检索结果-内蒙古大学图书馆

IEEE/ACS International Conference on Computer systems and Applications

作者： Ilyes Rebai Yassine BenAyed Walid Mahdi MIRACL: Multimedia InfoRmation System and Advanced Computing Laboratory Sfax Tunisia College of Computers and Information Technology Taif University Taif Saudi Arabia

State-of-the-art language identification (LID) systems are based on an iVector feature extractor front-end followed by a multi-class recognition back-end. Identification accuracy degrades considerably when LID systems face open-set languages. As compared to in-set identification task, the open-set task is adequate to mimic the real challenge of language identification. In this paper, we propose an approach to the problem of out-of-set (OOS) data detection in the context of open-set language identification with zero-knowledge for OOS languages. The main feature of this study is the emphasis on the in-set (target) language identification, on the one hand, and on OOS language detection, on the other hand. Accordingly, we propose a deep SVM based LID back-end system to improve the target languages identification. Along with that, we define three OOS thresholding formulations. These formulations are used to decide whether the speech segment is a target or OOS language. The experimental results demonstrate the effectiveness of the deep SVM back-end system as compared to state-of-the-art techniques. Besides that, the thresholding functions perfectly detect and reject the OOS data. A relative decrease of 6% in Equal Error Rate (EER) is reported over classical OOS detection methods, in discriminating target and OOS languages.

关键词： Support vector machines Kernel Speech Task analysis NIST Data models Training

来源：评论

学校读者我要写书评

暂无评论

Business Adaptation for BPaaS Using Fuzzy Logic systems

Business Adaptation for BPaaS Using Fuzzy Logic Systems

引用

ACS/IEEE International Conference on Computer systems and Applications

作者： Rima Grati Khouloud Boukadi Hanene Ben-Abdallah Mir@cl - Multimedia InfoRmation systems and Advanced Computing Laboratory Sfax Tunisia Faculty of Computing and Information Technology King Abdulaziz University Jeddah KSA

A cloud service is usually classified as Infrastructure as a Service, Platform as a Service or Software as a Service. This classification is not sufficient, when Business Processes are considered. Therefore, the next level of abstraction above SaaS is Business Process as a Service (BPaaS) [1]. BPaaS runs in a dynamic and volatile environment such as cloud computing and has hence very changing QoS (Quality of Service) parameters. Therefore, the BPaaS monitoring and adaptation are of a great importance to guarantee the QoS parameters defined in the Service Level Agreement (SLA). To address these issues, in this paper we proposed two Fuzzy systems for self-adaptive BPaaS that aim to prevent the SLA violations. The proposed approach objective is to satisfy two important issues: (i) the selection of service adaptation strategies and (ii) the cost as well as the impact of changes. We also presented the results of the experiments achieved to evaluate the proposed approach. These experimental results prove the effectiveness of the fuzzy systems.

关键词： Quality of service Fuzzy systems Time factors Context Fuzzy logic Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Sentiment lexicon enrichment using emotional vector representation

Sentiment lexicon enrichment using emotional vector represen...

引用

IEEE/ACS International Conference on Computer systems and Applications

作者： Hanen Ameur Salma Jamoussi Abdelmajid Ben Hamadou Technopole of Sfax Sfax Tunisia Multimedia InfoRmation systems and Advanced Computing Laboratory MIRACL-Sfax University Sfax Tunisia Multimedia Inf. Syst. & Adv. Comput. Lab. Universite de Sfax Sfax TN

With the explosive growth of social media sites, an enormous amount of opinionated data has become numerically documented online. The explosion of this kind of data gives rise of new areas: sentiment analysis and opinion mining. Our purpose in this paper is to determine the polarity of Facebook comments "positive or negative" using machine learning-based approach. This approach requires an adequate vector representation of linguistic units (words or sentences) to obtain better classification performance. For this reason, we present a new emotional vector representation of words which can faithfully translate their semantic and sentimental characteristics, based on emotion symbols. Furthermore, we propose an enrichment step that aims to enlarge the lexicon and dynamically update word representation according to new contexts. Finally, by using these word representations, we present the comments in the same feature space to classify them and predict their polarity. We use Support Vector Machines to show that our emotional vector representation of lexicon's word and its enrichment significantly improves accuracy for sentiment analysis problem compared with the well-known bag-of-words vector representations, using dataset derived from Facebook. Our results are also consistent and effective.

关键词： Sentiment analysis Semantics Support vector machines Facebook Task analysis Electronic mail

来源：评论

学校读者我要写书评

暂无评论

MOT Knowledge Model Integration Rules for Knowledge Warehousing

引用

Procedia Computer Science 2017年 112卷 544-553页

作者： Rim Ayadi Yasser Hachaichi Jamel Feki Multimedia InfoRmation Systems and Advanced Computing Laboratory University of Sfax Sfax Tunisia Department of Computer Science and Quantitative Methods Higher Institute of Business Administration of Sfax Faculty of Computing and IT University of Jeddah Jeddah Saudi Arabia

A knowledge warehousing process aims to build an intelligent decision support system. It collects, homogenizes, integrates and stores knowledge for a decision-making process. In this paper, we are interested in knowledge integration. More accurately, we propose an integration process for knowledge homogenized/modeled according to the MOT (Modeling with Object Types) knowledge model. This integration process consists of three ordered steps based on the type of schemas to integrate and their similarity. For this process, we define five integration rules based on semantic relationships between elements of MOT knowledge models, and then we develop an algorithm using these integration rules.

关键词： Knowledge warehouse Knowledge integration MOT Knowledge Semantic relationships Integration rules

来源：评论

学校读者我要写书评

暂无评论

Adapted pruning scheme for the framework of imbalanced data-sets

引用

Procedia Computer Science 2017年 112卷 1542-1553页

作者： Ikram CHAABANE Radhouane GUERMAZI Mohamed HAMMAMI Multimedia InfoRmation systems and Advanced Computing Laboratory Sfax University Tunis road Km 10 3021 Sfax Tunisia Saudi Electronic University Abu Bakr Street PO Box: 93499 11673 Riyad Kingdom of Saudi Arabia

Learning from imbalanced data is attracting an increasing interest by the machine learning community. This is mainly due to the high number of real applications that are affected by this situation. The adaptation of the standard decision trees to deal with imbalanced data represents one of the important number of approaches that have been developed to address this problem. This adaptation has been proposed under three different perspectives: splitting criterion, assignment rule and pruning. In this paper, we focus our attention to the pruning of decision trees. We propose an adaptation of the standard pruning algorithm MCCP to address the skewed-data problem. Our contribution affects two levels: adaption of the metric used in selecting nodes to be firstly pruned and change of the evaluation measure used in selecting the best decision-tree through the pruning set. Our goal is to show that, contrary to the popular belief in the literature enquiring into the uselessness of decision tree pruning, an adaptive pruning technique for imbalanced situations is more efficient and more accurate towards the minority class. A total of twelve binary class data-sets having different imbalance ratio are used to test the performance of the proposed method. Experimental results show that the proposed post-pruning approach can increase the performance of imbalanced decision trees in terms of evaluation measures that are recent and appropriate for the context of imbalanced classification.

关键词： imbalanced class decision-tree pruning skewed data-sets IBA B42

来源：评论

学校读者我要写书评

暂无评论

Design for a context-aware and collaborative mobile learning system

Design for a context-aware and collaborative mobile learning...

引用

IEEE International Conference on Computational Intelligence and computing Research

作者： Sameh Baccari Mahmoud Neji Computer Science Multimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL) Sfax Tunisia

ISBN: (纸本)9781509006137

Today, mobile learning is becoming a new important learning style in our modern life. It is handy because mobile devices are used not only for communicating but also for learning in a mobile context. Mobile devices have the potential to be used as powerful m-learning tools in different learning contexts. However this poses new challenges that are associated with their ability to cope with the available learning material. Our goal in this paper is to propose a new approach for context-aware and collaborative mobile learning. It takes into account the requirements of Mobility, Context-Awareness and Collaboration. Our approach is based on semantic modeling of learning resources and learning context. This modeling is complemented by a adaptation part made up of adaptation rules to propose and select relevant resources, learning partners and learning activities based not only on the learner's needs but also on its current context of learning environment. We have implemented this approach in a Mobile learning system called CCMLS: Collaborative and Context-aware Mobile Learning System.

关键词： Context Mobile communication Learning systems Adaptation models Context modeling Sensors Unified modeling language

来源：评论

学校读者我要写书评

暂无评论

Hand pose estimation system based on Viola-Jones algorithm for Android devices

Hand pose estimation system based on Viola-Jones algorithm f...

引用

ACS/IEEE International Conference on Computer systems and Applications

作者： Houssem Lahiani Monji Kherallah Mahmoud Neji Multimedia Information Systems and Advanced Computing Laboratory (Miracl) Sfax Tunisia Faculty of Sciences (FSS) University of Sfax Tunisia

This paper focuses on hand pose estimation by proposing a system that solves real-time static hand gesture detection and recognition issues for interacting with smartphones. The first step of our work consists in detecting and tracking the hand in a complex background. The second step consists in recognizing hand gestures using SVM “Support Vector Machine”. Finally, we developed a grammar to generate gesture commands for mobile applications control. This work presents a system based on a real-time hand gesture recognition algorithm for Android devices. The idea here is to allow the user interacting with the mobile device without the need to touch the screen. In this system, the Smartphone is able to perform all necessary steps to recognize gestures without the need to connect to a distant device.

关键词： Smart phones Feature extraction Gesture recognition Image color analysis Image segmentation Androids Humanoid robots

来源：评论

学校读者我要写书评

暂无评论

A property grammar-based method to enrich the arabic treebank ATB 7

引用

7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015

作者： Bahloul, Raja Bensalem Haddar, Kais Blache, Philippe Multimedia InfoRmation Systems and Advanced Computing Laboratory Higher Institute of Computer Science and Multimedia Sfax Tunisia Laboratoire Parole et Langage CNRS Université de Provence Marseille France

ISBN: (纸本)9783319527574

We present a method based on the formalism of Property Grammars to enrich the Arabic treebank ATB with syntactic constraints (so-called properties). The Property Grammar formalism is an effectively constraint-based approach that directly specifies the constraints on information categories. This can facilitate the enrichment process. The latter is based on three phases: the problem formalization, the Property Grammar induction from the ATB and the treebank regeneration with a new syntactic property-based representation. The enrichment of the ATB can make it more useful for many NLP applications such as the ambiguity resolution. This allows also the acquisition of new linguistic resources and the ease of the probabilistic parsing process. This enrichment process is purely automatic and independent from any language and source corpus formalism. This motivates its reuse. We obtained good and encouraging experiment results and various properties of different types. © Springer International Publishing AG 2016.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Semi-hierarchical naive Bayes classifier

Semi-hierarchical naive Bayes classifier

引用

International Joint Conference on Neural Networks

作者： Hasna Njah Salma Jamoussi Walid Mahdi Multimedia InfoRmation system and Advanced Computing Laboratory (MIRACL) University of Sfax College of Computers and Information Technology Taif University

ISBN: (纸本)9781509006212

The classification of high dimensional data is an arduous task especially with the emergence of high quality data acquisition techniques. This problem is accentuated when the whole set of features is needed to learn a classifier such as the case of genomic data. The Bayesian approach is suitable for these applications because it represents graphically and statistically the dependencies between the features. Unfortunately, learning a Bayesian classifier using a high number of features does not ensure a tradeoff between the dimensions' reduction, the semantic of the model and the predictive performance. We propose a new semi-hierarchical naive Bayes that uses the latent variables for abstracting the features of a given dataset in order to reduce the dimensionality. These variables are suitable for finding graphically and semantically analyzable models. We combined them with the observed variables in a tree-augmented naive Bayes structure in order to improve the prediction accuracy. An excessive experimental study showed that our method is suitable for high dimensional data and overcomes the existing methods.

关键词： Bayesian classifier Latent variable High dimensional data Bayesian classifier dimensional data graphically Bayes tradeoffs

来源：评论

学校读者我要写书评

暂无评论

Abstracts generation as information retrieval results

Abstracts generation as information retrieval results

引用

ACS/IEEE International Conference on Computer systems and Applications

作者： Mounira Chkiwa Anis Jedidi Faiez Gargouri Multimedia InfoRmation systems and Advanced Computing Laboratory Sfax University Tunisia

In this paper, we present a new variant to show results of information retrieval process. Search results proposed here are in the form of textual abstract instead of returning a list of links pointing to relevant web documents. Our current work materializes collaboration between two independent axes: Semantic Web and Fuzzy Logic. The automatic abstract generation represents an extension of our previous works aimed to create an information retrieval system dedicated for kids.

关键词： Semantics Ontologies information retrieval Fuzzy logic Fuzzy sets OWL

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：