys by controlling the spatial grain size (GS) gradient. Utilizing rolling processes and heat treatment technology, three categories of NiTi alloys with distinct spatial GS distributions were fabricated and subsequently examined through multi-field synchronous fracture tests.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!