检索结果-内蒙古大学图书馆

A theory of developmental mental architecture and the dav architecture design

International Journal of Humanoid Robotics 2005年第2期2卷 145-179页

作者： WENG, JUYANG ZENG, SHUQING Embodied Intelligence Laboratory Department of Computer Science and Engineering Michigan State University East LansingMI48824 United States

The software architecture of a developmental robot is a challenging new research subject. This paper presents a theory of developmental mental architecture. Five architecture types, from the simplest Type-1 (observation-driven Markov decision process) to Type-5 (DOSASE MDP), are introduced. The properties and limitations of a simpler one are discussed before the introduction of the next more complex one. Further, we present the architecture design of the Dav robot, a humanoid robot built in the Embodied Intelligence laboratory at Michigan State University. The framework of the Dav architecture is hand-designed, but the actual controller is developed, i.e. generated autonomously by the developmental program through real-time, online interactions with the real physical environment. We present the Dav architecture and the major components that realize the architecture. The designed architecture for Dav is the next generation version from its extensively tested predecessor, the SAIL developmental robot. Closely related to the issue of performance metrics, the paper also introduces the notion of intelligence completeness (concept completeness, intelligence-metric completeness, and factor completeness) and establishes the concept of the completeness theorem for developmental robotics. © 2005 World Scientific Publishing Company

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5026-5039页

作者： Li, Mengke Cheung, Yiu-Ming Lu, Yang Hu, Zhikai Lan, Weichao Huang, Hui Shenzhen518132 China Hong Kong Baptist University Department of Computer Science 999077 Hong Kong Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen361005 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This article therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. © 2020 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Case Study of Massive API Scrapping: Parler Data Breach After the Capitol Riot 7

A Case Study of Massive API Scrapping: Parler Data Breach Af...

引用

7th International Conference on Smart and Sustainable Technologies, SpliTech 2022

作者： Redding, David Ang, Jian Bhunia, Suman Miami University Department of Computer Science and Software Engineering OxfordOH45056 United States

ISBN: (纸本)9789532901160

After the United States Capitol Hill Riots, there was a massive API scraping of Parler, an open social media platform, which resulted in 70 terabytes of user data being collected. The data breach, a serious confidential personal data leak, was not performed illegally. This paper analyzes the data breach and its impact in depth. The breach was a result of a hacktivist going with the alias @donk_enby, performing a massive API scraping of Parler's servers. The scraping took metadata from user's public, private, and previously deleted posts, uploaded to Parler's servers. Parler had failed to clear the metadata of these posts. The metadata contained names, dates, locations, and other data about the users who posted content to Parler's site. Over 70,000 GPS locations of Parler's users have been uncovered including users' private properties. These locations have also been used to tie citizens to the Capitol Riots if they uploaded any content about the riot from that day. Forms containing government identification of users were also leaked from Parler's servers that were used for account verification. This paper demonstrate background on the events leading up to, including, and following the Capitol Riots. The paper also examine the hacktivist's methodology for performing the API scraping and discuss possible defensive strategies such as API rate limiting, API request sanitation, and API call authorization. © 2022 University of Split, FESB.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

An Evaluation System for Large Language Models based on Open-Ended Questions 11

An Evaluation System for Large Language Models based on Open...

引用

11th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2024

作者： Cao, Zhiyuan Ma, Zeyu Chen, Mingang Computer and Information Engineering College Shanghai Polytechnic University Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer software Technology Mathematical and Science College Shanghai Normal University Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer software Technology Shanghai China

ISBN: (纸本)9798350376982

We designed a large language model evaluation system based on open-ended questions. The system accomplished multidimensional evaluation of LLMs using open-ended questions, and it presented evaluation results with evaluation reports. Currently, the evaluation of large-scale language models often exists with two prominent limitations: (1) The evaluation methods are often single-minded, resulting in less credible results. (2) Most evaluations are based on datasets with closed-ended questions, treating generative large language models as discriminative models, which fails to adequately reflect the high output flexibility characteristic of these models. For these two limitations, we proposed an evaluation system for LLMs based on open-ended questions. Our experiments on the adapted open-source datasets demonstrated the effectiveness of this system. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Metadata challenges for situational properties of learning objects

Metadata challenges for situational properties of learning o...

引用

6th International Conference on Advanced Learning Technologies, ICALT 2006

作者： Hughes, Baden Farmer, Roderick A. Department of Computer Science and Software Engineering University of Melbourne Parkville Vic. 3010 Australia

ISBN: (纸本)0769526322

The abstraction of free-standing metadata describing learning objects is typified by an analytical model which primarily focuses on the encoding of discrete properties pertaining to the learning object itself. This process often neglects the contextual properties derived from the situations in which the learning object can be used optimally. We report the derivation of situated properties for learning objects through the use of the CASE framework and explore how these properties are best encoded. © 2006 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

1/f^β noise-based real-time animation of trees swaying in wind fields

1/f<SUP>β</SUP> noise-based real-time animation of trees sw...

引用

computer Graphics International Conference (CGI 2003)

作者： Ota, S Fujimoto, T Tamura, M Muraoka, K Fujita, K Chiba, N Iwate Software Center Japan Computer Science Department Faculty of Engineering Iwate University Japan Department of Communications Engineering Tohoku Institute of Technology Japan

ISBN: (纸本)0769519466

Trees are one of the most important elements of natural landscapes. Therefore, in computer graphics, there is a great demand for methods to realize the natural representation of trees in virtual landscapes in various fields such as entertainment industry or environmental assessment in construction. Many studies have been made on techniques in which the shapes of trees are modeled but only a few studies have been reported on methods to incorporate the shapes with motions in a wind field. Most of these studies use physical simulation techniques based on the equations of motion to generate the branch motions and cannot realize the motions of individual leaves. In this paper, we propose a method to create the natural motions of individual leaves and branches swaying in a wind field. This method generates the leaf and branch motions based on "1/f(beta) noise", which is observed in various natural phenomena. For the branch motion, a simple simulation method based on the spring model is applied to enhance the realism of the motion. This method enables the real-time creation of the leaf and branch motions. Diverse motions according to tree species and shapes and wind conditions can be easily realized by controlling the parameters.

关键词： tree leaf motion wind 1/f(beta) noise real-time animation

来源：评论

学校读者我要写书评

暂无评论

MICROFABRICATED ELECTROHYDRODYNAMIC PUMPS

引用

SENSORS AND ACTUATORS A-PHYSICAL 1990年第1-3期21卷 193-197页

作者： BART, SF TAVROW, LS MEHREGANY, M LANG, JH Laboratory for Electromagnetic and Electronic Systems Microsystems Technology Laboratory Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

Pumping is often cited as a general application which motivates the development of microfabricated motors and other actuators. In that spirit, this paper studies microfabricated electrohydrodynamic fluid pumps. In electrohydrodynamic (EHD) pumping, fluid forces are generated by the interaction of electric fields and charges in the fluid. In contrast to forces generated by mechanical pumping using an impeller or bellows, EHD pumping requires no moving parts and consequently offers the possibility of simplified fabrication and high reliability. This paper discusses electrohydrodynamic pumping and issues concerning its use in micronsize scale systems. The fundamental operating principles of the EHD pump are outlined and examples of configurations which meet the requirement for inducing free electric charge are shown. The possible performance achievable in micron size-scale regimes is indicated. Issues concerning fluid conductivity, instability and surface tension are addressed. A microfabricated structure which demonstrates the EHD pumping of a highly insulating silicone oil is described. The structure consists of an array of 10 μm by 235 μm highly doped, LPCVD polycrystalline silicon electrodes patterned over silicon nitride. The electrode array is excited with a traveling wave of electric potential. Pumping results are qualitatively described. This paper describes a study of electrohydrodynamic pumping, including issues concerning its application to micron size-scale systems. The fundamental operating principles of EHD pumps are outlined and the possible performance achievable in micron size-scale regimes is indicated. Surface and bulk instabilities are addressed. Finally, the preliminary results of an EHD pumping experiment with a microfabricated structure are described. A practical requirement for EHD pumping is the induction of free electric charge in the volume of the fluid to be pumped or on its interface with another material. Charge accumulation on a material

关键词： Pumps

来源：评论

学校读者我要写书评

暂无评论

Exploiting multivariate LSTM models with multistep price forecasting for agricultural produce in Sri Lankan context 2

Exploiting multivariate LSTM models with multistep price for...

引用

2nd International Conference on Advancements in Computing, ICAC 2020

作者： Navaratnalingam, Shriram Kodagoda, Nuwan Suriyawansa, Kushnara Srilanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781728184128

In Sri Lanka agricultural produces possess a large supply which involves various stakeholders and thus, fluctuation of the agricultural produce prices has a direct impact on the purchasing decisions of the consumer. So, the main purpose of this study is to address the problem faced by the consumer due to poor awareness of price fluctuation which consequently astonish the consumers and hinder them from making better purchasing decisions. The research study is being specially developed in a way to adapt the Sri Lankan agricultural consumer market that is mainly based on Pettah and Dambulla trade centers. As the study we exploited different types of LSTM model with multivariate inputs along with the different combination of multistep models. The result of the study reveals that better performance was obtained for the multivariate CNN LSTM model with encoder decoder multistep model which provided an average RMSE of 19.46 Sri Lankan rupees per kilogram with an average RMSPE of 14.9%. Also, study reveals a correlation between price fluctuation and standard days of the week, where a better prediction was obtained for Monday and Tuesday with an average RMSE of 17.2 and 17.7 Sri Lankan rupees per kilogram respectively with an average RMSPE of 12.2%. Based on the input timestep considered for model, though 14 days and 21 days provided a similar result with minor variation result reveals that 14 days provided a lesser standard deviation of 0.17 than 21 days standard deviation which is 0.98. © 2020 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Neural feature extraction for contextual emotion detection 12

Neural feature extraction for contextual emotion detection

引用

12th International Conference on Recent Advances in Natural Language Processing, RANLP 2019

作者： Mohammadi, Elham Amini, Hessam Kosseim, Leila Lab Department of Computer Science and Software Engineering Concordia University Montréal QC Canada

ISBN: (纸本)9789544520557

This paper describes a new approach for the task of contextual emotion detection. The approach is based on a neural feature extractor, composed of a recurrent neural network with an attention mechanism, followed by a classifier, that can be neural or SVM-based. We evaluated the model with the dataset of the task 3 of SemEval 2019 (EmoContext), which includes short 3-turn conversations, tagged with 4 emotion classes. The best performing setup was achieved using ELMo word embeddings and POS tags as input, bidirectional GRU as hidden units, and an SVM as the final classifier. This configuration reached 69.93% in terms of micro-average F1 score on the main 3 emotion classes, a score that outperformed the baseline system by 11.25%. © 2019 Association for Computational Linguistics (ACL). All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Bitmap Index Compression Algorithms for Big Data

引用

Tsinghua science and Technology 2015年第1期20卷 100-115页

作者： Zhen Chen Yuhao Wen Junwei Cao Wenxun Zheng Jiahui Chang Yinjun Wu Ge Ma Mourad Hakmaoui Guodong Peng the Research Institute of Information Technology Tsinghua University Tsinghua National Laboratory for Information Science and Technology (TNList) Tsinghua University Department of Electronic Engineering Tsinghua University Department of Physics Tsinghua University Department of Aerospace Engineering Tsinghua University Department of Automation Tsinghua University Department of Computer Science and Technology Tsinghua University Department of Mechanical Engineering Tsinghua University

With the growing popularity of Internet applications and the widespread use of mobile Internet, Internet traffic has maintained rapid growth over the past two decades. Internet Traffic Archival Systems（ITAS） for packets or flow records have become more and more widely used in network monitoring, network troubleshooting, and user behavior and experience analysis. Among the three key technologies in ITAS, we focus on bitmap index compression algorithm and give a detailed survey in this paper. The current state-of-the-art bitmap index encoding schemes include： BBC, WAH, PLWAH, EWAH, PWAH, CONCISE, COMPAX, VLC, DF-WAH, and VAL-WAH. Based on differences in segmentation, chunking, merge compress, and Near Identical（NI） features, we provide a thorough categorization of the state-of-the-art bitmap index compression algorithms. We also propose some new bitmap index encoding algorithms, such as SECOMPAX, ICX, MASC, and PLWAH＋, and present the state diagrams for their encoding algorithms. We then evaluate their CPU and GPU implementations with a real Internet trace from CAIDA. Finally, we summarize and discuss the future direction of bitmap index compression algorithms. Beyond the application in network security and network forensic, bitmap index compression with faster bitwise-logical operations and reduced search space is widely used in analysis in genome data, geographical information system, graph databases, image retrieval, Internet of things, etc. It is expected that bitmap index compression will thrive and be prosperous again in Big Data era since 1980s.

关键词： Internet traffic big data traffic archival network security bitmap index bitmap compression algorithm

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：