检索结果-内蒙古大学图书馆

A Novel and Effective Model for Automatic Modulation Classification Prediction Based on multi-BIGRU, multi-encoder, and Hyper-Cross

引用

IEEE ACCESS 2025年 13卷 20260-20277页

作者： Lin, Jianzheng China Univ Petr East China Coll Comp Sci & Technol Qingdao 266580 Peoples R China

Automatic Modulation Classification (AMC) is a pivotal technology in various communication systems. In recent years, deep learning (DL) has been widely applied in AMC methods due to its powerful feature extraction capabilities. However, currently proposed AMC methods still have room for improvement in classification performance. To further enhance the prediction accuracy of AMC, we propose a new model called MMH-AMC: Automatic Modulation Classification with multi-BIGRU, multi-encoder, and Hyber-Cross. multi-BIGRU employs a multi-layer bidirectional GRU architecture to extract deep distribution patterns of AP data from both directions simultaneously. multi-encoder adopts a multi-layer encoder architecture with a core of multi-Head Attention, aiming to extract deep-level IQ data distributions. To unify the feature distributions outputted by multi-encoder and Hyber-Cross modules, we designed and utilized the Hyber-Cross module. To validate the model's performance, we compared six different deep learning models and achieved the best performance in various scenarios.

关键词： Feature extraction Modulation Deep learning Data models Data mining Convolutional neural networks Computational modeling Training Signal to noise ratio Data augmentation Automatic modulation classification multi-BIGRU multi-encoder hyber-cross

来源：评论

学校读者我要写书评

暂无评论

MMEFU-Net: A Mamba-Guided multi-encoder Fusion U-Net for Tumor Segmentation in CT Images

引用

IEEE ACCESS 2025年 13卷 76257-76270页

作者： Xue, Renzheng Zhang, Zifeng Zhao, Yaxin Zhang, Qing Liang, Minghui Qiqihar Univ Sch Comp & Control Engn Qiqihar 161000 Peoples R China Qiqihar Univ Heilongjiang Key Lab Big Data Network Secur Detect Qiqihar 161000 Peoples R China Qiqihar Med Univ Sch Med Technol Qiqihar 161000 Peoples R China

Tumor segmentation is crucial for cancer diagnosis, treatment planning, and surgical interventions. However, traditional manual delineation methods are time-consuming, labor-intensive, and prone to subjective variability, highlighting the need for automated approaches. The significant variability in lesion shape and size within medical images further complicates segmentation tasks, necessitating models that can effectively capture both local and global features to achieve accurate results. To address these challenges, we propose MMEFU-Net, a novel deep learning framework designed for efficient and accurate tumor segmentation in medical CT images. The architecture integrates a multi-encoder structure comprising a detail branch, a context branch, and a Mamba-guided branch to extract complementary features, addressing the limitations of single-encoder models. Key innovations include the Mamba-Guided Fusion Attention (MGFA) module for balancing local details and global context, the Pixel Attention Feature Fusion (PAFF) module for enhancing detail branch features with complementary information from the context branch, the Dilated multi-Scale Fusion (DMSF) module for robust multi-scale feature modeling, and the introduction of the lightweight DySample operator for precise and efficient dynamic upsampling. Comprehensive experiments on five public and private benchmark datasets, encompassing both liver tumors and lung cancers, demonstrate that MMEFU-Net outperforms state-of-the-art U-Net, Transformer-based, and Mamba-based architectures. The model achieves superior Dice Similarity Coefficients (DSC) and Intersection over Union (IoU) scores while significantly reducing computational costs. Notably, MMEFU-Net improves the DSC by 2.16% compared to nnU-Net on the LiTS2017 dataset, with a 35x reduction in parameters and a 25x reduction in computational complexity. These findings suggest that MMEFU-Net has the potential to become a scalable and efficient solution for tumor segmen

关键词： Image segmentation Feature extraction Tumors Computational modeling Accuracy Convolution Computer architecture Computed tomography Transformers Medical diagnostic imaging multi-encoder deep learning (DL) tumor segmentation feature fusion light-weight model state space models

来源：评论

学校读者我要写书评

暂无评论

multi-encoder SEQUENTIAL ATTENTION NETWORK FOR CONTEXT-AWARE SPEECH RECOGNITION IN JAPANESE DIALOG CONVERSATION 24

MULTI-ENCODER SEQUENTIAL ATTENTION NETWORK FOR CONTEXT-AWARE...

引用

24th Conference of the Oriental-COCOSDA-International-Committee-for-the-Co-Ordination-and-Standardisation-of-Speech-Databases-and-Assessment-Techniques (O-COCOSDA)

作者： Tachimori, Nobuya Sakti, Sakriani Nakamura, Satoshi Onkyo Corp Osaka Japan Nara Inst Sci & Technol Nara Japan RIKEN Ctr Adv Intelligence Project AIP Tokyo Japan

ISBN: (纸本)9781665408707

Japanese automatic speech recognition (ASR) in conversation is considered challenging and highly ambiguous because the subjects are usually omitted and the number of homonyms is quite large. Since the speaker's utterance alone may not provide enough information, the context of the previous utterance from the dialog partner might help. A limited number of studies have addressed the idea of incorporating dialog-context information in end-to-end ASR tasks. However, these have mainly focused on the English language. Furthermore, although such models exploit dialog context history, the decoder handles the current input and the context simultaneously, ignoring the sequence of a conversation in the process. In this study, we propose a Japanese ASR that considers the dialog partner's conversation context in a sequential manner. Specifically, we use a multi-encoder sequential attention network and investigate several possible architectures. The experimental results reveal that context information helps to improve recognition performance over standard ASR and systems that process the context at the same time.

关键词： end-to-end speech recognition hierarchical attention context-aware multi-encoder

来源：评论

学校读者我要写书评

暂无评论

A multi-encoder neural conversation model

引用

NEUROCOMPUTING 2019年 358卷 344-354页

作者： Ren, Da Cai, Yi Lei, Xue Xu, Jingyun Li, Qing Leung, Ho-fung South China Univ Technol Sch Software Engn Guangzhou Guangdong Peoples R China Hong Kong Polytech Univ Dept Comp Hung Hom Kowloon Hong Kong Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China

With the development of deep neural networks, Sequence to sequence (Seq2Seq) models become a popular technique of conversation models. Current Seq2Seq models with single encoder-decoder structures tend to generate responses which contain high frequency patterns on datasets. However, these patterns are always generic and meaningless. Generic and meaningless responses will lead the conversation between computer and human to an end quickly. According to our observations, human conversations are always topic related. If the conversation data can be divided into different clusters according to their topics, high frequency patterns will be topic related rather than generic. We consider that a model trained in different clusters can generate more topic related and meaningful responses. Inspired by this idea, we propose a multi-encoder Neural Conversation (MENC) model. MENC can make use of topic information by its multi-encoder structure. To the best of our knowledge, it is the first work which applies multi-encoder structures into conversation models. We conduct our experiments on two daily conversation datasets. Our experiments show that MENC gets a better performance than other mainstream models on both subject and object evaluation metrics. (C) 2019 Published by Elsevier B.V.

关键词： multi-encoder Conversation Sequence-to-sequence models

来源：评论

学校读者我要写书评

暂无评论

TIME-Net: Transformer-Integrated multi-encoder Network for limited-angle artifact removal in dual-energy CBCT

引用

MEDICAL IMAGE ANALYSIS 2023年 83卷 102650页

作者： Zhang, Yikun Hu, Dianlin Yan, Zhihong Zhao, Qingxian Quan, Guotao Luo, Shouhua Zhang, Yi Chen, Yang Southeast Univ Lab Image Sci & Technol Key Lab Comp Network & Informat Integrat Nanjing Jiangsu Peoples R China Southeast Univ Sch Biol Sci & Med Engn Nanjing Jiangsu Peoples R China United Imaging Healthcare Co Ltd CT RPA Dept Shanghai Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu Peoples R China Southeast Univ Jiangsu Prov Joint Int Res Lab Med Informat Proc Nanjing Peoples R China

Dual-energy cone-beam computed tomography (DE-CBCT) is a promising imaging technique with foreseeable clinical applications. DE-CBCT images acquired with two different spectra can provide material-specific information. Meanwhile, the anatomical consistency and energy-domain correlation result in significant information redundancy, which could be exploited to improve image quality. In this context, this paper develops the Transformer-Integrated multi-encoder Network (TIME-Net) for DE-CBCT to remove the limited -angle artifacts. TIME-Net comprises three encoders (image encoder, prior encoder, and transformer encoder), two decoders (low-and high-energy decoders), and one feature fusion module. Three encoders extract various features for image restoration. The feature fusion module compresses these features into more compact shared features and feeds them to the decoders. Two decoders perform differential learning for DE-CBCT images. By design, TIME-Net could obtain high-quality DE-CBCT images using two complementary quarter-scans, holding great potential to reduce radiation dose and shorten the acquisition time. Qualitative and quantitative analyses based on simulated data and real rat data have demonstrated the promising performance of TIME-Net in artifact removal, subtle structure restoration, and reconstruction accuracy preservation. Two clinical applications, virtual non-contrast (VNC) imaging and iodine quantification, have proved the potential utility of the DE-CBCT images provided by TIME-Net.

关键词： Dual-energy cone-beam CT Limited-angle artifact removal Transformer multi-encoder Material decomposition

来源：评论

学校读者我要写书评

暂无评论

ATTENTION-BASED multi-encoder AUTOMATIC PRONUNCIATION ASSESSMENT

ATTENTION-BASED MULTI-ENCODER AUTOMATIC PRONUNCIATION ASSESS...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Lin, Binghuai Wang, Liyuan Tencent Technol Co Ltd Smart Platform Prod Dept Shenzhen Peoples R China

ISBN: (纸本)9781728176055

Automatic pronunciation assessment plays an important role in Computer-Assisted Pronunciation Training (CAPT). Traditional methods for pronunciation assessment of reading aloud tasks utilize features derived from automatic speech recognition (ASR) and thus are sensitive to the accuracy of ASR and the effectiveness of features. Moreover, the representation capability of the features is also affected by the inconsistent optimization goals between the ASR and scoring tasks. In this paper we propose an end-to-end (E2E) pronunciation scoring network based on attention mechanism and multi-encoder consisting of audio and text encoders. The network optimized by a multi-task learning (MTL) framework can provide scoring at sentence-level as well as detailed scoring at word-level. Due to data scarcity for pronunciation scoring, we utilize ASR data and synthetic data to pre-train the network in two steps, and then fine-tune the network using the limited high-quality scoring data. Experimental results based on the dataset recorded by Chinese English-as-second-language (ESL) learners and labeled by three experts demonstrate that the proposed model outperforms the baseline in Pearson correlation coefficient (PCC).

关键词： end-to-end pronunciation scoring attention multi-encoder pre-train

来源：评论

学校读者我要写书评

暂无评论

multi-modal Brain Image Segmentation Based on multi-encoder with Hybrid Lateral Connection (MEHLC-Net) 9

Multi-modal Brain Image Segmentation Based on Multi-Encoder ...

引用

9th International Conference on Biomedical and Bioinformatics Engineering (ICBBE)

作者： Bao, Zhengfeng Wang, Yiping Huang, Jinguo Kang, Guixia Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100088 Peoples R China Beijing Univ Posts & Telecommun Key Lab Ubiquitous Network Minist Educ Beijing 100088 Peoples R China

ISBN: (纸本)9781450397223

The imaging data of multi-modal brain has been put to a wide use in the identification of epilepsy and tumor lesions because it can provide multi-information about a target (epilepsy lesion, tumor, or tissue). However, most of the existing multi-modal medical image segmentation networks in the existing multi-modal segmentation schemes, on the one hand, adopt the input-level fusion strategy, which directly integrates the multi-modal images in the original input space. But it is hard to preserve the modality-specific properties. On the other hand, the decision-level fusion method with the use of the single network can better exploit the unique information of the corresponding modality, but with the problem that the features learned from a single modality cannot be easily combined with the features of other modality. In this paper, we have proposed multi-encoder with Hybrid Lateral Connection Network (MEHLC-Net), a semantic segmentation network based on 2D images with multi encoder structure for multi-modal MRI tumor sub-region segmentation. We use hybrid lateral connections instead of long connections in the U-Net structure to extract features, which can overcome the difficulty of highorder feature fusion caused by multiple encoders. We combine cross-connection with self-attention mechanisms to enhance the accuracy of the network. We evaluate our method on the multimodal data set of BRATS. Compared with the advanced No-New-Net, our model improves the TC of the DSC indicator by 0.13% and the ET indicator by 0.58% respectively.

关键词： Segmentation Hybrid-Connection multi-model multi-encoder

来源：评论

学校读者我要写书评

暂无评论

Combining Arterial and Venous CT Scans in a multi-encoder Network for Improved Hepatic Vessel Segmentation

Combining Arterial and Venous CT Scans in a Multi-Encoder Ne...

引用

Conference on Medical Imaging - Image Processing

作者： Thielke, Felix Kock, Farina Haensch, Annika Abolmaali, Nasreddin Schenk, Andrea Meine, Hans Fraunhofer Inst Digital Med MEVIS Max von Laue Str 2 D-28359 Bremen Germany Ruhr Univ Bochum Univ Hosp St Josef Hosp Inst Diagnost & Intervent Radiol & Nucl Med Gudrunstr 56 D-44791 Bochum Germany

ISBN: (纸本)9781510660335;9781510660342

The segmentation of hepatic vessel systems is important for many applications treating malignant liver disease such as selective internal radiation therapy. To enhance the different vessel systems, contrast agent is injected intravenously and CT scans are obtained at different time points and phases of contrast agent perfusion in liver vessels and parenchyma. We demonstrate that using the registered arterial phase as additional input for training an aU-Net for portal vein (PV) and hepatic vein (HV) segmentation increases the centerline Dice. However, using the registered venous phase for hepatic artery (HA) segmentation does not improve segmentation performance.

关键词： abdomen segmentation deep learning multi-encoder multi-phase liver vessels CT

来源：评论

学校读者我要写书评

暂无评论

multi-encoder attention-based architectures for sound recognition with partial visual assistance

引用

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2022年第1期2022卷 25-25页

作者： Boes, Wim Van Hamme, Hugo Katholieke Univ Leuven ESAT Leuven Belgium

Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries. As a consequence, modalities other than audio can often be exploited to improve the outputs of models designed for associated tasks. Frequently, however, not all contents are available for all samples of such a collection: For example, the original material may have been removed from the source platform at some point, and therefore, non-auditory features can no longer be acquired. We demonstrate that a multi-encoder framework can be employed to deal with this issue by applying this method to attention-based deep learning systems, which are currently part of the state of the art in the domain of sound recognition. More specifically, we show that the proposed model extension can successfully be utilized to incorporate partially available visual information into the operational procedures of such networks, which normally only use auditory features during training and inference. Experimentally, we verify that the considered approach leads to improved predictions in a number of evaluation scenarios pertaining to audio tagging and sound event detection. Additionally, we scrutinize some properties and limitations of the presented technique.

关键词： multi-encoder Transformer Conformer Sound recognition Audio tagging Sound event detection multimodal data Audiovisual data Missing data

来源：评论

学校读者我要写书评

暂无评论

multi-modal Brain Image Segmentation Based on multi-encoder with Hybrid Lateral Connection (MEHLC-Net) 22

Multi-modal Brain Image Segmentation Based on Multi-Encoder ...

引用

Proceedings of the 2022 9th International Conference on Biomedical and Bioinformatics Engineering

作者： Zhengfeng Bao Yiping Wang Jinguo Huang Guixia Kang Key Lab of Ubiquitous Network of Ministry of Education Beijing University of Posts and Telecommunications China

ISBN: (纸本)9781450397223

关键词： multi-model Hybrid-Connection Segmentation multi-encoder

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：