检索结果-内蒙古大学图书馆

European signal processing Conference (EUSIPCO)

作者： Xubo Liu Xinhao Mei Qiushi Huang Jianyuan Sun Jinzheng Zhao Haohe Liu Mark D. Plumbley Volkan Kilic Wenwu Wang Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey UK Department of Computer Science University of Surrey UK Department of Electrical and Electronics Engineering Izmir Katip Celebi University Turkey

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

Audio captioning aims at using language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio encoder and then a language decoder is used to generate the captions. Training an audio captioning system often encounters the problem of data scarcity. Transferring knowledge from pre-trained audio models such as Pre-trained Audio Neural Networks (PANNs) have recently emerged as a useful method to mitigate this issue. However, there is less attention on exploiting pre-trained language models for the decoder, compared with the encoder. BERT is a pre-trained language model that has been extensively used in natural language processing tasks. Nevertheless, the potential of using BERT as the language decoder for audio captioning has not been investigated. In this study, we demonstrate the efficacy of the pre-trained BERT model for audio captioning. Specifically, we apply PANNs as the encoder and initialize the decoder from the publicly available pre-trained BERT models. We conduct an empirical study on the use of these BERT models for the decoder in the audio captioning model. Our models achieve competitive results with the existing audio captioning methods on the AudioCaps dataset.

关键词： Training Knowledge engineering Bit error rate Neural networks Europe signal processing Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Channel Estimation Using RIDNet Assisted OMP for Hybrid-Field THz Massive MIMO Systems

Channel Estimation Using RIDNet Assisted OMP for Hybrid-Fiel...

引用

IEEE International Conference on communications (ICC)

作者： Hasan Nayir Erhan Karakoca Ali Görçin Khalid Qaraqe Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Department of Electronics and Communication Engineering Istanbul Technical University İstanbul Turkey Communications and Signal Processing Research (HİSAR) Lab. TÜBİTAK BİLGEM Kocaeli Turkey Department of Electronics and Communication Engineering Yildiz Technical University İstanbul Turkey

The terahertz (THz) band radio access with larger available bandwidth is anticipated to provide higher capacities for next-generation wireless communication systems. However, higher path loss at THz frequencies significantly limits the wireless communication range. Massive multiple-input multiple-output (mMIMO) is an attractive technology to increase the Rayleigh distance by generating higher gain beams using low wavelength and highly directive antenna array aperture. In addition, both far-field and near-field components of the antenna system should be considered for modeling THz electromagnetic propagation, where the channel estimation for this environment becomes a challenging task. This paper proposes a novel channel estimation method using a real image denoising network (RIDNet) and orthogonal matching pursuit (OMP) for hybrid-field THz mMIMO channels, including far-field and near-field constituents. The simulation experiments are performed using the ray-tracing tool. The results demonstrate that the proposed RIDNet-based method consistently provides lower channel estimation errors than the conventional OMP algorithm for all signal-to-noise ratio (SNR) regions. The performance gap becomes higher at low SNR regimes. Furthermore, the results imply that the same error performance of the OMP can be achieved by the RIDNet-based method using a lower number of RF chains and pilot symbols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RIDNet Assisted cGAN Based Channel Estimation for One-Bit ADC mmWave MIMO Systems

RIDNet Assisted cGAN Based Channel Estimation for One-Bit AD...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Erhan Karakoca Hasan Nayir Ali Görçin Khalid Qaraqe Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Department of Electronics and Communication Engineering Istanbul Technical University İstanbul Turkey Communications and Signal Processing Research (HİSAR) Lab. TÜBİTAK BİLGEM Kocaeli Turkey Department of Electronics and Communication Engineering Yildiz Technical University İstanbul Turkey

The estimation of millimeter-wave (mmWave) massive multiple input multiple output (MIMO) channels becomes compelling when one-bit analog-to-digital converters (ADCs) are utilized. Furthermore, as the number of antenna increases, pilot overhead scales up to provide consistent channel estimation, eventually degrading spectral efficiency. This study presents a channel estimation approach that combines a conditional generative adversarial network (cGAN) with a novel blind denoising network with a sparse feature attention mechanism. Performance analysis and simulations show that using a cGAN fused with a feature attention-based denoising neural network significantly enhances the channel estimation performance while requiring less pilot transmission.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic resource provisioning of a scalable E2E Network Slicing Orchestration System

arXiv

引用

arXiv 2022年

作者： Afolabi, Ibrahim Prados-Garzon, Jonathan Bagaa, Miloud Taleb, Tarik Ameigeiras, Pablo Department of Communications and Networking School of Electrical Engineering Aalto University Finland Department of Computer and Information Security Sejong University Seoul Korea Republic of Research Centre for Information and Communications Technologies of the University of Granada Department of Signal Theory Telematics and Communications University of Granada Granada Spain

Network slicing allows different applications and network services to be deployed on virtualized resources running on a common underlying physical infrastructure. Developing a scalable system for the orchestration of end-to-end (E2E) mobile network slices requires careful planning and very reliable algorithms. In this paper, we propose a novel E2E Network Slicing Orchestration System (NSOS) and a Dynamic Auto-Scaling Algorithm (DASA) for it. Our NSOS relies strongly on the foundation of a hierarchical architecture that incorporates dedicated entities per domain to manage every segment of the mobile network from the access, to the transport and core network part for a scalable orchestration of federated network slices. The DASA enables the NSOS to autonomously adapt its resources to changes in the demand for slice orchestration requests (SORs) while enforcing a given mean overall time taken by the NSOS to process any SOR. The proposed DASA includes both proactive and reactive resource provisioning techniques). The proposed resource dimensioning heuristic algorithm of the DASA is based on a queuing model for the NSOS, which consists of an open network of G/G/m queues. Finally, we validate the proper operation and evaluate the performance of our DASA solution for the NSOS by means of system-level simulations. © 2022, CC BY-NC-ND.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Learning to Broadcast with Layered Division Multiplexing

Learning to Broadcast with Layered Division Multiplexing

引用

IEEE International Symposium on Information Theory

作者： Roy Karasik Osvaldo Simeone Shlomo Shamai Shitz Department of Electrical and Computer Engineering Technion Haifa Israel Department of Engineering King&#x2019 s Communications Learning &amp Information Processing (KCLIP) Lab Centre for Telecommunications Research King&#x2019 s College London London U.K.

ISBN: (数字)9781665421591

ISBN: (纸本)9781665421607

A broadcast/multicast communication system is studied in which layered division multiplexing (LDM) is applied to support differential quality-of-service (QoS) levels. Focusing on a practical scenario in which the transmitter does not know the fading distribution, layer allocation is optimized based on a dataset sampled during deployment. The optimality gap caused by the availability of limited data is bounded via a generalization analysis, and is shown to be monotonically decreasing as the dataset grows larger. Numerical experiments demonstrate that LDM improves spectral efficiency even for small datasets; and that, for sufficiently large datasets, the proposed mirror-descent-based layer optimization scheme achieves an expected rate close to that achieved when the transmitter knows the fading distribution.

关键词： Fading channels Spectral efficiency Transmitting antennas Focusing Quality of service Gain measurement Resource management

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Classifier based Residual RNN for Image Captioning

Auxiliary Classifier based Residual RNN for Image Captioning

引用

European signal processing Conference (EUSIPCO)

作者： Özkan Çaylı Volkan Kılıç Aytuğ Onan Wenwu Wang Electrical and Electronics Engineering Graduate Program İzmir Katip Çelebi University Turkey Department of Computer Engineering İzmir Katip Çelebi University Turkey Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey UK

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

Image captioning aims to generate a description of visual contents with natural language automatically. This is useful in several potential applications, such as image understanding and virtual assistants. With recent advances in deep neural networks, natural and semantic text generation has been improved in image captioning. However, maintaining the gradient flow between neurons in consecutive layers becomes challenging as the network gets deeper. In this paper, we propose to integrate an auxiliary classifier in the residual recurrent neural network, which enables the gradient flow to reach the bottom layers for enhanced caption generation. Experiments on the MSCOCO and VizWiz datasets demonstrate the advantage of our proposed approach over the state-of-the-art approaches in several performance metrics.

关键词： Measurement Deep learning Visualization Recurrent neural networks Virtual assistants Semantics Neurons

来源：评论

学校读者我要写书评

暂无评论

Automated Image Captioning with Multi-layer Gated Recurrent Unit

Automated Image Captioning with Multi-layer Gated Recurrent ...

引用

European signal processing Conference (EUSIPCO)

作者： Özge Taylan Moral Volkan Kiliç Aytug Onan Wenwu Wang Electrical and Electronics Engineering Graduate Program Izmir Katip Celebi University Turkey Department of Computer Engineering Izmir Katip Celebi University Turkey Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey UK

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

Describing the semantic content of an image via natural language, known as image captioning, has recently attracted substantial interest in computer vision and language processing communities. Current image captioning approaches are mainly based on an encoder-decoder framework in which visual information is extracted by an image encoder and captions are generated by a text decoder, using convolution neural net-works (CNN) and recurrent neural networks (RNN), respectively. Although this framework is promising for image captioning, it has limitations in utilizing the encoded visual information for generating grammatically and semantically correct captions in the RNN decoder. More specifically, the RNN decoder is ineffective in using the contextual information from the encoded data due to its limited ability in capturing long-term complex dependencies. Inspired by the advantage of gated recurrent unit (GRU), in this paper, we propose an extension of conventional RNN by introducing a multi-layer GRU that modulates the most relevant information inside the unit to enhance the semantic coherence of captions. Experimental results on the MSCOCO dataset show the superiority of our proposed approach over the state-of-the-art approaches in several performance metrics.

关键词： Measurement Visualization Recurrent neural networks Semantics Natural languages Europe Logic gates

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Decision Forest for Acoustic Scene Classification

Deep Neural Decision Forest for Acoustic Scene Classificatio...

引用

European signal processing Conference (EUSIPCO)

作者： Jianyuan Sun Xubo Liu Xinhao Mei Jinzheng Zhao Mark D. Plumbley Volkan Kılıç Wenwu Wang Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey UK College of Computer Science and Technology Qingdao University China Department of Electrical and Electronics Engineering Izmir Katip Celebi University Turkey

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

Acoustic scene classification (ASC) aims to classify an audio clip based on the characteristic of the recording environment. In this regard, deep learning based approaches have emerged as a useful tool for ASC problems. Conventional approaches to improving the classification accuracy include integrating auxiliary methods such as attention mechanism, pre-trained models and ensemble multiple sub-networks. However, due to the complexity of audio clips captured from different environments, it is difficult to distinguish their categories without using any auxiliary methods for existing deep learning models using only a single classifier. In this paper, we propose a novel approach for ASC using deep neural decision forest (DNDF). DNDF combines a fixed number of convolutional layers and a decision forest as the final classifier. The decision forest consists of a fixed number of decision tree classifiers, which have been shown to offer better classification performance than a single classifier in some datasets. In particular, the decision forest differs substantially from traditional random forests as it is stochastic, differentiable, and capable of using the back-propagation to update and learn feature representations in neural network. Experimental results on the DCASE2019 and ESC-50 datasets demonstrate that our proposed DNDF method improves the ASC performance in terms of classification accuracy and shows competitive performance as compared with state-of-the-art baselines.

关键词： Deep learning Image analysis Neural networks Stochastic processes Training data Forestry Acoustics

来源：评论

学校读者我要写书评

暂无评论

Editorial

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity Science 2024年第3期6卷 289-289页

作者： Liao, Shengcai Liu, Xiaoming Tistarelli, Massimo Chellappa, Rama Kittler, Josef United Arab Emirates University College of Information Technology Al Ain United Arab Emirates Michigan State University Department of Computer Science and Engineering East LansingMI48824 United States University of Sassari Computer Vision Laboratory Sassari07100 Italy Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD21218 United States Johns Hopkins University Department of Biomedical Engineering BaltimoreMD21218 United States University of Surrey Centre for Vision Speech and Signal Processing GuildfordGU2 7XH United Kingdom

The 2022 International Joint Conference on Biometrics (IJCB 2022) was held at Abu Dhabi, United Arab Emirates, from October 10 to October 13, 2022. This marked the first biometrics conference held in the Middle East. The IJCB 2022 conference combined two major biometrics conferences: the IEEE Biometrics Theory, Applications, and Systems (BTAS) conference and the International Conference on Biometrics (ICB). The IJCB 2022 conference was technically co-sponsored by both IAPR TC4 (Technical Committee on Biometrics) and the IEEE Biometrics Council. © 2019 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time series numerical association rule mining variants in smart agriculture

arXiv

引用

arXiv 2022年

作者： Fister, Iztok Fister, Dušan Fister, Iztok Podgorelec, Vili Salcedo-Sanz, Sancho Faculty of Electrical Engineering and Computer Science University of Maribor Koroška cesta 46 MariborSI-2000 Slovenia Department of Signal Processing and Communications Universidad de Alcalá Alcalá de Henares Madrid28805 Spain

Numerical association rule mining offers a very efficient way of mining association rules, where algorithms can operate directly with categorical and numerical attributes. These methods are suitable for mining different transaction databases, where data are entered sequentially. However, little attention has been paid to the time series numerical association rule mining, which offers a new technique for extracting association rules from time series data. This paper presents a new algorithmic method for time series numerical association rule mining and its application in smart agriculture. We offer a concept of a hardware environment for monitoring plant parameters and a novel data mining method with practical experiments. The practical experiments showed the method’s potential and opened the door for further extension. Copyright © 2022, The Authors. All rights reserved.

关键词： Internet of things

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：