检索结果-内蒙古大学图书馆

Learning and segmenting dense voxel embeddings for 3D neuron reconstruction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lee, Kisuk Lu, Ran Luther, Kyle Seung, H. Sebastian The Brain & Cog. Sci. Dept. Massachusetts Institute of Technology CambridgeMA02139 United States The Neuroscience Institute Princeton University PrincetonNJ08544 United States The Dept. of Physics Princeton University PrincetonNJ08544 United States The Dept. of Computer Science The Neuroscience Institute Princeton University PrincetonNJ08544 United States

We show dense voxel embeddings learned via deep metric learning can be employed to produce a highly accurate segmentation of neurons from 3D electron microscopy images. A "metric graph" on a set of edges between voxels is constructed from the dense voxel embeddings generated by a convolutional network. Partitioning the metric graph with long-range edges as repulsive constraints yields an initial segmentation with high precision, with substantial accuracy gain for very thin objects. The convolutional embedding net is reused without any modification to agglomerate the systematic splits caused by complex "self-contact" motifs. Our proposed method achieves state-of-the-art accuracy on the challenging problem of 3D neuron reconstruction from the brain images acquired by serial section electron microscopy. Our alternative, object-centered representation could be more generally useful for other computational tasks in automated neural circuit reconstruction. Copyright © 2019, The Authors. All rights reserved.

关键词： Electron microscopy

Automatic detection and compression for passive acoustic monitoring of the African forest elephant

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bjorck, Johan Rappazzo, Brendan H. Chen, Di Bernstein, Richard Wrege, Peter H. Gomes, Carla P. Dept. of Computer Science Cornell University IthacaNY United States Bioacoustics Research Program Cornell Lab of Ornithology IthacaNY United States

In this work, we consider applying machine learning to the analysis and compression of audio signals in the context of monitoring elephants in sub-Saharan Africa. Earths biodiversity is increasingly under threat by sources of anthropogenic change (e.g. resource extraction, land use change, and climate change) and surveying animal populations is critical for developing conservation strategies. However, manually monitoring tropical forests or deep oceans is intractable. For species that communicate acoustically, researchers have argued for placing audio recorders in the habitats as a cost-effective and non-invasive method, a strategy known as passive acoustic monitoring (PAM). In collaboration with conservation efforts, we construct a large labeled dataset of passive acoustic recordings of the African Forest Elephant via crowdsourcing, compromising thousands of hours of recordings in the wild. Using state-of-the-art techniques in artificial intelligence we improve upon previously proposed methods for passive acoustic monitoring for classification and segmentation. In real-time detection of elephant calls, network bandwidth quickly becomes a bottleneck and efficient ways to compress the data are needed. Most audio compression schemes are aimed at human listeners and are unsuitable for low-frequency elephant calls. To remedy this, we provide a novel end-to-end differentiable method for compression of audio signals that can be adapted to acoustic monitoring of any species and dramatically improves over nive coding strategies. Copyright © 2019, The Authors. All rights reserved.

关键词： Cost effectiveness

Considerations and recommendations from the ISMRM Diffusion Study Group for preclinical diffusion MRI: Part 3 — Ex vivo imaging: data processing, comparisons with microscopy, and tractography

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Schilling, Kurt G. Howard, Amy F.D. Grussu, Francesco Ianus, Andrada Hansen, Brian Barrett, Rachel L.C. Aggarwal, Manisha Michielse, Stijn Nasrallah, Fatima Syeda, Warda Wang, Nian Veraart, Jelle Roebroeck, Alard Bagdasarian, Andrew F. Eichner, Cornelius Sepehrband, Farshid Zimmermann, Jan Soustelle, Lucas Bowman, Christien Tendler, Benjamin C. Hertanu, Andreea Jeurissen, Ben Verhoye, Marleen Frydman, Lucio van de Looij, Yohan Hike, David Dunn, Jeff F. Miller, Karla Landman, Bennett A. Shemesh, Noam Anderson, Adam McKinnon, Emilie Farquharson, Shawna Dell' Acqua, Flavio Pierpaoli, Carlo Drobnjak, Ivana Leemans, Alexander Harkins, Kevin D. Descoteaux, Maxime Xu, Duan Huang, Hao Santin, Mathieu D. Grant, Samuel C. Obenaus, Andre Kim, Gene S. Wu, Dan Le Bihan, Denis Blackband, Stephen J. Ciobanu, Luisa Fieremans, Els Bai, Ruiliang Leergaard, Trygve B. Zhang, Jiangyang Dyrby, Tim B. Johnson, G. Allan Cohen-Adad, Julien Budde, Matthew D. Jelescu, Ileana O. Radiology and Radiological Sciences Vanderbilt University Medical Center NashvilleTN United States Vanderbilt University Institute of Imaging Science Vanderbilt University NashvilleTN United States Department of Bioengineering Imperial College London London United Kingdom FMRIB Centre Wellcome Centre for Integrative Neuroimaging Nuffield Department of Clinical Neurosciences University of Oxford Oxford United Kingdom Radiomics Group Vall d’Hebron Institute of Oncology Vall d’Hebron Barcelona Hospital Campus Barcelona Spain Queen Square MS Centre Queen Square Institute of Neurology Faculty of Brain Sciences University College London London United Kingdom Champalimaud Research Champalimaud Foundation Lisbon Portugal Center of Functionally Integrative Neuroscience Aarhus University Aarhus Denmark Department of Neuroimaging Institute of Psychiatry Psychology and Neuroscience King's College London London United Kingdom NatBrainLab Department of Forensics and Neurodevelopmental Sciences Institute of Psychiatry Psychology and Neuroscience King's College London London United Kingdom Russell H. Morgan Department of Radiology and Radiological Science Johns Hopkins University School of Medicine BaltimoreMD United States Maastricht University Medical Center Maastricht Netherlands The Queensland Brain Institute The University of Queensland Queensland Australia Melbourne Neuropsychiatry Centre The University of Melbourne ParkvilleVIC Australia Department of Radiology and Imaging Sciences Indiana University IN United States Stark Neurosciences Research Institute Indiana University School of Medicine IN United States Center for Biomedical Imaging NYU Grossman School of Medicine New YorkNY United States Faculty of psychology and Neuroscience Maastricht University Maastricht Netherlands Department of Chemical & Biomedical Engineering FAMU-FSU College of Engineering Florida State University TallahasseeFL United States Center for Interdisciplinary Magnetic Res

Preclinical diffusion MRI (dMRI) has proven value in methods development and validation, characterizing the biological basis of diffusion phenomena, and comparative anatomy. While dMRI enables in vivo non-invasive characterization of tissue, ex vivo dMRI is increasingly being used to probe tissue microstructure and brain connectivity. Ex vivo dMRI has several experimental advantages that facilitate high spatial resolution and high signal-to-noise ratio (SNR) images, cutting-edge diffusion contrasts, and direct comparison with histological data as a methodological validation. However, there are a number of considerations that must be made when performing ex vivo experiments. The steps from tissue preparation, image acquisition and processing, and interpretation of results are complex, with many decisions that not only differ dramatically from in vivo imaging of small animals, but ultimately affect what questions can be answered using the data. This work concludes a 3-part series of recommendations and considerations for preclinical dMRI. Herein, we describe best practices for dMRI of ex vivo tissue, with a focus on image pre-processing, data processing and model fitting, and tractography. In each section, we attempt to provide guidelines and recommendations, but also highlight areas for which no guidelines exist (and why), and where future work should lie. We end by providing guidelines on code sharing and data sharing, and point towards open-source software and databases specific to small animal and ex vivo imaging. © 2024, CC BY.

关键词： Data Sharing

EEG-Based Emotion Classification Using Wavelet Decomposition and K-Nearest Neighbor 4

学校读者我要写书评

暂无评论

EEG-Based Emotion Classification Using Wavelet Decomposition...

4th International Conference on science and Technology, ICST 2018

作者： Putra, Agfianto Eko Atmaji, Catur Ghaleb, Fajrul Dept. of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Electronics and Instrumentations Study Program Universitates Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9781538658130

Research on the correlation of EEG signals to emotions based on high/low arousal and valence, has been done before. Some research using the Eigen-Emotion Pattern Kernel method and the Support Vector Machine. The others using the Higuchi Fractal Dimension (FD) Spectrum, the Multifractal Detrended Fluctuation Analysis (MDFA) and the Hidden Markov Model (HMM), but the accuracy is not too good. This research uses Wavelet Decomposition and k-Nearest Neighbor to improve accuracy. The results show that the optimum k values of the k-Nearest Neighbor parameters for this research are 21. Valence's classification accuracy results using Wavelet and k-NN, compared with previous research has the same relative accuracy, ie 57.5%. While the result of arousal classification accuracy using wavelet and k-NN is 64.0%, better than previous research. © 2018 IEEE.

关键词： Wavelet decomposition

Three-Class Classification of EEG Signals Using Support Vector Machine Methods 4

学校读者我要写书评

暂无评论

Three-Class Classification of EEG Signals Using Support Vect...

4th International Conference on science and Technology, ICST 2018

作者： Atmaji, Catur Putra, Agfianto Eko Tontowi, Irvan Albab Dept. of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Electronics and Instrumentation Undergraduate Program Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9781538658130

Many research on how the human brain works has been done in the last century. The use of electroencephalogram signal generated from quantifying the brain wave have been developed in many areas including the development of brain computer interface (BCI) concept. One type of BCI that interesting for the future use is motor imagery (MI) based-BCI which only requiring imagination of a person to control an object. This study proposed a feature extraction in eight different channels using discrete wavelet (DWT) coefficients. The wavelet coefficient is transformed to frequency domain using discrete fourier transform (DFT) and then average power spectrum is calculated. Level 5 of detail component of the DWT is chosen because from 512Hz sampling frequency (8 - 16Hz), it resemble mu rhythm of brain wave (8 - 12Hz) which affected from motor imagery activity. The classification of three classes, which are imagination of right body movement, left movement, and random word using multiclass support vector machine (SVM) shows a promising result with sensitivity of 96.88%, 86.12% and 52.78% from three different subjects. © 2018 IEEE.

关键词： Power spectrum

Single-Trial EEG Predicts Memory Retrieval Using Leave-One-Subject-Out Classification

学校读者我要写书评

暂无评论

Single-Trial EEG Predicts Memory Retrieval Using Leave-One-S...

2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

作者： Liao, Kueida Mollison, Matthew V. Curran, Tim Sa, Virginia R. De Dept. of Electrical and Computer Engineering UC San Diego San DiegoCA United States Dept. of Psychology and Neuroscience University of Colorado Boulder BoulderCO United States Dept. of Cognitive Science UC San Diego San DiegoCA United States

ISBN: (纸本)9781538654880

In this study, we perform single-trial EEG classification in memory retrieval predictions using classifiers trained on a leave-one-subject-out (LOSO) cross-validation basis. We also compare the performance to that of classification using leave-one-trial-out (LOTO) when trained on data for an individual subject. Unlike traditional single-trial EEG analysis performed within an individual subject, we show that it is possible to perform single-trial EEG classification using classifiers trained on different subjects leading the way to more general classifiers for brain-computer interface (BCI) applicable to first-time BCI users. © 2018 IEEE.

关键词： Brain computer interface

Identification of types of tree damage based on forest health monitoring (FHM) in the management of TAHURA WAR utilization blocks

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2024年第1期2970卷

作者： Rahmat Safe’i Rico Andrian Tri Maryono Sepia Tapasya Tri Rizky Putra Master of Forestry Study Program Forestry Department Faculty of Agriculture University of Lampung Jl. Prof. Dr. Ir. Soemantri Brodjonegoro No. 1 Bandar Lampung Lampung 35145 Indonesia Dept. Computer Science Faculty of Mathematics and Natural Science University of Lampung Jl. Prof. Dr. Ir. Soemantri Brodjonegoro No. 1 Bandar Lampung Lampung 35145 Indonesia Plant Protection Study Program Faculty of Agriculture University of Lampung Jl. Prof. Dr. Ir. Soemantri Brodjonegoro No. 1 Bandar Lampung Lampung 35145 Indonesia Departement of Forestry Faculty of Agriculture University of Lampung Jl. Prof. Dr. Ir. Soemantri Brodjonegoro No. 1 Bandar Lampung Lampung 35145 Indonesia

Regarding management, TAHURA WAR is divided into blocks, one of which is the utilization block. In this block, the community can carry out utilization and use of forest areas. One of the causes of forest use by the community in this block is damage to trees due to high human activities or other concomitant causes. This study aimed to identify the damage to trees based on FHM in the TAHURA WAR utilization block. This research was conducted on five FHM cluster plots of utilization blocks that have been built. Identification is made by measuring and analyzing trees’ location, type, and severity based on the FHM method. The results showed 14 varieties of tree damage from 345 trees. The most common types of damage found were open wounds (code 03) with 162 trees and cancer (code 01) with 78 trees with an average severity of 20-29%. The two types of tree damage were often found at the location of the lower bole (code 3) and lower and upper bole (code 4), with the status of the level of tree damage in the moderate category (6.7 – 9.9). Thus, in the TAHURA WAR utilization block, two dominant types of tree damage were identified. This condition resulted in a considerable decrease in the quantity and quality of wood in the TAHURA WAR utilization block.

关键词：

A generalization of linear positive systems with applications to nonlinear systems: Invariant sets and the Poincaré-Bendixson property

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Weiss, Eyal Margaliot, Michael The Dept. of Computer Science Bar-Ilan University Ramat Gan5290002 Israel The Department of Elec. Eng.-Systems The Sagol School of Neuroscience Tel-Aviv University Tel-Aviv69978 Israel

The dynamics of linear positive systems map the positive orthant to itself. In other words, it maps a set of vectors with zero sign variations to itself. This raises the following question: what linear systems map the set of vectors with k sign variations to itself? We address this question using tools from the theory of cooperative dynamical systems and the theory of totally positive matrices. This yields a generalization of positive linear systems called k-positive linear systems, that reduces to positive systems for k = 1. We describe applications of this new type of systems to the analysis of nonlinear dynamical systems. In particular, we show that such systems admit certain explicit invariant sets, and for the case k = 2 establish the Poincaré-Bendixson property for any bounded trajectory. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear dynamical systems

S227: SBNO2 IS A SPECIFIC DEPENDENCY OF STAT3-DRIVEN T-CELL MALIGNANCIES

学校读者我要写书评

暂无评论

HemaSphere 2022年第S3期6卷

作者： T. Brandstoetter B. Maurer J. Schmoellerl S. Kollmann J. Huuhtanen R. Grausenburger S. Mustjoki J. Zuber V. Sexl Dept. of Biomedical Sciences at the Institute of Pharmacology and Toxicology University of Veterinary Medicine Vienna Austria Research Institute of Molecular Pathology Vienna Austria Hematology Research Unit Helsinki University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center Helsinki Finland Department of Computer Science Aalto University Espoo Finland Translational Immunology Research program University of Helsinki Helsinki Finland