检索结果-内蒙古大学图书馆

19th International Conference on Advanced Information Systems engineering, CAiSE 2007

作者： Porres, Ivan Domínguez, Eladio Pérez, Beatriz Rodríguez, Áurea Zapata, María A. Department of Computer Science Åbo Akademi University Joukahaisenkatu 3-5 B Turku FIN-20520 Finland Dpt. of Computer Science and Systems Engineering University of Zaragoza Pedro Cerbuna 12 E-50009 Zaragoza Spain

来源：评论

学校读者我要写书评

暂无评论

Annotations Time Shift: A Key Parameter in Evaluating Musical Note Onset Detection Algorithms

Annotations Time Shift: A Key Parameter in Evaluating Musica...

引用

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

作者： Mina Mounir Peter Karsmakers Toon van Waterschoot Dpt. of Electrical Engineering KU Leuven Leuven Belgium Dpt. of Computer Science KU Leuven GEEL Belgium

Musical note onset detection is a building component for several MIR related tasks. The ambiguity in the definition of a note onset and the lack of a standard way to annotate onsets, introduce differences in datasets labeling, which in turn makes evaluations of note onset detection algorithms difficult to compare. This paper gives an overview of the parameters influencing the commonly used onset detection evaluation measure, i.e. the F1-score, pointing out a consistently missing parameter which is the overall time shift in annotations. This paper shows how crucial this parameter is in making reported F1-scores comparable among different algorithms and datasets, achieving a more reliable evaluation. As several MIR applications are concerned with the relative location of onsets to each other and not their absolute location, this paper suggests to include the overall time shift as a parameter when evaluating the algorithm performance. Experiments show a strong variability in the reported F1-score and up to 50% increase in the best-case F1-score when varying the overall time shift. Optimizing the time shift turns out to be crucial when training or testing algorithms with datasets that are annotated differently (e.g. manually, automatically, and with different annotators) and especially when using deep learning algorithms.

关键词： Annotations Labeling Signal processing algorithms Music Transient analysis Multiple signal classification Training

来源：评论

学校读者我要写书评

暂无评论

MSNER: A Multilingual Speech Dataset for Named Entity Recognition

arXiv

引用

arXiv 2024年

作者： Meeus, Quentin Moens, Marie-Francine Van Hamme, Hugo LIIR Lab Computer Science Dpt. KU Leuven Belgium PSI Electrical Engineering Dpt. KU Leuven Belgium

While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing MSNER, a freely available, multilingual speech corpus annotated with named entities. It provides annotations to the VoxPopuli dataset in four languages (Dutch, French, German, and Spanish). We have also releasing an efficient annotation tool that leverages automatic pre-annotations for faster manual refinement. This results in 590 and 15 hours of silver-annotated speech for training and validation, alongside a 17-hour, manually-annotated evaluation set. We further provide an analysis comparing silver and gold annotations. Finally, we present baseline NER models to stimulate further research on this newly available dataset. © 2024, CC BY.

关键词： Silver

来源：评论

学校读者我要写书评

暂无评论

Automated Chinese Language Proficiency Scoring by utilizing Siamese Convolutional Neural Network and fusion based approach 6

Automated Chinese Language Proficiency Scoring by utilizing ...

引用

6th International Conference on engineering and Emerging Technologies, ICEET 2020

作者： Kwong, Anne Muzamal, Junaid Hussain Zhang, Patrick Yu Lin, Guimin Dpt. Research and Development Digital Galaxy Technologies Limited Honkkong Guangdong Sheng China Al-Khawarizmi Institute of Computer Science KICS University of Engineering and Technology Lahore Lahore Pakistan

ISBN: (纸本)9781728145792

The previous approaches have failed to effectually score the language proficiency of a non-native speakers especially in case of non-English languages which are complex and a slight change of pronunciation can alter the nature of the word. In this study, we proposed an automated language scoring system to test the proficiency of Chinese language. We have employed a novel fusion approach of a 38-feature based model and a Siamese convolutional neural network (Siamese CNN) which can accuracy identify the difference between the native speech and the test taker's speech. The results show that out model have achieved comparable performance to the state of the art and solved the pronunciation problems as well. Furthermore, we have provided a fusion based approach and provided extensive amount of experiments which shows that our method is state of the art and can be utilized in real time Chinese language proficiency scoring. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Message: Data Insertion on a Proof-of-Work Cryptocurrency System

Bitcoin Message: Data Insertion on a Proof-of-Work Cryptocur...

引用

International Conference on Cyberworlds

作者： Matthew D. Sleiman Adrian P. Lauf Roman Yampolskiy Dpt. of Computer Engineering and Computer Science University of Louisville Louisville Kentucky USA

The Bit coin currency is steadily growing in popularity as an alternative to physical currencies. This paper presents an approach for utilizing the Bit coin system for creating permanent messages that are located on computers worldwide. By manipulating the amount field of Bit coin transactions, messages can be embedded into the Bit coin block chain. This approach was implemented by extending the Bit coin-Qt v0.7.2 application and the source code is freely available.

关键词： Online banking Encoding Peer-to-peer computing Cryptography computers Internet Decoding

来源：评论

学校读者我要写书评

暂无评论

Bayesian classification and active learning using lp-priors. Application to image segmentation 22

Bayesian classification and active learning using lp-priors....

引用

22nd European Signal Processing Conference, EUSIPCO 2014

作者： Ruiz, Pablo De La Blanca, Nicolás Pérez Molina, Rafael Katsaggelos, Aggelos K. Dept. Ciencias de la Computación e I.A. Universidad de Granada Spain Dpt. of Electrical Engineering and Computer Science Northwestern University United States

ISBN: (纸本)9780992862619

In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p p-priors are used to impose sparsity on the adaptive parameters. Using variational inference, all model parameters are estimated and the posterior probabilities of the classes given the samples are calculated. A relationship between the prior model used and the independent Gaussian prior model is provided. The posterior probabilities are used to classify new samples and to define two Active Learning methods to improve classifier performance: Minimum Probability and Maximum Entropy. In the experimental section the proposed Bayesian framework is applied to Image Segmentation problems on both synthetic and real datasets, showing higher accuracy than state-of-the-art approaches. © 2014 EURASIP.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Query expansion with a little help from twitter

Communications in Computer and Information Science

引用

Communications in computer and Information science 2013年 384卷 20-29页

作者： Anagnostopoulos, Ioannis Razis, Gerasimos Mylonas, Phivos Anagnostopoulos, Christos-Nikolaos Computer Science and Biomedical Informatics Dpt. University of Thessaly Greece Electrical and Computer Engineering School National Technical University of Athens Greece Cultural Technology and Communication Dpt. University of the Aegean Greece

With the advent and rapid spread of microblogging services, web information management finds a new research topic. Although classical information retrieval methods and techniques help search engines and services to present an adequate precision in lower recall levels (top-k results), the constantly evolving information needs of microblogging users demand a different approach, which has to be adapted to the dynamic nature of On-line Social Networks (OSNs). In this work, we use Twitter as microblogging service, aiming to investigate the query expansion provision that can be extracted from large graphs, and compare it against classical query expansion methods that require mainly prior knowledge, such as browsing history records or access and management of search logs. We provide a direct comparison with mainstream media services, such as Google, Yahoo!, Bing, NBC and Reuters, while we also evaluate our approach by subjective comparisons in respect to the Google Hot Searches service. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Toward Secure Consumer IoT Communications using DNA Encryption and Blockchain Technology

Toward Secure Consumer IoT Communications using DNA Encrypti...

引用

International Conference on Pattern Analysis and Intelligent Systems (PAIS)

作者： Ankush Verma Geetanjali Rathee Chaker Abdelaziz Kerrache Dpt. of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India Dpt. of Computer Science Université Amar Telidji de Laghouat Laghouat Algeria

ISBN: (数字)9798350350265

ISBN: (纸本)9798350350272

Recently, the Internet of Things (IoT) has gained widespread popularity, yet its security remains a critical challenge due to the massive amount of information generated by connected devices. While encryption algorithms are commonly employed to protect this information, they are susceptible to various attacks. This paper introduces a novel encryption method to enhance data security in the Consumer IoT domain. The proposed approach combines DNA-inspired encryption with blockchain technology. The DNA encryption algorithm is utilized for the primary encryption phase, followed by the secure handling of encrypted data using blockchain. To evaluate the proposed scheme, a comparison is made with traditional techniques such as RSA, DNA, and a hybrid of both, considering encryption and decryption times. Simulations are conducted using MATLAB software, and an analytical study is performed to assess the performance of the suggested scheme.

关键词： Smart cities Software algorithms DNA Medical services Software Encryption Blockchains

来源：评论

学校读者我要写书评

暂无评论

Towards an Efficient and Secure Cache Management Using Apriori-Based Interests Prediction in Named Data Networking

Towards an Efficient and Secure Cache Management Using Aprio...

引用

Intelligent Systems and Embedded Design (ISED), International Conference on

作者： Chaker Abdelaziz Kerrache Geetanjali Rathee Younes Guellouma Hocine Gasmi Benameur Ziani Dpt. of Computer Science Université Amar Telidji de Laghouat Laghouat Algeria Dpt. of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

Cache management is an important component in any network and it has even more importance in the Future Internet Architectures (FIAs) including Named Data Networking (NDN), because the caches play the key role in reducing the overall network latency and scalability. In this paper, we discuss the functionality of cache management in NDN, its types as well as its importance for the NDN architecture. In addition, we propose a machine learning-empowered cache management and interests predication for NDN to only preserve the cache only to the secure and really needed data. Our proposal uses Apriori algorithm which is supervised learning algorithm to find the association rules and then to recommend the next requested data. Implementation and experiments on real data traffic depicted that the network’ performance and its influence on the cache increased by 3.2% for two content store sizes of 20 and 40 MB. In addition, a larger cache size of 80 MB shows an increase of the cache hit ratio reaching 90% and hence, clearly reducing the network latency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal and Anticipative Models for the Dimensioning of 3G Multiservice Networks

Causal and Anticipative Models for the Dimensioning of 3G Mu...

引用

IEEE Global Telecommunications Conference GLOBECOM'03

作者： Jaumard, Brigitte Meyer, Christophe Pooyania, Raha Solari, Yannick Voisin, Catherine Dpt. of Computer Science Université de Montréal Montréal Que. H3C 3J7 Canada Dpt. of Electrical Engineering Ecl. Polytech. de Montreal Montréal Que. H3C 3A7 Canada

We study mathematical models and discuss optimization algorithms for the dimensioning of 3G multimedia networks. We propose two models which aims at dimensioning networks with both a radio and a core component. The first one is an anticipative one in which we assume that we know a priori the traffic over the planning period and the dimensioning is defined with a best possible call admission control procedure. The second one is a causal one in which we define an explicit call admission control procedure which makes the accept/reject decisions without any knowledge on the forthcoming traffic. We then compare, on an experimental basis, the dimensioning obtained by both models on some multi-service networks.

关键词： Telecommunication networks

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：