Filters








5,224 Hits in 4.1 sec

SIAMCAT: user-friendly and versatile machine learning workflows for statistically rigorous microbiome analyses [article]

Jakob Wirbel, Konrad Zych, Morgan Essex, Nicolai Karcher, Ece Kartal, Guillem Salazar, Peer Bork, Shinichi Sunagawa, Georg Zeller
2020 bioRxiv   pre-print
Here, we present the SIAMCAT R package, a versatile and user-friendly toolbox for comparative metagenome analyses using machine learning (ML), statistical tests, and visualization.  ...  However, computational tools tailored to such analyses are still scarce.  ...  Acknowledgments We are grateful to Mike Smith, Paul I. Costea, and Kersten Breuer for helpful discussions and advice on the implementation of SIAMCAT.  ... 
doi:10.1101/2020.02.06.931808 fatcat:jraubeuycrbt5chykvybdlzzuy

Advanced Intelligent Control through Versatile Intelligent Portable Platforms

Luige Vladareanu
2020 Sensors  
and intelligent communication, including remote control, adaptive sensor networks, human-robot (H2R) interaction systems and machine-to-machine (M2M) interfaces.  ...  The innovative multi-sensor fusion techniques, integrated through the Versatile Intelligent Portable (VIP) platforms are developed, combined with computer vision, virtual and augmented reality (VR&AR)  ...  For emotion recognition, transfer learning and the fine-tuning of three CNN models (VGG, Inception V3 and ResNet) have been used.  ... 
doi:10.3390/s20133644 pmid:32610597 pmcid:PMC7374349 fatcat:pdjc2zwt3nablactkfjculzsr4

The versatility of graded acoustic measures in classification of predation threats by the tufted titmouseBaeolophus bicolor: exploring a mixed framework for threat communication

Kathryn E. Sieving, Stacia A. Hetrick, Michael L. Avery
2010 Oikos  
The strongest models (ANOVA and classification tree analysis) grouped hawk with cat and owl, and control with snake, and were based on the number or proportion of a) chick and D notes per chick-a-dee call  ...  Two conceptual frameworks are typically applied to the information encoded in alarm calls and to associated anti-predator behaviors.  ...  Acknowledgements Á We are grateful to S. Phelps for support in the planning and implementation of the study, S.  ... 
doi:10.1111/j.1600-0706.2009.17682.x fatcat:rv4ipplz25hmvm73zrtdyhjdka

Experiences and examples from versatile cluster development on the area of ageing and technology

V. Tornberg, S. Väyrynen
2002 Gerontechnology  
Conclusion: Older adults benefited from this gerontechnology program because it allowed them to adapt the delivery of information to their preferred learning style.  ...  The task required that they process e-mails sent by customers who had various questions regarding products they had purchased or intended to purchase from a company's website.  ...  Distance Learning Menu at http://www.hcoa.org, whose mean number of accuracy proxies exceed 3.0/page.  ... 
doi:10.4017/gt.2002.02.01.108.00 fatcat:uclvx5qtxvhvfhznkbwsiytg7i

The versatile use of exhaled volatile organic compounds in human health and disease

Agnes W Boots, Joep J B N van Berkel, Jan W Dallinga, Agnieszka Smolinska, Emile F Wouters, Frederik J van Schooten
2012 Journal of Breath Research  
This paper describes the currently available methodologies regarding sampling, sample analysis and data processing as well as their advantages and potential drawbacks.  ...  As monitoring tool, breathomics can be applied to elucidate the heterogeneity observed in chronic diseases, to study the pathogen(s) responsible for occurring infections and to monitor treatment efficacy  ...  will not be selected in classification models.  ... 
doi:10.1088/1752-7155/6/2/027108 pmid:22621865 fatcat:y6nrjruqtvg6pdg2iga4p5wthu

Secure File/Data Transfer Between Airgap Network

Arathi Navaneeth, Vignesh P P, Sreehari N R, K. Pramilarani
2021 International Journal of Scientific Research in Science Engineering and Technology  
It is always expensive and hard to manage the data manually without adopting machine learning and image processing techniques using metadata.  ...  The contribution of this research article is to demonstrate a securing computer data storage secrecy and privacy in cloud communication framework in terms of automatic data classification using computer  ...  Provides keen accuracy and a lot of versatile nature to accumulate the new advancement as compared to different algorithms.  ... 
doi:10.32628/ijsrset21843 fatcat:mkak566bizf6zn5lwrjzkpjugm

Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

Jakob Wirbel, Konrad Zych, Morgan Essex, Nicolai Karcher, Ece Kartal, Guillem Salazar, Peer Bork, Shinichi Sunagawa, Georg Zeller
2021 Genome Biology  
When naively transferred across studies, ML models lost accuracy and disease specificity, which could however be resolved by a novel training set augmentation strategy.  ...  This reveals some biomarkers to be disease-specific, with others shared across multiple conditions. SIAMCAT is freely available from siamcat.embl.de.  ...  Acknowledgements We are grateful to Mike Smith, Paul I. Costea, and Kersten Breuer for the helpful discussions and advice on the implementation of SIAMCAT.  ... 
doi:10.1186/s13059-021-02306-1 pmid:33785070 pmcid:PMC8008609 fatcat:tr3wuhuto5b6bfp4ksdevnhchm

Representation learning applications in biological sequence analysis [article]

Hitoshi Iuchi, Taro Matsutani, Keisuke Yamada, Shunsuke Sumi, Shion Hosoda, Shitao Zhao, Tsukasa Fukunaga, Michiaki Hamada
2021 bioRxiv   pre-print
To tackle this issue, the application of natural language processing (NLP) to biological sequence analysis has received increased attention, because biological sequences are regarded as sentences and k-mers  ...  This transformation is called representation learning and can be applied to biological sequences.  ...  TF, JP19J20117 to SH and JP20J20016 to TM] and JST CREST [grant numbers: JPMJCR1881 and JPMJCR21F1 to MH].  ... 
doi:10.1101/2021.02.26.433129 fatcat:ooti6qvrtnedhawlzzkndgjawa

Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images

Nam Nhut Phan, Chi-Cheng Huang, Ling-Ming Tseng, Eric Y. Chuang
2021 Frontiers in Oncology  
The two-step deep learning models showed promising classification results of the four breast cancer intrinsic subtypes with accuracy ranging from 0.68 (ResNet50) to 0.78 (ResNet101) in both validation  ...  We also show the deep learning model prediction performance is significantly improved relatively to the common Genefu tool for breast cancer classification.  ...  Melissa Stauffer for editing the text of this manuscript.  ... 
doi:10.3389/fonc.2021.769447 pmid:34926274 pmcid:PMC8673486 fatcat:ticvre46bbd4fgbg4q7rw4crky

Surface Defect Detection and Root Cause Analysis

Tianchen Liu, Fan Zhu, Haoran Yu, Haisong Gu
2020 Global Journal of Science Frontier Research  
At the same time, there are many challenges using deep learning for this area, such as the detection accuracy, shortage of data and, lack of knowledge of root cause of defects.  ...  We use a generalized multi-image matting algorithm to extract common defects automatically. We apply this technology to identify defects that stem from systematic errors in the surface operation.  ...  It enables the model to efficiently learn to extract features from these images in order to perform well on a specific problem.  ... 
doi:10.34257/gjsfrivol20is3pg1 fatcat:buanbk4v7na4tpezpwjk2yik4m

Representation learning applications in biological sequence analysis

Hitoshi Iuchi, Taro Matsutani, Keisuke Yamada, Natsuki Iwano, Shunsuke Sumi, Shion Hosoda, Shitao Zhao, Tsukasa Fukunaga, Michiaki Hamada
2021 Computational and Structural Biotechnology Journal  
Considering the importance and growing trend for the application of representation learning to biological research, in the present study, we have reviewed the existing knowledge in representation learning  ...  Specifically, representation learning is an approach used for this transformation process, which can be applied to biological sequences.  ...  The main advantage of obtaining features through unsupervised learning is that it can retain versatility for the transfer learning to various tasks.  ... 
doi:10.1016/j.csbj.2021.05.039 pmid:34141139 pmcid:PMC8190442 fatcat:l6vn645zwraytm5zwta6l5nmyy

Ternion: An Autonomous Model for Fake News Detection

Noman Islam, Asadullah Shaikh, Asma Qaiser, Yousef Asiri, Sultan Almakdi, Adel Sulaiman, Verdah Moazzam, Syeda Aiman Babar
2021 Applied Sciences  
Specifically, this paper proposes a novel scheme comprising three steps, namely, stance detection, author credibility verification, and machine learning-based classification, to verify the authenticity  ...  For this study, the fake news dataset was taken from Kaggle.  ...  [32] provided a model of decent accuracy to identify fake news using a framed model combined with knowledge engineering and machine learning.  ... 
doi:10.3390/app11199292 fatcat:5x5ctzziizgipo6al7moxgu34m

Identifying protein subcellular localisation in scientific literature using bidirectional deep recurrent neural network [article]

Rakesh David, Rhys-Joshua D Menezes, Jan De Klerk, Ian R Castleden, Cornelia M Hooper, Gustavo Carneiro, Matthew Gilliham
2020 biorxiv/medrxiv   pre-print
Consequently, our approach can be used to extract protein functional features from unstructured text in the literature with high accuracy.  ...  The developed system will improve dissemination or protein functional data to the scientific community and unlock the potential of big data text analytics for generating new hypotheses from diverse datasets  ...  Acknowledgements This research was supported by University of Adelaide Interdisciplinary Research Funding Scheme awarded to M.G. and Australian Research Council through CE140100008 to M.G.  ... 
doi:10.1101/2020.09.09.290577 fatcat:nosfzvxmzvc5vhnfwjj5fpvfbi

Identifying protein subcellular localisation in scientific literature using bidirectional deep recurrent neural network

Rakesh David, Rhys-Joshua D. Menezes, Jan De Klerk, Ian R. Castleden, Cornelia M. Hooper, Gustavo Carneiro, Matthew Gilliham
2021 Scientific Reports  
We provide a framework for extracting protein functional features from unstructured text in the literature with high accuracy, improving data dissemination and unlocking the potential of big data text  ...  AbstractThe increased diversity and scale of published biological data has to led to a growing appreciation for the applications of machine learning and statistical methodologies to gain new insights.  ...  Acknowledgements This research was supported by University of Adelaide Interdisciplinary Research Funding Scheme awarded to M.G. and Australian Research Council through CE140100008 to M.G.  ... 
doi:10.1038/s41598-020-80441-8 pmid:33462256 fatcat:debgp7hmq5al5pk46mjgynhfsa

Combining Context-aware Embeddings and an Attentional Deep Learning Model for Arabic Affect Analysis on Twitter

Hanane Elfaik, El Habib Nfaoui
2021 IEEE Access  
In addition, our proposed model outperforms the best recently reported model in the literature, with an enhancement of 2.62% in accuracy.  ...  In this paper, we address the problem of Arabic affect detection (multilabel emotion classification) by combining the transformer-based model for Arabic language understanding AraBERT and an attention-based  ...  Analysing these texts and identifying emotion from their words and semantics is a difficult challenge.  ... 
doi:10.1109/access.2021.3102087 fatcat:4y4ah7mxnzf7dfuducohavjboy
« Previous Showing results 1 — 15 out of 5,224 results