检索结果-内蒙古大学图书馆

2019 International Conference on Sustainable Technologies for Industry 4.0, STI 2019

作者： Mahmud, Bahar Uddin Shuva, Rajib Das Bose, Shib Shankar Rahman Majumder, Md. Mujibur Jahan, Busrat Alam, Md. Mahbubul Feni University Dept. of Computer Science and Engineering Feni3900 Bangladesh WellDev Bangladesh Ltd Software Development Department Dhaka Bangladesh Venturas LTD Software Development Department Dhaka Bangladesh

ISBN: (纸本)9781728160979

In order to process a hand drawn input graph and digitize it, various digital geometric techniques have been used. These techniques utilize the inherent combinatorial properties of the relative arrangement of the object and grid lines. Aberrations like jaggedness, waviness, etc are overcome using geometrical techniques. This proposed algorithm uses properties of isothetic cover and digital-geometric straightness combined with the idea of Farey sequence to identify nodes, annotations and edges. We convert the input 2D image into pgm format and take this as input to our algorithm. Additionally, we use outer isothetic cover to recognize the nodes and annotations in the graph. The edges are analyzed with the idea of digital straightness combined with Farey sequence and geometric refinement on the seed vectors. Moreover, results of the two phases are finally compiled to associate each annotation with its associated node or edge using nearest distance measure. © 2019 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

DP-Net: Dynamic programming guided deep neural network compression

arXiv

引用

arXiv 2020年

作者： Yang, Dingcheng Yu, Wenjian Zhou, Ao Mu, Haoyuan Yao, Gary Wang, Xiaoyi BNRist Dept. Computer Science & Tech. Tsinghua University Beijing Engineering Research Center for IoT Software and Systems Beijing University of Technology Department of Electrical Engineering and Computer Science Case Western Reserve University

—In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an optimization process to train a clustering-friendly DNN. Experiments showed that the DP-Net allows larger compression than the state-of-the-art counterparts while preserving accuracy. The largest 77X compression ratio on Wide ResNet is achieved by combining DP-Net with other compression techniques. Furthermore, the DP-Net is extended for compressing a robust DNN model with negligible accuracy loss. At last, a custom accelerator is designed on FPGA to speed up the inference computation with DP-Net. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Requirements Dependency Extraction by Integrating Active Learning with Ontology-Based Retrieval

Requirements Dependency Extraction by Integrating Active Lea...

引用

IEEE International Conference on Requirements engineering

作者： Gouri Deshpande Quim Motger Cristina Palomares Ikagarjot Kamra Katarzyna Biesialska Xavier Franch Guenther Ruhe Jason Ho dept. of Computer Science University of Calgary Calgary Canada dept. of Service and Information System Engineering (ESSI) Universitat Politècnica de Catalunya Barcelona Spain dept. of Electrical and Software Engineering University of Calgary Calgary Canada Blackline Safety. Inc Calgary Canada

ISBN: (数字)9781728174389

ISBN: (纸本)9781728174396

Context: Incomplete or incorrect detection of requirement dependencies has proven to result in reduced release quality and substantial rework. Additionally, the extraction of dependencies is challenging since requirements are mostly documented in natural language, which makes it a cognitively difficult task. Moreover, with ever-changing and new requirements, a manual analysis process must be repeated, which imposes extra hardship even for domain experts. Objective: The three main objectives of this research are: 1) Proposing a new dependency extraction method using a variant of Active Learning (AL). 2) Evaluating this AL and Ontology-based Retrieval (OBR) as baseline methods for dependency extraction on the two industrial data sets. 3) Analyzing the value gained from integrating these diverse approaches to form two hybrid methods. Method: Building on the general AL, ensemble and semi-supervised machine learning, a variant of AL was developed, which was further integrated with OBR to form two hybrid methods (Hybrid1, Hybrid2) for extracting three types of dependencies (requires, refines, other): Hybrid1 used OBR as a substitute for human expert; Hybrid2 used dependencies extracted through the OBR as an additional input for training set in AL. Results: For two industrial case studies, AL extracted more dependencies than OBR. Hybrid1 showed improvement for both data sets. For one of them, F1 score increased to 82.6% compared to the AL baseline score of 49.9%. Hybrid2 increased the accuracy by 25% to the level of 75.8% compared to the AL baseline accuracy. OBR also complemented the AL approach by reducing 50% of the human effort.

关键词： Training Ontologies Machine learning Data mining Electronic mail Requirements engineering Safety

来源：评论

学校读者我要写书评

暂无评论

Robust software Rejuvenation for CPS with State Estimation and Disturbances

Robust Software Rejuvenation for CPS with State Estimation a...

引用

American Control Conference (ACC)

作者： Raffaele Romagnoli Bruce H. Krogh Bruno Sinopoli Dept. of Electrical and Computer Engineering Carnegie Mellon University (CMU) Pittsburgh PA USA Software Engineering Institute CMU Department of Electrical and Systems Engineering Washington University St. Louis MO USA

ISBN: (数字)9781538682661

ISBN: (纸本)9781538682678

software rejuvenation has been proposed and demonstrated as a strategy to protect cyber-physical systems (CSPs) against unanticipated and undetectable cyber attacks, but the supporting theory has neglected the effects of modeling uncertainties and disturbances and has assumed the availability of perfect state information from the sensor measurements. This paper addresses these issues by providing sufficient conditions for the successful implementation of software rejuvenation in the face of these real-world considerations. The results are illustrated for a simple position control system.

关键词： software Ellipsoids Safety Symmetric matrices Noise measurement State estimation Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Faster RCNN Detection Based OpenCV CSRT Tracker Using Drone Data

Faster RCNN Detection Based OpenCV CSRT Tracker Using Drone ...

引用

2019 International Conference on Information Science and Communications Technologies, ICISCT 2019

作者： Farhodov, Xurshedjon Kwon, Oh-Heum Kang, Kyung Won Lee, Suk-Hwan Kwon, Ki-Ryong Pukyong National University Dept. of IT Convergence and Application Engineering Busan Korea Republic of Dongeui University Dept.of Computer Software Engineering Busan Korea Republic of Tongmyong University Dept. of Information Communication Engineering Busan Korea Republic of Tongmyong University Dept.of Information Security Busan Korea Republic of

ISBN: (纸本)9781728125640

Object tracking is one of the well-known topic in computer Vision sphere with challenging and problematic tasks that frames come with problems like overlapping, camera motion blur, changing object appearance, environmental variations and so on. Using OpenCV based CSRT (Channel and Spatial Reliability Tracking) tracker itself, without integration object detection part may face problems which mentioned above. To overcome that challenges we integrated deep learning based object detection with CSRT tracker and got better tracking results. © 2019 IEEE.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Quantifying the quality of indoor maps 4

Quantifying the quality of indoor maps

引用

4th ISPRS Geospatial Week 2019

作者： Assali, M. Pipelidis, G. Podolskiy, V. Iwaszczuk, D. Heinen, L. Gerndt, M. Dept. of Computer Architecture and Parallel Systems Dept. of Informatics Technical University of Munich Munich Germany Software and Systems Engineering Research Group Dept. of Informatics Technical University of Munich Munich Germany Remote Sensing and Image Analysis Group Dept. of Civil and Environmental Engineering Science Technische Universität Darmstadt Germany BMW Group IT Munich Germany

Indoor maps are required for multiple applications, such as, navigation, building maintenance and robotics. One of common methods for map generation is laser scanning. In such maps, not only geometry of the map is of interest, but also its quality. This study aims at developing methods for real-time generation of indoor maps using features extracted from pointclouds obtained by a robot with their simultaneous quality assessment. We investigate, how this quality can be quantified for feature-based maps. First, we introduce a method for modeling 2D maps into 3D models that enable their usage for localization. Second, we review and evaluate a number of algorithms that can enable us to address features in a map. Hence, we enable the generation of objects from a pointcloud that has been sensed. Finally, we study several aspects of the map quality and we formalize them into metrics that can be applied to quantify their quality. © Authors 2019.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

LSTM-based approach to monitor operator situation awareness via HMI state prediction 2

LSTM-based approach to monitor operator situation awareness ...

引用

2nd IEEE International Conference on Industrial Internet Cloud, ICII 2019

作者： Singh, Harsh V.P. Mahmoud, Qusay Computers and Controls Design Dept. Ontario Power Generation Canada PickeringON Canada Dept. of Electrical Computer and Software Engineering Ontario Tech University OshawaONL1G 0C5 Canada

ISBN: (纸本)9781728129778

Situational Awareness is an indispensable barrier against execution human errors from cascading across system processes. Therefore, early detection and intervention is vital for preventing accidents in time-critical scenarios. Evidently, legacy human-machine interfaces especially those prevalent in nuclear power plant and aviation industry, are complex, elaborate and require continual supervision of operator situational aware-ness. In this paper, a novel approach towards achieving non-intrusive real-time monitoring of operator situational awareness is framed as a supervised learning task suitable for applying deep recurrent neural network (RNN) models. Results, include performance evaluation of few typical RNN Long-Short Term Memory (LSTM) based time-series forecast models for predicting expected operator n-step ahead response pattern given current human-machine interface state as inputs. © 2019 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Using Structured event to represent complaints of patients: A medical assistant for doctors 5

Using Structured event to represent complaints of patients: ...

引用

5th IEEE International Conference on computer and Communications, ICCC 2019

作者： Song, Haowei Li, Gangmin Liu, Zuopeng Bai, Xuming Xi'An Jiaotong-Liverpool University Dept. Computer Science and Software Engineering Suzhou Jiangsu China Second Affiliated Hospital of Aoochow University Interventional Radiology Suzhou Jiangsu China

ISBN: (纸本)9781728147437

Extracting relations between entities from complaints of patients is a significant but challenging problem in intelligent medical diagnose. It can help doctors to record the main information from the complaints of patients. As the development of technologies, Doctors need a more effective and convenient way to capture entire information from patients' complaints and build Electronic Health Records (EHRs). This paper proposes an event generation model which input the complaints of patients directly then output a series of events as complementary to traditional keywords based chief complaint capture. The event generation model adopts an open Chinese Information Extraction (open Chinese IE) and build a part-of-speech tagging to do dependency grammar analysis. Two kinds of evaluations are taken. One is metrics recall-oriented understanding for gusting evaluation (ROUGE). It measures the fitness of the generated events with the standard reference from doctors. The other are accuracy and Matthews Correlation Coefficient (MCC). They test the performance of grammar analysis. The results show our model have an excellent and robust performance. © 2019 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

WIP abstract: Interactive explanation for planning-based systems 10

WIP abstract: Interactive explanation for planning-based sys...

引用

10th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2019, part of the 2019 CPS-IoT Week

作者： Zhao, Ellin Sukkerd, Roykrong Dept. of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Institute for Software Research Carnegie Mellon University PittsburghPA United States

ISBN: (纸本)9781450362856

As Cyber-Physical Systems (CPSs) become more autonomous, it becomes harder for humans who interact with the CPSs to understand the behavior of the systems. Particularly for CPSs that must perform tasks while optimizing for multiple quality objectives and acting under uncertainty, it can be difficult for humans to understand the system behavior generated by an automated planner. This work-in-progress presents an approach at clarifying system behavior through interactive explanation by allowing end-users to ask Why and Why-Not questions about specific behaviors of the system, and providing answers in the form of contrastive explanation. © 2019 Copyright held by the owner/author(s).

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Task Offloading for Automatic Speech Recognition in Edge-Cloud Computing Based Mobile Networks

Task Offloading for Automatic Speech Recognition in Edge-Clo...

引用

IEEE Symposium on computers and Communications (ISCC)

作者： Shitong Cheng Zhenghui Xu Xiuhua Li Xiongwei Wu Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong SAR China College of Intelligence and Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Dept. Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9781728180861

ISBN: (纸本)9781728180878

Explosively increasing multimedia services and applications, e.g., automatic speech recognition (ASR), have aggravated the burden on the cloud server in mobile networks. To address the challenge, mobile edge computing has emerged for partially alleviating the workload of the cloud server and enhancing the quality of service of mobile users. In this paper, we aim to employ the technique of edge-cloud computing to accelerate the processing of ASR tasks generated by users in mobile networks. Particularly, we deploy a convolutional neural network based encoder in each edge server to extract features of the audio data. Based on certain network constraints (i.e., user association and edge servers' storage/computing capacity), we propose a low-complexity and distributed iterative greedy method to address the formulated nonlinear mixed-integer nonconvex optimization problem. Simulation results demonstrate the effectiveness of the proposed scheme on reducing the total delay in the network.

关键词：

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：