检索结果-内蒙古大学图书馆

International Conference on Neural Information Processing

作者： I. Wickert F.M.G. Franca Computer Systems Engineering Program COPPE-UFRJ Rio de Janeiro Brazil

The paper presents a comparison between two unsupervised neural network models: (i) the well-known fuzzy ART, and (ii) AUTOWISARD, a new unsupervised version of the classic WISARD weightless neural network model. It is shown that AUTOWISARD is simple, fast and stable, whilst keeping compatibility with the original WISARD architecture. Experimental test results over binary patterns benchmarks have shown that, although both unsupervised learning models are remarkably simple, AUTOWISARD consistently exhibits better classification skills than fuzzy ART. It is also shown that such superiority happens thanks to AU-TOWISARD's richer internal representation of the trained patterns and the training methods employed by the algorithm, such as the learning window and partial training strategies.

关键词： Subspace constraints Neurons Fuzzy control Pattern recognition Fuzzy sets Resonance Testing Fuzzy neural networks Neural networks Stability

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of Information Technology Investment (a case study of ODOO ERP: Project Management Module Implementation in Indonesia Based Company) 10

Feasibility study of Information Technology Investment (a ca...

引用

10th International Conference on ICT for Smart Society, ICISS 2019

作者： Jingga, Fredy Kosala, Raymond Supangkat, Suhono Harso Ranti, Benny School of Information Systems Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta11480 Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9781728148809

IT Governance are one of the needs in managing Enterprise Level IT. This study shows part of the decision domain of IT Governance Help, which are IT Investment and Prioritization. The purpose of this study is to determine feasibility of implementation open source ERP system Odoo project management module that replaces current system based on operational, economic, and technical aspects. The method used are Fit/Gap Analysis and Cost Benefit model using economic impact worksheet. The analysis is done by comparing the requirement with features owned by current system and Odoo ERP system. This research resulted that Odoo ERP System is feasible in the 3 aspects, the operational feasibility Odoo reaching 72% Fit, the economic feasibility with ROI of 84%, and technical feasibility indicating the technical requirement can be fulfilled by leasing AWS server. The conclusion is the open source ERP system Odoo project management module is feasible to be applied in terms of 3 aspects that have been studied, those are operational, economic, and technical. © 2019 IEEE.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Safe adaptation in context-aware feature models 12

Safe adaptation in context-aware feature models

引用

4th International Workshop on Feature-Oriented Software Development, FOSD'12

作者： Marinho, Fabiana G. Andrade, Rossana M.C. Costa, Paulo A.S. Maia, Paulo H.M. Vidal, Vania M.P. Werner, Claudia Department of Computer Science Federal University of Ceará Fortaleza Brazil Group of Computer Network Software Engineering and Systems - GREat Federal University of Ceará Fortaleza Brazil Systems Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9781450313094

Software product lines, usually described using feature models, have proven to be a feasible solution to develop mobile and context-aware applications. These applications use con- text information to provide services and data for their users from anywhere and at any time. However, building feature models for mobile and context-aware software product lines demands advanced skills of software engineers, since it comprises system and context information. Moreover, to guarantee a correct application execution, these models must be thoroughly specified, composed and verified to check whether some composition and adaptation rules are violated. Although this is an important task, there is a lack of formalization of such rules, which makes it difficult to use those rules for feature models verification. In this paper, we propose an approach to prevent defects in context-aware feature models and in their product reconfiguration based on formal methods. To validate our work, we developed a prototype to check the correctness of context-aware feature models. Copyright 2012 ACM.

关键词： Formal methods

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Logic as energy: A SAT-based approach

Logic as energy: A SAT-based approach

引用

2nd International Symposium on Brain, Vision, and Artificial Intelligence, BVAI 2007

作者： Lima, Priscila M. V. Morveli-Espinoza, M. Mariela M. França, Felipe M. G. LAM - Computer Architecture and Microelectronics Laboratory Universidade Federal Do Rio de Janeiro Brazil Departament d'Informàtica Universitat Autònoma de Barcelona Spain COPPE - Systems Engineering and Computer Science Program Universidade Federal Do Rio de Janeiro Brazil

ISBN: (纸本)3540755543

This paper presents the implementation of ARQ-PROP II, a limited-depth propositional reasoner, via the compilation of its specification into an exact formulation using the satyrus platform. satyrus' compiler takes as input the definition of a problem as a set of pseudo-Boolean constraints and produces, as output, the Energy function of a higher-order artificial neural network. This way, satisfiability of a formula can be associated to global optima. In the case of ARQ-PROP II, global optima is associated to Resolution-based refutation, in such a way that allows for simplified abduction and prediction to be unified with deduction. Besides experimental results on deduction with ARQ-PROP II, this work also corrects the mapping of satisfiability into Energy minima originally proposed by Gadi Pinkas. © 2007 Springer-Verlag Berlin Heidelberg.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

EvolTrack: Improving design evolution awareness in software development

引用

Journal of the Brazilian computer Society 2010年第2期16卷 117-131页

作者： de Cepêda, Rafael da Silva Viterbo Magdaleno, Andréa Magalhães Murta, Leonardo Gresta Paulino Werner, Cláudia Maria Lima COPPE/UFRJ-Systems Engineering and Computer Science Department Zip 21945-970 P.O. Box 68511 Rio de Janeiro RJ Brazil IC/UFF-Instituto de Computação Universidade Federal Fluminense Niterói RJ Brazil

Software differs from most manufactured products because it is intangible. This characteristic makes it difficult to detect, control, and understand how it evolves. This paper presents an approach based on software visualization that can detect and externalize design evolution made in a software project during its initial development or at any further phase. By using this approach, a developer can be aware of the current state of the software as a whole and can additionally verify if the current design, also called emerging design, is evolving according to the team expectations and leader guidance, preventing problems caused by misunderstandings of the expected software solution. The approach was evaluated with free/open source software (FOSS) projects. The results indicate that the approach behaves as expected when applied to real software development projects, with minor performance bottlenecks. © 2010 The Brazilian computer Society.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Sparse KPCA for feature extraction in speech recognition

Sparse KPCA for feature extraction in speech recognition

引用

2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05

作者： Lima, A. Zen, H. Nankaku, Y. Tokuda, K. Kitamura, T. Resende, F.G. Nagoya Institute of Technology Department of Computer Science and Engineering Nagoya 466-8555 Japan Federal University of Rio de Janeiro Dept. of Electronics and Computer Engineering/EPoli Program of Electrical Engineering/COPPE Rio de Janeiro 21945-970 Brazil

ISBN: (纸本)0780388747

This paper presents an analysis of the applicability of Sparse Kernel Principal Component Analysis (SKPCA) for feature extraction in speech recognition, as well as, a proposed approach to make the SKPCA technique realizable for a large amount of training data, which is an usual context in speech recognition systems. Although the KPCA (Kernel Principal Component Analysis) has proved to be an efficient technique for being applied to speech recognition, it has the disadvantage of requiring training data reduction, when its amount is excessively large. The standard approach to perform this data reduction is to randomly choose frames from the original data set, which does not necessarily provide a good statistical representation of the original data set. In order to solve this problem a likelihood related re-estimation procedure was applied to the KPCA framework, thus creating the SKPCA. The experimental results show the efficiency of SKPCA technique with the proposed approach over the KPCA with the standard sparse solution using randomly chosen frames and the standard feature extraction techniques. © 2005 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Canonically Correlated Autoencoder-Enabled Prediction Model for Customer Churn Prediction

引用

computers, Materials & Continua 2022年第11期73卷 3757-3769页

作者： Olfat M.Mirza GJose Moses R.Rajender E.Laxmi Lydia Seifedine Kadry Cheadchai Me-Ead Orawit Thinnukool Department of Computer Science College of Computers and Information SystemsUmm Al-Qura UniversityMakkahSaudi Arabia Department of Computer Science Engineering Malla Reddy Engineering College500100India Department of Computer Science Engineering Lendi Institute of Engineering&TechnologyDenkada535005India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeNorway Program in Statistics and Information Management Faculty of ScienceMaejo UniversityChiang Mai50290Thailand Department of Modern Management and Information Technology College of Arts Media and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Presently,customer retention is essential for reducing customer churn in telecommunication *** churn prediction(CCP)is important to predict the possibility of customer retention in the quality of *** risks of customer churn also get essential,the rise of machine learning(ML)models can be employed to investigate the characteristics of customer ***,deep learning(DL)models help in prediction of the customer behavior based characteristic *** the DL models necessitate hyperparameter modelling and effort,the process is difficult for research communities and business *** this view,this study designs an optimal deep canonically correlated autoencoder based prediction(ODCCAEP)model for competitive customer dependent application *** addition,the O-DCCAEP method purposes for determining the churning nature of the *** O-DCCAEP technique encompasses preprocessing,classification,and hyperparameter ***,the DCCAE model is employed to classify the churners or ***,the hyperparameter optimization of the DCCAE technique occurs utilizing the deer hunting optimization algorithm(DHOA).The experimental evaluation of the O-DCCAEP technique is carried out against an own dataset and the outcomes highlighted the betterment of the presented O-DCCAEP approach on existing approaches.

关键词： Churn prediction customer retention deep learning machine learning archimedes optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Efficient categorization of memory sharing patterns in software DSM systems 15

Efficient categorization of memory sharing patterns in softw...

引用

15th International Parallel and Distributed Processing Symposium, IPDPS 2001

作者： De Castro, M.C.S. De Amorim, C.L. Computer Science Department Federal University of Juiz de Fora Minas Gerais Brazil COPPE - Systems Engineering Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)0769509908

This work introduces a new technique that enables SDSMs to categorize dynamically and accurately memory sharing patterns in both classes of regular and irregular applications. The categorization is carried out automatically at run-time on a per-page basis, requiring no user or compiler assistance. We evaluate the potential benefits of our technique using execution-driven simulations of 8 applications running on TrendMarks on a network of 8 workstations. Surprisingly, we found that producer-consumer(s) and migratory are the dominant patterns even in irregular applications. Preliminary results suggest that the categorization technique we propose is a promising option to further improve the performance of current adaptive SDSM systems. © 2001 IEEE.

关键词： adaptive software DSM systems latency-hiding techniques memory sharing patterns

来源：评论

学校读者我要写书评

暂无评论

Context-based process line

Context-based process line

引用

作者： Nunes, Vanessa Werner, Claudia Santoro, Flavia Maria COPPE/UFRJ Systems Engineering and Computer Science Program P.O. Box 68511 Rio de Janeiro RJ Brazil NP2Tec and Postgraduate Information Systems Program UNIRIO Av. Pasteur 458 Urca - Rio de Janeiro RJ Brazil

ISBN: (纸本)9789898425065

Complexity and dynamism of day-to-day activities in organizations are inextricably linked, one impacting the other, increasing the challenges for constant adaptation of the way to organize work to address emerging demands. In this scenario, there are a variety of information, insight and reasoning being processed between people and systems, during process execution. We argue that process variations could be decided in real time, using context information collected. This paper presents a proposal for a business process line cycle, with a set of activities encapsulated in the form of components as central artefact. We explain how composition and adaptation of work may occur in real time and discuss a scenario for this proposal.

关键词： Enterprise resource management

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：