检索结果-内蒙古大学图书馆

25th International Conference on Pattern Recognition (ICPR)

作者： Wu, Changjie Wang, Qing Zhang, Jianshu Du, Jun Wang, Jiaming Wu, Jiajia Hu, Jinshui Univ Sci & Technol China NEL SILP Hefei Anhui Peoples R China iFLYTEK CO LTD AI Res Hefei Anhui Peoples R China

ISBN: (纸本)9781728188089

Recently, many researches propose to employ attention based encoder-decoder models to convert a sequence of trajectory points into a LaTeX string for online handwritten mathematical expression recognition (OHMER), and the recognition performance of these models critically relies on the accuracy of the attention. In this paper, unlike previous methods which basically employ a soft attention model, we propose to employ a posterior attention model, which modifies the attention probabilities after observing the output probabilities generated by the soft attention model. In order to further improve the posterior attention mechanism, we propose a stroke average pooling layer to aggregate point-level features obtained from the encoder into stroke-level features. We argue that posterior attention is better to be implemented on stroke-level features than point-level features as the output probabilities generated by stroke is more convincing than generated by point, and we prove that through experimental analysis. Validated on the CROHME competition task, we demonstrate that stroke based posterior attention achieves expression recognition rates of 54.26% on CROHME 2014 and 51.75% on CROHME 2016. According to attention visualization analysis, we empirically demonstrate that the posterior attention mechanism can achieve better alignment accuracy than the soft attention mechanism.

关键词： Posterior attention Stroke Online handwritten mathematical expression recognition sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Linear-Time Korean Morphological Analysis Using an Action-based Local Monotonic Attention Mechanism

引用

ETRI JOURNAL 2020年第1期42卷 101-107页

作者： Hwang, Hyunsun Lee, Changki Kangwon Natl Univ Dept Comp Sci Chunchon South Korea

For Korean language processing, morphological analysis is a critical component that requires extensive work. This morphological analysis can be conducted in an end-to-end manner without requiring a complicated feature design using a sequence-to-sequence model. However, the sequence-to-sequence model has a time complexity of O(n(2)) for an input length n when using the attention mechanism technique for high performance. In this study, we propose a linear-time Korean morphological analysis model using a local monotonic attention mechanism relying on monotonic alignment, which is a characteristic of Korean morphological analysis. The proposed model indicates an extreme improvement in a single threaded environment and a high morphometric F1-measure even for a hard attention model with the elimination of the attention mechanism formula.

关键词： deep learning korean morphological analysis local attention mechanism natural language processing sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Context Aware Energy Disaggregation Using Adaptive Bidirectional LSTM Models

引用

IEEE TRANSACTIONS ON SMART GRID 2020年第4期11卷 3054-3067页

作者： Kaselimi, Maria Doulamis, Nikolaos Voulodimos, Athanasios Protopapadakis, Eftychios Doulamis, Anastasios Natl Tech Univ Athens Sch Rural & Surveying Engn Athens 15780 Greece Univ West Attica Dept Informat & Comp Engn Athens 12243 Greece

Energy disaggregation, or Non-Intrusive Load Monitoring (NILM), describes various processes aiming to identify the individual contribution of appliances, given the aggregate power signal. In this paper, a non-causal adaptive context-aware bidirectional deep learning model for energy disaggregation is introduced. The proposed model, CoBiLSTM, harnesses the representational power of deep recurrent Long Short-Term Memory (LSTM) neural networks, while fitting two basic properties of NILM problem which state of the art methods do not appropriately account for: non-causality and adaptivity to contextual factors (e.g., seasonality). A Bayesian-optimized framework is introduced to select the best configuration of the proposed regression model, driven by a self-training adaptive mechanism. Furthermore, the proposed model is structured in a modular way to address multi-dimensionality issues that arise when the number of appliances increases. Experimental results indicate the proposed method's superiority compared to the current state of the art.

关键词： Adaptation models Biological system modeling Context modeling Home appliances Hidden Markov models Load modeling Aggregates Deep learning NILM non-intrusive load monitoring energy disaggregation recurrent neural networks LSTM bidirectional Bayesian optimization adaptability sequence-to-sequence learning context-aware

来源：评论

学校读者我要写书评

暂无评论

Multi-step-ahead flood forecasting using an improved BiLSTM-S2S model

引用

JOURNAL OF FLOOD RISK MANAGEMENT 2022年第4期15卷

作者： Cao, Qing Zhang, Hanchen Zhu, Feilin Hao, Zhenchun Yuan, Feifei Nanjing Univ Informat Sci & Technol Minist Water Resources Key Lab Hydrometeorol Disaster Mech & Warning Nanjing Peoples R China Nanjing Univ Informat Sci & Technol Sch Hydrol & Water Resources Nanjing Jiangsu Peoples R China Hohai Univ State Key Lab Hydrol Water Resources & Hydraul En Nanjing Peoples R China Ningxia Univ Inst Environm Engn Yinchuan 750021 Ningxia Peoples R China Ningxia Key Lab Resource Assessment & Environm Re Yinchuan Ningxia Peoples R China China Arab Joint Int Res Lab Featured Resources & Yinchuan Ningxia Peoples R China

Rainfall-runoff modeling is a complex hydrological issue that still has room for improvement. This study developed a coupled bidirectional long short-term memory (LSTM) with sequence-to-sequence (Seq2Seq) learning (BiLSTM-Seq2seq) model to simulate multi-step-ahead runoff for flood events. The bidirectional LSTM with Seq2Seq learning (LSTM-Seq2Seq) and multilayer perceptron (MLP) was set as benchmarks. The results show that: (1) root mean absolute error is reduced by approximately 19% up to 27%, and the Nash-Sutcliffe coefficient of efficiency is improved by 14% up to 34% for 6-h-ahead runoff prediction for BiLSTM-Seq2Seq compared LSTM-Seq2Seq and MLP;(2) The BiLSTM-Seq2Seq model has good performance not only for one-peak flood events but also for multi-peak flood events;and (3) BiLSTM-Seq2Seq can mitigate the time-delay problem and time lag is shortened by 39% up to 69% in comparison to LSTM-Seq2Seq and MLP. These results suggest that the time-delay problem can be mitigated by BiLSTM-Seq2Seq, which has excellent potential in time series predictions in the hydrological field.

关键词： bidirectional long short-term memory flood modeling flood risk multi-step-ahead runoff forecast sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Against Insider Threats with Hybrid Anomaly Detection with Local-Feature Autoencoder and Global Statistics (LAGS)

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2020年第4期E103D卷 888-891页

作者： Jang, Minhae Ryu, Yeonseung Kim, Jik-Soo Cho, Minkyoung KEPCO Res Inst Digital Solut Lab Daejeon South Korea Myongji Univ Dept Comp Engn Seoul South Korea

Internal user threats such as information leakage or system destruction can cause significant damage to the organization, however it is very difficult to prevent or detect this attack in advance. In this paper, we propose an anomaly-based insider threat detection method with local features and global statistics over the assumption that a user shows different patterns from regular behaviors during harmful actions. We experimentally show that our detection mechanism can achieve superior performance compared to the state of the art approaches for CMU CERT dataset.

关键词： abnormal detection sequence-to-sequence learning autoencoder reconstruction error

来源：评论

学校读者我要写书评

暂无评论

ConvS2S-VC: Fully Convolutional sequence-to-sequence Voice Conversion

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2020年 28卷 1849-1863页

作者： Kameoka, Hirokazu Tanaka, Kou Kwasny, Damian Kaneko, Takuhiro Hojo, Nobukatsu NTT Corp NTT Commun Sci Labs Atsugi Kanagawa 2430198 Japan

This article proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully convolutional architecture. This is particularly advantageous in that it is suitable for parallel computations using GPUs. It is also beneficial since it enables effective normalization techniques such as batch normalization to be used for all the hidden layers in the networks. Second, it achieves many-to-many conversion by simultaneously learning mappings among multiple speakers using only a single model instead of separately learning mappings between each speaker pair using a different model. This enables the model to fully utilize available training data collected from multiple speakers by capturing common latent features that can be shared across different speakers. Owing to this structure, our model works reasonably well even without source speaker information, thus making it able to handle any-to-many conversion tasks. Third, we introduce a mechanism, called the conditional batch normalization that switches batch normalization layers in accordance with the target speaker. This particular mechanism has been found to be extremely effective for our many-to-many conversion model. We conducted speaker identity conversion experiments and found that ConvS2S-VC obtained higher sound quality and speaker similarity than baseline methods. We also found from audio examples that it could perform well in various tasks including emotional expression conversion, electrolaryngeal speech enhancement, and English accent conversion.

关键词： Acoustics Training Computational modeling Task analysis Feature extraction Decoding Data models Attention fully convolutional model many-to-many VC sequence-to-sequence learning voice conversion (VC)

来源：评论

学校读者我要写书评

暂无评论

A sequence-to-sequence Model With Attention and Monotonicity Loss for Tool Wear Monitoring and Prediction

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2021年 70卷 1页

作者： Wang, Gang Zhang, Feng Hefei Univ Technol Sch Management Hefei 230009 Peoples R China

Recently, deep learning has been successfully applied in tool wear monitoring systems. However, since the tool wear accumulates in the cutting process, the state of the cutting tool shows a degradation trend, which has not been fully exploited by the current deep learning models. In this article, an end-to-end deep learning model, named sequence-to-sequence model with attention and monotonicity loss (SMAML) is proposed to simultaneously monitor and predict the tool wear. In the proposed SMAML, the encoder is utilized to extract features from signals collected by different sensors using the group convolution, while the decoder is designed to produce sequential outputs, including the results of tool wear monitoring and multistep-ahead prediction. Besides, a monotonicity loss function is proposed to capture the degeneration characters in these sequential outputs. The experiments are conducted on real-world datasets, which were collected from a high-speed CNC machine. The experimental results demonstrate the effectiveness of the proposed model which outperforms other conventional machine learning and deep learning models.

关键词： Attention mechanism deep learning monotonicity loss sequence-to-sequence learning tool wear monitoring and prediction

来源：评论

学校读者我要写书评

暂无评论

Voice Transformer Network: sequence-to-sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining 21

Voice Transformer Network: Sequence-to-Sequence Voice Conver...

引用

Interspeech Conference

作者： Huang, Wen-Chin Hayashi, Tomoki Wu, Yi-Chiao Kameoka, Hirokazu Toda, Tomoki Nagoya Univ Nagoya Aichi Japan NTT Commun Sci Labs Tokyo Japan

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While seq2seq models based on recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been successfully applied to VC, the use of the Transformer network, which has shown promising results in various speech processing tasks, has not yet been investigated. Nonetheless, their data-hungry property and the mispronunciation of converted speech make seq2seq models far from practical. To this end, we propose a simple yet effective pretraining technique to transfer knowledge from learned TTS models, which benefit from large-scale, easily accessible TTS corpora. VC models initialized with such pretrained model parameters are able to generate effective hidden representations for high-fidelity, highly intelligible converted speech. Experimental results show that such a pretraining scheme can facilitate data-efficient training and outperform an RNN-based seq2seq VC model in terms of intelligibility, naturalness, and similarity.

关键词： Voice Conversion sequence-to-sequence learning Transformer pretraining

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning for Dependability Assessment of Industrial Wireless Communication Systems ⁎

引用

IFAC-PapersOnLine 2021年第4期54卷 165-170页

作者： Danfeng Sun Lutz Rauchhaupt Ulrich Jumar Institut f. Automation und Kommunikation e.V. 39106 Magdeburg Germany

Wireless communication systems for the industrial domain will rapidly grow in the forthcoming years, which is bringing a strong need for quantitative dependability assessment. Empirical formulas and artificial intelligence have been applied in dependability assessment for years. However, these methods always focused on a single task, while multiple tasks are common and have inner relationships, such as dependability scoring and prediction. These relationships are useful and can improve every task performance. Hence, we propose the multi-task learning model to solve three tasks: dependability scoring, prediction, and scoring prediction, where we design a denoising sequence to sequence neural network with a decay attention. To validate the novelty, we measured and collected a dataset from a realistic system, and then we compared the multi-task learning results of three tasks with benchmarks, which indicates superiority.

关键词： Machine leaning multi-task learning sequence-to-sequence learning dependability assessment wireless communication system

来源：评论

学校读者我要写书评

暂无评论

ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第9期41卷 2035-2048页

作者： Shi, Baoguang Yang, Mingkun Wang, Xinggang Lyu, Pengyuan Yao, Cong Bai, Xiang Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Hubei Peoples R China Megvii Face Inc Beijing 100190 Peoples R China

A challenging aspect of scene text recognition is to handle text with distortions or irregular layout. In particular, perspective text and curved text are common in natural scenes and are difficult to recognize. In this work, we introduce ASTER, an end-to-end neural network model that comprises a rectification network and a recognition network. The rectification network adaptively transforms an input image into a new one, rectifying the text in it. It is powered by a flexible Thin-Plate Spline transformation which handles a variety of text irregularities and is trained without human annotations. The recognition network is an attentional sequence-to-sequence model that predicts a character sequence directly from the rectified image. The whole model is trained end to end, requiring only images and their groundtruth text. Through extensive experiments, we verify the effectiveness of the rectification and demonstrate the state-of-the-art recognition performance of ASTER. Furthermore, we demonstrate that ASTER is a powerful component in end-to-end recognition systems, for its ability to enhance the detector.

关键词： Scene text recognition thin-plate spline image transformation sequence-to-sequence learning

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：