Article
Engineering, Biomedical
Chuanmeizhi Wang, Bijan Pesaran, Maryam M. Shanechi
Summary: This paper presents a multiscale model-based Granger-like causality method for studying neural processes. The method, which combines spike trains and field potential signals, is able to recover multiscale neural causality and improve the prediction of neural signals compared to single-scale causality. The study shows the importance of understanding causal interactions across different scales of brain activity.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Environmental Sciences
Weisheng Li, Xuesong Liang, Meilin Dong
Summary: The MDECNN method proposed in this study is a multiscale perception dense coding convolutional neural network that achieves high-quality pan-sharpened images by extracting rich spatial information from input panchromatic images and learning feature mapping relationships to maintain spectral quality. Experiments demonstrate superior performance compared to existing methods.
Article
Chemistry, Physical
Min Li, John Zeng Hui Zhang
Summary: The study developed a coarse-grained water model based on cluster-level electrostatic dipoles and refined it using experimental data. The new model accurately predicts water properties and can be used for building efficient multi-resolution water models.
PHYSICAL CHEMISTRY CHEMICAL PHYSICS
(2021)
Article
Neurosciences
Azat Nasretdinov, Sebastian A. Barrientos, Ivani Brys, Par Halje, Per Petersson
Summary: Psychedelic substances have gained significant attention as potential treatments for psychiatric conditions. Imaging studies suggest that psychedelics alter neuronal firing rates, functional connectivity, and high-frequency oscillations in the brain. To understand the relationship between imaging data and electrophysiological measurements, researchers analyzed the local field potential (LFP) in rodents treated with LSD or ketamine. The results indicate that LSD and ketamine cause altered brain states through different mechanisms, with ketamine leading to increased neuronal activity but reduced connectivity, while LSD reduces connectivity without changing LFP power.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Vishruth B. Gowda, M. T. Gopalakrishna, J. Megha, Shilpa Mohankumar
Summary: This article introduces a foreground segmentation algorithm that solves the challenges of darkness, dynamic background information, and camera jitter by using a triplet CNN, a Transposed Convolutional Neural Network (TCNN), and a Features Pooling Module (FPM). The results show that the algorithm outperforms other state-of-the-art algorithms on the CDnet2014 datasets and enhances the foreground segmentation performance.
Article
Chemistry, Physical
Michael R. DeLyser, W. G. Noid
Summary: Investigated a new class of one-body potentials called square gradient (SG) potentials that can improve the accuracy and transferability of coarse-grained (CG) models. These SG potentials can tune interfacial properties and enhance the performance of various models.
JOURNAL OF CHEMICAL PHYSICS
(2022)
Article
Computer Science, Artificial Intelligence
Serbulent Unsal, Heval Atas, Muammer Albayrak, Kemal Turhan, Aybar C. Acar, Tunca Dogan
Summary: This Analysis compares the performances and advantages of recent deep learning approaches in protein prediction tasks and finds that they show promising results in extracting complex sequence-structure-function relationships.
NATURE MACHINE INTELLIGENCE
(2022)
Article
Biochemical Research Methods
Jim Clauwaert, Gerben Menschaert, Willem Waegeman
Summary: The paper introduces a new approach to gather insights on the transcription process in Escherichia coli, utilizing a transformer-based neural network framework to identify transcription factors and characterize their binding sites and consensus sequences.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Neurosciences
Miriam Schwalm, Dennis R. Tabuena, Curtis Easton, Thomas J. Richner, Pierre Mourad, Hirofumi Watari, William J. Moody, Albrecht Stroh
Summary: In this study, we analyze the cortical representation of brain states based on local photometry recordings and mesoscale cortical calcium imaging, complemented by electrophysiological recordings in mice. We identify two distinct functional states in the sensory cortices, which differ in their spatiotemporal characteristics on the local and global cortical scales. We examine how intrinsic and stimulus-evoked neuronal activity propagates throughout the cortex in a state-dependent manner, supporting the notion that cortical state is a relevant variable to consider for a wide range of neurophysiological experiments.
JOURNAL OF NEUROPHYSIOLOGY
(2022)
Article
Neurosciences
Shengcui Cheng, Xiaoling Chen, Yuanyuan Zhang, Ying Wang, Xin Li, Xiaoli Li, Ping Xie
Summary: This study introduces a novel method, bivariate empirical mode decomposition-MSTE (BMSTE), to quantify the multiscale interaction at local-frequency bands between the cortex and the muscles. Simulation and experimental results confirm the effectiveness of the BMSTE method in describing the multiscale time-frequency characteristics and coupling strength.
COGNITIVE NEURODYNAMICS
(2023)
Article
Computer Science, Software Engineering
Gleb Tkachev, Steffen Frey, Thomas Ertl
Summary: The proposed machine learning approach detects and visualizes complex behavior in spatiotemporal volumes by training models to predict future data values and evaluating prediction errors; Aggregating prediction errors and visualizing them highlights regions of interesting behavior; Applicable to datasets from various domains, meaningful results are produced with minimal assumptions.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2021)
Article
Engineering, Manufacturing
Guo Yilin, Jerry Fuh Ying Hsi, Lu Wen Feng
Summary: Additive manufacturing allows for complex geometries in parts, expanding the design space to microarchitecture scale. Optimizing structures within this expanded design space can improve performance. A surrogate model based on 3D convolutional neural networks provides flexibility in predicting material properties of microscale structures.
VIRTUAL AND PHYSICAL PROTOTYPING
(2021)
Article
Environmental Sciences
Yongshi Jie, Hongyan He, Kun Xing, Anzhi Yue, Wei Tan, Chunyu Yue, Cheng Jiang, Xuan Chen
Summary: The paper proposes a MECA-Net network for road extraction, which solves the challenge of road identification in remote sensing images through multiscale feature encoding and long-range context-aware modules.
Article
Computer Science, Information Systems
Li Zhang, Zhipeng Fu, Huaping Guo, Yange Sun, Xirui Li, Mingliang Xu
Summary: A novel method for detecting steel surface defects through a multiscale local and global feature fusion mechanism is proposed in this paper to improve the detection performance. The proposed method utilizes a convolutional neural network model with downsampling and convolution operations to obtain rough multiscale feature maps. By introducing a context-extraction block and self-attention learning, multiscale global context information is obtained to compensate for the shortcomings of CNNs. Furthermore, the method achieves high accuracy on NEU-DET and GC10-DET datasets, surpassing other algorithms such as Faster RCNN and EDDN.
Article
Computer Science, Interdisciplinary Applications
Alessia Pini, Helle Sorensen, Anders Tolver, Simone Vantini
Summary: This article addresses the problem of performing inference on the parameters of a functional mixed effect model for multivariate functional data, focusing on the analysis of 3D acceleration curves of trotting horses. The inference is done locally, using adjusted p-value functions on the same domain as the data, which can be thresholded to select statistically significant regions and coordinates. The procedure is based on nonparametric permutation tests, showing improved power by considering random effects. The method is applied to acceleration curves of trotting horses, effectively identifying group differences.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2023)
Article
Engineering, Biomedical
Jeffrey Rosenfeld, Yan T. Wong, Edwin Yan, Julian Szlawski, Anand Mohan, Jonathan C. M. Clark, Marcello Rosa, Arthur Lowery
JOURNAL OF NEURAL ENGINEERING
(2020)
Article
Behavioral Sciences
Peter E. Yoo, Thomas J. Oxley, Maureen A. Hagan, Sam John, Stephen M. Ronayne, Gil S. Rind, Alexander M. Brinded, Nicholas L. Opie, Bradford A. Moffat, Yan T. Wong
FRONTIERS IN BEHAVIORAL NEUROSCIENCE
(2020)
Article
Multidisciplinary Sciences
Hamidreza Abbaspourazad, Mahdi Choudhury, Yan T. Wong, Bijan Pesaran, Maryam M. Shanechi
Summary: The study reveals that multiple scales of principal modes exist in controlling movements, and a predictive mode is shared between scales, reflecting the neural control of naturalistic reach-and-grasp behaviors in macaques.
NATURE COMMUNICATIONS
(2021)
Article
Engineering, Biomedical
Darren Mao, Hamish Innes-Brown, Matthew A. Petoe, Colette M. McKay, Yan T. Wong
Summary: This study aimed to quantify the information about hearing responses in EEG recordings using ERSP and ITC features. Results showed that classifiers using ITC features were better at decoding responses to lower-intensity stimuli compared to ERSP features, and combining both feature sets did not significantly improve decoding. This suggests that ERSP brain dynamics may have a limited contribution to EEG responses in this context.
JOURNAL OF NEURAL ENGINEERING
(2021)
Article
Clinical Neurology
Tim Allison-Walker, Maureen A. Hagan, Nicholas S. C. Price, Yan T. Wong
Summary: The depth of electrode stimulation affects neural responses in the cortex, with superficial stimulation sites exhibiting higher firing rates and lower thresholds, while deep stimulation evokes more widespread activity across the cortical column.
Review
Anatomy & Morphology
Sabrina J. Meikle, Yan T. Wong
Summary: Neural implants have the potential to restore visual capabilities in blind individuals through electrical stimulation, with the ultimate goal of emulating naturalistic vision requiring stimulation of multiple brain areas to recreate different aspects of vision.
BRAIN STRUCTURE & FUNCTION
(2022)
Article
Neurosciences
Matthew J. Sykes, Orsolya S. Kekesi, Yan T. Wong, Fei-Yue Zhao, David Spanswick, Wendy L. Imlach
Summary: Acetylcholine plays a crucial role in regulating excitatory and inhibitory synaptic activity in neurons within the spinal dorsal horn. Specific responses to ACh induction in rat and marmoset lamina II neurons show consistent cell-type specific reactions, highlighting the importance of cholinergic signaling in nociception modulation across species.
Review
Chemistry, Analytical
Jose Gabriel Arganaras, Yan Tat Wong, Rezaul Begg, Nemai Chandra Karmakar
Summary: Radar technology is being used for gait monitoring to prevent falls, offering potential benefits in maintaining quality of life for older adults. Wearable radar technology has significant potential in gait monitoring and fall prevention applications.
Article
Engineering, Biomedical
Sabrina J. Meikle, Maureen A. Hagan, Nicholas S. C. Price, Yan T. Wong
Summary: This study investigates whether current steering technique can enhance the resolution of artificial vision without increasing the number of physical electrodes implanted in the brain. The results show that current steering can systematically shift the activation location of neurons and improve the effectiveness of artificial vision.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Ishara Paranawithana, Darren Mao, Colette M. McKay, Yan T. Wong
Summary: This study analyzed the changes in functional connectivity of language areas in normal hearing infants at different ages using functional near-infrared spectroscopy. The results showed that the connectivity with primary language regions significantly strengthens with age in the first year of life. This research is important for understanding the effects of altered connectivity on language delays in infants with hearing impairments.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Engineering, Biomedical
Julian Szlawski, Timothy Feleppa, Anand Mohan, Yan T. Wong, Arthur J. Lowery
Summary: This study presents an approach to generating pre-compliance safety data for brain-machine interfaces (BMI) by simulating the Specific Absorption Rate (SAR) and tissue heating. The results show that the electromagnetic emissions of the BMI system comply with safety standards, indicating the system is safe.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Proceedings Paper
Engineering, Biomedical
Thomas A. Shiels, Thomas J. Oxley, Paul B. Fitzgerald, Nicholas L. Opie, Yan T. Wong, David B. Grayden, Sam E. John
Summary: Brain-Computer Interfaces (BCIs) show potential in enabling individuals with paralysis to control assistive technology. This study demonstrates that participants, including those with multiple sclerosis, were able to achieve high decoding accuracy in imagined motor tasks, comparable to participants without limb function deficits. The use of EEG signals during motor tasks showed promise for individuals with paralysis.
2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC)
(2021)
Proceedings Paper
Engineering, Biomedical
Sabrina Jade Meikle, Maureen Ann Hagan, Nicholas Seow Chiang Price, Yan Tat Wong
Summary: Current steering technique can improve visual perception for cortical implant patients by creating a complete visual field representation through eliciting neural responses between physical electrode locations.
2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC)
(2021)
Article
Neuroimaging
Thomas J. Oxley, Peter E. Yoo, Gil S. Rind, Stephen M. Ronayne, C. M. Sarah Lee, Christin Bird, Victoria Hampshire, Rahul P. Sharma, Andrew Morokoff, Daryl L. Williams, Christopher MacIsaac, Mark E. Howard, Lou Irving, Ivan Vrljic, Cameron Williams, Sam E. John, Frank Weissenborn, Madeleine Dazenko, Anna H. Balabanski, David Friedenberg, Anthony N. Burkitt, Yan T. Wong, Katharine J. Drummond, Patricia Desmond, Douglas Weber, Timothy Denison, Leigh R. Hochberg, Susan Mathers, Terence J. O'Brien, Clive N. May, J. Mocco, David B. Grayden, Bruce C. Campbell, Peter Mitchell, Nicholas L. Opie
Summary: This study describes the first-in-human experience of a minimally invasive, fully implanted, wireless, ambulatory motor neuroprosthesis using an endovascular stent-electrode array to transmit electrocorticography signals from the motor cortex for multiple command control of digital devices in two participants with flaccid upper limb paralysis.
JOURNAL OF NEUROINTERVENTIONAL SURGERY
(2021)
Article
Neurosciences
Omid G. Sani, Hamidreza Abbaspourazad, Yan T. Wong, Bijan Pesaran, Maryam M. Shanechi
Summary: The PSID algorithm is developed to model neural activity while dissociating and prioritizing its behaviorally relevant dynamics. Through simulation, it was found that behaviorally relevant dynamics are lower-dimensional than previously expected, and can be more accurately learned using PSID.
NATURE NEUROSCIENCE
(2021)