检索结果-内蒙古大学图书馆

11th IFAC conference on Control Applications in Marine Systems, Robotics, and Vehicles (CAMS)

作者： Martinsen, Andreas B. Lekkas, Anastasios M. Norwegian Univ Sci & Technol NTNU Dept Engn Cybernet NO-7491 Trondheim Norway

We propose a new framework, based on reinforcement learning, for solving the straight-path following problem for underactuated marine vessels under the influence of unknown ocean current. A dynamic model from the Marine Systems Simulator is employed to simulate the motion of a mariner-class vessel, however the policy search algorithm has no prior knowledge of the system it is assigned to control. A deep neural network is used as function approximator and the deep deterministic policy gradients method is employed to extract a suitable policy that minimizes the cross-track error. Two intuitive reward functions, which in addition prevent noisy rudder behavior, are proposed and compared. the simulation results demonstrate excellent performance, also in comparison with the line-of-sight guidance law. (C) 2018, IFAC (international Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Deep reinforcement learning path following marine control systems deep deterministic policy gradients

来源：评论

学校读者我要写书评

暂无评论

Dissolved Oxygen (DO) Meter Hydrological Modelling Using Predictive Algorithms

Dissolved Oxygen (DO) Meter Hydrological Modelling Using Pre...

引用

IEEE international conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management

作者： Aljay R. Lorenzo Allysa Y. Dula Neil Aldrin C. Valeroso John David C. Munda Brian Noli G. Supang Maria Victoria C. Padilla Gilfred Allen M. Madrigal Timothy M. Amado Lean Karlo S. Tolentino Eecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he PhiiinesEecronics Engineering Deren Technoogic Universiy of he Phiiines

ISBN: (数字)9781728130446

ISBN: (纸本)9781728130453

Dissolved oxygen is one of the critical indicators of a body of water's health and water quality. It refers to the presence of free, non-compound oxygen found in water. It also influences the growth and survival of the aquatic organisms living in it. this study aims to develop a low-cost, multi-function device that could determine the value of the dissolved oxygen (DO) level through hydrological modelling of water parameters such as temperature, pH, and conductivity using Decision Tree, Decision forest, and Multi-layer Perceptron machine learning algorithms. Using various metrics, the most efficient model was built using Random Forest algorithm, for it yielded the most reliable metrics when compared to the other two algorithms. the evaluated model has the following metrics: the Coefficient of Determination, or how well a model explains and predicts future outcomes, is 0.99. the Mean Absolute Error, or the average magnitude of the errors in a set of predictions, is 0.32. the Mean Squared Error, utilized in order to measure the performance of an estimator, is 0.36. the Root Mean Squared Error, or how concentrated the data is around the line of best fit, is 0.60. Relative to Atlas Scientific's DO Sensor, the device can predict the dissolved oxygen level of a given water pond with 2.61% error. the final device is a handheld device consisting of the sensors for the highest- ranking parameters with respect to their relationship to DO: temperature, conductivity, and pH.

关键词： Water parameters Dissolved oxygen Python Machine learning Hydrological modelling Water meter

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques in Software engineering for automated Software Reuse and Design

Artificial Intelligence Techniques in Software Engineering f...

引用

international conference on Computing, Communication & Automation (ICCCA)

作者： Divanshi Priyadarshni Wangoo Department of CSE & IT Amity School of Engineering and Technology Amity University Noida Uttar Pradesh India

ISBN: (纸本)9781538669488

Mining of software engineering data have proved successful for reusability of components in software development. Artificial Intelligence improves a large application domain of software engineering activities. intelligent knowledge discovery integrates Artificial Intelligence with data Mining for intelligent computing of software engineering tasks. the integration of artificial intelligence with data mining for supporting software engineering applications leads to Software Intelligence. this paper analyzes three artificial intelligence techniques that uses data mining, business intelligence, machine learning for promoting automated software reuse for software construction and overall software development. the business intelligence tools are used for intelligent knowledge discovery of code that will be used for reusability of applications and components. An analysis of several AI techniques in software reuse domain of software engineering is discussed for automated software reuse and identification of potential research prospects in the field.

关键词： Software engineering Artificial intelligence data mining Software reusability Task analysis Business intelligence

来源：评论

学校读者我要写书评

暂无评论

Hand Detection and Location Based on Improved SSD for Space Human-Robot Interaction 11th

Hand Detection and Location Based on Improved SSD for Space ...

引用

11th international conference on intelligent Robotics and Applications (ICIRA)

作者： Gao, Qing Liu, Jinguo Ju, Zhaojie Zhang, Lu Li, Yangmin Liu, Yuwang Chinese Acad Sci State Key Lab Robot Shenyang Inst Automat Shenyang 110016 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Portsmouth Sch Comp Portsmouth PO1 3HE Hants England Chinese Acad Sci Key Lab Space Utilizat Technol & Engn Ctr Space Utilizat Beijing 100094 Peoples R China Hong Kong Polytech Univ Dept Ind & Syst Engn Hong Kong 999077 Peoples R China

ISBN: (纸本)9783319975863;9783319975856

In the astronaut-space robot interaction based on hand gestures, the detection and location of hands are the premise and basis of vision-based hand gesture recognition and hand tracking. In this paper, the SSD (Single Shot Multibox Detector) which is a kind of deep learning model is utilized to detect and locate astronaut's hands for space human-robot interaction (SHRI) based on hand gestures. First of all, in order to meet the needs of hand detection and location, an improved SSD model is designed to detect hands when they are shown as small targets in images. then, a platform for SHRI is built and a set of hand gestures for SHRI are designed. Finally, the proposed SSD model is validated experimentally on a homemade hand gesture database for proving the superiority of this improved SSD model to small target hands detection.

关键词： Human-robot interaction Hands detection SSD Deep learning

来源：评论

学校读者我要写书评

暂无评论

IoT-architecture-based all-in-one monitoring system design and implementation for data center 11th

IoT-architecture-based all-in-one monitoring system design a...

引用

11th EAI international conference on Communications and Networking in China, ChinaCom 2016

作者： Zhou, Jinde Xu, Wenjun Yang, Fan Lin, Jiaru Key Lab of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9783319666273

Modularization and integration are becoming the mainstream trend in the development of data center. However, the integrated monitoring of power and environment has been a challenge in data centers. An All-in-One monitoring system design and implementation has been developed based on Internet of things (IoT) architecture in this paper. the hardware is composed of two levels: one integrated monitoring gateway and several monitoring modules through the CAN-BUS network. the two-level structure design enables us to achieve module splicing and flexible deployment easily as well as rapid troubleshooting. A series of software applications are developed to establish the sensor network and collect sensor data. In addition, a web interface is provided for users to master the state of data center conveniently. Laboratory tests verify that the proposed system is able to offer automatic and intelligent support for data center management, thus significantly reducing the cost of labor and operation. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Sequence Transformation Model for Chinese Named Entity Recognition 11th

A Sequence Transformation Model for Chinese Named Entity Rec...

引用

11th international conference on Knowledge Science, engineering and Management (KSEM)

作者： Wang, Qingyue Song, Yanjing Liu, Hao Cao, Yanan Liu, Yanbing Guo, Li Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Beijing Inst Technol Software Inst Beijing Peoples R China Chinese Acad Sci Inst Informat Engn Beijing Peoples R China

ISBN: (纸本)9783319993652;9783319993645

Chinese Named Entity Recognition (NER), as one of basic natural language processing tasks, is still a tough problem due to Chinese polysemy and complexity. In recent years, most of previous works regard NER as a sequence tagging task, including statistical models and deep learning methods. In this paper, we innovatively consider NER as a sequence transformation task in which the unlabeled sequences (source texts) are converted to labeled sequences (NER labels). In order to model this sequence transformation task, we design a sequence-to-sequence neural network, which combines a Conditional Random Fields (CRF) layer to efficiently use sentence level tag information and the attention mechanism to capture the most important semantic information of the encoded sequence. In experiments, we evaluate different models both on a standard corpus consisting of news data and an unnormalized one consisting of short messages. Experimental results showed that our model outperforms the state-of-the-art methods on recognizing short interdependence entity.

关键词： Named Entity Recognition Deep learning Sequence to sequence neural network Conditional Random Fields

来源：评论

学校读者我要写书评

暂无评论

Resiliency of businesses during 2010 maule earthquake: An investigation of the 2017 LFE study Program 11

Resiliency of businesses during 2010 maule earthquake: An in...

引用

11th National conference on Earthquake engineering 2018: Integrating Science, engineering, and Policy, NCEE 2018

作者： Bastidas, Ana Maria Parra Hyde, Sandra Julius, Alexandria Peck, Quinn Carlos H. Parra and Asociados Pontificia Universidad Javeriana Cali Cali Colombia International Code Council PortlandOR United States Graduate Research Associate Civil Environmental and Geodetic Engineering Department Ohio State University ColumbusOH United States ARUP SeattleWA United States

ISBN: (纸本)9781510873254

the resiliency of small businesses had an important impact on the social and economic recovery of small communities after the 2010 Maule earthquake in Chile. the EERI/CIGIDEN learning from Earthquakes (LFE) 2017 Study Program intended to study the resilience of communities by studying the case of Chilean communities affected during the 2010 Maule earthquake. the 2017 LFE Study Program’s business group found minor impacts from the 2010 Maule earthquake on some small businesses. Some small businesses recovered quickly after the 2010 Maule earthquake. the resiliency characteristics and the effects of the earthquake on small businesses were obtained from interviews with business owners who were selected randomly based on their availability to participate in the interviews. For this report, two small businesses are considered. the first business is a winery in the Colchagua Valley, O’Higgins Region. the second business is small local market in Santa Cruz, O’Higgins Region. the information gathered from the interviews includes qualitative descriptions of the baseline economic and physical conditions of the businesses before the earthquake and impacts of the earthquake on business revenue, facilities, operations and personnel. the 2017 LFE study program business group focused upon personal interviews of business owners who had experienced the effects of the 2010 Maule Earthquake;the interviews offer a snapshot of the ongoing recovery of small businesses in Chile after the earthquake. the information provided in this paper establishes a level of recovery for January 2017 which can be compared with findings gathered in 2010 just after the earthquakes or information gathered in the years following the earthquake. this data is valuable for researchers wishing to evaluate aspects of the recovery process for small businesses in Chile and other countries. Additionally, the resiliency evaluation techniques and other benefits of the 2017 LFE study program obtained by the business g

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Prediction Based on Expressway Operating Vehicle data

Traffic Flow Prediction Based on Expressway Operating Vehicl...

引用

international conference on intelligent Computation Technology and Automation, ICICTA

作者： Yunfei Ai Zhiming Bai Hang Su Nan Zhong Yunhua Sun Jiandong Zhao National Engineering Laboratory for Transportation Safety and Emergency Informatics Beijing China School of Mechanical and Electronic Control Engineering Beijing Jiaotong University Beijing P.R. China School of Traffic and Transportation Beijing Jiaotong University Beijing P.R. China

Expressway traffic flow prediction is an important basis for traffic and transportation management department, and it is also an important support for promoting the development of intelligent transportation. therefore, this paper predicts the expressway traffic flow based on the data of expressway operating vehicles in Jiangxi Province. the main work includes: cleaning the abnormal data of the original data, then fill in the missing data with the trend-history filling algorithm, and next calculating the speed time series in the cycle of 10 minutes. Finally, the support vector machine algorithm is used to predict the expressway traffic flow, and the prediction result is great. It can provide data foundation and technical support for decision management of traffic management departments.

关键词： Handheld computers conferences Automation

来源：评论

学校读者我要写书评

暂无评论

Fathoming the future of artificially intelligent robots

引用

international Journal of Design and Nature and Ecodynamics 2018年第1期13卷 1-15页

作者： White, Brian E. Complexity Are Us ← Systems Engineering Strategies United States

the world abounds with massive efforts to further develop artificial intelligence, mostly with hopes of achieving greater benefits to humankind. Not surprisingly, there is relatively little concern about the dangers associated with the, as yet hypothetical, eventual situation where robots might possess human-like capabilities of cognition, emotional experience, learning, etc. the following five propositions will be examined: 1. Could the most advanced robots ‘evolve’ to truly human-being levels of achievement within a foreseeable time frame? 2. Will robots ultimately take over all the jobs, including the making of robots, with relatively few human owners of robots (and most everything else) in charge? 3. Will humans live much longer and essentially turn into pseudo-robots through receiving more replacement body parts, even involving portions of the brain? 4. What are the possibilities of being psychologically manipulated by authoritarians using Big data in knowing what citizens care about and how people think? 5. Will humans keep losing not only manual jobs but also knowledge positions with increasing robotic capabilities and the attractions of robotic replacements? the conclusive answers: a ‘no’ to Proposition 1;a ‘maybe’ to 2;possible ‘yeses’ to 3 and 4;and a definite ‘yes’ to 5;will be explained. this subject quite obviously overlaps some combination of at least three of our conference themes, viz., Complex Systems engineering, Global Issues and Social Systems. the paper’s focus will be on framing the above-described topics in a matrix with two dimensions: holistic thinking perspectives (big picture, operational, functional, structural, generic, continuum, temporal, quantitative and scientific) and journalist questions (who, what, where, when, why and how). Several of the more interesting topics from this milieu will be elaborated upon to stimulate further thought, discussion, and research efforts. © 2018 WIT Press.

关键词： Systems engineering

来源：评论

学校读者我要写书评

暂无评论

Pattern discovery from big data of food sampling inspections based on extreme learning machine 11th

Pattern discovery from big data of food sampling inspections...

引用

11th IFIP WG 8.9 Working conference on Research and Practical Issues of Enterprise Information Systems, CONFENIS 2017

作者： Liu, Yi Li, Xin Wang, Jianxin Chen, Feng Wang, Junyu Shi, Yiwei Zheng, Lirong State Key Laboratory of ASIC & System Fudan University Shanghai200433 China Beijing Forestry University Beijing100083 China Information Center for China State Food & Drug Administration Beijing100053 China

ISBN: (纸本)9783319948447

Food sampling programs are implemented from time to time in local areas or throughout the country in order to guarantee food safety and to improve food quality. the hidden patterns in the accumulated huge amount of data and their potential values are worthy to research. In this paper, Extreme learning machine (ELM) is employed on real data sets collected from the food safety inspections of China in recent two years, in order to mine the relationship between food quality and food category, manufacturing site and season, inspection site and season, and many other attributes. Experimental results indicate that the ELM approach has better prediction precision and generalization ability than Logistic regression that was adopted in preceding work. the patterns obtained are helpful for making more effective food sampling plans and for more targeted food safety tracing. © IFIP international Federation for Information Processing 2018.

关键词： Big data

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：