Article
Ophthalmology
Carlyn Patterson Gentile, Nabin R. Joshi, Kenneth J. Ciuffreda, Kristy B. Arbogast, Christina Master, Geoffrey K. Aguirre
Summary: The study used Principal Component Analysis (PCA) to characterize developmental changes of prVEP in youths, revealing narrowing and amplitude reduction of the P100 peak with maturation, as well as a broader and smaller P100 peak in male subjects compared to female subjects.
TRANSLATIONAL VISION SCIENCE & TECHNOLOGY
(2021)
Article
Multidisciplinary Sciences
Qingyi Wang, Yiqiong Zhang, Shuai Yin, Yuduo Wang, Genping Wu
Summary: The proposed method for underdetermined blind source separation (UBSS) includes three main steps: screening single source points using principal component analysis, estimating the mixing matrix using a combination of OPTICS and an improved potential function, and recovering source signals using an improved subspace projection method. The method is independent of input parameters, offers high accuracy and robustness, and performs well in noisy environments.
Article
Telecommunications
Enrico Testi, Andrea Giorgetti
Summary: This paper proposes a blind methodology for counting and locating nodes in a wireless network using power measurements collected by sensors. The approach allows for detection and localization of nodes without prior knowledge of the network's specific features, and achieves low localization error under certain conditions.
IEEE COMMUNICATIONS LETTERS
(2022)
Article
Acoustics
Wenshuai Wang, Kuangang Fan, Qinghua Ouyang, Ye Yuan
Summary: This paper introduces an acoustic UAV detection method based on blind source separation (BSS) framework to solve the UAV sound detection problem with multi-source interference. The experimental results show that the proposed method achieves effective detection of UAVs with high detection rate of over 90% in different tests and demonstrates good robustness.
Article
Chemistry, Analytical
Norsalina Hassan, Dzati Athiar Ramli
Summary: Blind source separation (BSS) is a method to recover source signals without knowing the mixing process or source signals. Sparse component analysis (SCA) is a commonly used solution for underdetermined BSS, which includes mixing matrix estimation and source recovery estimation. Adaptive time-frequency thresholding (ATFT) is introduced to improve the accuracy of the mixing matrix estimation, while least squares methods are used for source recovery estimation.
Article
Computer Science, Interdisciplinary Applications
Ivana Labounkova, Rene Labounek, Igor Nestrasil, Jan Odstrcilik, Ralf P. Tornow, Radim Kolar
Summary: Dynamic optical imaging of retinal hemodynamics is an evolving technique in vision and eye-disease research, with video-recording capturing distinct functional phenomena. The use of blind source separation as an automated localizer of temporally synchronized hemodynamics in retina video-imaging has shown promising results, with the detection of reproducible areas and reduction of noise in patterns' dynamics through post-processing methods. The study also revealed differences in phase shifts between different dynamic patterns and detected low frequency oscillations possibly related to respiratory effects in the time-courses of the recordings.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Artificial Intelligence
Sam Ansari, Abbas Saad Alatrany, Khawla A. Alnajjar, Tarek Khater, Soliman Mahmoud, Dhiya Al-Jumeily, Abir Jaafar Hussain
Summary: Blind source separation is an important signal processing technique for extracting desired signals from a mixture of other signals. This paper presents a systematic literature survey focusing on AI-based frameworks, examining various techniques used in blind source separation and their performance in real-world scenarios. The study identifies research gaps and outlines potential avenues for future research.
Article
Computer Science, Hardware & Architecture
Huanzhuo Wu, Zuo Xiang, Giang T. Nguyen, Yunbin Shen, Frank H. P. Fitzek
Summary: COIN leverages network nodes' computing power to offload applications' computations, but the monolithic design of source separation algorithms and the lack of a flexible transport layer hinders its exploitation.
Article
Computer Science, Artificial Intelligence
Shuang Ma, Hongjuan Zhang, Zhuoyun Miao
Summary: A novel algorithm based on the analysis sparse constraint of the source over an adaptive analysis dictionary is proposed in this paper to address the blind source separation problem. The alternating scheme used in the method helps to estimate the dictionary, the source, and the mixing matrix alternatively, leading to an improved separation performance according to numerical experiments.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Zhanyu Zhu, Xingjie Chen, Zhaomin Lv
Summary: This study proposes a two-stage single-source point screening method that combines the cosine angle algorithm and the L1-norm optimization algorithm for estimating the mixing matrix and achieving blind source separation. Experimental results demonstrate that this method can obtain more accurate and robust mixing matrix estimation, leading to better separation of the source signals.
Article
Computer Science, Theory & Methods
Qiao Zhou, Jie-Peng Yao, Jin-Hai Li, Zhong-Yi Wang, Lan Huang
Summary: In this paper, a smart and universal single-channel blind source separation method is proposed, which combines variational mode decomposition and independent component analysis. By designing a new fitness function and using a loop mode with evaluation parameters feedback, the method can automatically recover the original source signals in multiple scenarios. Experimental results show that the proposed method outperforms traditional time-frequency-based methods and deep learning methods in terms of extraction accuracy and waveform integrity. It provides a better and more extensive means for the analysis and application of multicomponent signals.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Acoustics
Jiawei Jian, Li Wang, Zhong-Rong Lu
Summary: This paper proposes a novel method for underdetermined operational modal analysis (OMA) using blind source separation (BSS). The method efficiently transforms the underdetermined problem into determined or overdetermined ones and recovers modal responses and mode shapes using an improved second-order blind identification (SOBI) technique. The effectiveness of the proposed strategy is verified through numerical examples, an experimental frame case, and a field test of a pedestrian bridge.
JOURNAL OF SOUND AND VIBRATION
(2023)
Article
Biochemical Research Methods
Kuangnan Fang, Rui Ren, Qingzhao Zhang, Shuangge Ma
Summary: Dimension reduction techniques like PCA, PLS, and CCA are extensively used in the analysis of high-dimensional omics data. Integrative analysis, which outperforms meta-analysis and individual-data analysis, has been developed for multiple datasets with compatible designs. We developed the R package iSFun to facilitate integrative dimension reduction analysis, offering comprehensive analysis options under different models and penalties.
Article
Engineering, Electrical & Electronic
Hong Zhong, Yang Ding, Yahui Qian, Liangmo Wang, Baogang Wen
Summary: This paper proposes a novel nonlinear underdetermined blind source separation (UBSS) solution for bearing fault diagnosis. It utilizes source number estimation and improved sparse component analysis (SCA) to deal with the problem of nonlinear mixture of vibration signals. The proposed approach includes ensemble empirical mode decomposition (EEMD), correlation coefficient (CC), and adaptive threshold singular value decomposition (ATSVD) for source number estimation, and short-time Fourier transform (STFT) for transforming observed signals into the time-frequency domain. The results from simulations and experiments demonstrate that the proposed UBSS solution can accurately estimate the source number and effectively separate the signals.
Article
Computer Science, Artificial Intelligence
Takuya Isomura, Taro Toyoizumi
Summary: The study theoretically validates that a cascade of linear PCA and ICA can accurately solve nonlinear BSS problems, effectively recovering nonlinearly mixed sources, and suggests the importance of employing sensors with sufficient dimensionality to identify true hidden sources of real-world data.
NEURAL COMPUTATION
(2021)
Article
Audiology & Speech-Language Pathology
Ian C. Bruce, Yousof Erfani, Muhammad S. A. Zilany
Article
Computer Science, Theory & Methods
Tarmizi Adam, Raveendran Paramesran
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2019)
Review
Engineering, Electrical & Electronic
Md Yeasir Arafat, Anis Salwa Mohd Khairuddin, Uswah Khairuddin, Raveendran Paramesran
IET INTELLIGENT TRANSPORT SYSTEMS
(2019)
Article
Engineering, Electrical & Electronic
Ganesh Krishnasamy, Raveendran Paramesran
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2019)
Article
Neurosciences
T. J. M. Kwan, M. S. A. Zilany, E. Davies-Venn, Ahmad Khairi Abdul Wahab
EXPERIMENTAL BRAIN RESEARCH
(2019)
Article
Engineering, Electrical & Electronic
Tarmizi Adam, Raveendran Paramesran
SIGNAL IMAGE AND VIDEO PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Md Ekramul Hossain, Muhammad S. A. Zilany, Evelyn Davies-Venn
COMPUTER SPEECH AND LANGUAGE
(2019)
Article
Computer Science, Artificial Intelligence
Wissam A. Jassim, Muhammad S. Zilany
COMPUTER SPEECH AND LANGUAGE
(2019)
Article
Neurosciences
Md Rakibul Mowla, Jesus D. Gonzalez-Morales, Jacob Rico-Martinez, Daniel A. Ulichnie, David E. Thompson
Article
Chemistry, Analytical
Ahmad Suliman, Md Rakibul Mowla, Alaleh Alivar, Charles Carlson, Punit Prakash, Balasubramaniam Natarajan, Steve Warren, David E. Thompson
Summary: Heart rate variability (HRV) features are important for clinical applications such as sleep staging. This study compares the use of ballistocardiograms (BCGs) and electrocardiograms (ECGs) for estimating HRV parameters and sleep staging, and finds that timing differences between BCGs and ECGs can affect the accuracy of sleep staging. The results suggest that BCG-based sleep staging can be comparable to ECG-based techniques, but there may be an increase in sleep-scoring error with larger timing differences.
Article
Medicine, Research & Experimental
Gail I. S. Harmata, Ariane E. Rhone, Christopher K. Kovach, Sukhbinder Kumar, Md Rakibul Mowla, Rup K. Sainju, Yasunori Nagahama, Hiroyuki Oya, Brian K. Gehlbach, Michael A. Ciliberto, Rashmi N. Mueller, Hiroto Kawasaki, Kyle T. S. Pattinson, Kristina Simonyan, Paul W. Davenport, Matthew A. Howard III, Mitchell Steinschneider, Aubrey C. Chan, George B. Richerson, John A. Wemmie, Brian J. Dlouhy
Summary: Postictal apnea, a sudden breathing pause after a seizure, can be caused by amygdala seizures. This study found that electrical stimulation in a specific region of the amygdala can reproduce prolonged breathing loss even after the stimulation ends. The persistent apnea is resistant to rising CO2 levels and air hunger, suggesting impaired CO2 chemosensitivity. Using es-fMRI, they observed changes in activity in brain regions related to chemosensation and interoception. These findings provide insights into SUDEP and may lead to prevention strategies.
Article
Biology
Md Rakibul Mowla, Rachael Cano, Katie J. Dhuyvetter, David E. Thompson
COMPUTERS IN BIOLOGY AND MEDICINE
(2020)
Article
Engineering, Biomedical
David E. Thompson, Md. Rakibul Mowla, Katie J. Dhuyvetter, Joseph W. Tillman, Jane E. Huggins
BRAIN-COMPUTER INTERFACES
(2019)
Article
Engineering, Biomedical
Fabien Lotte, Camille Jeunet, Ricardo Chavarriaga, Laurent Bougrain, Dave E. Thompson, Reinhold Scherer, Md Rakibul Mowla, Andrea Kuebler, Moritz Grosse-Wentrup, Karen Dijkstra, Natalie Dayan
BRAIN-COMPUTER INTERFACES
(2019)
Article
Computer Science, Artificial Intelligence
Siong-Shi Ling, Raveendran Paramesran, Yong-Poh Yu
ADVANCES IN ELECTRICAL AND COMPUTER ENGINEERING
(2019)