检索结果-内蒙古大学图书馆

作者： Nikhil Lahoti San Jose State University

学位级别：硕士

Convolutional Neural Network (CNN) has been used widely for the tasks of object recognition and facial recognition because of their remarkable results on these common visual tasks. In order to evaluate the performance of CNN for embedded devices effectively, it is essential to provide a comprehensive benchmark evaluation environment. Even though there are many benchmark suites available for use, but these benchmark suites require installation of various packages and proprietary libraries. This creates a bottleneck in using them in applications which are executed on resource constraint devices like embedded devices. In this paper, we propose an evaluation platform which can be used for evaluation on any platform that supports Cuda and OpenCL. This evaluation platform was executed on Nvidia TX2 Jetson board embedded device and commodity hardware without needing any extra proprietary libraries to execute the model. We also achieved 4.5-fold gain in execution speed of the Cuda and OpenCL model. The model also exactly predicts images as the Python based with 100% accuracy. We also provide in-depth statistics about the CNN network execution pattern by executing the model on embedded devices and commodity hardware.

关键词： CNN Benchmark Suite Embedded devices Cuda OpenCL Deep Neural Network artificial intelligence and robotics Other Computer Sciences

来源：评论

学校读者我要写书评

暂无评论

Optimizing E-Commerce Product Classification Using Transfer Learning

Optimizing E-Commerce Product Classification Using Transfer ...

引用

作者： Rashmeet Kaur Khanuja San Jose State University

学位级别：硕士

The global e-commerce market is snowballing at a rate of 23% per year. In 2017, retail e-commerce users were 1.66 billion and sales worldwide amounted to 2.3 trillion US dollars, and e-retail revenues are projected to grow to 4.88 trillion USD in 2021. With the immense popularity that e-commerce has gained over past few years comes the responsibility to deliver relevant results to provide rich user experience. In order to do this, it is essential that the products on the ecommerce website be organized correctly into their respective categories. Misclassification of products leads to irrelevant results for users which not just reflects badly on the website, it could also lead to lost customers. With ecommerce sites nowadays providing their portal as a platform for third party merchants to sell their products as well, maintaining a consistency in product categorization becomes difficult. Therefore, automating this process could be of great utilization. This task of automation done on the basis of text could lead to discrepancies since the website itself, its various merchants, and users, all could use different terminologies for a product and its category. Thus, using images becomes a plausible solution for this problem. Dealing with images can best be done using deep learning in the form of convolutional neural networks. This is a computationally expensive task, and in order to keep the accuracy of a traditional convolutional neural network while reducing the hours it takes for the model to train, this project aims at using a technique called transfer learning. Transfer learning refers to sharing the knowledge gained from one task for another where new model does not need to be trained from scratch in order to reduce the time it takes for training. This project aims at using various product images belonging to five categories from an ecommerce platform and developing an algorithm that can accurately classify products in their respective categories while taking as les

关键词： convolutional neural networks deep learning dropout e-commerce product categorization keras transfer learning artificial intelligence and robotics

来源：评论

学校读者我要写书评

暂无评论

Image Retrieval Using Image Captioning

Image Retrieval Using Image Captioning

引用

作者： Nivetha Vijayaraju San Jose State University

学位级别：硕士

The rapid growth in the availability of the Internet and smartphones have resulted in the increase in usage of social media in recent years. This increased usage has thereby resulted in the exponential growth of digital images which are available. Therefore, image retrieval systems play a major role in fetching images relevant to the query provided by the users. These systems should also be able to handle the massive growth of data and take advantage of the emerging technologies, like deep learning and image captioning. This report aims at understanding the purpose of image retrieval and various research held in image retrieval in the past. This report will also analyze various gaps in the past research and it will state the role of image captioning in these systems. Additionally, this report proposes a new methodology using image captioning to retrieve images and presents the results of this method, along with comparing the results with past research.

关键词： Image retrieval deep learning image captioning artificial intelligence and robotics Databases and Information Systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Monitoring Cyber-Physical Systems

Deep Learning for Monitoring Cyber-Physical Systems

引用

作者： Gangopadhyay, Tryambak Iowa State University

学位级别：M.S.

Different cyber-physical systems involving sequential data require accurate frameworks for predicting the state of the system leading to effective monitoring. If the framework is explanatory, the insights provided by the explanations can improve scientific understanding of the system. Detecting the transition to an impending instability is important to initiate effective control in a combustion system. Building robust frameworks is important in this context. As one of the early applications of characterizing instability in a combustion system using Deep Neural Networks, we train our proposed deep convolutional neural network (CNN) model on sequential image frames extracted from hi-speed flame videos by inducing instability in the system following a particular protocol- varying the acoustic length. We leverage the sound pressure data to define a non-dimensional instability measure used for applying an inexpensive but noisy labeling technique for training. We attempt to detect the onset of instability in a transient dataset where instability is induced by a different protocol. With the continuous variation of the control parameter, we can successfully detect the critical transition to a state of high combustion instability demonstrating the robustness of our proposed detection framework, which is independent of the combustion inducing protocol. We propose another model which considers the temporal correlations. The model can explain the contribution of each image in the input sequence for generating a single prediction label without compromising on the accuracy. After encoding the images of the input sequence using 2D convolutional neural network and long short term memory recurrent neural network, we capture the global temporal structure by using a temporal attention mechanism. The attention weights highlight the significant image frames that are most relevant for each prediction. We demonstrate the performance of our models in a problem where explainability and robu

关键词： artificial intelligence and robotics Mechanical Engineering

来源：评论

学校读者我要写书评

暂无评论

Integration of Robotic Perception, Action, and Memory

Integration of Robotic Perception, Action, and Memory

引用

作者： Li Yang Ku University of Massachusetts Amherst

学位级别：博士

In the book "On intelligence", Hawkins states that intelligence should be measured by the capacity to memorize and predict patterns. I further suggest that the ability to predict action consequences based on perception and memory is essential for robots to demonstrate intelligent behaviors in unstructured environments. However, traditional approaches generally represent action and perception separately---as computer vision modules that recognize objects and as planners that execute actions based on labels and poses. I propose here a more integrated approach where action and perception are combined in a memory model, in which a sequence of actions can be planned based on predicted action outcomes. In this framework, hierarchical visual features based on convolutional neural networks are introduced to capture the essential affordances. These features in different hierarchies are associated with robot controllers of corresponding kinematic subchains to support manipulation. Through learning from demonstration, both actions and informative features in the memory model can be learned efficiently. As more demonstrations are recorded and more interactions are observed, the robot becomes more capable of predicting the consequences of actions, thus, is better at planning sequences of actions to solve tasks under different circumstances.

关键词： artificial intelligence and robotics Cognitive Neuroscience robotics

来源：评论

学校读者我要写书评

暂无评论

ROBOCUP@HOME: Analysis and results of evolving competitions for domestic and service robots

引用

artificial intelligence 2015年 229卷 258-281页

作者： Iocchi, Luca Holz, Dirk Ruiz-del-Solar, Javier Sugiura, Komei van der Zant, Tijn Univ Roma La Sapienza Dept Comp Control & Management Engn Rome Italy Univ Bonn Autonomous Intelligent Syst Grp Bonn Germany Univ Chile Dept Elect Engn Santiago Chile Univ Chile Adv Min Technol Ctr Santiago Chile Natl Inst Informat & Commun Technol Informat Serv Platform Lab Tokyo Japan Univ Groningen Cognit Robot Lab NL-9700 AB Groningen Netherlands

Scientific competitions are becoming more common in many research areas of artificial intelligence and robotics, since they provide a shared testbed for comparing different solutions and enable the exchange of research results: Moreover, they are interesting for general audiences and industries. Currently, many major research areas in artificial intelligence and robotics are organizing multiple-year competitions that are typically associated with scientific conferences. One important aspect of such competitions is that they are organized for many years. This introduces a temporal evolution that is interesting to analyze. However, the problem of evaluating a competition over many years remains unaddressed. We believe that this issue is critical to properly fuel changes over the years and measure the results of these decisions. Therefore, this article focuses on the analysis and the results of evolving competitions. In this article, we present the ROBOCUP@HOME competition, which is the largest worldwide competition for domestic service robots, and evaluate its progress over the past seven years. We show how the definition of a proper scoring system allows for desired functionalities to be related to tasks and how the resulting analysis fuels subsequent changes to achieve general and robust solutions implemented by the teams. Our results show not only the steadily increasing complexity of the tasks that ROBOCUP@HOME robots can solve but also the increased performance for all of the functionalities addressed in the competition. We believe that the methodology used in ROBOCUP@HOME for evaluating competition advances and for stimulating changes can be applied and extended to other robotic competitions as well as to multi-year research projects involving artificial intelligence and robotics. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Robotic competitions artificial intelligence and robotics Benchmarking

来源：评论

学校读者我要写书评

暂无评论

[email protected] : Analysis and results of evolving competitions for domestic and service robots

引用

artificial intelligence 2015年 229卷 258-281页

作者： Luca Iocchi Dirk Holz Javier Ruiz-del-Solar Komei Sugiura Tijn van der Zant Department of Computer Control and Management Engineering Sapienza University of Rome Italy Autonomous Intelligent Systems Group University of Bonn Germany Department of Electrical Engineering & Advanced Mining Technology Center Universidad de Chile Chile Information Services Platform Laboratory National Institute of Information and Communications Technology Japan Cognitive Robotics Laboratory University of Groningen The Netherlands

Scientific competitions are becoming more common in many research areas of artificial intelligence and robotics, since they provide a shared testbed for comparing different solutions and enable the exchange of research results. Moreover, they are interesting for general audiences and industries. Currently, many major research areas in artificial intelligence and robotics are organizing multiple-year competitions that are typically associated with scientific conferences. One important aspect of such competitions is that they are organized for many years. This introduces a temporal evolution that is interesting to analyze. However, the problem of evaluating a competition over many years remains unaddressed. We believe that this issue is critical to properly fuel changes over the years and measure the results of these decisions. Therefore, this article focuses on the analysis and the results of evolving competitions. In this article, we present the [email protected] competition, which is the largest worldwide competition for domestic service robots, and evaluate its progress over the past seven years. We show how the definition of a proper scoring system allows for desired functionalities to be related to tasks and how the resulting analysis fuels subsequent changes to achieve general and robust solutions implemented by the teams. Our results show not only the steadily increasing complexity of the tasks that [email protected] robots can solve but also the increased performance for all of the functionalities addressed in the competition. We believe that the methodology used in [email protected] for evaluating competition advances and for stimulating changes can be applied and extended to other robotic competitions as well as to multi-year research projects involving artificial intelligence and robotics.

关键词： Robotic competitions artificial intelligence and robotics Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Opportunistic service differentiation and Cloud resource management in support of enhanced vehicular applications

Opportunistic service differentiation and Cloud resource man...

引用

作者： Salahuddin, Mohammad Ali Western Michigan University

学位级别：Ph.D.

An integral part of Intelligent Transportation Systems (ITS) are Vehicular Ad hoc Networks (VANETs), which consist of vehicles with on-board units (OBUs) and fixed road-side units (RSUs). Wireless Access in Vehicular Environment (WAVE) offers QoS via service differentiation by using application defined priorities. However, WAVE has unbounded delay and is oblivious to network load and severity of vehicles with respect to their environment. Our context severity metric innovatively enhances WAVE to be sensitive to vehicle and environment interactions. Our novel Opportunistic Service Differentiation (OSD) technique, dynamically readjusts the WAVE packet priorities to improve utilization of lower latency queues, prioritizing packets in order of context severity. This also overcomes the unbounded delay in WAVE, which is crucial for safety applications. On the other end, our novel RSU Cloud is a unique approach to hosting non-safety services on specialized RSU micro-datacenters. Optimal provisioning of constrained resources is critical in RSU Clouds. Furthermore, inherently dynamic demands from the vehicles require replications, migrations and, or instantiations of new or existing services, on virtual machines (VMs) in the RSU Cloud. We leverage the deep programmability of Software Defined Networking (SDN) to dynamically reconfigure the RSU Cloud. However, frequent changes to service hosts and data flows not only result in degradation of services, but are also costly for service providers. In Mininet, we analyze this reconfiguration overhead, which is used to design and model optimal RSU Cloud resource management (CRM). CRM will optimally select service hosts and data forwarding rules, such that, the reconfigurations in the network are minimized with varying demands. We begin by designing the Pareto Optimal Frontier of non-dominated solutions (POF), such that, each solution is a configuration that minimizes either the number of service instances or the RSU Cloud infrastruc

关键词： Opportunistic service differentiation cloud resource management intelligent transportation systems vehicular ad hoc networks wireless access in vehicular environment RSU clouds artificial intelligence and robotics Computer Engineering OS and Networks Software Engineering

来源：评论

学校读者我要写书评

暂无评论

Genome optimization and evolution simulation using genetic algorithms and GA-TRMR

Genome optimization and evolution simulation using genetic a...

引用

作者： Mortazavi, Ponehsadat University of Colorado

学位级别：master

There are various desirable traits in organisms that humans wish to improve. To change a trait, the genetic background affecting that trait must be manipulated. In this thesis, genetic algorithms (GA) is suggested as a search strategy to efficiently sample from the combinatorial sequence space to identify the optimum genome sequence. Also, we proposed a restricted form of GA that approximates the search of a Trackable Multiplex Recombineering (TRMR) based approach, and is named GA-TRMR. The performance of GA and GA-TRMR strategies are simulated on various synthetic fitness landscapes through generations. The landscapes are constructed using fitness functions modeling for various degrees of epistasis. Both algorithms demonstrated viability for finding the optimum sequence. GA-TRMR specifically, when is equipped with a form of local sampling algorithm along with a selite set, turns into a powerful search algorithm which could find the optimum genome sequence in interaction with TRMR. Advisors/Committee Members: Aaron Clauset, Robin Deanne Dowell-Deen, Ryan T. Gill

关键词： Evolution simulation Gene network Genetic Algorithms Genome optimization Synthetic fitness landscape Trackable Multiplex Recombineering artificial intelligence and robotics Bioinformatics Computer Sciences Genetics

来源：评论

学校读者我要写书评

暂无评论

A Location-Based Incentive Mechanism for Participatory Sensing Systems with Budget Constraints

A Location-Based Incentive Mechanism for Participatory Sensi...

引用

作者： Jaimes, Luis G. University of South Florida

学位级别：M.S.C.S.

Participatory Sensing (PS) systems rely on the willingness of mobile users to participate in the collection and reporting of data using a variety of sensors either embedded or integrated in their cellular phones. Users agree to use their cellular phone resources to sense and transmit the data of interest because these data will be used to address a collective problem that otherwise would be very difficult to assess and solve. However, this new data collection paradigm has not been very successful yet mainly because of the lack of incentives for participation and privacy concerns. Without adequate incentive and privacy guaranteeing mechanisms most users will not be willing to participate. This thesis concentrates on incentive mechanisms for user participation in PS system. Although several schemes have been proposed thus far, none has used location information and imposed budget and coverage constraints, which will make the scheme more realistic and efficient. A recurrent reverse auction incentive mechanism with a greedy algorithm that selects a representative subset of the users according to their location given a fixed budget is proposed. Compared to existing mechanisms, GIA (i.e., Greedy Incentive Algorithm) improves the area covered by more than 60 percent acquiring a more representative set of samples after every round, i.e., reduces the collection of unnecessary (redundant) data, while maintaining the same number of active users in the system and spending the same budget.

关键词： Crowd-Sourced Sensing Mobile Network Coverage Pervasive Computing Reverse Auctions Ubiquitous Sensing American Studies artificial intelligence and robotics Arts and Humanities Computer Sciences

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：