检索结果-内蒙古大学图书馆

G-gene: A gene alignment method for online partial stroke gestures recognition

Proceedings of the ACM on Human-computer Interaction 2018年第EICS期2卷 1–17页

作者： Carcangiu, Alessandro Spano, Lucio Davide Dep. of Electric and Electronic Engineering University of Cagliari Via Marengo 2 Cagliari09123 Italy Dep. of Mathematics and Computer Science University of Cagliari Via Ospedale 72 Cagliari09124 Italy

The large availability of touch-sensitive screens fostered the research in gesture recognition. The Machine Learning community focused mainly on accuracy and robustness to noise, creating classifiers that precisely recognize gestures after their performance. Instead, the User Interface engineering community developed compositional gesture descriptions that model gestures and their sub-parts. They are suitable for building guidance systems, but they lack a robust and accurate recognition support. In this paper, we establish a compromise between the accuracy and the provided information introducing G-Gene, a method for transforming compositional stroke gesture definitions into profile Hidden Markov Models (HMMs), able to provide both a good accuracy and information on gesture sub-parts. It supports online recognition without using any global feature, and it updates the information while receiving the input stream, with an accuracy useful for prototyping the interaction. We evaluated the approach in a user interface development task, showing that it requires less time and effort for creating guidance systems with respect to common gesture classification approaches. © 2018 Association for Computing Machinery.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Autonomous Detection of Plant Disease Symptoms Directly from Aerial Imagery

Plant Phenome Journal

引用

Plant Phenome Journal 2019年第1期2卷 1-9页

作者： Wu, Harvey Wiesner-Hanks, Tyr Stewart, Ethan L. DeChant, Chad Kaczmar, Nicholas Gore, Michael A. Nelson, Rebecca J. Lipson, Hod Dep. of Computer Science Columbia Univ. New York 10027 NY United States Dep. of Mechanical Engineering and Institute of Data Science Columbia Univ. New York 10027 NY United States Plant Breeding and Genetics Section School of Integrative Plant Science Cornell Univ. Ithaca 14853 NY United States Plant Pathology and Plant-Microbe Biology Section School of Integrative Plant Science Cornell Univ. Ithaca 14853 NY United States

Core Ideas A deep learning model identified plant disease in UAV images with 95% accuracy. Transfer learning allowed for faster model optimization. This method detected plant disease symptoms at a very fine spatial scale. The detection, diagnosis and quantification of plant diseases using digital technologies is an important research frontier. New and accurate methods would be an asset to growers, for whom early disease detection can mean the difference between successful intervention and massive losses, and plant breeders, who often must rely on time-consuming phenotyping by eye. We have developed such a method for detecting an important maize (Zea mays L.) disease. Northern leaf blight [NLB;causal agent Setosphaeria turcica (Luttrell) Leonard & Suggs] is a foliar disease of maize that causes significant yield losses. Accurately measuring NLB infection is necessary both for breeding more resistant maize lines and for guiding crop management decisions. Visual disease scoring in a large area is time-consuming and human evaluations are subjective and prone to error. In this work, we demonstrate an automated, high-throughput system for the detection of NLB in field images of maize plants. Through the use of an unmanned aerial vehicle (UAV) to acquire high resolution images, we trained a convolutional neural network (CNN) model on lower resolution sub-images, achieving 95.1% accuracy on a separate test set of sub-images. The CNN model was used to create interpretable heat maps of the original images, indicating the locations of putative lesions. Detecting lesions at a fine spatial scale allows for the potential of unprecedented high-resolution disease detection for plant breeding and crop management strategies. © 2019 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensing with magnetostriction by coupling geometrical effect to an embedded fiber Bragg grating

Sensing with magnetostriction by coupling geometrical effect...

引用

Optical Sensors, Sensors 2019

作者： Jiménez, Raúl E. Frailey, David M. Law, Chiu Tai Acuna, Rodrigo Escuela de Física Universidad Nacional de Colombia - Medellín Medellín20036 Colombia Dep. of Electrical Engineering and Computer Science University of Wisconsin MilwaukeeWI53211 United States

This paper discusses the geometrical effects on the performance of a fiber optic magnetic field sensor based on a magnetostrictive composites. Experimental results for the cases under study agree with the discussed th... 详细信息

ISBN: (纸本)9781943580613

关键词： Fiber Bragg gratings

来源：评论

学校读者我要写书评

暂无评论

Intercross: An Android app for plant breeding and genetics cross management

arXiv

引用

arXiv 2021年

作者： Rife, Trevor W. Courtney, Chaney Bauchet, Guillaume Neilsen, Mitchell Poland, Jesse A. Wheat Genetics Resource Center Dep. of Plant Pathology 4024 Throckmorton Plant Sciences Center Kansas State Univ 1712 Claflin Road ManhattanKS66506 United States Boyce Thompson Institute Cornell University 533 Tower Road IthacaNY14853 United States Terre de Lin 605 Route de la Vallée Saint-Pierre-le-Viger76740 France Dep. of Computer Science 2184 Engineering Hall Kansas State University 1701D Platt St. ManhattanKS66506 United States

Plant breeding is fundamentally comprised of three cyclic activities: 1) intermating lines to generate novel allelic combinations, 2) evaluation of new plant cultivars in distinct environments, and 3) selection of superior individuals to be used as parents in the next breeding cycle. While digital technologies and tools are commonly utilized for the latter two stages, many plant research programs still rely on manual annotation and paper tags to track the crosses that constitute the basis of a plant breeding program. This presence of analog data is a crack in the foundation of a digital breeding ecosystem and a significant occasion for errors to be introduced that will propagate through the entire breeding program. However, implementing digital cross tracking into breeding programs is difficult due to the non-standardized workflows that different breeders have adopted. Intercross, an open-source Android app, aims to provide scientists with a robust and simple solution for planning, tracking, and managing the crosses being made each season and aims to serve as the primary tool to digitize crossing data for breeding programs. The simplicity and flexibility of Intercross allows rapid and broad adoption by diverse breeding programs and will solidify the concepts of a digital breeding ecosystem. © 2021, CC BY-SA.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Monitoring system of agricultural performance based on multisensor data and cross-validation technique in merging temporal images

引用

Agronomy Journal 2022年第1期115卷

作者： N. P. G. Bhavani Prameeladevi Chillakuru Ramana Lakshmi Adusumilli Roobaea Alroobaea Saeed Rubaiee Abdulkader S. Hanbazazah Suman Mann Saveetha School of Engineering Chennai Tamil Nadu 602105 India Contribution: Data curation Formal analysis Rajalakshmi Engineering College Chennai Tamil Nadu 602105 India Contribution: Investigation Methodology Dep. of Computer Science and Engineering Prasad V Potluri Siddhartha Institute of Technology Kanuru Vijayawada Andhra Pradesh 520007 India Contribution: Resources Software Dep. of Computer Science College of Computers and Information Technology Taif Univ. P. O. Box 11099 Taif 21944 Saudi Arabia Contribution: Funding acquisition Supervision Dep. of Industrial and Systems Engineering College of Engineering Univ. of Jeddah Jeddah Saudi Arabia Contribution: Funding acquisition Visualization Contribution: Funding acquisition Writing - original draft Writing - review & editing Maharaja Surajmal Institute of Technology New Delhi 110058 India Contribution: Conceptualization Writing - original draft

Several approaches to forecasting agricultural production have been used across the country, but they have focused on information widely detected with technology that was not very successful. Unfortunately, because of many difficulties such as climate variables (50% global fog cover) with limited temporal accuracy, the remotely detected information necessary to predict crop production was often insufficient. As a result of these problems, existing methods of estimating agricultural production are ineffective or out of date. Several efforts have been made to overcome these challenges by combining images with high temporal accuracy but poor geographic detail. On the other hand, it is this kind of situation that is most suitable for extremely large and homogeneous agricultural areas. An innovative theoretical framework has developed that explains this absence of high-quality satellite images. This intelligent method was built around this new theoretical framework, which incorporates its use of something like the energy equation to improve the predictions of multiple cultures. Many producers were contacted and data regarding agricultural production were obtained to validate the results of the smart technology. The excellent reliability of this intelligent method has been shown by a comparative contrast between projected crop yields and actual output in various areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Immersive technologies in higher education: Applications, challenges, and good practices 3

Immersive technologies in higher education: Applications, ch...

引用

3rd International Conference on Education and E-Learning, ICEEL 2019

作者： Calvet, Laura Bourdin, Pierre Prados, Ferran IN3-Computer Science Dep. Universitat Oberta de Catalunya Barcelona Spain Área de empresa Universidad Internacional de Valencia Valencia Spain Computer Science Dep. Universitat Oberta de Catalunya Barcelona Spain Eventlab Edifici Teatre Departament de Psicologia Clínica i Psicobiologia Universitat de Barcelona Barcelona Spain Medical Physics and Biomedical Engineering Department University College London London United Kingdom

ISBN: (纸本)9781450372251

Immersive technologies are becoming increasingly popular in a wide range of fields from gaming to therapy. While there is a high number of case studies in education with promising results in terms of students' performance and engagement, there has still not been widespread adoption. Indeed, more research focused on large-size samples, assessing and discussing the effects on the medium and large term is required, as well as comparisons among different hardware and software, and guidelines for instructors that want to introduce these technologies in their classrooms. In this paper, we focus on the use of immersive technologies applications in higher education. In particular, we explain the basics of immersive technologies, review the main applications in higher education, discuss benefits and challenges, and describe good practices for instructors. © 2019 Association for Computing Machinery. ACM ISBN 978-1-4503-7225-1/19/11…$15.00

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Understanding Semantic Style by Analysing Student Code 18

Understanding Semantic Style by Analysing Student Code

引用

20th Australasian Computing Education Conference, ACE 2018

作者： De Ruvo, Giuseppe Tempero, Ewan Rowe, Gerard B. Giacaman, Nasser Dep. of Electrical and Computer Engineering University of Auckland Auckland New Zealand Andrew Luxton-Reilly Dep. of Computer Science University of Auckland Auckland New Zealand Dep. of Electrical and Computer Engineering University of Auckland Auckland New Zealand

ISBN: (纸本)9781450363402

Good coding style is recognised by the software engineering profession as being important, and this is reflected in the standard computing curricula. Feedback on some aspects of coding style is now commonly provided by IDEs and by tools such as Checkstyle, but this feedback focuses on coding standards that are largely based on syntax. However, some aspects of coding style relate to the semantics of code — of the many ways to achieve some functionality, some are preferred because they are simpler, yet students struggle to create them. In this paper, we introduce the concept of semantic style, and in particular semantic style indicators that may be manifestations of poor knowledge of some programming concepts. We describe 16 semantic style indicators and demonstrate their prevalence in almost 19,000 code samples submitted by over 900 novice students. Half the students submitted code exhibiting two or more of these indicators, demonstrating the potential value to learn by providing feedback on semantic style. We also find many indicators are present in the code of students attending their fourth year of a highly competitive Software engineering programme, demonstrating the need for more attention to teaching of semantic style issues.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reversible dielectric breakdown in h-BN stacks: a statistical study of the switching voltages

Reversible dielectric breakdown in h-BN stacks: a statistica...

引用

Annual International Symposium on Reliability Physics

作者： J. B. Roldán D. Maldonado F. Jiménez-Molinos C. Acal J.E. Ruiz-Castro A.M. Aguilera F. Hui J. Kong Y. Shi X. Jing C. Wen M.A. Villena M. Lanza Dep. Electrónica y Tecnología de Computadores Universidad de Granada Granada Spain Dep. Estadística e Investigación Operativa Universidad de Granada Granada Spain Faculty of Materials Science and Engineering Technion – Israel Institute of Technology Haifa Israel Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology MA USA IMEC Leuven Belgium Institute of Functional Nano and Soft Materials (FUNSOM) Soochow University Suzhou China

ISBN: (数字)9781728131993

ISBN: (纸本)9781728132006

Memristor devices with the Au/Ag/h-BN/Fe structure have been fabricated and characterized. The switching voltages, and other newly-defined parameters extracted, like V 2dmax1 and V 2dmax2 , have been analyzed statistically in an exhaustive manner. The conduction across the memristor can be described well with a Quantum Point Contact (QPC) model that accounts for quantized filamentary conduction. The distributions of set and reset voltages have been proved to be accurately reproduced by using Weibull distributions. We also present an analysis making use of phase-type distributions to characterize the measured data stochasticity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation on data augmentation for object detection using deep neural network for traffic signs application 18

Investigation on data augmentation for object detection usin...

引用

18th International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2019

作者： Mohamed Elhawary, Hossamelden Shapiai, Mohd Ibrahim Zamzuri, Hairi Fauzi, Hilman Dep. of Computer Engineering Arab Academy for Science and Technology Cairo Egypt Malaysian Japanese International Institute Universiti Teknologi Malaysia Kuala Lumpur Malaysia MooVita Ptl. Ltd. Malaysia Faculty of Electrical Engineering Telkom University Bandung Indonesia

ISBN: (纸本)9781643680125

Data augmentation is being widely used to enrich the datasets and enhance the performance of neural network for classification and detection. However most of the recent works focus only on the augmentation for classification. A technique for detection augmentation by template blending has been introduced in the literature. The limitation of blending technique is an extra polygon shape of each object needed to blend with the scene. In this paper we investigate the effect of the geometric transformations for detection augmentation on the Malaysian Traffic Sign Detection (MTSD) datasets. We propose and investigate a new augmentation framework for object detection datasets and train using faster-rcnn with ZF network as a backbone. We measure the Average Precision (AP) as stated in paper [PASCAL VOC] and show the correlation matrix for each class. Our findings show that data augmentation improving the performance for true positive. However, many false positive also occur but decreased by 19.7% after augmentation. © 2019 The authors and IOS Press. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FPGA-based OpenCL accelerator for discovering temporal patterns in gene expression data using biclustering 2018

FPGA-based OpenCL accelerator for discovering temporal patte...

引用

6th International Workshop on Parallelism in Bioinformatics, PBio 2018, held as part of EuroMPI 2018

作者： Duarte, Rui P. Simes, Lvaro Henriques, Rui Neto, Horácio C. INESC-ID Dep. of Computer Science and Engineering Univ. de Lisboa Portugal INESC-ID Dep. of Electrical and Computer Engineering Univ. de Lisboa Portugal

ISBN: (纸本)9781450365314

Biclustering is a prominent task for the analysis of biological data, including gene expression data from microarray experiments or molecular concentrations from mass spectrometry. Biclustering performs simultaneous clustering on biological entities and samples, enabling the discovery of nontrivial regulatory modules with putative biological functions. Although several biclustering algorithms have been proposed, existing algorithms are challenged by efficiency aspects given the inherent NP-hard nature of this task and the high-dimensionality of biological data. This work proposes principles to accelerate state-of-the-art biclustering algorithms, with a focus on the Qualitative BIClustering (QUBIC) algorithm given its inherent efficiency and ability to identify statistically significant biclusters. To this end, this work introduces a parallel architecture for QUBIC based on an heterogeneous system composed by a FPGA and a CPU that communicate through the OpenCL framework. The proposed architecture is sound and surpasses the need for dedicated electronic solutions. Results show a reduction up to 29x in the execution time of the functions accelerated on the FPGA, when compared to a software-only implementation. © 2018 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：