检索结果-内蒙古大学图书馆

IEEE International conference on computer Design: VLSI in computers and Processors, (ICCD)

作者： Jianqi Chen Benjamin Carrion Schafer Department of Electrical and Computer Engineering The University of Texas at Dallas TX USA University of Texas at Dallas Dallas TX USA

This paper presents a method to generate a variety of micro-architectures for a given hardware accelerator mapped onto reconfigurable fabric optimized for different operating frequencies. The most optimal micro-architecture is then loaded onto the fabric for a given operating frequency in order to minimize the power consumption. State-of-the-art FPGAs are runtime reconfigurable and provide multiple clock domains. This enables these devices to reconfigure any accelerator mapped on them and their frequencies at runtime. At the same time, FPGA vendors have embraced high-Level Synthesis (HLS) to increase the design productivity and help designers with limited hardware development skills to program these devices. One of the advantages of HLS over traditional RT-level hardware design is that HLS allows to automatically generate micro-architectures with unique area, performance and power trade-offs by setting different synthesis options, which is impractical or very time consuming at the RT-level. This work leverages these two features and investigates the benefit of adapting the micro-architecture of hardware accelerators mapped onto a reconfigurable fabric at runtime when the operating frequency changes to reduce the power consumption, while maximizing the throughput. To enable the frequency-aware micro-architectural adaptation we also propose a simple micro-architectural resource manager and show that the overhead in terms of area and delay is negligible. We conduct two sets of experiments. The first shows that our proposed approach leads to faster circuits which consume less power than just statically scaling the frequency of the fastest micro-architecture for a variety of different test cases. The second case, presents case study of a face detection application mapped onto a battery-operated wireless camera sensor node powered by solar cells.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Distances with Message Passing Neural Networks 24

Learning Graph Distances with Message Passing Neural Network...

引用

24th International conference on Pattern Recognition (ICPR)

作者： Riba, Pau Fischer, Andreas Llados, Josep Fornes, Alicia Univ Autonoma Barcelona Dept Comp Sci Comp Vis Ctr Barcelona Spain Univ Fribourg DIVA Grp Dept Informat Fribourg Switzerland Univ Appl Sci & Arts Western Switzerland Inst Complex Syst Fribourg Switzerland

ISBN: (纸本)9781538637883

Graph representations have been widely used in pattern recognition thanks to their powerful representation formalism and rich theoretical background. A number of error-tolerant graph matching algorithms such as graph edit distance have been proposed for computing a distance between two labelled graphs. However, they typically suffer from a high computational complexity, which makes it difficult to apply these matching algorithms in a real scenario. In this paper, we propose an efficient graph distance based on the emerging field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure and learns a metric with a siamese network approach. The performance of the proposed graph distance is validated in two application cases, graph classification and graph retrieval of handwritten words, and shows a promising performance when compared with (approximate) graph edit distance benchmarks.

关键词： computer architecture Message passing Neural networks Measurement Shape Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Accessories-Aware Ear Recognition

Towards Accessories-Aware Ear Recognition

引用

2018 IEEE International Work conference on Bioinspired Intelligence, IWOBI 2018

作者： Emersic, Ziga Playa, Nil Oleart Struc, Vitomir Peer, Peter Faculty of Computer and Information Science University of Ljubljana Slovenia Barcelona School of Telecommunications Engineering Universitat Politcnica de Catalunya Spain Faculty of Electrical Engineering University of Ljubljana Slovenia

ISBN: (纸本)9781538675069

Automatic ear recognition is gaining popularity within the research community due to numerous desirable properties, such as high recognition performance, the possibility of capturing ear images at a distance and in a covert manner, etc. Despite this popularity and the corresponding research effort that is being directed towards ear recognition technology, open problems still remain. One of the most important issues stopping ear recognition systems from being widely available are ear occlusions and accessories. Ear accessories not only mask biometric features and by this reduce the overall recognition performance, but also introduce new non-biometric features that can be exploited for spoofing purposes. Ignoring ear accessories during recognition can, therefore, present a security threat to ear recognition and also adversely affect performance. Despite the importance of this topic there has been, to the best of our knowledge, no ear recognition studies that would address these problems. In this work we try to close this gap and study the impact of ear accessories on the recognition performance of several state-of-the-art ear recognition techniques. We consider ear accessories as a tool for spoofing attacks and show that CNN-based recognition approaches are more susceptible to spoofing attacks than traditional descriptor-based approaches. Furthermore, we demonstrate that using inpainting techniques or average coloring can mitigate the problems caused by ear accessories and slightly outperforms (standard) black color to mask ear accessories. © 2018 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Near Real-time performance of Population-based Nature-Inspired Algorithms on Cheaper and Older Smartphones 5

Near Real-time Performance of Population-based Nature-Inspir...

引用

5th International conference on Soft Computing and Machine Intelligence, ISCMI 2018

作者： Fister, Iztok Deb, Suash University of Maribor Faculty of Electrical Engineering and Computer Science Koroska cesta 46 Maribor2000 Slovenia Victoria University Decision Sciences and Modeling Program Melbourne Australia IT and Educational Consultant Ranchi Jharkhand India

ISBN: (纸本)9781728113012

For solving optimization problems, stochastic population-based nature-inspired algorithms use inspirations from nature. Despite their applicability in real-world environments, their bottleneck is high time complexity. Usually, they are searching for optimal solutions on computing devices of full computational power. However, in some situations, we deal with devices of limited computational power. Some examples of such devices are smartphones, which have been becoming very powerful for running various applications. However, there is still a lack of researches that would study the performance of nature-inspired algorithms on these devices. In this paper, we analyze the performance of one member of the nature-inspired algorithms, the so-called Bat algorithm, on the Android smartphone. Although smartphones nowadays offer a computational power comparable with the personal computer, we focus on the cheaper and older smartphones that are most widespread today. © 2018 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Effectiveness e-authentic assessment in computer network course

引用

Journal of Physics: conference Series 2020年第1期1481卷

作者： Ambiyar Raimon Efendi Yuyun Irawati Waskito Suryadimal Technical and Vocational Education Universitas Negeri Padang Jalan Prof Hamka Padang 25131 Indonesia Computer Science Faculty Universitas Dharmas Indonesia Dharmasraya Indonesia

This study aims to identify the quality and effectiveness of the application of authentic web-based assessments in computer network learning on wireless material, and to identify profiles of students' skills and knowledge competencies in learning computer networks on wireless material. The trial was conducted at the Faculty of computer Science, University of Dharmas Indonesia. This research uses a descriptive method. The population in this study were students of the Informatics Engineering Study program. Sampling is done using the purposive sampling method. Based on the results of the study, the quality of authentic assessments showed validity for assessment of performance of 0.94 (high) and reliability of 0.93 (very high), while the validity for the description question was 0.97 (very high) and reliability was 0.98 (very high). Based on observations on the effectiveness of the implementation of authentic assessments and student questionnaires, the level of application of authentic assessments is in categories both at the stage of assessment preparation, implementation of assessment and reflection. The skills competency profile of most students is in very good category, while the knowledge competencies of most students fall into sufficient categories for each indicator of the problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adventures of two student research computing facilitators 18

Adventures of two student research computing facilitators

引用

2018 Practice and Experience in Advanced Research Computing conference: Seamless Creativity, PEARC 2018

作者： Howard, Noah Nellutla, Saritha Colella, Nicholas McCoy, Evan Legaard, Kasey Whitsel, Larry Wilson, Chris Segee, Bruce School of Computing and Information Science University of Maine United States Bridgewater State University Department of Chemical Sciences United States Harvard University Department of Chemistry and Chemical Biology United States Department of Electrical and Computer Engineering University of Maine United States Research Scientist University of Maine United States Advanced Computing Group University of Maine System United States

ISBN: (纸本)9781450364461

The NSF-sponsored Northeast Cyberteam program (https://***) is matching student research computing facilitators with research projects at small and medium sized institutions that need help making use of high performance computing resources. Students are selected based on relevant domain knowledge and level of interest in exploring the Research Computing Facilitator role as a career path. Each student is paired with an experienced mentor, and each project lasts 3-5 months. The poster presents results from two of the ~10 Northeast Cyberteam projects that are either completed or in progress at the time of the conference. Students will be prepared to discuss the research projects that they supported, how their efforts advanced each project, reflections on what they learned about the Research Computing Facilitator role, and recommendations on how other sites might make best use of students as Research Computing Facilitators. In the first project, conducted at the University of Maine, improvements to application performance and parallelization have enabled production of forest attribute data at significantly higher volume, changing the philosophy of forest mapping from creating a single map to creating and assessing thousands of maps, making it possible to assess and (to some degree) trade off errors between maps. The second project expanded efforts to introduce computational chemistry into the undergraduate chemistry curriculum at Bridgewater State University. Having access to a high performance computer cluster allows for studying "real world" systems and also provides students with an opportunity to experience how research computing is done in academia and/or chemical/pharmaceutical industries. © 2018 Copyright held by the owner/author(s).

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Ranking paragraphs foriImproving answer recall in open-domain Question Answering

Ranking paragraphs foriImproving answer recall in open-domai...

引用

2018 conference on Empirical Methods in Natural Language Processing, EMNLP 2018

作者： Lee, Jinhyuk Yun, Seongjun Kim, Hyunjae Ko, Miyoung Kang, Jaewoo Department of Computer Science and Engineering Korea University Korea Republic of

ISBN: (纸本)9781948087841

Recently, open-domain question answering (QA) has been combined with machine comprehension models to find answers in a large knowledge source. As open-domain QA requires retrieving relevant documents from text corpora to answer questions, its performance largely depends on the performance of document retrievers. However, since traditional information retrieval systems are not effective in obtaining documents with a high probability of containing answers, they lower the performance of QA systems. Simply extracting more documents increases the number of irrelevant documents, which also degrades the performance of QA systems. In this paper, we introduce Paragraph Ranker which ranks paragraphs of retrieved documents for a higher answer recall with less noise. We show that ranking paragraphs and aggregating answers using Paragraph Ranker improves performance of open-domain QA pipeline on the four open-domain QA datasets by 7.8% on average. © 2018 Association for Computational Linguistics

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

A Millimeter Wave Beam Tracking in Vehicular Scenario via Particle Filter 6

A Millimeter Wave Beam Tracking in Vehicular Scenario via Pa...

引用

6th IEEE International conference on Network Infrastructure and Digital Content, IC-NIDC 2018

作者： Kang, Jeongwan Orikumhi, Igbafe Park, Young-Mi Kim, Sunwoo Department of Electronics and Computer Engineering Hanyang University Seoul Korea Republic of Agency for Defense Development Daejeon Korea Republic of

ISBN: (纸本)9781538660669

Mobility tracking has been highlighted as one of the key issues in millimeter wave communication. Although several beam tracking algorithms have been proposed to improve mobility tracking, these algorithms suffer high complexity. In this paper, we propose a low complexity beam tracking protocol via particle filter. In the proposed algorithm, a single beam pair is trained to track a path by exploiting the location information of the mobile station. We investigate several effects on the performance of the proposed tracking algorithm, such as the signal-to-noise ratio (SNR) and the array size of the base station antennas. It is observed that as the signal-to-noise ratio and the array size increases, the beam tracking performance improves. © 2018 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Reduced Kernel PCA for Nonlinear Process Monitoring

Machine Learning based Reduced Kernel PCA for Nonlinear Proc...

引用

International conference on Internet of Things, Embedded Systems and Communications (IINTEC)

作者： Khaled Dhibi Radhia Fezai Majdi Mansouri Abdelmalek Kouadri Kais Bouzrara Laboratory of Automatic Signal and Image Processing National School of Engineers of Monastir University of Monastir Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha QATAR

ISBN: (数字)9781728151847

ISBN: (纸本)9781728151854

Process monitoring is an essential part of industrial systems. It requires higher product quality and safety operations. Therefore, a nonlinear data-driven approach based reduced KPCA (RKPCA) for statistical monitoring of industrial processes is developed. RKPCA is a novel machine learning tool which merges dimensionality reduction and supervised learning. The use of classical KPCA for modeling and monitoring purposes can impose a high computational load when a large number of measurements are recorded. The main idea of the proposed RKPCA approach is to reduce the number of observations (samples) in the data matrix using the Euclidean distance between samples as dissimilarity metric so that only one observation is kept in case of redundancy. The Tennessee Eastman Process (TEP) is used to evaluate the fault detection abilities of the proposed RKPCA technique. The performance of the proposed method is evaluated and compared to the classical KPCA in terms of false alarms rates (FAR), missed detection rates (MDR) and computation times (CT).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection based on Hybrid Feature Extraction and SVM

Diabetic Retinopathy Detection based on Hybrid Feature Extra...

引用

International conference on Mathematics, Actuarial Science, computer Science and Statistics (MACS)

作者： Tahira Nazir Ali Javed Momina Masood Junaid Rashid Samira Kanwal University of Engineering and Technology Taxila Pakistan

ISBN: (数字)9781728149561

ISBN: (纸本)9781728149578

Diabetes is a disease caused by high blood sugar levels in the body. Diabetic retinopathy (DR) is a vision-threatening disease that primarily affects people who have diabetes for many years. It is the major cause of blindness in people with diabetes. Medical work in this domain indicated that blindness could be prevented by providing proper treatment by diagnosing DR at the initial stage. The proper screening requires the training of manual graders to understand the type of DR. However, the overall cost of this screening program increases due to the complexity of this process and workload on pathologists. State of the art methods has focused on simple retinal image analysis to eliminate the patients who are not affected by this disease. Therefore, reducing the overall cost of this process by decreasing the workload of pathologists. The focus of this research work is to automatically detect the severity level of DR instead of just providing information about its presence that can further reduce the DR costs. Therefore, we designed an automated framework to extract the anatomy independent features and trained the SVM classifier to detect different DR stages. We used the Kaggle DR-data set to evaluate the performance of the proposed method. For each stage of DR, which indicates the effectiveness of the proposed technique, an average accuracy of 96.4% was achieved. Experimental results show that the proposed method can efficiently and reliably detect DR in large image data sets. The main contribution of the proposed work is to design efficient, cost-effective and fully automatic DR screening techniques.

关键词： Diabetes Feature extraction Support vector machines Retina Retinopathy Image color analysis computer science

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：