检索结果-内蒙古大学图书馆

Convolutional neural networks with low-rank regularization 4

学校读者我要写书评

暂无评论

Convolutional neural networks with low-rank regularization

4th International Conference on Learning Representations, ICLR 2016

作者： Tai, Cheng Xiao, Tong Zhang, Yi Wang, Xiaogang Weinan, E. Program in Applied and Computational Mathematics Princeton University United States Department of Electronic Engineering Chinese University of Hong Kong Hong Kong Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the decomposition, we further propose a new method for training low-rank constrained CNNs from scratch. Interestingly, while achieving a significant speedup, sometimes the low-rank constrained CNNs delivers significantly better performance than their non-constrained counterparts. On the CIFAR-10 dataset, the proposed low-rank NIN model achieves 91.31% accuracy (without data augmentation), which also improves upon state-of-the-art result. We evaluated the proposed method on CIFAR-10 and ILSVRC12 datasets for a variety of modern CNNs, including AlexNet, NIN, VGG and GoogleNet with success. For example, the forward time of VGG-16 is reduced by half while the performance is still comparable. Empirical success suggests that low-rank tensor decompositions can be a very useful tool for speeding up large CNNs. © ICLR 2016: San Juan, Puerto Rico. All Rights Reserved.

关键词： Iterative methods

How will the Kenai fisheries respond to changing environmental conditions: scenario based studies of coupled socio-ecological systems dynamics using an agent-based model

学校读者我要写书评

暂无评论

How will the Kenai fisheries respond to changing environment...

Oceans (Conference)

作者： Martin Cenek Maxwell Franklin E. Jamie Trammell Spencer Dahl Department of Computer Science University of Alaska Anchorage Anchorage AK 99508 Department of Civil Engineering University of Alaska Anchorage Anchorage AK 99508 Alaska Heritage Program University of Alaska Anchorage Anchorage AK 99508 Columbia University New York NY US

ISBN: (纸本)9781509064298;9780692946909

Alaska's Kenai fisheries are managed for maximum efficiency while ensuring fair allocation across multiple stakeholder groups and long term sustainability of the fishery. Managers must work to meet the fishery's goals while adapting their commercial and subsistence eco-service management practices to meet changing ecological conditions. Pre- and in-season fishery management practices are supported by historical and location-based management knowledge. Unexpected changes to environmental conditions may be outside the adaptive capacity of the management. Furthermore, managers currently lack a tool to test how proposed policy will alter fishery outcomes. We present an agent-based simulation framework designed for the Kenai case-study that incorporates stakeholder harvest and effort data, as well as Oncorhynchus nerka and Oncorhynchus tshawytscha salmon run-timing dynamics for the last 35 years. The resulting high-fidelity and verified model was used for scenario-based studies to understand how shifting ecological and social drivers effect the seasonal outcomes of fishery dynamics. Scenarios were determined from plausible future changes to system drivers identified during participatory stakeholder meetings and in scientific literature from southeast Alaska. Using our model, we uncovered recent instability in the Kenai fisheries coupled socio-ecological system dynamics, and determined equations that describe the strategy of fishery managers in responding to in-season drivers. Sensitivity of seasonal fishery outcomes to different drivers was quantified via the scenario-based studies. Our results show our agent-based simulation framework to be a capable decision support tool, one that resource managers might use for testing outcomes of proposed policy change in response to environmental change.

关键词： Data models Biological system modeling Stakeholders Rivers Correlation Electronic mail Timing

Measurements of the Temperature and E-mode Polarization of the Cosmic Microwave Background from the Full 500-square-degree SPTpol Dataset

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chou, T.-L. Ade, P.A.R. Anderson, A.J. Austermann, J.E. Balkenhol, L. Beall, J.A. Bender, A.N. Benson, B.A. Bianchini, F. Bleem, L.E. Carlstrom, J.E. Chang, C.L. Chaubal, P. Chiang, H.C. Citron, R. Moran, C. Corbett Crawford, T.M. Crites, A.T. de Haan, T. Dobbs, M.A. Dutcher, D. Everett, W. Gallicchio, J. George, E.M. Gupta, N. Halverson, N.W. Holder, G.P. Holzapfel, W.L. Hrubes, J.D. Huang, N. Hubmayr, J. Irwin, K.D. Knox, L. Lee, A.T. Li, D. Lowitz, A. McMahon, J.J. Montgomery, J. Natoli, T. Nibarger, J.P. Noble, G.I. Novosad, V. Omori, Y. Padin, S. Patil, S. Pryke, C. Quan, W. Reichardt, C.L. Ruhl, J.E. Saliwanchik, B.R. Schaffer, K.K. Sievers, C. Smecher, G. Stark, A.A. Tucker, C. Veach, T. Vieira, J.D. Wang, G. Whitehorn, N. Wu, W.L.K. Yefremenko, V. Zebrowski, J.A. Department of Astronomy and Astrophysics University of Chicago 5640 South Ellis Avenue ChicagoIL60637 United States Kavli Institute for Cosmological Physics University of Chicago 5640 South Ellis Avenue ChicagoIL60637 United States Cardiff University CardiffCF10 3XQ United Kingdom Fermi National Accelerator Laboratory MS209 P.O. Box 500 BataviaIL60510 United States NIST Quantum Devices Group 325 Broadway Mailcode 817.03 BoulderCO80305 United States Department of Physics University of Colorado BoulderCO80309 United States Sorbonne Universit’e CNRS UMR 7095 Institut d’Astrophysique de Paris 98 bis bd Arago Paris75014 France High Energy Physics Division Argonne National Laboratory 9700 S. Cass Avenue ArgonneIL60439 United States SLAC National Accelerator Laboratory 2575 Sand Hill Road Menlo ParkCA94025 United States Department of Physics University of Chicago 5640 South Ellis Avenue ChicagoIL60637 United States Enrico Fermi Institute University of Chicago 5640 South Ellis Avenue ChicagoIL60637 United States School of Physics University of Melbourne ParkvilleVIC3010 Australia Department of Physics McGill University 3600 Rue University MontrealQCH3A 2T8 Canada School of Mathematics Statistics & Computer Science University of KwaZulu-Natal Durban South Africa University of Chicago 5640 South Ellis Avenue ChicagoIL60637 United States Jet Propulsion Laboratory PasadenaCA91109 United States Department of Physics Cornell University IthacaNY United States Department of Astronomy Cornell University IthacaNY United States Department of Physics University of California BerkeleyCA94720 United States Physics Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Ibaraki Tsukuba305-0801 Japan Canadian Institute for Advanced Research CIFAR Program in Gravity and the Extreme Universe TorontoONM5G 1Z8 Canada Joseph Henry Laboratories of Physics Jadwin Hall Princeton University PrincetonNJ08544

Using the full four-year SPTpol 500 deg2 dataset in both the 95 GHz and 150 GHz frequency bands, we present measurements of the temperature and E-mode polarization of the cosmic microwave background (CMB), as well as the E-mode polarization auto-power spectrum (EE) and temperature-E-mode cross-power spectrum (TE) in the angular multipole range 50 0 = 70.48 ± 2.16 km s−1 Mpc−1 and Ωm = 0.271 ± 0.026, when using only the SPTpol data and a Planck-based prior on the optical depth to reionization. The ΛCDM parameter constraints are consistent across the 95 GHz-only, 150 GHz-only, TE-only, and EE-only data splits. Between the 1000 data splits, the ΛCDM parameter constraints are borderline consistent at the ∼ 2σ level. This consistency improves when including a parameter AL, the degree of lensing of the CMB inferred from the smearing of acoustic peaks. When marginalized over AL, the ΛCDM parameter constraints from SPTpol are consistent with those from Planck. The power spectra presented here are the most sensitive measurements of the lensed CMB damping tail to date for roughly > 1700 in TE and > 2000 in EE. Copyright © 2025, The Authors. All rights reserved.

关键词： Cosmology

Optimal Learning for Sequential Decision Making for Expensive Cost Functions with Stochastic Binary Feedbacks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Yingfei Wang, Chu Powell, Warren Department of Computer Science Princeton University PrincetonNJ08540 United States Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States Department of Operations Research and Financial Engineering Princeton University PrincetonNJ08544 United States

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance. The learner takes an active role in selecting samples from the instance pool. The goal is to maximize the probability of success in either offline (training) or online (testing) phases. Our problem is motivated by real-world applications where observations are time consuming and/or expensive. We develop a knowledge gradient policy using an online Bayesian linear classifier to guide the experiment by maximizing the expected value of information of labeling each alternative. We provide a finite-time analysis of the estimated error and show that the maximum likelihood estimator based produced by the KG policy is consistent and asymptotically normal. We also show that the knowledge gradient policy is asymptotically optimal in an offline setting. This work further extends the knowledge gradient to the setting of contextual bandits. We report the results of a series of experiments that demonstrate its efficiency. Copyright © 2017, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

Author Correction: Expanded encyclopaedias of DNA elements in the human and mouse genomes

学校读者我要写书评

暂无评论

Nature 2022年第7909期605卷 E3页

作者： Jill E Moore Michael J Purcaro Henry E Pratt Charles B Epstein Noam Shoresh Jessika Adrian Trupti Kawli Carrie A Davis Alexander Dobin Rajinder Kaul Jessica Halow Eric L Van Nostrand Peter Freese David U Gorkin Yin Shen Yupeng He Mark Mackiewicz Florencia Pauli-Behn Brian A Williams Ali Mortazavi Cheryl A Keller Xiao-Ou Zhang Shaimae I Elhajjajy Jack Huey Diane E Dickel Valentina Snetkova Xintao Wei Xiaofeng Wang Juan Carlos Rivera-Mulia Joel Rozowsky Jing Zhang Surya B Chhetri Jialing Zhang Alec Victorsen Kevin P White Axel Visel Gene W Yeo Christopher B Burge Eric Lécuyer David M Gilbert Job Dekker John Rinn Eric M Mendenhall Joseph R Ecker Manolis Kellis Robert J Klein William S Noble Anshul Kundaje Roderic Guigó Peggy J Farnham J Michael Cherry Richard M Myers Bing Ren Brenton R Graveley Mark B Gerstein Len A Pennacchio Michael P Snyder Bradley E Bernstein Barbara Wold Ross C Hardison Thomas R Gingeras John A Stamatoyannopoulos Zhiping Weng University of Massachusetts Medical School Program in Bioinformatics and Integrative Biology Worcester MA USA. The Broad Institute of Harvard and MIT Cambridge MA USA. Department of Genetics School of Medicine Stanford University Palo Alto CA USA. Cold Spring Harbor Laboratory Functional Genomics Cold Spring Harbor NY USA. Altius Institute for Biomedical Sciences Seattle WA USA. Department of Medicine University of Washington School of Medicine Seattle WA USA. Department of Cellular and Molecular Medicine Institute for Genomic Medicine Stem Cell Program Sanford Consortium for Regenerative Medicine University of California San Diego La Jolla CA USA. Program in Computational and Systems Biology Massachusetts Institute of Technology Cambridge MA USA. Center for Epigenomics Department of Cellular and Molecular Medicine University of California San Diego La Jolla CA USA. Ludwig Institute for Cancer Research University of California San Diego La Jolla CA USA. Institute for Human Genetics Department of Neurology University of California San Francisco San Francisco CA USA. Genomics Analysis Laboratory The Salk Institute for Biological Studies La Jolla CA USA. HudsonAlpha Institute for Biotechnology Huntsville AL USA. Division of Biology and Biological Engineering California Institute of Technology Pasadena CA USA. Department of Developmental and Cell Biology University of California Irvine Irvine CA USA. Department of Biochemistry and Molecular Biology The Pennsylvania State University University Park PA USA. Environmental Genomics and Systems Biology Division Lawrence Berkeley National Laboratory Berkeley CA USA. Department of Genetics and Genome Sciences Institute for Systems Genomics UConn Health Farmington CT USA. Département de Biochimie et Médecine Moléculaire Université de Montréal Montréal Quebec Canada. Division of Experimental Medicine McGill University Montreal Quebec Canada. Institut de Recherches Cliniques de Montréal (IR

Quantum computing at the frontiers of biological sciences

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Emani, Prashant S. Warrell, Jonathan Anticevic, Alan Bekiranov, Stefan Gandal, Michael McConnell, Michael J. Sapiro, Guillermo Aspuru-Guzik, Alán Baker, Justin Bastiani, Matteo McClure, Patrick Murray, John Sotiropoulos, Stamatios N. Taylor, Jacob Senthil, Geetha Lehner, Thomas Gerstein, Mark B. Harrow, Aram W. Program in Computational Biology and Bioinformatics Yale University New HavenCT06520 United States Department of Molecular Biophysics and Biochemistry Yale University New HavenCT06520 United States Yale School of Medicine Department of Psychiatry New HavenCT06511 United States University of Virginia School of Medicine Department of Biochemistry and Molecular Genetics CharlottesvilleVA22903 United States Department of Psychiatry Semel Institute David Geffen School of Medicine University of California–Los Angeles 695 Charles E. Young Drive South Los AngelesCA90095 United States Univ. of Virginia School of Medicine Department of Neuroscience CharlottesvilleVA22903 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Chemistry University of Toronto 80 St. George Street TorontoONM5S 3H6 Canada TorontoONM5S 1M1 Canada CIFAR Artificial Intelligence Research Chair Vector Institute TorontoONM5S 1M1 Canada Department of Computer Science University of Toronto 40 St. George Street TorontoONM5S 2E4 Canada Schizophrenia and Bipolar Disorder Program McLean Hospital BelmontMA02478 United States Department of Psychiatry Harvard Medical School BostonMA02114 United States Sir Peter Mansfield Imaging Centre School of Medicine University of Nottingham NottinghamNG7 2RD United Kingdom Machine Learning Team National Institute of Mental Health BethesdaMD20892 United States Section on Functional Imaging Methods National Institute of Mental Health BethesdaMD20892 United States Department of Psychiatry Yale University School of Medicine New HavenCT06511 United States Department of Physics Yale University New HavenCT06511 United States Joint Center for Quantum Information and Computer Science University of Maryland College ParkMD20742 United States National Institute of Standards and Technology GaithersburgMD20899 United States Office of Genomics Research Coordination N

The search for meaningful structure in biological data has relied on cutting-edge advances in computational technology and data science methods. However, challenges arise as we push the limits of scale and complexity in biological problems. Innovation in massively parallel, classical computing hardware and algorithms continues to address many of these challenges, but there is a need to simultaneously consider new paradigms to circumvent current barriers to processing speed. Accordingly, we articulate a view towards quantum computation and quantum information science, where algorithms have demonstrated potential polynomial and exponential computational speedups in certain applications, such as machine learning. The maturation of the field of quantum computing, in hardware and algorithm development, also coincides with the growth of several collaborative efforts to address questions across length and time scales, and scientific disciplines. We use this coincidence to explore the potential for quantum computing to aid in one such endeavor: the merging of insights from genetics, genomics, neuroimaging and behavioral phenotyping. By examining joint opportunities for computational innovation across fields, we highlight the need for a common language between biological data analysis and quantum computing. Ultimately, we consider current and future prospects for the employment of quantum computing algorithms in the biological sciences. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sanders, Lauren M. Yang, Jason H. Scott, Ryan T. Qutub, Amina Ann Martin, Hector Garcia Berrios, Daniel C. Hastings, Jaden J.A. Rask, Jon Mackintosh, Graham Hoarfrost, Adrienne L. Chalk, Stuart Kalantari, John Khezeli, Kia Antonsen, Erik L. Babdor, Joel Barker, Richard Baranzini, Sergio E. Beheshti, Afshin Delgado-Aparicio, Guillermo M. Glicksberg, Benjamin S. Greene, Casey S. Haendel, Melissa Hamid, Arif A. Heller, Philip Jamieson, Daniel Jarvis, Katelyn J. Komarova, Svetlana V. Komorowski, Matthieu Kothiyal, Prachi Mahabal, Ashish Manor, Uri Mason, Christopher E. Matar, Mona Mias, George I. Miller, Jack Myers, Jerry G. Nelson, Charlotte Oribello, Jonathan Park, Seung-Min Parsons-Wingerter, Patricia Prabhu, R.K. Reynolds, Robert J. Saravia-Butler, Amanda Saria, Suchi Sawyer, Aenor Singh, Nitin Kumar Soboczenski, Frank Snyder, Michael Soman, Karthik Theriot, Corey A. van Valen, David Venkateswaran, Kasthuri Warren, Liz Worthey, Liz Zitnik, Marinka Costes, Sylvain V. Blue Marble Space Institute of Science Space Biosciences Division NASA Ames Research Center Moffett Field CA94035 United States Center for Emerging and Re-Emerging Pathogens Department of Microbiology Biochemistry and Molecular Genetics Rutgers New Jersey Medical School NewarkNJ07103 United States KBR Space Biosciences Division NASA Ames Research Center Moffett Field CA94035 United States AI MATRIX Consortium Department of Biomedical Engineering University of Texas San Antonio and UT Health Sciences San AntonioTX78249 United States Biological Systems and Engineering Division Lawrence Berkeley National Lab. BerkeleyCA94608 United States DOE Agile BioFoundry EmeryvilleCA94608 United States Joint BioEnergy Institute EmeryvilleCA94608 United States Department of Physiology and Biophysics Weill Cornell Medicine New YorkNY10065 United States Office of the Center Director NASA Ames Research Center Moffett Field CA94035 United States Bay Area Environmental Research Institute NASA Ames Research Center Moffett Field CA94035 United States Space Biosciences Division NASA Ames Research Center Moffett Field CA94035 United States Department of Chemistry University of North Florida JacksonvilleFL32224 United States Center for Individualized Medicine Department of Surgery Department of Quantitative Health Sciences Mayo Clinic RochesterMN55905 United States Department of Emergency Medicine Center for Space Medicine Baylor College of Medicine HoustonTX77030 United States Department of Microbiology and Immunology Department of Otolaryngology Head and Neck Surgery University of California San Francisco San FranciscoCA94143 United States The Gilroy AstroBiology Research Group The University of Wisconsin - Madison MadisonWI53706 United States Weill Institute for Neurosciences Department of Neurology University of California San Francisco San FranciscoCA94158 United States Data Science Analytics Georgia Institute of Technology Lima15024

Space biology research aims to understand fundamental effects of spaceflight on organisms, develop foundational knowledge to support deep space exploration, and ultimately bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals, and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data, and model organisms from both spaceborne and ground-analog studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally autonomous, light, agile, and intelligent to expedite knowledge discovery. Here we present a summary of recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning, and modeling applications which offer key solutions toward these space biology challenges. In the next decade, the synthesis of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modeling and analytics, support maximally autonomous and reproducible experiments, and efficiently manage spaceborne data and metadata, all with the goal to enable life to thrive in deep space. © 2021, CC BY.

关键词： Predictive analytics

Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Health

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Scott, Ryan T. Antonsen, Erik L. Sanders, Lauren M. Hastings, Jaden J.A. Park, Seung-Min Mackintosh, Graham Reynolds, Robert J. Hoarfrost, Adrienne L. Sawyer, Aenor Greene, Casey S. Glicksberg, Benjamin S. Theriot, Corey A. Berrios, Daniel C. Miller, Jack Babdor, Joel Barker, Richard Baranzini, Sergio E. Beheshti, Afshin Chalk, Stuart Delgado-Aparicio, Guillermo M. Haendel, Melissa Hamid, Arif A. Heller, Philip Jamieson, Daniel Jarvis, Katelyn J. Kalantari, John Khezeli, Kia Komarova, Svetlana V. Komorowski, Matthieu Kothiyal, Prachi Mahabal, Ashish Manor, Uri Martin, Hector Garcia Mason, Christopher E. Matar, Mona Mias, George I. Myers, Jerry G. Nelson, Charlotte Oribello, Jonathan Parsons-Wingerter, Patricia Prabhu, R.K. Qutub, Amina Ann Rask, Jon Saravia-Butler, Amanda Saria, Suchi Singh, Nitin Kumar Soboczenski, Frank Snyder, Michael Soman, Karthik van Valen, David Venkateswaran, Kasthuri Warren, Liz Worthey, Liz Yang, Jason H. Zitnik, Marinka Costes, Sylvain V. KBR Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States Department of Emergency Medicine Center for Space Medicine Baylor College of Medicine HoustonTX77030 United States Blue Marble Space Institute of Science Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States Department of Physiology and Biophysics Weill Cornell Medicine New YorkNY10065 United States Department of Urology Department of Radiology Stanford University School of Medicine StanfordCA94305 United States Bay Area Environmental Research Institute NASA Ames Research Center Moffett FieldCA94035 United States Mortality Research & Consulting Inc. HoustonTX77058 United States Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States UC Space Health Department of Orthopaedic Surgery University of California San Francisco San FranciscoCA94143 United States Center for Health AI Department of Biochemistry and Molecular Genetics University of Colorado School of Medicine Anschutz Medical Campus AuroraCO80045 United States Hasso Plattner Institute for Digital Health at Mount Sinai Department of Genetics and Genomic Sciences Icahn School of Medicine at Mount Sinai New YorkNY10065 United States Department of Preventive Medicine and Community Health UTMB GalvestonTX77551 United States Human Health and Performance Directorate NASA Johnson Space Center HoustonTX77058 United States Department of Microbiology and Immunology Department of Otolaryngology Head and Neck Surgery University of California San Francisco San FranciscoCA94143 United States The Gilroy AstroBiology Research Group The University of Wisconsin Madison MadisonWI53706 United States Weill Institute for Neurosciences Department of Neurology University of California San Francisco San FranciscoCA94158 United States Department of Chemistry University of North Florida JacksonvilleFL32224 United States Data Scienc

Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in data and space health systems are necessary to enable Earth-independence, rather than Earth-reliance. Promising developments in the fields of artificial intelligence and machine learning for biology and health can address these needs. We propose an appropriately autonomous and intelligent Precision Space Health system that will monitor, aggregate, and assess biomedical statuses;analyze and predict personalized adverse health outcomes;adapt and respond to newly accumulated data;and provide preventive, actionable, and timely insights to individual deep space crew members and iterative decision support to their crew medical officer. Here we present a summary of recommendations from a workshop organized by the National Aeronautics and Space Administration, on future applications of artificial intelligence in space biology and health. In the next decade, biomonitoring technology, biomarker science, spacecraft hardware, intelligent software, and streamlined data management must mature and be woven together into a Precision Space Health system to enable humanity to thrive in deep space. © 2021, CC BY.

关键词： Earth (planet)

DNA steganalysis using deep recurrent neural networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Bae, Ho Lee, Byunghan Kwon, Sunyoung Yoon, Sungroh Interdisciplinary Program in Bioinformatics Seoul National University Seoul08826 Electrical and Computer Engineering Seoul National University Seoul08826 Electronic and IT Media Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of Clova AI Research NAVER Corp. Seongnam13561 ASRI INMC Seoul National University Seoul08826

Recent advances in next-generation sequencing technologies have facilitated the use of deoxyribonucleic acid (DNA) as a novel covert channels in steganography. There are vari-ous methods that exist in other domains to detect hidden messages in conventional covert channels. However, they have not been applied to DNA steganography. The current most common detection approaches, namely frequency analysis-based methods, often overlook important signals when directly applied to DNA steganography because those methods de-pend on the distribution of the number of sequence characters. To address this limitation, we propose a general sequence learning-based DNA steganalysis framework. The proposed approach learns the intrinsic distribution of coding and non-coding sequences and detects hidden messages by exploiting distribution variations after hiding these messages. Using deep recurrent neural networks (RNNs), our framework identifies the distribution varia-tions by using the classification score to predict whether a sequence is to be a coding or non-coding sequence. We compare our proposed method to various existing methods and biological sequence analysis methods implemented on top of our framework. According to our experimental results, our approach delivers a robust detection performance compared to other tools. Copyright © 2017, The Authors. All rights reserved.

关键词： Steganography