检索结果-内蒙古大学图书馆

Quantum annealing versus classical machine learning applied to a simplified computational biology problem

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Richard Di Felice, Rosa Rohs, Remo Lidar, Daniel Department of Chemistry University of Southern California Los AngelesCA90089 United States Computational Biology and Bioinformatics Program Department of Biological Sciences University of Southern California Los AngelesCA90089 United States Center for Quantum Information Science & Technology University of Southern California Los AngelesCA90089 United States Department of Physics and Astronomy University of Southern California Los AngelesCA90089 United States Center S3 CNR Institute of Nanoscience Via Campi 213/A Modena41125 Italy Department of Computer Science University of Southern California Los AngelesCA90089 United States Department of Electrical Engineering University of Southern California Los AngelesCA90089 United States

Transcription factors regulate gene expression, but how these proteins recognize and specifically bind to their DNA targets is still debated. Machine learning models are effective means to reveal interaction mechanisms. Here we studied the ability of a quantum machine learning approach to predict binding specificity. Using simplified datasets of a small number of DNA sequences derived from actual binding affinity experiments, we trained a commercially available quantum annealer to classify and rank transcription factor binding. The results were compared to state-of-the-art classical approaches for the same simplified datasets, including simulated annealing, simulated quantum annealing, multiple linear regression, LASSO, and extreme gradient boosting. Despite technological limitations, we find a slight advantage in classification performance and nearly equal ranking performance using the quantum annealer for these fairly small training data sets. Thus, we propose that quantum annealing might be an effective method to implement machine learning for certain computational biology problems. Copyright © 2018, The Authors. All rights reserved.

关键词： Simulated annealing

Extracting Human Face Similarity Judgments: Pairs or Triplets? 38

学校读者我要写书评

暂无评论

Extracting Human Face Similarity Judgments: Pairs or Triplet...

38th Annual Meeting of the cognitive science Society: Recognizing and Representing Events, CogSci 2016

作者： Li, Linjie Malave, Vicente Song, Amanda Yu, Angela J. Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA United States Department of Cognitive Science University of California La Jolla San DiegoCA United States

ISBN: (纸本)9780991196739

Two experimental protocols, pairwise rating and triplet ranking, have been commonly used for eliciting perceptual similarity judgments for faces and other objects. However, there has been little systematic comparison of the two methods. Pairwise rating has the advantage of greater precision, but triplet ranking is potentially a cognitive less taxing task, thus resulting in less noisy responses. Here, we introduce several information-theoretic measures of how useful responses from the two protocols are for the purpose of response prediction and parameter estimation. Using face similarity data collected on Amazon Mechanical Turk, we demonstrate that triplet ranking is significantly better for extracting subject-specific preferences, while the two are comparable when pooling across subjects. While the specific conclusions should be interpreted cautiously, due to the particularly simple Bayesian model for response generation utilized here, the work provides a information-theoretic framework for quantifying how repetitions within and across subjects can help to combat noise in human responses, as well as giving some insight into the nature of similarity representation and response noise in humans. More generally, this work demonstrates that substantial noise and inconsistency corrupt similarity judgments, both within- and across-subjects, with consequent implications for experimental design and data interpretation. © 2016 Proceedings of the 38th Annual Meeting of the cognitive science Society, CogSci 2016. All rights reserved.

关键词： Information theory

Long-term Room Temperature Instability in Thermal Conductivity of InGaZnO Thin Films

学校读者我要写书评

暂无评论

Long-term Room Temperature Instability in Thermal Conductivi...

作者： Cui, Boya Bruce Buchholz, D. Zeng, Li Bedzyk, Michael Chang, Robert P. H. Grayson, Matthew Applied Physics Program Northwestern University EvanstonIL60208 United States Electrical Engineering and Computer Science Northwestern University EvanstonIL60208 United States Material Science and Engineering Northwestern University EvanstonIL60208 United States

The cross-plane thermal conductivities of InGaZnO (IGZO) thin films in different morphologies were measured on three occasions within 19 months, using the 3ω method at room temperature 300 K. Amorphous (a-), semi-crystalline (semi-c-) and crystalline (c-) IGZO films were grown by pulsed laser deposition (PLD), followed by X-ray diffraction (XRD) for evaluation of film quality and crystallinity. Semi-c-IGZO shows the highest thermal conductivity, even higher than the most ordered crystal-like phase. After being stored in dry low-oxygen environment for months, a drastic decrease of semi-c-IGZO thermal conductivity was observed, while the thermal conductivity slightly reduced in c-IGZO and remained unchanged in a-IGZO. This change in thermal conductivity with storage time can be attributed to film structural relaxation and vacancy diffusion to grain boundaries. © 2016 Materials Research Society.

关键词： Thin films

Non-intrusive load monitoring and analytics for device prediction

学校读者我要写书评

暂无评论

Non-intrusive load monitoring and analytics for device predi...

International Multiconference of Engineers and computer Scientists 2016, IMECS 2016

作者： Rao, Kovvali Manasa Ravichandran, Durga Mahesh, Kavi Department of Environmental Engineering Arizona State University TempeAS United States Data Science Program University of Southern California Los AngelesCA United States KAnOE Department of Computer Science PES University India

ISBN: (纸本)9789881925381

Non-intrusive load monitoring (NILM) is a critical problem in creating consumer awareness about electrical power consumption in households with the objective of eliminating wastage and reducing overall energy consumption in a society. Many approaches have been explored in non-intrusive load monitoring in recent times with a focus on machine learning of appliance-level details and user activity from analysis of aggregate power consumption. Several technologies and devices have also been developed to collect power consumption data and perform analysis on voltage and current waveforms. However, not much work has been done in analyzing NILM data against demographic parameters such as time of day or day of week as well as occupancy data of households. This article presents a novel approach to identifying active devices and predicting future power usage using demographic data in addition to aggregate power usage over time. We find that SVM (Support Vector Machine) with Edge Analysis works best for device identification and ARMA (Autoregressive Moving Average Model)works best for predicting future power consumption using time series forecasting. We have also collected real aggregate power consumption data from a typical household in India and produced perhaps the first such dataset.

关键词： Forecasting

Predicting breast tumor proliferation from whole-slide images: The TUPAC16 challenge

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Veta, Mitko Heng, Yujing J. Stathonikos, Nikolas Bejnordi, Babak Ehteshami Beca, Francisco Wollmann, Thomas Rohr, Karl Shah, Manan A. Wang, Dayong Rousson, Mikael Hedlund, Martin Tellez, David Ciompi, Francesco Zerhouni, Erwan Lanyi, David Viana, Matheus Kovalev, Vassili Liauchuk, Vitali Phoulady, Hady Ahmady Qaiser, Talha Graham, Simon Rajpoot, Nasir Sjöblom, Erik Molin, Jesper Paeng, Kyunghyun Hwang, Sangheum Park, Sunggyun Jia, Zhipeng Chang, Eric I-Chao Xu, Yan Beck, Andrew H. Van Diest, Paul J. Pluim, Josien P.W. Medical Image Analysis Group Eindhoven University of Technology Eindhoven Netherlands Department of Pathology Beth Israel Deaconess Medical Center Harvard Medical School BostonMA United States Department of Pathology University Medical Center Utrecht Utrecht Netherlands Diagnostic Image Analysis Group Radboud University Medical Center Nijmegen Netherlands Department of Pathology Stanford University School of Medicine Biomedical Computer Vision Group University of Heidelberg BIOQUANT IPMB DKFZ Heidelberg Germany Harker School San Jose United States ContextVision AB Linköping Sweden Foundations of Cognitive Computing IBM Research Zürich Rüschlikon Switzerland Visual Analytics and Insights IBM Research Brazil Saõ Paulo Brazil Biomedical Image Analysis Department United Institute of Informatics Minsk Belarus Department of Computer Science and Engineering University of South Florida TampaFL United States Department of Computer Science University of Warwick Warwick United Kingdom Research Sectra Linköping Sweden Lunit Inc. Seoul Korea Republic of Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China Microsoft Research Beijing China Biology and Medicine Engineering Beihang University Beijing China IBM Research Brazil

Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is a highly subjective and labor-intensive task. Previous efforts to automate tumor proliferation assessment by image analysis only focused on mitosis detection in predefined tumor regions. However, in a realworld scenario, automatic mitosis detection should be performed in whole-slide images (WSIs) and an automatic method should be able to produce a tumor proliferation score given a WSI as input. To address this, we organized the TUmor Proliferation Assessment Challenge 2016 (TUPAC16) on prediction of tumor proliferation scores from WSIs. The challenge dataset consisted of 500 training and 321 testing breast cancer histopathology WSIs. In order to ensure fair and independent evaluation, only the ground truth for the training dataset was provided to the challenge participants. The first task of the challenge was to predict mitotic scores, i.e., to reproduce the manual method of assessing tumor proliferation by a pathologist. The second task was to predict the gene expression based PAM50 proliferation scores from the WSI. The best performing automatic method for the first task achieved a quadratic-weighted Cohen's kappa score of κ = 0.567, 95% CI [0.464, 0.671] between the predicted scores and the ground truth. For the second task, the predictions of the top method had a Spearman's correlation coefficient of r = 0.617, 95% CI [0.581 0.651] with the ground truth. This was the first comparison study that investigated tumor proliferation assessment from WSIs. The achieved results are promising given the difficulty of the tasks and weakly-labeled nature of the ground truth. However, further research is needed to improve the practical utility of image analysis methods for this task. Copyright © 2018, The Authors. All rights reserved.

关键词： Diseases

Rainfall forecasting using PSPline and rice production with ocean-atmosphere interaction

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental science 2018年第1期195卷

作者： Rezzy Eko Caraka Budi Darmawan Supatmanto Muhammad Tahmid Joko Soebagyo M Ali Mauludin Akbar Iskandar Bens Pardamean Bioinformatics and Data Science Research Center (BDSRC) Bina Nusantara University Jakarta Indonesia 11480 Weather Modification Technology Center Agency for the Assessment and Application of Technology (BPPT Indonesia Agency for Meteorology Climatology and Geophysics Indonesia College of Technology Wastukancana Purwakarta Laboratory of Sociology and Extension Padjadjaran University Informatics Engineering STMIK AKBA Makassar Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

The role of climate can be affected by plants. The weather can accelerate and multiply the existence of various plant pests and diseases, accelerate the growth and development of grass among plants, and encourage the emergence of infection and significant damage to plants. The elements of climate that affect the growth of plants are one of them is rainfall. In this paper, we performed the simulation using the non-parametric penalized spline (PSPLINE) method and studied the effect on rice production in Lampung. It can be concluded that the increasing fluctuation, frequency, and intensity of climate anomalies in the last decade caused by the ENSO phenomenon have an impact on changes in distribution patterns, intensity, and period of the wet season so that the start of the rainy season and the dry season becomes too late. As a result, there is a seasonal shift from normal average conditions that can ultimately have severe implications for food crops. In a nutshell penalized spline gives high accuracy with R 2 = 96.227% and MAPE = 1.62%.

关键词：

Task-driven convolutional recurrent models of the visual system

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Nayebi, Aran Bear, Daniel Kubilius, Jonas Kar, Kohitij Ganguli, Surya Sussillo, David DiCarlo, James J. Yamins, Daniel L.K. Neurosciences PhD Program Stanford University StanfordCA94305 United States Department of Psychology Stanford University StanfordCA94305 United States Department of Computer Science Stanford University StanfordCA94305 United States Department of Applied Physics Stanford University StanfordCA94305 United States McGovern Institute for Brain Research MIT CambridgeMA02139 United States Department of Brain and Cognitive Sciences MIT CambridgeMA02139 United States Brain and Cognition KU Leuven Leuven Belgium Google Brain Google Inc. Mountain ViewCA94043 United States Wu Tsai Neurosciences Institute StanfordCA94305 United States

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, novel cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors. Copyright © 2018, The Authors. All rights reserved.

关键词： Neurons

A Bayesian mixture model for clustering on the stiefel manifold

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Sengupta, Subhajit Pal, Subhadip Mitra, Riten Guo, Ying Banerjee, Arunava Ji, Yuan Program for Computational Genomics and Medicine NorthShore University HealthSystem Department of Bioinformatics and Biostatistics University of Louisville Department of Biostatistics and Bioinformatics Emory University Department of Computer and Information Science and Engineering University of Florida Department of Public Health Sciences University of Chicago

Analysis of a Bayesian mixture model for the Matrix Langevin distribution on the Stiefel manifold is presented. The model exploits a particular parametrization of the Matrix Langevin distribution, various aspects of which are elaborated on. A general, and novel, family of conjugate priors, and an efficient Markov chain Monte Carlo (MCMC) sampling scheme for the corresponding posteriors is then developed for the mixture model. Theoretical properties of the prior and posterior distributions, including posterior consistency, are explored in detail. Extensive simulation experiments are presented to validate the efficacy of the framework. Real-world examples, including a large scale neuroimaging dataset, are analyzed to demonstrate the computational tractability of the approach. Copyright © 2017, The Authors. All rights reserved.

关键词： Mixtures

Wildlife-microbiome interactions and disease: exploring opportunities for disease mitigation across ecological scales

学校读者我要写书评

暂无评论

Drug Discovery Today: Disease Models 2018年 28卷 105-115页

作者： Williams, Candace L. Caraballo-Rodríguez, Andrés Mauricio Allaband, Celeste Zarrinpar, Amir Knight, Rob Gauglitz, Julia M. Institute for Conservation Research San Diego Zoo Global United States Collaborative Mass Spectrometry Innovation Center Skaggs School of Pharmacy and Pharmaceutical Sciences University of California La Jolla San Diego 92307 CA United States Biomedical Sciences Graduate Program University of California La Jolla San Diego 92307 CA United States Department of Medicine University of California La Jolla San Diego 92307 CA United States Veterans Affairs San Diego Healthcare System San Diego California University of California La Jolla San Diego 92307 CA United States Department of Pediatrics University of California La Jolla San Diego 92037 CA United States Department of Bioengineering University of California La Jolla San Diego 92093 CA United States Department of Computer Science and Engineering University of California La Jolla San Diego 92093 CA United States Center for Microbiome Innovation University of California La Jolla San Diego 92307 CA United States

Captive wildlife are a unique set of animals, whose diverse host–microbe symbioses are underexplored. Compared to their wild counterparts they are particularly susceptible to a variety of diseases, many of which have explicit or purported links to the microbiome. In this perspective, we will examine how the microbiome influences gastrointestinal disorders, metabolic dysregulation, reproduction, and disease susceptibility in captive wildlife. Investigation of wildlife, and specifically captive wildlife, affords a unique opportunity to gain understanding of the broad diversity of the associated microbiota and learn from nature's molecular and microbial responses to disease. Studies like these could lead to the discovery of new interventions, ranging from dietary changes to the use of microbes or their natural products as treatment. Intervention strategies can lead to the discovery of medically relevant small molecules and the development of a novel platform for N-of-1 targeted medical investigations. © 2019 Elsevier Ltd

关键词：